{"conversations": [{"role": "user", "content": "Show the first name, last name, and email for guests residing in California."}, {"role": "assistant", "content": "SELECT first_name, last_name, email FROM hospitality_technology.guests WHERE state_province = 'CA'"}, {"role": "user", "content": "Only show those who have a phone number."}, {"role": "assistant", "content": "SELECT first_name, last_name, email, phone_number FROM hospitality_technology.guests WHERE state_province = 'CA' AND phone_number IS NOT NULL"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE hospitality_technology.properties ( property_id.text, property_name.text, address_line1.text, address_line2.text, city.text, state_province.text, postal_code.text, country_code.text, phone_number.text, email_address.text, property_type.text, star_rating.numeric, timezone.text, manager_staff_id.text, created_at.timestamp, updated_at.timestamp )\nCREATE TABLE hospitality_technology.rooms ( room_id.text, property_id.text, room_number.text, room_type_id.text, floor.integer, status.text, is_smoking.boolean, features.text, current_condition.text, last_cleaned_at.timestamp )\nCREATE TABLE hospitality_technology.guests ( guest_id.text, first_name.text, last_name.text, email.text, phone_number.text, date_of_birth.date, address_line1.text, city.text, state_province.text, postal_code.text, country_code.text, preferences.text, loyalty_member_id.text, communication_consent.boolean, created_at.timestamp, updated_at.timestamp )\nCREATE TABLE hospitality_technology.reservations ( reservation_id.text, property_id.text, guest_id.text, room_id.text, room_type_id.text, check_in_date.date, check_out_date.date, actual_check_in_ts.timestamp, actual_check_out_ts.timestamp, num_adults.integer, num_children.integer, status.text, booking_source.text, rate_plan_id.text, total_amount.numeric, amount_paid.numeric, special_requests.text, created_at.timestamp, updated_at.timestamp )\nCREATE TABLE hospitality_technology.staff ( staff_id.text, property_id.text, first_name.text, last_name.text, position.text, work_email.text, work_phone.text, hire_date.date, termination_date.date, is_active.boolean, access_level.integer, manager_id.text, created_at.timestamp )\nCREATE TABLE hospitality_technology.services ( service_id.text, property_id.text, service_name.text, description.text, category.text, price.numeric, unit.text, is_available.boolean, department.text )\nCREATE TABLE hospitality_technology.service_orders ( order_id.text, reservation_id.text, guest_id.text, service_id.text, staff_id_ordered.text, staff_id_delivered.text, order_timestamp.timestamp, delivery_timestamp.timestamp, quantity.integer, unit_price.numeric, total_price.numeric, status.text, notes.text, bill_id.text )\nCREATE TABLE hospitality_technology.payments ( payment_id.text, reservation_id.text, guest_id.text, bill_id.text, amount.numeric, currency_code.text, payment_method.text, card_type.text, card_last_four.text, transaction_ref.text, payment_timestamp.timestamp, status.text, staff_id_processed.text, notes.text )\nCREATE TABLE hospitality_technology.reviews ( review_id.text, property_id.text, reservation_id.text, guest_id.text, rating_overall.integer, rating_cleanliness.integer, rating_service.integer, rating_location.integer, rating_value.integer, comment.text, review_source.text, review_date.timestamp, is_public.boolean, staff_response.text, response_staff_id.text, response_date.timestamp )\n"} {"conversations": [{"role": "user", "content": "Show pairs of time entries for the same lawyer on the same date with different billing rates, including both entry IDs, the lawyer ID, the work date, and both billing rates."}, {"role": "assistant", "content": "SELECT a.entry_id AS entry1_id, b.entry_id AS entry2_id, a.lawyer_id, a.date_worked, a.billing_rate AS rate1, b.billing_rate AS rate2\nFROM legal_services.time_entries a\nJOIN legal_services.time_entries b\n ON a.lawyer_id = b.lawyer_id\n AND a.date_worked = b.date_worked\n AND a.entry_id < b.entry_id\n AND a.billing_rate <> b.billing_rate;"}, {"role": "user", "content": "Actually, I only want to include entries where both are billable."}, {"role": "assistant", "content": "SELECT a.entry_id AS entry1_id, b.entry_id AS entry2_id, a.lawyer_id, a.date_worked, a.billing_rate AS rate1, b.billing_rate AS rate2\nFROM legal_services.time_entries a\nJOIN legal_services.time_entries b\n ON a.lawyer_id = b.lawyer_id\n AND a.date_worked = b.date_worked\n AND a.entry_id < b.entry_id\n AND a.billing_rate <> b.billing_rate\nWHERE a.is_billable = true\n AND b.is_billable = true;"}, {"role": "user", "content": "Also, sort the results by lawyer_id, then by date_worked, and then by the absolute difference in billing rates descending."}, {"role": "assistant", "content": "SELECT a.entry_id AS entry1_id, b.entry_id AS entry2_id, a.lawyer_id, a.date_worked, a.billing_rate AS rate1, b.billing_rate AS rate2\nFROM legal_services.time_entries a\nJOIN legal_services.time_entries b\n ON a.lawyer_id = b.lawyer_id\n AND a.date_worked = b.date_worked\n AND a.entry_id < b.entry_id\n AND a.billing_rate <> b.billing_rate\nWHERE a.is_billable = true\n AND b.is_billable = true\nORDER BY a.lawyer_id, a.date_worked, ABS(a.billing_rate - b.billing_rate) DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.time_entries ( entry_id.text, case_id.text, lawyer_id.text, date_worked.date, hours_spent.numeric, billing_rate.numeric, description.text, is_billable.boolean, is_billed.boolean, invoice_id.text, created_at.timestamp )\n"} {"conversations": [{"role": "user", "content": "List pairs of distinct routes that originate from the same location but go to different destinations. Show the route ID and route number for both routes and the common origin location ID."}, {"role": "assistant", "content": "SELECT\n r1.route_id AS route1_id,\n r1.route_number AS route1_number,\n r2.route_id AS route2_id,\n r2.route_number AS route2_number,\n r1.origin_location_id AS shared_origin_location_id\nFROM transportation.routes AS r1\nJOIN transportation.routes AS r2\n ON r1.origin_location_id = r2.origin_location_id\n AND r1.route_id < r2.route_id\nWHERE\n r1.destination_location_id != r2.destination_location_id;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.routes ( route_id text, route_number text, description text, origin_location_id text, destination_location_id text, distance_km numeric, estimated_duration_minutes integer, type text )\n"} {"conversations": [{"role": "user", "content": "Show me all customers (customer_id, first_name, last_name) who have made trades in the last 30 days, along with the total trade amount for each customer, sorted by total trade amount in descending order."}, {"role": "assistant", "content": "SELECT c.customer_id, c.first_name, c.last_name, SUM(t.total_amount) AS total_trade_amount FROM financial_services.customers c JOIN financial_services.accounts a ON c.customer_id = a.customer_id JOIN financial_services.trades t ON a.account_id = t.account_id WHERE t.trade_timestamp >= CURRENT_DATE - INTERVAL '30 days' GROUP BY c.customer_id, c.first_name, c.last_name ORDER BY total_trade_amount DESC;"}, {"role": "user", "content": "Now modify the query to only include trades executed on the 'NYSE' venue and include the trade count for each customer."}, {"role": "assistant", "content": "SELECT c.customer_id, c.first_name, c.last_name, SUM(t.total_amount) AS total_trade_amount, COUNT(t.trade_id) AS trade_count FROM financial_services.customers c JOIN financial_services.accounts a ON c.customer_id = a.customer_id JOIN financial_services.trades t ON a.account_id = t.account_id WHERE t.trade_timestamp >= CURRENT_DATE - INTERVAL '30 days' AND t.execution_venue = 'NYSE' GROUP BY c.customer_id, c.first_name, c.last_name ORDER BY total_trade_amount DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE financial_services.customers (\n customer_id character varying(64) NOT NULL, -- unique identifier for the customer\n first_name character varying(100) NOT NULL, -- customer's first name\n last_name character varying(100) NOT NULL, -- customer's last name\n date_of_birth date NOT NULL, -- customer's date of birth\n ssn_hash character varying(128), -- hashed social security number (or national ID)\n address text NOT NULL, -- customer's primary address\n city character varying(100) NOT NULL,\n state character varying(50) NOT NULL,\n zip_code character varying(20) NOT NULL,\n country character varying(50) NOT NULL,\n email character varying(128) UNIQUE, -- customer's email address\n phone_number character varying(32),\n created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of customer record creation\n status character varying(32) NOT NULL, -- e.g., Active, Inactive, Pending Verification\n risk_profile character varying(50), -- e.g., Low, Medium, High\n PRIMARY KEY (customer_id)\n)\nCREATE TABLE financial_services.securities (\n security_id character varying(64) NOT NULL, -- unique identifier for the security\n ticker_symbol character varying(20) NOT NULL UNIQUE, -- stock ticker or fund symbol\n isin_code character varying(12) UNIQUE, -- International Securities Identification Number\n cusip_code character varying(9) UNIQUE, -- CUSIP number\n security_name text NOT NULL, -- full name of the security\n security_type character varying(50) NOT NULL, -- e.g., Stock, Bond, ETF, Mutual Fund, Option, Future\n exchange character varying(50), -- primary exchange where traded (e.g., NYSE, NASDAQ)\n currency character varying(3) NOT NULL, -- currency the security is denominated in\n issuer_name character varying(255), -- name of the issuing entity\n sector character varying(100), -- industry sector\n last_updated timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP,\n PRIMARY KEY (security_id)\n)\nCREATE TABLE financial_services.trades (\n trade_id character varying(64) NOT NULL, -- unique identifier for the trade\n account_id character varying(64) NOT NULL, -- investment account executing the trade\n security_id character varying(64) NOT NULL, -- security being traded\n order_id character varying(64), -- related order ID if applicable\n trade_type character varying(10) NOT NULL, -- 'Buy' or 'Sell'\n quantity numeric(19, 8) NOT NULL, -- number of units traded\n price_per_unit numeric(19, 8) NOT NULL, -- price per unit of the security\n total_amount numeric(19, 4) NOT NULL, -- total value of the trade (quantity * price)\n commission numeric(10, 4), -- commission fee charged for the trade\n trade_timestamp timestamp NOT NULL, -- exact time the trade was executed\n settlement_date date, -- date the trade settles\n status character varying(32) NOT NULL, -- e.g., Executed, Settled, Cancelled\n execution_venue character varying(100), -- where the trade was executed\n PRIMARY KEY (trade_id),\n FOREIGN KEY (account_id) REFERENCES financial_services.accounts(account_id),\n FOREIGN KEY (security_id) REFERENCES financial_services.securities(security_id)\n)\nCREATE TABLE financial_services.market_data (\n data_point_id bigserial NOT NULL, -- auto-incrementing primary key\n security_id character varying(64) NOT NULL, -- identifier for the security\n data_timestamp timestamp NOT NULL, -- timestamp for the data point (e.g., end of day, intraday)\n open_price numeric(19, 8), -- opening price for the period\n high_price numeric(19, 8), -- highest price during the period\n low_price numeric(19, 8), -- lowest price during the period\n close_price numeric(19, 8) NOT NULL, -- closing price for the period\n adjusted_close_price numeric(19, 8), -- closing price adjusted for dividends and splits\n volume bigint, -- trading volume during the period\n source character varying(50), -- source of the market data (e.g., Bloomberg, Refinitiv)\n PRIMARY KEY (data_point_id),\n UNIQUE (security_id, data_timestamp), -- Ensure unique data point per security per time\n FOREIGN KEY (security_id) REFERENCES financial_services.securities(security_id)\n)\nCREATE TABLE financial_services.employees (\n employee_id character varying(64) NOT NULL, -- unique identifier for the employee\n first_name character varying(100) NOT NULL,\n last_name character varying(100) NOT NULL,\n job_title character varying(100) NOT NULL, -- e.g., Teller, Branch Manager, Financial Advisor, Analyst\n department character varying(100), -- e.g., Retail Banking, Wealth Management, IT\n branch_id character varying(64), -- Identifier for the branch they work at (if applicable)\n email character varying(128) NOT NULL UNIQUE,\n phone_extension character varying(20),\n hire_date date NOT NULL,\n termination_date date, -- Date of termination, null if currently employed\n manager_id character varying(64), -- Self-referencing key for manager relationship\n status character varying(32) NOT NULL, -- e.g., Active, Terminated, On Leave\n PRIMARY KEY (employee_id),\n FOREIGN KEY (branch_id) REFERENCES financial_services.branches(branch_id), -- Assuming a branches table exists\n FOREIGN KEY (manager_id) REFERENCES financial_services.employees(employee_id)\n)\n"} {"conversations": [{"role": "user", "content": "For each event, display its event_id, the event_id of the previous event in the same transaction (if any), and the log_index of both events."}, {"role": "assistant", "content": "SELECT curr.event_id AS current_event_id,\n prev.event_id AS previous_event_id,\n curr.log_index AS current_log_index,\n prev.log_index AS previous_log_index,\n curr.transaction_id\nFROM web3.events curr\nLEFT JOIN web3.events prev\n ON curr.transaction_id = prev.transaction_id\n AND curr.log_index = prev.log_index + 1;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE web3.events ( event_id character varying(64) NOT NULL, contract_id character varying(64) NOT NULL, event_name character varying(128) NOT NULL, data text NOT NULL, emitted_at timestamp NOT NULL, transaction_id character varying(64) NOT NULL, log_index integer NOT NULL, PRIMARY KEY (event_id) )\n"} {"conversations": [{"role": "user", "content": "For each asset, I want to know how many orders have the status 'filled', showing the asset symbol."}, {"role": "assistant", "content": "SELECT m.value AS asset_symbol,\n COUNT(*) AS filled_order_count\nFROM trading_platform.orders o\nJOIN trading_platform.metadata m\n ON o.asset_id = m.asset_id\n AND m.key = 'symbol'\nWHERE o.status = 'filled'\nGROUP BY m.value;"}, {"role": "user", "content": "Include assets that have zero filled orders, showing filled_order_count as 0."}, {"role": "assistant", "content": "WITH asset_symbols AS (\n SELECT DISTINCT asset_id,\n value AS asset_symbol\n FROM trading_platform.metadata\n WHERE key = 'symbol'\n)\nSELECT a.asset_symbol,\n COALESCE(f.filled_order_count, 0) AS filled_order_count\nFROM asset_symbols a\nLEFT JOIN (\n SELECT asset_id,\n COUNT(*) AS filled_order_count\n FROM trading_platform.orders\n WHERE status = 'filled'\n GROUP BY asset_id\n) f\n ON a.asset_id = f.asset_id;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE trading_platform.users (\n user_id character varying(64) NOT NULL, -- unique identifier for the user\n username character varying(128) NOT NULL, -- username of the user\n email character varying(128) NOT NULL, -- email address of the user\n password_hash text NOT NULL, -- hashed password of the user\n created_at timestamp NOT NULL, -- time when the user account was created\n PRIMARY KEY (user_id)\n)\nCREATE TABLE trading_platform.orders (\n order_id character varying(64) NOT NULL, -- unique identifier for the order\n user_id character varying(64) NOT NULL, -- identifier of the user placing the order\n wallet_id character varying(64) NOT NULL, -- identifier of the wallet used for the order\n asset_id character varying(64) NOT NULL, -- identifier of the asset being traded\n order_type character varying(32) NOT NULL, -- type of the order (e.g., buy, sell)\n quantity numeric(38,14) NOT NULL, -- quantity of the asset in the order\n price numeric(38,14) NOT NULL, -- price per unit of the asset\n status character varying(32) NOT NULL, -- status of the order (e.g., open, filled, canceled)\n created_at timestamp NOT NULL, -- time when the order was created\n PRIMARY KEY (order_id)\n)\nCREATE TABLE trading_platform.dapps (\n dapp_id character varying(64) NOT NULL, -- unique identifier for the DApp\n name character varying(128) NOT NULL, -- name of the DApp\n description text NOT NULL, -- description of the DApp\n url character varying(256) NOT NULL, -- URL of the DApp\n PRIMARY KEY (dapp_id)\n)\nCREATE TABLE trading_platform.peers (\n peer_id character varying(64) NOT NULL, -- unique identifier for the peer\n ip_address character varying(15) NOT NULL, -- IP address of the peer\n port integer NOT NULL, -- port number of the peer\n last_seen timestamp NOT NULL, -- last time the peer was active\n PRIMARY KEY (peer_id)\n)\nCREATE TABLE trading_platform.metadata (\n metadata_id character varying(64) NOT NULL, -- unique identifier for the metadata\n asset_id character varying(64) NOT NULL, -- identifier of the asset the metadata is associated with\n key character varying(128) NOT NULL, -- key of the metadata\n value text NOT NULL, -- value of the metadata\n PRIMARY KEY (metadata_id)\n)\nCREATE TABLE trading_platform.logs (\n log_id character varying(64) NOT NULL, -- unique identifier for the log entry\n user_id character varying(64), -- identifier of the user associated with the log entry\n action character varying(128) NOT NULL, -- action performed\n details text NOT NULL, -- details of the action\n logged_at timestamp NOT NULL, -- time when the log entry was created\n PRIMARY KEY (log_id)\n)\n"} {"conversations": [{"role": "user", "content": "Which rooms on the 4th floor are non-smoking, along with their property IDs and type IDs?"}, {"role": "assistant", "content": "SELECT room_id, property_id, room_number, room_type_id FROM hospitality_technology.rooms WHERE floor = 4 AND is_smoking = FALSE;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE hospitality_technology.rooms ( room_id character varying(64) NOT NULL, property_id character varying(64) NOT NULL, room_number character varying(10) NOT NULL, room_type_id character varying(64) NOT NULL, floor integer, status character varying(50) NOT NULL, is_smoking boolean NOT NULL DEFAULT false, features text, current_condition text, last_cleaned_at timestamp with time zone, PRIMARY KEY (room_id), FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id), FOREIGN KEY (room_type_id) REFERENCES hospitality_technology.room_types(room_type_id) )\n"} {"conversations": [{"role": "user", "content": "List all managers (employees who have other employees reporting to them) along with the count of their direct reports, showing only those with more than 5 reports."}, {"role": "assistant", "content": "SELECT e.employee_id, e.first_name, e.last_name, COUNT(r.employee_id) as direct_reports_count FROM financial_services.employees e JOIN financial_services.employees r ON e.employee_id = r.manager_id WHERE e.status = 'Active' GROUP BY e.employee_id, e.first_name, e.last_name HAVING COUNT(r.employee_id) > 5 ORDER BY direct_reports_count DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE financial_services.employees ( employee_id text PRIMARY KEY, first_name text, last_name text, job_title text, department text, branch_id text, email text, phone_extension text, hire_date date, termination_date date, manager_id text, status text )\n"} {"conversations": [{"role": "user", "content": "Show all SUI coins with 'exists' status and more than 8 decimal places. Display coin_type, symbol, name, and decimals."}, {"role": "assistant", "content": "SELECT coin_type, symbol, name, decimals\nFROM sui_coins_metadata\nWHERE status = 'exists' AND decimals > 8;"}, {"role": "user", "content": "Add the total balance for each coin_type by joining with sui_coins."}, {"role": "assistant", "content": "SELECT scm.coin_type, scm.symbol, scm.name, scm.decimals, SUM(sc.balance::numeric) AS total_balance\nFROM sui_coins_metadata scm\nJOIN sui_coins sc ON scm.coin_type = sc.coin_type\nWHERE scm.status = 'exists' AND scm.decimals > 8\nGROUP BY scm.coin_type, scm.symbol, scm.name, scm.decimals;"}, {"role": "user", "content": "Can you also include only coins where the total_balance is greater than 1,000,000 and show the description?"}, {"role": "assistant", "content": "SELECT scm.coin_type, scm.symbol, scm.name, scm.decimals, scm.description, SUM(sc.balance::numeric) AS total_balance\nFROM sui_coins_metadata scm\nJOIN sui_coins sc ON scm.coin_type = sc.coin_type\nWHERE scm.status = 'exists' AND scm.decimals > 8\nGROUP BY scm.coin_type, scm.symbol, scm.name, scm.decimals, scm.description\nHAVING SUM(sc.balance::numeric) > 1000000;"}, {"role": "user", "content": "Actually, only show the top 5 coins with the highest total_balance."}, {"role": "assistant", "content": "SELECT scm.coin_type, scm.symbol, scm.name, scm.decimals, scm.description, SUM(sc.balance::numeric) AS total_balance\nFROM sui_coins_metadata scm\nJOIN sui_coins sc ON scm.coin_type = sc.coin_type\nWHERE scm.status = 'exists' AND scm.decimals > 8\nGROUP BY scm.coin_type, scm.symbol, scm.name, scm.decimals, scm.description\nHAVING SUM(sc.balance::numeric) > 1000000\nORDER BY total_balance DESC\nLIMIT 5;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE nft_holders ( block_number bigint NOT NULL, contract_address varchar NOT NULL, wallet_address varchar NOT NULL, token_id varchar NOT NULL, contract_type varchar NOT NULL, amount varchar NOT NULL, pk varchar NOT NULL )\nCREATE TABLE sui_coins ( object_id varchar NOT NULL, status varchar NOT NULL, coin_type varchar NOT NULL, balance varchar NOT NULL, owner varchar NOT NULL )\nCREATE TABLE sui_coins_metadata (\n object_id varchar NOT NULL, -- object id of the coin metadata object\n coin_type varchar NOT NULL, -- coin type, eg. 0x...66::reap_token::REAP_TOKEN\n status varchar NOT NULL, -- coin status, eg. exists, deleted\n decimals bigint NOT NULL, -- decimals of the coin\n description varchar NOT NULL, -- description of the coin\n icon_url varchar NOT NULL, -- icon url of the coin\n symbol varchar NOT NULL, -- symbol of the coin\n name varchar NOT NULL -- name of the coin\n)\nCREATE TABLE sui_nfts ( object_id text, status text, collection_type text, package_id text, previous_transaction text, display text, owner text, name text )\nCREATE TABLE nft_metadata ( blockchain text, contract_address text, token_id text, contract_name text, erc_type text, amount bigint, minter text, owner text, mint_block_number bigint, mint_time bigint, mint_transaction_hash text, mint_price text, token_uri text, metadata text, name text, image_uri text, traits text, updated_at bigint, status text, rarity_score real, rarity_rank integer, unique_attribute_count integer, pk integer )\nCREATE TABLE nft_collections ( blockchain varchar NOT NULL, contract_address varchar NOT NULL, name varchar NOT NULL, symbol varchar NOT NULL, deploy_block_number bigint NOT NULL, deploy_block_time bigint NOT NULL, erc_type varchar NOT NULL, owner varchar NOT NULL, traits varchar NOT NULL, description varchar NOT NULL, slug varchar NOT NULL, media_info varchar NOT NULL, image_url varchar NOT NULL, banner_image_url varchar NOT NULL, updated_at bigint NOT NULL, banner varchar NOT NULL, token_count bigint NOT NULL, floor_price varchar NOT NULL, floor_price_symbol varchar NOT NULL, floor_price_contract varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE token_prices ( uuid text, blockchain text, address text, decimals bigint, symbol text, price real, timestamp timestamp )\nCREATE TABLE token_prices_latest (\n blockchain varchar(36) NOT NULL, -- blockchain fields for the functionType in contract\n address varchar(42) NOT NULL, -- address fields for the functionType in contract\n decimals bigint NOT NULL, -- decimals fields for the functionType in contract\n symbol varchar(36) NOT NULL, -- symbol fields for the functionType in contract\n price real NOT NULL, -- price fields for the functionType in contract\n timestamp timestamp(6) NOT NULL -- timestamp fields for the functionType in contract\n)\nCREATE TABLE erc20_approval ( block_number bigint NOT NULL, block_timestamp timestamp(6) NOT NULL, transaction_index integer NOT NULL, transaction_hash varchar NOT NULL, log_index integer NOT NULL, contract_address varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE token_balances ( block_number.bigint, block_timestamp.timestamp, tick.text, wallet_address.text, total_supply.decimal, amount.decimal )\nCREATE TABLE token_info (\n block_timestamp timestamp(3) NOT NULL, -- Timestamp of the block containing the inscription (matches block_timestamp in transactions table)\n block_number bigint NOT NULL, -- Block number containing the inscription (matches block_number in transactions table)\n tx_index integer NOT NULL, -- Index of the transaction containing the inscription (matches transaction_index in transactions table)\n tx_hash varchar(66) NOT NULL, -- Unique identifier of the transaction containing the inscription (matches hash in transactions table)\n tick varchar NOT NULL, -- Token tick\n max_supply decimal(38,0) NOT NULL, -- Max supply\n lim decimal(38,0) NOT NULL, -- Limit of each mint\n wlim decimal(38,0) NOT NULL, -- Limit of each address can maximum mint\n dec integer NOT NULL, -- Decimal for minimum divie\n creator varchar(42) NOT NULL -- Address originating the inscription (matches from_address in transactions table)\n)\nCREATE TABLE mud_holesky_redstone (\n address varchar NOT NULL, -- address fields for the functionType in contract\n table_id varchar NOT NULL, -- table_id fields for the functionType in contract\n key_bytes varchar NOT NULL, -- key_bytes fields for the functionType in contract\n key0 varchar NOT NULL, -- key0 fields for the functionType in contract\n key1 varchar NOT NULL, -- key1 fields for the functionType in contract\n static_data varchar NOT NULL, -- static_data fields for the functionType in contract\n encoded_lengths varchar NOT NULL, -- encoded_lengths fields for the functionType in contract\n dynamic_data varchar NOT NULL, -- dynamic_data fields for the functionType in contract\n is_deleted boolean NOT NULL, -- is_deleted fields for the functionType in contract\n block_number bigint NOT NULL, -- Block number uniquely identifying the block\n log_index bigint NOT NULL -- Index of the log within the transaction\n)\nCREATE TABLE token_info_bitcoin ( block_timestamp.timestamp, block_number.bigint, tx_index.integer, tx_hash.text, tick.text, max_supply.decimal, lim.decimal, wlim.decimal, dec.integer, creator.text )\nCREATE TABLE token_activities_avalanche (\n block_timestamp timestamp(3) NOT NULL, -- Timestamp of the block containing the inscription (matches block_timestamp in transactions table)\n block_number bigint NOT NULL, -- Block number containing the inscription (matches block_number in transactions table)\n tx_index integer NOT NULL, -- Index of the transaction containing the inscription (matches transaction_index in transactions table)\n tx_hash varchar(66) NOT NULL, -- Unique identifier of the transaction containing the inscription (matches hash in transactions table)\n log_index integer NOT NULL, -- Index of the log within the transaction\n type varchar(20) NOT NULL, -- Operation: Type of event (deploy, mint, transfer, list)\n tick varchar(255) NOT NULL, -- Ticker: Identifier of the inscription\n id varchar(255) NOT NULL, -- Unique identifier of the inscription\n amt decimal(38,0) NOT NULL, -- Amount to mint: States the amount of the inscription to operation. When operation is mint, has to be less or equal to \"lim\"\n from_address varchar(42) NOT NULL, -- Address sending the inscription\n to_address varchar(42) NOT NULL -- Address receiving the inscription\n)\nCREATE TABLE token_balances_avalanche ( block_number bigint, block_timestamp timestamp, tick varchar, wallet_address varchar, total_supply decimal, amount decimal )\n"} {"conversations": [{"role": "user", "content": "List the full name (first name and last name) of all citizens who have uploaded documents whose expiry date is in the past."}, {"role": "assistant", "content": "SELECT DISTINCT T1.first_name, T1.last_name FROM government_services.citizens AS T1 INNER JOIN government_services.documents AS T2 ON T1.citizen_id = T2.citizen_id WHERE T2.expiry_date < CURRENT_DATE;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.citizens ( citizen_id text PRIMARY KEY, national_id_number text, first_name text, last_name text, date_of_birth date, gender text, primary_address text, contact_email text, contact_phone text, registration_date timestamp, is_verified boolean )\nCREATE TABLE government_services.agencies ( agency_id text PRIMARY KEY, agency_name text, jurisdiction_level text, primary_contact_email text, main_phone_number text, website_url text, established_date date, parent_agency_id text )\nCREATE TABLE government_services.documents ( document_id text PRIMARY KEY, application_id text, citizen_id text, document_type text, file_reference text, upload_timestamp timestamp, expiry_date date, verification_status text, verified_by_employee_id text, verification_timestamp timestamp )\nCREATE TABLE government_services.payments ( payment_id text PRIMARY KEY, application_id text, citizen_id text, service_id text, amount numeric, currency text, payment_method text, payment_provider_reference text, payment_timestamp timestamp, status text, notes text )\nCREATE TABLE government_services.service_locations ( location_id text PRIMARY KEY, agency_id text, location_name text, address text, city text, state text, postal_code text, latitude numeric, longitude numeric, operating_hours text, contact_phone text, is_accessible boolean )\nCREATE TABLE government_services.appointments ( appointment_id text PRIMARY KEY, citizen_id text, employee_id text, location_id text, service_id text, scheduled_start_time timestamp, scheduled_end_time timestamp, purpose text, status text, booking_method text, created_at timestamp, notes text )\n"} {"conversations": [{"role": "user", "content": "Show the property name, star rating, and number of rooms for each property."}, {"role": "assistant", "content": "SELECT p.property_name, p.star_rating, COUNT(r.room_id) AS room_count\nFROM hospitality_technology.properties p\nLEFT JOIN hospitality_technology.rooms r ON p.property_id = r.property_id\nGROUP BY p.property_id, p.property_name, p.star_rating;"}, {"role": "user", "content": "Only include properties that have more than 30 rooms."}, {"role": "assistant", "content": "SELECT p.property_name, p.star_rating, COUNT(r.room_id) AS room_count\nFROM hospitality_technology.properties p\nLEFT JOIN hospitality_technology.rooms r ON p.property_id = r.property_id\nGROUP BY p.property_id, p.property_name, p.star_rating\nHAVING COUNT(r.room_id) > 30;"}, {"role": "user", "content": "Add a column showing the total number of unique room types at each property."}, {"role": "assistant", "content": "SELECT p.property_name, p.star_rating, COUNT(r.room_id) AS room_count, COUNT(DISTINCT rt.room_type_id) AS unique_room_type_count\nFROM hospitality_technology.properties p\nLEFT JOIN hospitality_technology.rooms r ON p.property_id = r.property_id\nLEFT JOIN hospitality_technology.room_types rt ON p.property_id = rt.property_id\nGROUP BY p.property_id, p.property_name, p.star_rating\nHAVING COUNT(r.room_id) > 30;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE hospitality_technology.properties ( property_id text, property_name text, address_line1 text, address_line2 text, city text, state_province text, postal_code text, country_code text, phone_number text, email_address text, property_type text, star_rating numeric, timezone text, manager_staff_id text, created_at timestamp, updated_at timestamp )\nCREATE TABLE hospitality_technology.rooms (\n room_id character varying(64) NOT NULL, -- unique identifier for the room\n property_id character varying(64) NOT NULL, -- FK to properties table\n room_number character varying(10) NOT NULL, -- room number identifier (e.g., '101', 'Suite 2B')\n room_type_id character varying(64) NOT NULL, -- FK to room_types table\n floor integer, -- floor number the room is on\n status character varying(50) NOT NULL, -- e.g., Available, Occupied, Cleaning, OutOfOrder, Maintenance\n is_smoking boolean NOT NULL DEFAULT false, -- smoking allowed flag\n features text, -- description of features (e.g., Balcony, Sea View, Jacuzzi)\n current_condition text, -- notes on room condition\n last_cleaned_at timestamp with time zone, -- timestamp of last cleaning\n PRIMARY KEY (room_id),\n FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id),\n FOREIGN KEY (room_type_id) REFERENCES hospitality_technology.room_types(room_type_id)\n)\nCREATE TABLE hospitality_technology.room_types (\n room_type_id character varying(64) NOT NULL, -- unique identifier for the room type\n property_id character varying(64) NOT NULL, -- FK to properties table (type might be property-specific)\n type_name character varying(100) NOT NULL, -- e.g., Standard King, Deluxe Queen, Executive Suite\n description text, -- description of the room type\n base_rate numeric(10, 2) NOT NULL, -- standard price per night\n max_occupancy integer NOT NULL, -- maximum number of guests\n bed_type character varying(50), -- e.g., King, Queen, 2 Doubles, Twin\n area_sqft numeric(8,2), -- size of the room in square feet\n amenities text, -- comma-separated list or JSON of amenities\n PRIMARY KEY (room_type_id),\n FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id)\n)\nCREATE TABLE hospitality_technology.guests ( guest_id text, first_name text, last_name text, email text, phone_number text, date_of_birth date, address_line1 text, city text, state_province text, postal_code text, country_code text, preferences text, loyalty_member_id text, communication_consent boolean, created_at timestamp, updated_at timestamp )\nCREATE TABLE hospitality_technology.reservations ( reservation_id.text, property_id.text, guest_id.text, room_id.text, room_type_id.text, check_in_date.date, check_out_date.date, actual_check_in_ts.timestamp, actual_check_out_ts.timestamp, num_adults.integer, num_children.integer, status.text, booking_source.text, rate_plan_id.text, total_amount.numeric, amount_paid.numeric, special_requests.text, created_at.timestamp, updated_at.timestamp )\nCREATE TABLE hospitality_technology.staff ( staff_id text, property_id text, first_name text, last_name text, position text, work_email text, work_phone text, hire_date date, termination_date date, is_active boolean, access_level integer, manager_id text, created_at timestamp )\nCREATE TABLE hospitality_technology.service_orders ( order_id character varying(64) NOT NULL, reservation_id character varying(64), guest_id character varying(64) NOT NULL, service_id character varying(64) NOT NULL, staff_id_ordered character varying(64), staff_id_delivered character varying(64), order_timestamp timestamp with time zone NOT NULL DEFAULT current_timestamp, delivery_timestamp timestamp with time zone, quantity integer NOT NULL DEFAULT 1, unit_price numeric(10, 2) NOT NULL, total_price numeric(12, 2) NOT NULL, status character varying(50) NOT NULL, notes text, bill_id character varying(64), PRIMARY KEY (order_id), FOREIGN KEY (reservation_id) REFERENCES hospitality_technology.reservations(reservation_id), FOREIGN KEY (guest_id) REFERENCES hospitality_technology.guests(guest_id), FOREIGN KEY (service_id) REFERENCES hospitality_technology.services(service_id), FOREIGN KEY (staff_id_ordered) REFERENCES hospitality_technology.staff(staff_id), FOREIGN KEY (staff_id_delivered) REFERENCES hospitality_technology.staff(staff_id) )\nCREATE TABLE hospitality_technology.payments (\n payment_id character varying(64) NOT NULL, -- unique identifier for the payment transaction\n reservation_id character varying(64), -- FK to reservations (if payment is for a stay)\n guest_id character varying(64) NOT NULL, -- FK to guests (who paid)\n bill_id character varying(64), -- FK to bills/invoices this payment applies to\n amount numeric(12,2) NOT NULL, -- amount of the payment\n currency_code character varying(3) NOT NULL, -- ISO currency code (e.g., USD, EUR)\n payment_method character varying(50) NOT NULL, -- e.g., CreditCard, Cash, BankTransfer, Points, Voucher\n card_type character varying(50), -- e.g., Visa, MasterCard, Amex (if CC)\n card_last_four character varying(4), -- last 4 digits of CC (if CC)\n transaction_ref character varying(128), -- reference ID from payment gateway or processor\n payment_timestamp timestamp with time zone NOT NULL DEFAULT current_timestamp, -- when the payment occurred\n status character varying(50) NOT NULL, -- e.g., Pending, Succeeded, Failed, Refunded, Disputed\n staff_id_processed character varying(64), -- FK to staff (who processed the payment)\n notes text, -- notes about the payment\n PRIMARY KEY (payment_id),\n FOREIGN KEY (reservation_id) REFERENCES hospitality_technology.reservations(reservation_id),\n FOREIGN KEY (guest_id) REFERENCES hospitality_technology.guests(guest_id),\n FOREIGN KEY (staff_id_processed) REFERENCES hospitality_technology.staff(staff_id)\n)\nCREATE TABLE hospitality_technology.reviews ( review_id character varying(64) NOT NULL, property_id character varying(64) NOT NULL, reservation_id character varying(64) UNIQUE, guest_id character varying(64) NOT NULL, rating_overall integer, rating_cleanliness integer, rating_service integer, rating_location integer, rating_value integer, comment text, review_source character varying(100), review_date timestamp with time zone NOT NULL DEFAULT current_timestamp, is_public boolean DEFAULT true, staff_response text, response_staff_id character varying(64), response_date timestamp with time zone, PRIMARY KEY (review_id), FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id), FOREIGN KEY (reservation_id) REFERENCES hospitality_technology.reservations(reservation_id), FOREIGN KEY (guest_id) REFERENCES hospitality_technology.guests(guest_id), FOREIGN KEY (response_staff_id) REFERENCES hospitality_technology.staff(staff_id) )\n"} {"conversations": [{"role": "user", "content": "Provide a report of each user with their username and the count of all log entries from the last 30 days."}, {"role": "assistant", "content": "SELECT u.user_id, u.username, COUNT(l.log_id) AS log_count\nFROM trading_platform.users u\nLEFT JOIN trading_platform.logs l\n ON u.user_id = l.user_id\n AND l.logged_at >= CURRENT_DATE - INTERVAL '30 days'\nGROUP BY u.user_id, u.username;"}, {"role": "user", "content": "Actually, show only logs where the action includes the word 'trade'."}, {"role": "assistant", "content": "SELECT u.user_id, u.username, COUNT(l.log_id) AS log_count\nFROM trading_platform.users u\nJOIN trading_platform.logs l\n ON u.user_id = l.user_id\nWHERE l.logged_at >= CURRENT_DATE - INTERVAL '30 days'\n AND l.action ILIKE '%trade%'\nGROUP BY u.user_id, u.username;"}, {"role": "user", "content": "Also include the earliest log date for each user in that period."}, {"role": "assistant", "content": "SELECT u.user_id,\n u.username,\n COUNT(l.log_id) AS log_count,\n MIN(l.logged_at) AS first_log_date\nFROM trading_platform.users u\nJOIN trading_platform.logs l\n ON u.user_id = l.user_id\nWHERE l.logged_at >= CURRENT_DATE - INTERVAL '30 days'\n AND l.action ILIKE '%trade%'\nGROUP BY u.user_id, u.username;"}, {"role": "user", "content": "Finally, sort the results by log_count descending and limit to the top 5 users."}, {"role": "assistant", "content": "SELECT u.user_id,\n u.username,\n COUNT(l.log_id) AS log_count,\n MIN(l.logged_at) AS first_log_date\nFROM trading_platform.users u\nJOIN trading_platform.logs l\n ON u.user_id = l.user_id\nWHERE l.logged_at >= CURRENT_DATE - INTERVAL '30 days'\n AND l.action ILIKE '%trade%'\nGROUP BY u.user_id, u.username\nORDER BY log_count DESC\nLIMIT 5;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE trading_platform.users (\n user_id character varying(64) NOT NULL, -- unique identifier for the user\n username character varying(128) NOT NULL, -- username of the user\n email character varying(128) NOT NULL, -- email address of the user\n password_hash text NOT NULL, -- hashed password of the user\n created_at timestamp NOT NULL, -- time when the user account was created\n PRIMARY KEY (user_id)\n)\nCREATE TABLE trading_platform.orders (\n order_id character varying(64) NOT NULL, -- unique identifier for the order\n user_id character varying(64) NOT NULL, -- identifier of the user placing the order\n wallet_id character varying(64) NOT NULL, -- identifier of the wallet used for the order\n asset_id character varying(64) NOT NULL, -- identifier of the asset being traded\n order_type character varying(32) NOT NULL, -- type of the order (e.g., buy, sell)\n quantity numeric(38,14) NOT NULL, -- quantity of the asset in the order\n price numeric(38,14) NOT NULL, -- price per unit of the asset\n status character varying(32) NOT NULL, -- status of the order (e.g., open, filled, canceled)\n created_at timestamp NOT NULL, -- time when the order was created\n PRIMARY KEY (order_id)\n)\nCREATE TABLE trading_platform.utxos (\n utxo_id character varying(64) NOT NULL, -- unique identifier for the UTXO\n transaction_id character varying(64) NOT NULL, -- identifier of the transaction that created the UTXO\n output_index integer NOT NULL, -- index of the output in the transaction\n address character varying(128) NOT NULL, -- address that can spend the UTXO\n amount numeric(38,14) NOT NULL, -- amount of the asset in the UTXO\n spent boolean NOT NULL, -- whether the UTXO has been spent\n PRIMARY KEY (utxo_id)\n)\nCREATE TABLE trading_platform.dapps (\n dapp_id character varying(64) NOT NULL, -- unique identifier for the DApp\n name character varying(128) NOT NULL, -- name of the DApp\n description text NOT NULL, -- description of the DApp\n url character varying(256) NOT NULL, -- URL of the DApp\n PRIMARY KEY (dapp_id)\n)\nCREATE TABLE trading_platform.peers (\n peer_id character varying(64) NOT NULL, -- unique identifier for the peer\n ip_address character varying(15) NOT NULL, -- IP address of the peer\n port integer NOT NULL, -- port number of the peer\n last_seen timestamp NOT NULL, -- last time the peer was active\n PRIMARY KEY (peer_id)\n)\nCREATE TABLE trading_platform.logs (\n log_id character varying(64) NOT NULL, -- unique identifier for the log entry\n user_id character varying(64), -- identifier of the user associated with the log entry\n action character varying(128) NOT NULL, -- action performed\n details text NOT NULL, -- details of the action\n logged_at timestamp NOT NULL, -- time when the log entry was created\n PRIMARY KEY (log_id)\n)\n"} {"conversations": [{"role": "user", "content": "Show the IDs and registration dates of all verified citizens who could be eligible for at least one active service. Display the citizen ID and registration date."}, {"role": "assistant", "content": "SELECT DISTINCT c.citizen_id, c.registration_date\nFROM government_services.citizens c\nJOIN government_services.services s ON s.is_active = true\nWHERE c.is_verified = true;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.citizens ( citizen_id character varying(64) NOT NULL, national_id_number character varying(128) NOT NULL UNIQUE, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, date_of_birth date NOT NULL, gender character varying(20), primary_address text NOT NULL, contact_email character varying(128) UNIQUE, contact_phone character varying(32), registration_date timestamp NOT NULL, is_verified boolean DEFAULT false, PRIMARY KEY (citizen_id) )\nCREATE TABLE government_services.services ( service_id.text, agency_id.text, service_name.text, description.text, category.text, eligibility_criteria.text, standard_fee.numeric, average_processing_time_days.integer, is_active.boolean, online_application_url.text )\n"} {"conversations": [{"role": "user", "content": "Show me the top 5 ERC20 tokens with the highest total supply, along with their names and contract addresses, but only include tokens where the price is greater than $0.10."}, {"role": "assistant", "content": "SELECT tm.name, tm.contract_address, tm.total_supply FROM token_metas tm JOIN token_prices_latest tpl ON tm.contract_address = tpl.address WHERE tm.is_erc20 = 1 AND tpl.price > 0.10 ORDER BY CAST(tm.total_supply AS decimal) DESC LIMIT 5;"}, {"role": "user", "content": "Can you also include the symbol and decimals for these tokens?"}, {"role": "assistant", "content": "SELECT tm.name, tm.symbol, tm.contract_address, tm.total_supply, tm.decimals FROM token_metas tm JOIN token_prices_latest tpl ON tm.contract_address = tpl.address WHERE tm.is_erc20 = 1 AND tpl.price > 0.10 ORDER BY CAST(tm.total_supply AS decimal) DESC LIMIT 5;"}, {"role": "user", "content": "Now filter these results to only show tokens with decimals equal to 18."}, {"role": "assistant", "content": "SELECT tm.name, tm.symbol, tm.contract_address, tm.total_supply, tm.decimals FROM token_metas tm JOIN token_prices_latest tpl ON tm.contract_address = tpl.address WHERE tm.is_erc20 = 1 AND tpl.price > 0.10 AND tm.decimals = 18 ORDER BY CAST(tm.total_supply AS decimal) DESC LIMIT 5;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE token_metas ( block_timestamp timestamp(6) NOT NULL, block_number bigint NOT NULL, transaction_hash varchar NOT NULL, transaction_index bigint NOT NULL, from_address varchar NOT NULL, contract_address varchar NOT NULL, symbol varchar NOT NULL, total_supply varchar NOT NULL, name varchar NOT NULL, decimals bigint NOT NULL, is_erc20 integer NOT NULL, is_erc721 integer NOT NULL, is_erc1155 integer NOT NULL, is_proxy integer NOT NULL, extra_info varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE erc1155_approval_for_all ( block_number bigint NOT NULL, block_timestamp timestamp(3) NOT NULL, transaction_index integer NOT NULL, transaction_hash varchar(66) NOT NULL, log_index integer NOT NULL, contract_address varchar(42) NOT NULL )\nCREATE TABLE erc20_balances ( block_number bigint NOT NULL, contract_address varchar NOT NULL, wallet_address varchar NOT NULL, amount varchar NOT NULL, pk varchar NOT NULL )\nCREATE TABLE erc20_balances_historical ( block_number bigint NOT NULL, contract_address varchar NOT NULL, wallet_address varchar NOT NULL, amount varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE nft_holders ( block_number bigint NOT NULL, contract_address varchar NOT NULL, wallet_address varchar NOT NULL, token_id varchar NOT NULL, contract_type varchar NOT NULL, amount varchar NOT NULL, pk varchar NOT NULL )\nCREATE TABLE nft_holder_historical ( block_number bigint NOT NULL, contract_address varchar NOT NULL, wallet_address varchar NOT NULL, token_id varchar NOT NULL, contract_type varchar NOT NULL, amount varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE sui_coins ( object_id varchar NOT NULL, status varchar NOT NULL, coin_type varchar NOT NULL, balance varchar NOT NULL, owner varchar NOT NULL )\nCREATE TABLE sui_coins_metadata ( object_id varchar NOT NULL, coin_type varchar NOT NULL, status varchar NOT NULL, decimals bigint NOT NULL, description varchar NOT NULL, icon_url varchar NOT NULL, symbol varchar NOT NULL, name varchar NOT NULL )\nCREATE TABLE sui_nfts ( object_id varchar NOT NULL, status varchar NOT NULL, collection_type varchar NOT NULL, package_id varchar NOT NULL, previous_transaction varchar NOT NULL, display varchar NOT NULL, owner varchar NOT NULL, name varchar NOT NULL )\nCREATE TABLE nft_metadata ( blockchain varchar NOT NULL, contract_address varchar NOT NULL, token_id varchar NOT NULL, contract_name varchar NOT NULL, erc_type varchar NOT NULL, amount bigint NOT NULL, minter varchar NOT NULL, owner varchar NOT NULL, mint_block_number bigint NOT NULL, mint_time bigint NOT NULL, mint_transaction_hash varchar NOT NULL, mint_price varchar NOT NULL, token_uri varchar NOT NULL, metadata varchar NOT NULL, name varchar NOT NULL, image_uri varchar NOT NULL, traits varchar NOT NULL, updated_at bigint NOT NULL, status varchar NOT NULL, rarity_score real NOT NULL, rarity_rank integer NOT NULL, unique_attribute_count integer NOT NULL, pk integer NOT NULL )\nCREATE TABLE nft_collections ( blockchain varchar NOT NULL, contract_address varchar NOT NULL, name varchar NOT NULL, symbol varchar NOT NULL, deploy_block_number bigint NOT NULL, deploy_block_time bigint NOT NULL, erc_type varchar NOT NULL, owner varchar NOT NULL, traits varchar NOT NULL, description varchar NOT NULL, slug varchar NOT NULL, media_info varchar NOT NULL, image_url varchar NOT NULL, banner_image_url varchar NOT NULL, updated_at bigint NOT NULL, banner varchar NOT NULL, token_count bigint NOT NULL, floor_price varchar NOT NULL, floor_price_symbol varchar NOT NULL, floor_price_contract varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE token_prices ( uuid varchar(36) NOT NULL, blockchain varchar(36) NOT NULL, address varchar(42) NOT NULL, decimals bigint NOT NULL, symbol varchar(36) NOT NULL, price real NOT NULL, timestamp timestamp(6) NOT NULL )\nCREATE TABLE token_prices_latest ( blockchain varchar(36) NOT NULL, address varchar(42) NOT NULL, decimals bigint NOT NULL, symbol varchar(36) NOT NULL, price real NOT NULL, timestamp timestamp(6) NOT NULL )\nCREATE TABLE erc20_approval ( block_number bigint NOT NULL, block_timestamp timestamp(6) NOT NULL, transaction_index integer NOT NULL, transaction_hash varchar NOT NULL, log_index integer NOT NULL, contract_address varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE token_balances ( block_number bigint NOT NULL, block_timestamp timestamp(3) NOT NULL, tick varchar NOT NULL, wallet_address varchar(42) NOT NULL, total_supply decimal(38,0) NOT NULL, amount decimal(38,0) NOT NULL )\nCREATE TABLE token_info ( block_timestamp timestamp(3) NOT NULL, block_number bigint NOT NULL, tx_index integer NOT NULL, tx_hash varchar(66) NOT NULL, tick varchar NOT NULL, max_supply decimal(38,0) NOT NULL, lim decimal(38,0) NOT NULL, wlim decimal(38,0) NOT NULL, dec integer NOT NULL, creator varchar(42) NOT NULL )\nCREATE TABLE token_activities ( block_timestamp timestamp(3) NOT NULL, block_number bigint NOT NULL, tx_index integer NOT NULL, tx_hash varchar(66) NOT NULL, log_index integer NOT NULL, type varchar NOT NULL, tick varchar NOT NULL, id varchar(255) NOT NULL, amt decimal(38,0) NOT NULL, from_address varchar(42) NOT NULL, to_address varchar(42) NOT NULL )\nCREATE TABLE mud_holesky_redstone ( address varchar NOT NULL, table_id varchar NOT NULL, key_bytes varchar NOT NULL, key0 varchar NOT NULL, key1 varchar NOT NULL, static_data varchar NOT NULL, encoded_lengths varchar NOT NULL, dynamic_data varchar NOT NULL, is_deleted boolean NOT NULL, block_number bigint NOT NULL, log_index bigint NOT NULL )\nCREATE TABLE token_balances_bitcoin ( block_number bigint NOT NULL, block_timestamp timestamp(3) NOT NULL, tick varchar(255) NOT NULL, wallet_address varchar(42) NOT NULL, total_supply varchar NOT NULL, amount varchar NOT NULL )\nCREATE TABLE token_activities_bitcoin ( block_timestamp timestamp(3) NOT NULL, block_number bigint NOT NULL, tx_index integer NOT NULL, tx_hash varchar(66) NOT NULL, log_index integer NOT NULL, type varchar(20) NOT NULL, tick varchar(255) NOT NULL, id varchar(255) NOT NULL, amt decimal(38,0) NOT NULL, from_address varchar(62) NOT NULL, to_address varchar(62) NOT NULL )\nCREATE TABLE token_activities_avalanche ( block_timestamp timestamp(3) NOT NULL, block_number bigint NOT NULL, tx_index integer NOT NULL, tx_hash varchar(66) NOT NULL, log_index integer NOT NULL, type varchar(20) NOT NULL, tick varchar(255) NOT NULL, id varchar(255) NOT NULL, amt decimal(38,0) NOT NULL, from_address varchar(42) NOT NULL, to_address varchar(42) NOT NULL )\nCREATE TABLE token_balances_avalanche ( block_number bigint NOT NULL, block_timestamp timestamp(3) NOT NULL, tick varchar(20) NOT NULL, wallet_address varchar(42) NOT NULL, total_supply decimal(38,0) NOT NULL, amount decimal(38,0) NOT NULL )\nCREATE TABLE token_info_avalanche ( block_timestamp timestamp(3) NOT NULL, block_number bigint NOT NULL, tx_index integer NOT NULL, tx_hash varchar(66) NOT NULL, tick varchar(20) NOT NULL, max_supply decimal(38,0) NOT NULL, lim decimal(38,0) NOT NULL, wlim decimal(38,0) NOT NULL, dec integer NOT NULL, creator varchar(42) NOT NULL, minted decimal(38,0) NOT NULL, holders decimal(38,0) NOT NULL, txs decimal(38,0) NOT NULL, updated_timestamp timestamp(3) NOT NULL, completed_timestamp timestamp(3) NOT NULL, id varchar(255) NOT NULL )\n"} {"conversations": [{"role": "user", "content": "Provide a count of notifications, separated by whether they have been read or not."}, {"role": "assistant", "content": "SELECT CASE WHEN T1.read_at IS NULL THEN 'Unread' ELSE 'Read' END, count(T1.notification_id) FROM trading_platform.notifications AS T1 GROUP BY CASE WHEN T1.read_at IS NULL THEN 'Unread' ELSE 'Read' END"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE trading_platform.notifications ( notification_id.text, user_id.text, message.text, sent_at.timestamp, read_at.timestamp )\n"} {"conversations": [{"role": "user", "content": "I need to find all components associated with a specific supplier. Can you help with that?"}, {"role": "assistant", "content": "HGETALL component:\nIF HGET component: supplier_id = 'sup:ACME_AERO' THEN INCLUDE"}, {"role": "user", "content": "Can you also show me the material ID for each of these components?"}, {"role": "assistant", "content": "HGETALL component:\nIF HGET component: supplier_id = 'sup:ACME_AERO' THEN INCLUDE\nHGET component: material_id"}, {"role": "user", "content": "What if I want to exclude components with a specific material ID?"}, {"role": "assistant", "content": "HGETALL component:\nIF HGET component: supplier_id = 'sup:ACME_AERO' THEN INCLUDE\nHGET component: material_id\nIF HGET component: material_id != 'mat:TI64' THEN INCLUDE"}, {"role": "user", "content": "Can you add the component name to the result as well?"}, {"role": "assistant", "content": "HGETALL component:\nIF HGET component: supplier_id = 'sup:ACME_AERO' THEN INCLUDE\nHGET component: material_id\nIF HGET component: material_id != 'mat:TI64' THEN INCLUDE\nHGET component: component_name"}], "system": "You are an expert in writing database language. You can write a corresponding database language query to answer the user's question based on the table structure described by the table creation statement. \n##Table Structure\nUse Hashes. Key pattern: 'component:'. Example: HSET component:LGSTRUT01 part_number \"PN-5521-A\" component_name \"Landing Gear Strut\" material_id \"mat:TI64\" supplier_id \"sup:ACME_AERO\" ... Consider Sets for reverse lookups (e.g., 'material_components:' -> Set).\n"} {"conversations": [{"role": "user", "content": "List all guests who have a loyalty member ID, showing their full name (first and last name), email, and loyalty ID."}, {"role": "assistant", "content": "SELECT first_name, last_name, email, loyalty_member_id FROM hospitality_technology.guests WHERE loyalty_member_id IS NOT NULL;"}, {"role": "user", "content": "Can you also include the date they registered as a guest?"}, {"role": "assistant", "content": "SELECT first_name, last_name, email, loyalty_member_id, created_at FROM hospitality_technology.guests WHERE loyalty_member_id IS NOT NULL;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE hospitality_technology.rooms (\n room_id character varying(64) NOT NULL, -- unique identifier for the room\n property_id character varying(64) NOT NULL, -- FK to properties table\n room_number character varying(10) NOT NULL, -- room number identifier (e.g., '101', 'Suite 2B')\n room_type_id character varying(64) NOT NULL, -- FK to room_types table\n floor integer, -- floor number the room is on\n status character varying(50) NOT NULL, -- e.g., Available, Occupied, Cleaning, OutOfOrder, Maintenance\n is_smoking boolean NOT NULL DEFAULT false, -- smoking allowed flag\n features text, -- description of features (e.g., Balcony, Sea View, Jacuzzi)\n current_condition text, -- notes on room condition\n last_cleaned_at timestamp with time zone, -- timestamp of last cleaning\n PRIMARY KEY (room_id),\n FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id),\n FOREIGN KEY (room_type_id) REFERENCES hospitality_technology.room_types(room_type_id)\n)\nCREATE TABLE hospitality_technology.room_types ( room_type_id.text, property_id.text, type_name.text, description.text, base_rate.numeric, max_occupancy.integer, bed_type.text, area_sqft.numeric, amenities.text )\nCREATE TABLE hospitality_technology.guests ( guest_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, email character varying(255) UNIQUE, phone_number character varying(30), date_of_birth date, address_line1 character varying(255), city character varying(100), state_province character varying(100), postal_code character varying(20), country_code character varying(3), preferences text, loyalty_member_id character varying(64) UNIQUE, communication_consent boolean DEFAULT true, created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, updated_at timestamp with time zone NOT NULL DEFAULT current_timestamp, PRIMARY KEY (guest_id) )\nCREATE TABLE hospitality_technology.staff (\n staff_id character varying(64) NOT NULL, -- unique identifier for the staff member\n property_id character varying(64) NOT NULL, -- FK to properties table (primary property)\n first_name character varying(100) NOT NULL,\n last_name character varying(100) NOT NULL,\n position character varying(100) NOT NULL, -- e.g., Front Desk Agent, Housekeeper, Manager, Concierge\n work_email character varying(255) UNIQUE, -- staff member's work email\n work_phone character varying(30),\n hire_date date NOT NULL,\n termination_date date, -- date employment ended (if applicable)\n is_active boolean NOT NULL DEFAULT true, -- currently employed flag\n access_level integer NOT NULL, -- permission level within systems (e.g., 1=basic, 5=admin)\n manager_id character varying(64), -- FK to staff table (self-referencing for supervisor)\n created_at timestamp with time zone NOT NULL DEFAULT current_timestamp,\n PRIMARY KEY (staff_id),\n FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id),\n FOREIGN KEY (manager_id) REFERENCES hospitality_technology.staff(staff_id)\n)\nCREATE TABLE hospitality_technology.services ( service_id character varying(64) NOT NULL, property_id character varying(64) NOT NULL, service_name character varying(150) NOT NULL, description text, category character varying(100), price numeric(10, 2) NOT NULL, unit character varying(30), is_available boolean NOT NULL DEFAULT true, department character varying(100), PRIMARY KEY (service_id), FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id) )\nCREATE TABLE hospitality_technology.payments (\n payment_id character varying(64) NOT NULL, -- unique identifier for the payment transaction\n reservation_id character varying(64), -- FK to reservations (if payment is for a stay)\n guest_id character varying(64) NOT NULL, -- FK to guests (who paid)\n bill_id character varying(64), -- FK to bills/invoices this payment applies to\n amount numeric(12,2) NOT NULL, -- amount of the payment\n currency_code character varying(3) NOT NULL, -- ISO currency code (e.g., USD, EUR)\n payment_method character varying(50) NOT NULL, -- e.g., CreditCard, Cash, BankTransfer, Points, Voucher\n card_type character varying(50), -- e.g., Visa, MasterCard, Amex (if CC)\n card_last_four character varying(4), -- last 4 digits of CC (if CC)\n transaction_ref character varying(128), -- reference ID from payment gateway or processor\n payment_timestamp timestamp with time zone NOT NULL DEFAULT current_timestamp, -- when the payment occurred\n status character varying(50) NOT NULL, -- e.g., Pending, Succeeded, Failed, Refunded, Disputed\n staff_id_processed character varying(64), -- FK to staff (who processed the payment)\n notes text, -- notes about the payment\n PRIMARY KEY (payment_id),\n FOREIGN KEY (reservation_id) REFERENCES hospitality_technology.reservations(reservation_id),\n FOREIGN KEY (guest_id) REFERENCES hospitality_technology.guests(guest_id),\n FOREIGN KEY (staff_id_processed) REFERENCES hospitality_technology.staff(staff_id)\n)\n"} {"conversations": [{"role": "user", "content": "Can you help me retrieve the list of components made of a specific material along with their supplier details?"}, {"role": "assistant", "content": "SMEMBERS material_components:mat:TI64\nHGETALL component:\nHGET component: supplier_id"}, {"role": "user", "content": "Can you also include the part number for each component in the result?"}, {"role": "assistant", "content": "SMEMBERS material_components:mat:TI64\nHGETALL component:\nHGET component: supplier_id\nHGET component: part_number"}, {"role": "user", "content": "If I want to filter out components from a specific supplier, how can I modify the query?"}, {"role": "assistant", "content": "SMEMBERS material_components:mat:TI64\nHGETALL component:\nHGET component: supplier_id\nHGET component: part_number\nIF HGET component: supplier_id != 'sup:ACME_AERO' THEN INCLUDE"}, {"role": "user", "content": "Can you also sort the results based on the part number?"}, {"role": "assistant", "content": "SMEMBERS material_components:mat:TI64\nHGETALL component:\nHGET component: supplier_id\nHGET component: part_number\nIF HGET component: supplier_id != 'sup:ACME_AERO' THEN INCLUDE\nSORT BY part_number ASC"}], "system": "You are an expert in writing database language. You can write a corresponding database language query to answer the user's question based on the table structure described by the table creation statement. \n##Table Structure\nUse Hashes. Key pattern: 'component:'. Example: HSET component:LGSTRUT01 part_number \"PN-5521-A\" component_name \"Landing Gear Strut\" material_id \"mat:TI64\" supplier_id \"sup:ACME_AERO\" ... Consider Sets for reverse lookups (e.g., 'material_components:' -> Set).\n"} {"conversations": [{"role": "user", "content": "Show me each service order along with the next order placed by the same guest, including both order IDs and the time difference in minutes between the two orders."}, {"role": "assistant", "content": "SELECT a.order_id,\n b.order_id AS next_order_id,\n EXTRACT(EPOCH FROM (b.order_timestamp - a.order_timestamp)) / 60 AS diff_minutes\nFROM hospitality_technology.service_orders a\nJOIN hospitality_technology.service_orders b\n ON a.guest_id = b.guest_id\n AND b.order_timestamp > a.order_timestamp;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE hospitality_technology.service_orders ( order_id.text, reservation_id.text, guest_id.text, service_id.text, staff_id_ordered.text, staff_id_delivered.text, order_timestamp.timestamp, delivery_timestamp.timestamp, quantity.integer, unit_price.numeric, total_price.numeric, status.text, notes.text, bill_id.text )\n"} {"conversations": [{"role": "user", "content": "What is the maintenance schedule for platform 3 at station DEF for the next month?"}, {"role": "assistant", "content": "I'm sorry, but I don't have access to the maintenance schedule for platforms. The data I have only includes static information about platform details such as ID, station, number, track, status, length, and accessibility. For maintenance schedules, you may need to consult the station management or relevant department."}], "system": "You are an SQL statement expert and you can refuse the user's question if the question is not related to the table structure. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE train_station_management.platforms ( platform_id text, station_id text, platform_number text, track_number text, status text, length_meters numeric, accessible boolean )\n"} {"conversations": [{"role": "user", "content": "Show each service's name along with the total number of appointments scheduled and the number of unique locations these appointments are scheduled at."}, {"role": "assistant", "content": "SELECT s.service_name, COUNT(a.application_id) AS appointment_count, COUNT(DISTINCT ap.location_id) AS unique_location_count\nFROM government_services.services s\nJOIN government_services.applications a ON s.service_id = a.service_id\nJOIN government_services.appointments ap ON a.application_id = ap.application_id\nGROUP BY s.service_name;"}, {"role": "user", "content": "I got an error: relation 'appointments' does not exist."}, {"role": "assistant", "content": "-- The appointments table is not present in the provided schema. If you want to count by another join, perhaps by documents or payments, please specify.\n-- Alternatively, do you want appointment information replaced with application submissions per service and their associated location from service_locations?\nSELECT s.service_name, COUNT(a.application_id) AS application_count, COUNT(DISTINCT sl.location_id) AS unique_location_count\nFROM government_services.services s\nJOIN government_services.applications a ON s.service_id = a.service_id\nJOIN government_services.service_locations sl ON s.agency_id = sl.agency_id\nGROUP BY s.service_name;"}, {"role": "user", "content": "Show only those services where application_count is greater than 50."}, {"role": "assistant", "content": "SELECT s.service_name, COUNT(a.application_id) AS application_count, COUNT(DISTINCT sl.location_id) AS unique_location_count\nFROM government_services.services s\nJOIN government_services.applications a ON s.service_id = a.service_id\nJOIN government_services.service_locations sl ON s.agency_id = sl.agency_id\nGROUP BY s.service_name\nHAVING COUNT(a.application_id) > 50;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.citizens (\n citizen_id character varying(64) NOT NULL, -- unique identifier for the citizen\n national_id_number character varying(128) NOT NULL UNIQUE, -- official national identification number\n first_name character varying(100) NOT NULL,\n last_name character varying(100) NOT NULL,\n date_of_birth date NOT NULL,\n gender character varying(20),\n primary_address text NOT NULL, -- full primary residential address\n contact_email character varying(128) UNIQUE,\n contact_phone character varying(32),\n registration_date timestamp NOT NULL, -- when the citizen profile was created\n is_verified boolean DEFAULT false, -- whether identity has been officially verified\n PRIMARY KEY (citizen_id)\n)\nCREATE TABLE government_services.agencies ( agency_id.text, agency_name.text, jurisdiction_level.text, primary_contact_email.text, main_phone_number.text, website_url.text, established_date.date, parent_agency_id.text )\nCREATE TABLE government_services.services ( service_id text PRIMARY KEY, agency_id text, service_name text, description text, category text, eligibility_criteria text, standard_fee numeric, average_processing_time_days int, is_active boolean, online_application_url text )\nCREATE TABLE government_services.applications ( application_id character varying(64) NOT NULL, citizen_id character varying(64) NOT NULL, service_id character varying(64) NOT NULL, submitted_at timestamp NOT NULL, status character varying(50) NOT NULL, last_updated_at timestamp NOT NULL, assigned_employee_id character varying(64), decision_date date, notes text, reference_number character varying(100) UNIQUE, PRIMARY KEY (application_id) )\nCREATE TABLE government_services.documents ( document_id.text, application_id.text, citizen_id.text, document_type.text, file_reference.text, upload_timestamp.timestamp, expiry_date.date, verification_status.text, verified_by_employee_id.text, verification_timestamp.timestamp )\nCREATE TABLE government_services.payments ( payment_id text, application_id text, citizen_id text, service_id text, amount numeric, currency text, payment_method text, payment_provider_reference text, payment_timestamp timestamp, status text, notes text )\nCREATE TABLE government_services.service_locations (\n location_id character varying(64) NOT NULL, -- unique identifier for the physical location\n agency_id character varying(64) NOT NULL, -- FK to agencies table\n location_name character varying(200), -- e.g., Downtown DMV Office\n address text NOT NULL,\n city character varying(100),\n state character varying(50),\n postal_code character varying(20),\n latitude numeric(9, 6),\n longitude numeric(9, 6),\n operating_hours text, -- description of opening times\n contact_phone character varying(32),\n is_accessible boolean, -- accessibility information (e.g., wheelchair access)\n PRIMARY KEY (location_id)\n)\nCREATE TABLE government_services.notifications ( notification_id text PRIMARY KEY, citizen_id text, application_id text, message_subject text, message_body text, channel text, sent_at timestamp, status text, related_entity_type text, related_entity_id text )\n"} {"conversations": [{"role": "user", "content": "Show me the list of hashtags that have been used, along with the time they were first used."}, {"role": "assistant", "content": "SELECT tag_name, created_at \nFROM social_media.hashtags;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE social_media.users (\n user_id character varying(64) NOT NULL, -- unique identifier for the user\n username character varying(50) NOT NULL UNIQUE, -- user's unique handle\n email character varying(128) NOT NULL UNIQUE, -- user's email address\n password_hash text NOT NULL, -- hashed password\n full_name character varying(100), -- user's full name\n profile_picture_url text, -- URL to the profile picture\n bio text, -- short user biography\n location character varying(100), -- user's location\n created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of account creation\n updated_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of last profile update\n is_verified boolean NOT NULL DEFAULT false, -- verification status\n PRIMARY KEY (user_id)\n)\nCREATE TABLE social_media.comments (\n comment_id character varying(64) NOT NULL, -- unique identifier for the comment\n post_id character varying(64) NOT NULL, -- identifier of the post being commented on (FK to posts.post_id)\n user_id character varying(64) NOT NULL, -- identifier of the user who made the comment (FK to users.user_id)\n parent_comment_id character varying(64), -- identifier of the parent comment if it's a reply (FK to comments.comment_id)\n content text NOT NULL, -- textual content of the comment\n created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of comment creation\n updated_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of last comment edit\n PRIMARY KEY (comment_id)\n)\nCREATE TABLE social_media.likes (\n like_id character varying(64) NOT NULL, -- unique identifier for the like\n user_id character varying(64) NOT NULL, -- identifier of the user who liked (FK to users.user_id)\n post_id character varying(64), -- identifier of the post being liked (FK to posts.post_id, nullable)\n comment_id character varying(64), -- identifier of the comment being liked (FK to comments.comment_id, nullable)\n created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of when the like occurred\n PRIMARY KEY (like_id),\n CONSTRAINT unique_user_like UNIQUE (user_id, post_id, comment_id), -- prevent duplicate likes\n CONSTRAINT check_like_target CHECK (post_id IS NOT NULL OR comment_id IS NOT NULL) -- ensure it likes something\n)\nCREATE TABLE social_media.follows (\n follow_id character varying(64) NOT NULL, -- unique identifier for the follow relationship\n follower_user_id character varying(64) NOT NULL, -- identifier of the user who is following (FK to users.user_id)\n following_user_id character varying(64) NOT NULL, -- identifier of the user being followed (FK to users.user_id)\n created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of when the follow started\n PRIMARY KEY (follow_id),\n CONSTRAINT unique_follow UNIQUE (follower_user_id, following_user_id) -- prevent duplicate follows\n)\nCREATE TABLE social_media.hashtags (\n hashtag_id character varying(64) NOT NULL, -- unique identifier for the hashtag\n tag_name character varying(100) NOT NULL UNIQUE, -- the actual hashtag text (without '#')\n created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp when the hashtag was first used\n PRIMARY KEY (hashtag_id)\n)\nCREATE TABLE social_media.post_hashtags (\n post_hashtag_id character varying(64) NOT NULL, -- unique identifier for the post-hashtag link\n post_id character varying(64) NOT NULL, -- identifier of the post (FK to posts.post_id)\n hashtag_id character varying(64) NOT NULL, -- identifier of the hashtag (FK to hashtags.hashtag_id)\n PRIMARY KEY (post_hashtag_id),\n CONSTRAINT unique_post_hashtag UNIQUE (post_id, hashtag_id) -- prevent duplicate tags on a post\n)\nCREATE TABLE social_media.messages (\n message_id character varying(64) NOT NULL, -- unique identifier for the message\n conversation_id character varying(64) NOT NULL, -- identifier for the conversation thread (FK to conversations.conversation_id)\n sender_user_id character varying(64) NOT NULL, -- identifier of the sender (FK to users.user_id)\n content text, -- textual content of the message\n media_url text, -- URL to attached media (image/video)\n media_type character varying(20), -- type of media ('image', 'video', null)\n sent_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp when message was sent\n read_at timestamp, -- timestamp when message was read by recipient(s)\n PRIMARY KEY (message_id)\n)\nCREATE TABLE social_media.conversations (\n conversation_id character varying(64) NOT NULL, -- unique identifier for the conversation\n created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp when conversation was initiated\n last_message_at timestamp, -- timestamp of the last message in the conversation\n is_group_chat boolean NOT NULL DEFAULT false, -- indicates if it's a group chat or direct message\n group_name character varying(100), -- name of the group chat (if applicable)\n PRIMARY KEY (conversation_id)\n)\nCREATE TABLE social_media.conversation_participants (\n participant_id character varying(64) NOT NULL, -- unique identifier for the participant entry\n conversation_id character varying(64) NOT NULL, -- identifier of the conversation (FK to conversations.conversation_id)\n user_id character varying(64) NOT NULL, -- identifier of the user in the conversation (FK to users.user_id)\n joined_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp when user joined the conversation\n last_read_at timestamp, -- timestamp indicating up to when the user has read messages\n PRIMARY KEY (participant_id),\n CONSTRAINT unique_user_conversation UNIQUE (conversation_id, user_id) -- prevent user being added multiple times\n)\nCREATE TABLE social_media.notifications (\n notification_id character varying(64) NOT NULL, -- unique identifier for the notification\n recipient_user_id character varying(64) NOT NULL, -- user receiving the notification (FK to users.user_id)\n sender_user_id character varying(64), -- user triggering the notification (FK to users.user_id, can be null for system notifications)\n notification_type character varying(30) NOT NULL, -- type of notification ('like', 'comment', 'follow', 'mention', 'message')\n target_entity_id character varying(64), -- ID of the related entity (post_id, comment_id, user_id, conversation_id)\n target_entity_type character varying(20), -- type of the related entity ('post', 'comment', 'user', 'conversation')\n created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp notification was created\n read_at timestamp, -- timestamp notification was marked as read\n PRIMARY KEY (notification_id)\n)\nCREATE TABLE social_media.user_settings (\n setting_id character varying(64) NOT NULL, -- unique identifier for the setting entry\n user_id character varying(64) NOT NULL UNIQUE, -- user the settings belong to (FK to users.user_id)\n theme character varying(20) DEFAULT 'light', -- UI theme ('light', 'dark')\n email_notifications_enabled boolean DEFAULT true, -- enable/disable email notifications\n push_notifications_enabled boolean DEFAULT true, -- enable/disable push notifications\n private_profile boolean DEFAULT false, -- is the user profile private\n updated_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of last setting change\n PRIMARY KEY (setting_id)\n)\n"} {"conversations": [{"role": "user", "content": "List all node pairs that operate on the same port and were last_seen within 30 minutes of each other, showing both node_ids, the port, and the time difference in minutes."}, {"role": "assistant", "content": "SELECT n1.node_id AS node1_id, n2.node_id AS node2_id, n1.port,\n ABS(EXTRACT(EPOCH FROM (n1.last_seen - n2.last_seen))) / 60 AS minutes_diff\nFROM blockchain.nodes n1\nJOIN blockchain.nodes n2\n ON n1.port = n2.port\n AND n1.node_id < n2.node_id\nWHERE ABS(EXTRACT(EPOCH FROM (n1.last_seen - n2.last_seen))) <= 1800;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE blockchain.nodes ( node_id text PRIMARY KEY, ip_address text, port int, last_seen timestamp )\n"} {"conversations": [{"role": "user", "content": "For each booking, show the booking_id, seat_number, fare, and the city of the origin location for the trip that was booked."}, {"role": "assistant", "content": "SELECT b.booking_id, b.seat_number, b.fare, orig.city AS origin_city\nFROM transportation.bookings b\nJOIN transportation.trips t ON b.trip_id = t.trip_id\nJOIN transportation.routes r ON t.route_id = r.route_id\nJOIN transportation.locations orig ON r.origin_location_id = orig.location_id;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.drivers ( driver_id character varying(64) NOT NULL, employee_id character varying(64) NOT NULL UNIQUE, first_name character varying(128) NOT NULL, last_name character varying(128) NOT NULL, license_number character varying(64) NOT NULL UNIQUE, license_expiry_date date NOT NULL, contact_number character varying(32), email character varying(128) UNIQUE, hire_date date NOT NULL, status character varying(32) NOT NULL, PRIMARY KEY (driver_id) )\nCREATE TABLE transportation.routes ( route_id character varying(64) NOT NULL, route_number character varying(32) NOT NULL UNIQUE, description text, origin_location_id character varying(64) NOT NULL, destination_location_id character varying(64) NOT NULL, distance_km numeric(10, 2), estimated_duration_minutes integer, type character varying(32) NOT NULL, PRIMARY KEY (route_id) )\nCREATE TABLE transportation.locations ( location_id character varying(64) NOT NULL, name character varying(255) NOT NULL, type character varying(64) NOT NULL, address_line1 character varying(255), city character varying(128), state_province character varying(128), postal_code character varying(32), country character varying(64) NOT NULL, latitude numeric(9, 6), longitude numeric(9, 6), timezone character varying(64), PRIMARY KEY (location_id) )\nCREATE TABLE transportation.maintenance_logs ( log_id character varying(64) NOT NULL, vehicle_id character varying(64) NOT NULL, service_date date NOT NULL, odometer_reading integer, service_type character varying(128) NOT NULL, description text NOT NULL, cost numeric(10, 2), mechanic_name character varying(128), next_service_due_date date, PRIMARY KEY (log_id) )\nCREATE TABLE transportation.bookings ( booking_id character varying(64) NOT NULL, passenger_id character varying(64) NOT NULL, trip_id character varying(64) NOT NULL, seat_number character varying(16), booking_time timestamp with time zone NOT NULL, status character varying(32) NOT NULL, fare numeric(10, 2) NOT NULL, payment_transaction_id character varying(128), special_requests text, PRIMARY KEY (booking_id) )\n"} {"conversations": [{"role": "user", "content": "Show me all active accounts with a balance greater than 2000."}, {"role": "assistant", "content": "SELECT account_id, account_number, customer_id, account_type, balance, currency\nFROM financial_services.accounts\nWHERE status = 'Open' AND balance > 2000;"}, {"role": "user", "content": "Add the opened date and last updated timestamp to the output, and order the result by balance descending."}, {"role": "assistant", "content": "SELECT account_id, account_number, customer_id, account_type, balance, currency, opened_date, last_updated_at\nFROM financial_services.accounts\nWHERE status = 'Open' AND balance > 2000\nORDER BY balance DESC;"}, {"role": "user", "content": "I only want to see accounts opened in the last 12 months. Can you add that filter?"}, {"role": "assistant", "content": "SELECT account_id, account_number, customer_id, account_type, balance, currency, opened_date, last_updated_at\nFROM financial_services.accounts\nWHERE status = 'Open' \n AND balance > 2000\n AND opened_date >= CURRENT_DATE - INTERVAL '12 months'\nORDER BY balance DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE financial_services.customers (\n customer_id character varying(64) NOT NULL, -- unique identifier for the customer\n first_name character varying(100) NOT NULL, -- customer's first name\n last_name character varying(100) NOT NULL, -- customer's last name\n date_of_birth date NOT NULL, -- customer's date of birth\n ssn_hash character varying(128), -- hashed social security number (or national ID)\n address text NOT NULL, -- customer's primary address\n city character varying(100) NOT NULL,\n state character varying(50) NOT NULL,\n zip_code character varying(20) NOT NULL,\n country character varying(50) NOT NULL,\n email character varying(128) UNIQUE, -- customer's email address\n phone_number character varying(32),\n created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of customer record creation\n status character varying(32) NOT NULL, -- e.g., Active, Inactive, Pending Verification\n risk_profile character varying(50), -- e.g., Low, Medium, High\n PRIMARY KEY (customer_id)\n)\nCREATE TABLE financial_services.accounts (\n account_id character varying(64) NOT NULL, -- unique identifier for the account\n customer_id character varying(64) NOT NULL, -- foreign key linking to the customer\n account_number character varying(128) NOT NULL UNIQUE, -- unique account number visible to customer\n account_type character varying(50) NOT NULL, -- e.g., Checking, Savings, Investment, Loan, Credit Card\n balance numeric(19, 4) NOT NULL DEFAULT 0.00, -- current account balance\n currency character varying(3) NOT NULL, -- currency code (e.g., USD, EUR)\n opened_date date NOT NULL, -- date the account was opened\n status character varying(32) NOT NULL, -- e.g., Open, Closed, Frozen\n interest_rate numeric(5, 4), -- annual interest rate, if applicable\n last_updated_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of last account update\n PRIMARY KEY (account_id),\n FOREIGN KEY (customer_id) REFERENCES financial_services.customers(customer_id)\n)\nCREATE TABLE financial_services.transactions (\n transaction_id character varying(64) NOT NULL, -- unique identifier for the transaction\n account_id character varying(64) NOT NULL, -- account involved in the transaction\n related_account_id character varying(64), -- counterpart account for transfers\n transaction_type character varying(50) NOT NULL, -- e.g., Deposit, Withdrawal, Transfer, Payment, Fee, Interest\n amount numeric(19, 4) NOT NULL, -- transaction amount\n currency character varying(3) NOT NULL, -- transaction currency\n transaction_date timestamp NOT NULL, -- exact time of the transaction\n effective_date date NOT NULL, -- date the transaction affects the balance\n description text, -- description or memo of the transaction\n status character varying(32) NOT NULL, -- e.g., Pending, Completed, Failed, Reversed\n reference_number character varying(128), -- external reference if applicable (e.g., check number)\n PRIMARY KEY (transaction_id),\n FOREIGN KEY (account_id) REFERENCES financial_services.accounts(account_id),\n FOREIGN KEY (related_account_id) REFERENCES financial_services.accounts(account_id)\n)\nCREATE TABLE financial_services.securities (\n security_id character varying(64) NOT NULL, -- unique identifier for the security\n ticker_symbol character varying(20) NOT NULL UNIQUE, -- stock ticker or fund symbol\n isin_code character varying(12) UNIQUE, -- International Securities Identification Number\n cusip_code character varying(9) UNIQUE, -- CUSIP number\n security_name text NOT NULL, -- full name of the security\n security_type character varying(50) NOT NULL, -- e.g., Stock, Bond, ETF, Mutual Fund, Option, Future\n exchange character varying(50), -- primary exchange where traded (e.g., NYSE, NASDAQ)\n currency character varying(3) NOT NULL, -- currency the security is denominated in\n issuer_name character varying(255), -- name of the issuing entity\n sector character varying(100), -- industry sector\n last_updated timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP,\n PRIMARY KEY (security_id)\n)\nCREATE TABLE financial_services.trades (\n trade_id character varying(64) NOT NULL, -- unique identifier for the trade\n account_id character varying(64) NOT NULL, -- investment account executing the trade\n security_id character varying(64) NOT NULL, -- security being traded\n order_id character varying(64), -- related order ID if applicable\n trade_type character varying(10) NOT NULL, -- 'Buy' or 'Sell'\n quantity numeric(19, 8) NOT NULL, -- number of units traded\n price_per_unit numeric(19, 8) NOT NULL, -- price per unit of the security\n total_amount numeric(19, 4) NOT NULL, -- total value of the trade (quantity * price)\n commission numeric(10, 4), -- commission fee charged for the trade\n trade_timestamp timestamp NOT NULL, -- exact time the trade was executed\n settlement_date date, -- date the trade settles\n status character varying(32) NOT NULL, -- e.g., Executed, Settled, Cancelled\n execution_venue character varying(100), -- where the trade was executed\n PRIMARY KEY (trade_id),\n FOREIGN KEY (account_id) REFERENCES financial_services.accounts(account_id),\n FOREIGN KEY (security_id) REFERENCES financial_services.securities(security_id)\n)\nCREATE TABLE financial_services.market_data (\n data_point_id bigserial NOT NULL, -- auto-incrementing primary key\n security_id character varying(64) NOT NULL, -- identifier for the security\n data_timestamp timestamp NOT NULL, -- timestamp for the data point (e.g., end of day, intraday)\n open_price numeric(19, 8), -- opening price for the period\n high_price numeric(19, 8), -- highest price during the period\n low_price numeric(19, 8), -- lowest price during the period\n close_price numeric(19, 8) NOT NULL, -- closing price for the period\n adjusted_close_price numeric(19, 8), -- closing price adjusted for dividends and splits\n volume bigint, -- trading volume during the period\n source character varying(50), -- source of the market data (e.g., Bloomberg, Refinitiv)\n PRIMARY KEY (data_point_id),\n UNIQUE (security_id, data_timestamp), -- Ensure unique data point per security per time\n FOREIGN KEY (security_id) REFERENCES financial_services.securities(security_id)\n)\nCREATE TABLE financial_services.loans (\n loan_id character varying(64) NOT NULL, -- unique identifier for the loan, could be same as account_id\n account_id character varying(64) NOT NULL UNIQUE, -- link to the general account record\n loan_type character varying(50) NOT NULL, -- e.g., Mortgage, Personal, Auto, Student\n principal_amount numeric(19, 4) NOT NULL, -- original loan amount\n current_principal_balance numeric(19, 4) NOT NULL, -- remaining principal\n interest_rate numeric(6, 4) NOT NULL, -- annual interest rate\n term_months integer NOT NULL, -- loan term in months\n origination_date date NOT NULL, -- date the loan was disbursed\n maturity_date date NOT NULL, -- date the loan is due to be fully repaid\n monthly_payment numeric(12, 4), -- scheduled monthly payment amount\n collateral_description text, -- description of collateral, if secured loan\n status character varying(32) NOT NULL, -- e.g., Active, Paid Off, Defaulted\n PRIMARY KEY (loan_id),\n FOREIGN KEY (account_id) REFERENCES financial_services.accounts(account_id)\n)\n"} {"conversations": [{"role": "user", "content": "I want to see the total sum of transaction amounts and their average amount for each transaction_type along with the total number of transactions, grouped by currency."}, {"role": "assistant", "content": "SELECT transaction_type, currency, COUNT(*) AS total_transactions, SUM(amount) AS total_amount, AVG(amount) AS average_amount FROM financial_services.transactions GROUP BY transaction_type, currency;"}, {"role": "user", "content": "Can you filter out transactions where the status is not 'SUCCESSFUL' or 'PENDING'?"}, {"role": "assistant", "content": "SELECT transaction_type, currency, COUNT(*) AS total_transactions, SUM(amount) AS total_amount, AVG(amount) AS average_amount FROM financial_services.transactions WHERE status IN ('SUCCESSFUL', 'PENDING') GROUP BY transaction_type, currency;"}, {"role": "user", "content": "Also, show only the results where the total_amount is greater than 10000."}, {"role": "assistant", "content": "SELECT transaction_type, currency, COUNT(*) AS total_transactions, SUM(amount) AS total_amount, AVG(amount) AS average_amount FROM financial_services.transactions WHERE status IN ('SUCCESSFUL', 'PENDING') GROUP BY transaction_type, currency HAVING SUM(amount) > 10000;"}, {"role": "user", "content": "Sort the results by average_amount in ascending order."}, {"role": "assistant", "content": "SELECT transaction_type, currency, COUNT(*) AS total_transactions, SUM(amount) AS total_amount, AVG(amount) AS average_amount FROM financial_services.transactions WHERE status IN ('SUCCESSFUL', 'PENDING') GROUP BY transaction_type, currency HAVING SUM(amount) > 10000 ORDER BY average_amount ASC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE financial_services.transactions ( transaction_id text, account_id text, related_account_id text, transaction_type text, amount numeric, currency text, transaction_date timestamp, effective_date date, description text, status text, reference_number text )\n"} {"conversations": [{"role": "user", "content": "Show the first name, last name, and position of all staff members who are not currently active."}, {"role": "assistant", "content": "SELECT first_name , last_name , position FROM hospitality_technology.staff WHERE is_active = false"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE hospitality_technology.properties (\n property_id character varying(64) NOT NULL, -- unique identifier for the property (hotel, resort, etc.)\n property_name character varying(255) NOT NULL, -- name of the property\n address_line1 character varying(255) NOT NULL, -- primary address line\n address_line2 character varying(255), -- secondary address line\n city character varying(100) NOT NULL, -- city\n state_province character varying(100), -- state or province\n postal_code character varying(20) NOT NULL, -- zip or postal code\n country_code character varying(3) NOT NULL, -- ISO country code (e.g., USA, CAN)\n phone_number character varying(30), -- main contact phone\n email_address character varying(255), -- main contact email\n property_type character varying(50) NOT NULL, -- e.g., Hotel, Resort, B&B, Motel\n star_rating numeric(2,1), -- star rating (e.g., 4.5)\n timezone character varying(64) NOT NULL, -- IANA timezone ID (e.g., America/New_York)\n manager_staff_id character varying(64), -- FK to staff table for the general manager\n created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, -- record creation time\n updated_at timestamp with time zone NOT NULL DEFAULT current_timestamp, -- record last update time\n PRIMARY KEY (property_id)\n)\nCREATE TABLE hospitality_technology.rooms (\n room_id character varying(64) NOT NULL, -- unique identifier for the room\n property_id character varying(64) NOT NULL, -- FK to properties table\n room_number character varying(10) NOT NULL, -- room number identifier (e.g., '101', 'Suite 2B')\n room_type_id character varying(64) NOT NULL, -- FK to room_types table\n floor integer, -- floor number the room is on\n status character varying(50) NOT NULL, -- e.g., Available, Occupied, Cleaning, OutOfOrder, Maintenance\n is_smoking boolean NOT NULL DEFAULT false, -- smoking allowed flag\n features text, -- description of features (e.g., Balcony, Sea View, Jacuzzi)\n current_condition text, -- notes on room condition\n last_cleaned_at timestamp with time zone, -- timestamp of last cleaning\n PRIMARY KEY (room_id),\n FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id),\n FOREIGN KEY (room_type_id) REFERENCES hospitality_technology.room_types(room_type_id)\n)\nCREATE TABLE hospitality_technology.staff (\n staff_id character varying(64) NOT NULL, -- unique identifier for the staff member\n property_id character varying(64) NOT NULL, -- FK to properties table (primary property)\n first_name character varying(100) NOT NULL,\n last_name character varying(100) NOT NULL,\n position character varying(100) NOT NULL, -- e.g., Front Desk Agent, Housekeeper, Manager, Concierge\n work_email character varying(255) UNIQUE, -- staff member's work email\n work_phone character varying(30),\n hire_date date NOT NULL,\n termination_date date, -- date employment ended (if applicable)\n is_active boolean NOT NULL DEFAULT true, -- currently employed flag\n access_level integer NOT NULL, -- permission level within systems (e.g., 1=basic, 5=admin)\n manager_id character varying(64), -- FK to staff table (self-referencing for supervisor)\n created_at timestamp with time zone NOT NULL DEFAULT current_timestamp,\n PRIMARY KEY (staff_id),\n FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id),\n FOREIGN KEY (manager_id) REFERENCES hospitality_technology.staff(staff_id)\n)\nCREATE TABLE hospitality_technology.reviews (\n review_id character varying(64) NOT NULL, -- unique identifier for the review\n property_id character varying(64) NOT NULL, -- FK to properties table\n reservation_id character varying(64) UNIQUE, -- FK to reservations (link review to a specific stay, optional but good)\n guest_id character varying(64) NOT NULL, -- FK to guests table\n rating_overall integer, -- overall score (e.g., 1-5 or 1-10)\n rating_cleanliness integer,\n rating_service integer,\n rating_location integer,\n rating_value integer,\n comment text, -- guest's written feedback\n review_source character varying(100), -- e.g., DirectSurvey, TripAdvisor, Google, Booking.com\n review_date timestamp with time zone NOT NULL DEFAULT current_timestamp, -- when the review was submitted\n is_public boolean DEFAULT true, -- whether the review is publicly visible\n staff_response text, -- official response from the property\n response_staff_id character varying(64), -- FK to staff (who responded)\n response_date timestamp with time zone, -- when the response was posted\n PRIMARY KEY (review_id),\n FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id),\n FOREIGN KEY (reservation_id) REFERENCES hospitality_technology.reservations(reservation_id),\n FOREIGN KEY (guest_id) REFERENCES hospitality_technology.guests(guest_id),\n FOREIGN KEY (response_staff_id) REFERENCES hospitality_technology.staff(staff_id)\n)\n"} {"conversations": [{"role": "user", "content": "Show me the number of game servers in each region and the average maximum number of players they can accommodate. Exclude any servers that are currently offline."}, {"role": "assistant", "content": "SELECT region, COUNT(server_id) AS server_count, AVG(max_players) AS average_max_players FROM gaming_technology.servers WHERE status != 'offline' GROUP BY region;"}, {"role": "user", "content": "Please filter the results to only include regions that have more than 5 active servers."}, {"role": "assistant", "content": "SELECT region, COUNT(server_id) AS server_count, AVG(max_players) AS average_max_players FROM gaming_technology.servers WHERE status != 'offline' GROUP BY region HAVING COUNT(server_id) > 5;"}, {"role": "user", "content": "Can you also include the total number of current players across all active servers in each of those regions?"}, {"role": "assistant", "content": "SELECT region, COUNT(server_id) AS server_count, AVG(max_players) AS average_max_players, SUM(current_players) AS total_current_players FROM gaming_technology.servers WHERE status != 'offline' GROUP BY region HAVING COUNT(server_id) > 5;"}, {"role": "user", "content": "Order the final results by the total number of current players in descending order."}, {"role": "assistant", "content": "SELECT region, COUNT(server_id) AS server_count, AVG(max_players) AS average_max_players, SUM(current_players) AS total_current_players FROM gaming_technology.servers WHERE status != 'offline' GROUP BY region HAVING COUNT(server_id) > 5 ORDER BY total_current_players DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE gaming_technology.players (\n player_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for the player\n username character varying(100) NOT NULL UNIQUE, -- player's chosen display name\n email character varying(255) NOT NULL UNIQUE, -- player's email address for login/recovery\n password_hash text NOT NULL, -- securely hashed password\n registration_date timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP, -- when the player account was created\n last_login timestamp with time zone, -- timestamp of the last successful login\n country_code character(2), -- player's country (ISO 3166-1 alpha-2)\n status character varying(20) NOT NULL DEFAULT 'active', -- account status (e.g., active, banned, suspended)\n profile_data jsonb, -- flexible field for avatar url, bio, preferences etc.\n PRIMARY KEY (player_id)\n)\nCREATE TABLE gaming_technology.games (\n game_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for the game\n title character varying(200) NOT NULL, -- official title of the game\n developer_id uuid NOT NULL, -- FK linking to the developers table\n publisher_id uuid, -- FK linking to a potential publishers table (optional)\n genre character varying(100), -- primary genre (e.g., RPG, FPS, Strategy)\n release_date date, -- official release date\n description text, -- short description or synopsis of the game\n platform character varying(50) NOT NULL, -- primary platform (e.g., PC, PlayStation 5, Xbox Series X, Mobile)\n engine character varying(100), -- game engine used (e.g., Unreal Engine 5, Unity)\n website character varying(255), -- official website URL\n PRIMARY KEY (game_id)\n -- FOREIGN KEY (developer_id) REFERENCES gaming_technology.developers(developer_id) -- Example FK constraint\n)\nCREATE TABLE gaming_technology.game_sessions (\n session_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for the game session\n player_id uuid NOT NULL, -- FK linking to the players table\n game_id uuid NOT NULL, -- FK linking to the games table\n server_id uuid, -- FK linking to the servers table (nullable for single-player)\n start_time timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP, -- when the session began\n end_time timestamp with time zone, -- when the session ended (null if ongoing)\n duration_seconds integer, -- calculated duration of the session in seconds\n score integer, -- player's score for the session, if applicable\n session_data jsonb, -- flexible field for session-specific info (e.g., map played, character used)\n PRIMARY KEY (session_id)\n -- FOREIGN KEY (player_id) REFERENCES gaming_technology.players(player_id),\n -- FOREIGN KEY (game_id) REFERENCES gaming_technology.games(game_id),\n -- FOREIGN KEY (server_id) REFERENCES gaming_technology.servers(server_id)\n)\nCREATE TABLE gaming_technology.servers (\n server_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for the game server instance\n game_id uuid NOT NULL, -- FK linking to the game this server hosts\n server_name character varying(150), -- display name for the server\n region character varying(50) NOT NULL, -- geographical region (e.g., us-east-1, eu-west-2)\n ip_address character varying(45), -- IP address (IPv4 or IPv6)\n port integer, -- network port number\n current_players integer NOT NULL DEFAULT 0, -- number of players currently connected\n max_players integer NOT NULL, -- maximum player capacity\n status character varying(30) NOT NULL DEFAULT 'offline', -- server status (e.g., online, offline, maintenance)\n last_heartbeat timestamp with time zone, -- last time the server reported its status\n PRIMARY KEY (server_id)\n -- FOREIGN KEY (game_id) REFERENCES gaming_technology.games(game_id)\n)\nCREATE TABLE gaming_technology.achievements (\n achievement_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for an achievement definition\n game_id uuid NOT NULL, -- FK linking to the game the achievement belongs to\n name character varying(150) NOT NULL, -- name of the achievement\n description text NOT NULL, -- how to unlock the achievement\n icon_url character varying(255), -- URL for the achievement's icon\n points integer DEFAULT 0, -- points awarded for unlocking (optional)\n hidden boolean DEFAULT false, -- whether the achievement details are hidden until unlocked\n PRIMARY KEY (achievement_id)\n -- FOREIGN KEY (game_id) REFERENCES gaming_technology.games(game_id)\n)\nCREATE TABLE gaming_technology.player_achievements (\n player_achievement_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for this unlock instance\n player_id uuid NOT NULL, -- FK linking to the player who unlocked it\n achievement_id uuid NOT NULL, -- FK linking to the achievement definition\n unlocked_at timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP, -- when the achievement was unlocked\n PRIMARY KEY (player_achievement_id),\n UNIQUE (player_id, achievement_id) -- Ensure a player can only unlock an achievement once\n -- FOREIGN KEY (player_id) REFERENCES gaming_technology.players(player_id),\n -- FOREIGN KEY (achievement_id) REFERENCES gaming_technology.achievements(achievement_id)\n)\nCREATE TABLE gaming_technology.in_game_items (\n item_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for the item definition\n game_id uuid NOT NULL, -- FK linking to the game this item belongs to\n item_name character varying(150) NOT NULL, -- name of the item\n item_type character varying(50) NOT NULL, -- type (e.g., Cosmetic, Consumable, Weapon, Armor)\n description text, -- description of the item\n rarity character varying(30), -- item rarity (e.g., Common, Rare, Epic, Legendary)\n cost_currency character varying(10), -- currency code if purchasable (e.g., USD, EUR, GOLD)\n cost_amount numeric(12, 2), -- price if purchasable\n attributes jsonb, -- flexible field for item stats or properties\n PRIMARY KEY (item_id)\n -- FOREIGN KEY (game_id) REFERENCES gaming_technology.games(game_id)\n)\nCREATE TABLE gaming_technology.player_inventory (\n inventory_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for an inventory entry\n player_id uuid NOT NULL, -- FK linking to the player owning the item\n item_id uuid NOT NULL, -- FK linking to the item definition\n quantity integer NOT NULL DEFAULT 1, -- number of items held (for stackable items)\n acquired_at timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP, -- when the item was acquired\n instance_data jsonb, -- data specific to this instance (e.g., weapon mods, durability)\n PRIMARY KEY (inventory_id),\n -- Optional unique constraint if items are non-stackable or unique instances\n -- UNIQUE (player_id, item_id) -- Use if quantity is always 1\n -- FOREIGN KEY (player_id) REFERENCES gaming_technology.players(player_id),\n -- FOREIGN KEY (item_id) REFERENCES gaming_technology.in_game_items(item_id)\n)\n"} {"conversations": [{"role": "user", "content": "Show me all cryptocurrency assets that have been traded more than 50 times but have never been traded in quantities greater than 100, along with their average trade price."}, {"role": "assistant", "content": "SELECT a.asset_id, a.name, a.symbol, COUNT(t.trade_id) AS trade_count, AVG(t.price) AS avg_price FROM trading_platform.assets a JOIN trading_platform.trades t ON a.asset_id = t.asset_id WHERE a.type = 'cryptocurrency' GROUP BY a.asset_id, a.name, a.symbol HAVING COUNT(t.trade_id) > 50 AND MAX(t.quantity) <= 100;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE trading_platform.users ( user_id character varying(64) NOT NULL, username character varying(128) NOT NULL, email character varying(128) NOT NULL, password_hash text NOT NULL, created_at timestamp NOT NULL, PRIMARY KEY (user_id) )\nCREATE TABLE trading_platform.wallets ( wallet_id character varying(64) NOT NULL, user_id character varying(64) NOT NULL, address character varying(128) NOT NULL, private_key text NOT NULL, created_at timestamp NOT NULL, PRIMARY KEY (wallet_id) )\nCREATE TABLE trading_platform.orders ( order_id character varying(64) NOT NULL, user_id character varying(64) NOT NULL, wallet_id character varying(64) NOT NULL, asset_id character varying(64) NOT NULL, order_type character varying(32) NOT NULL, quantity numeric(38,14) NOT NULL, price numeric(38,14) NOT NULL, status character varying(32) NOT NULL, created_at timestamp NOT NULL, PRIMARY KEY (order_id) )\nCREATE TABLE trading_platform.trades ( trade_id character varying(64) NOT NULL, order_id character varying(64) NOT NULL, buyer_id character varying(64) NOT NULL, seller_id character varying(64) NOT NULL, asset_id character varying(64) NOT NULL, quantity numeric(38,14) NOT NULL, price numeric(38,14) NOT NULL, traded_at timestamp NOT NULL, PRIMARY KEY (trade_id) )\nCREATE TABLE trading_platform.assets ( asset_id character varying(64) NOT NULL, name character varying(128) NOT NULL, symbol character varying(32) NOT NULL, type character varying(32) NOT NULL, PRIMARY KEY (asset_id) )\nCREATE TABLE trading_platform.utxos ( utxo_id character varying(64) NOT NULL, transaction_id character varying(64) NOT NULL, output_index integer NOT NULL, address character varying(128) NOT NULL, amount numeric(38,14) NOT NULL, spent boolean NOT NULL, PRIMARY KEY (utxo_id) )\nCREATE TABLE trading_platform.dapps ( dapp_id character varying(64) NOT NULL, name character varying(128) NOT NULL, description text NOT NULL, url character varying(256) NOT NULL, PRIMARY KEY (dapp_id) )\nCREATE TABLE trading_platform.peers ( peer_id character varying(64) NOT NULL, ip_address character varying(15) NOT NULL, port integer NOT NULL, last_seen timestamp NOT NULL, PRIMARY KEY (peer_id) )\nCREATE TABLE trading_platform.metadata ( metadata_id character varying(64) NOT NULL, asset_id character varying(64) NOT NULL, key character varying(128) NOT NULL, value text NOT NULL, PRIMARY KEY (metadata_id) )\nCREATE TABLE trading_platform.kyc_audit ( kyc_audit_id character varying(64) NOT NULL, user_id character varying(64) NOT NULL, status character varying(32) NOT NULL, reviewed_at timestamp NOT NULL, PRIMARY KEY (kyc_audit_id) )\nCREATE TABLE trading_platform.notifications ( notification_id character varying(64) NOT NULL, user_id character varying(64) NOT NULL, message text NOT NULL, sent_at timestamp NOT NULL, read_at timestamp, PRIMARY KEY (notification_id) )\n"} {"conversations": [{"role": "user", "content": "What is the current market price of a Boeing 737 MAX aircraft?"}, {"role": "assistant", "content": "I'm sorry, but I don't have access to the current market price of aircraft models. The data I have is limited to technical specifications and general information about aircraft models such as passenger capacity, range, and status. For pricing information, you may need to consult with manufacturers or industry reports."}], "system": "You are an SQL statement expert and you can refuse the user's question if the question is not related to the table structure. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE manufacturing.aircraft_models (\n model_id character varying(64) NOT NULL, -- unique identifier for the aircraft model\n model_name character varying(128) NOT NULL, -- commercial name of the model (e.g., 737 MAX, A320neo)\n manufacturer character varying(128) NOT NULL, -- manufacturer name (e.g., Boeing, Airbus)\n passenger_capacity integer, -- typical passenger capacity\n max_range_km integer, -- maximum flight range in kilometers\n engine_type character varying(100), -- type of engines used\n wingspan_m numeric(6,2), -- wingspan in meters\n status character varying(50) NOT NULL, -- e.g., 'In Production', 'Development', 'Discontinued'\n first_flight_date date, -- date of the model's first flight\n PRIMARY KEY (model_id)\n)\n"} {"conversations": [{"role": "user", "content": "List the patient ID and subscriber name for all patients who have both at least one diagnosis recorded and at least one primary insurance policy."}, {"role": "assistant", "content": "SELECT DISTINCT pi.patient_id, pi.subscriber_name FROM healthcare.patient_insurance pi JOIN healthcare.diagnoses d ON pi.patient_id = d.patient_id WHERE pi.is_primary = true;"}, {"role": "user", "content": "Refine this list to only include patients whose most recent diagnosis is marked as chronic."}, {"role": "assistant", "content": "WITH LatestDiagnosis AS ( SELECT patient_id, diagnosis_id, diagnosis_date, is_chronic, ROW_NUMBER() OVER(PARTITION BY patient_id ORDER BY diagnosis_date DESC) as rn FROM healthcare.diagnoses ) SELECT DISTINCT pi.patient_id, pi.subscriber_name FROM healthcare.patient_insurance pi JOIN LatestDiagnosis ld ON pi.patient_id = ld.patient_id WHERE pi.is_primary = true AND ld.rn = 1 AND ld.is_chronic = true;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.diagnoses (\n diagnosis_id character varying(64) NOT NULL, -- unique identifier for the diagnosis entry\n record_id character varying(64) NOT NULL, -- FK linking to the specific medical record entry\n patient_id character varying(64) NOT NULL, -- FK to patients table\n doctor_id character varying(64) NOT NULL, -- FK to doctors table (diagnosing doctor)\n diagnosis_code character varying(20) NOT NULL, -- standard code (e.g., ICD-10)\n code_type character varying(10) NOT NULL DEFAULT 'ICD-10', -- type of code used\n description text, -- textual description of the diagnosis\n diagnosis_date date NOT NULL, -- date the diagnosis was made\n status character varying(32) NOT NULL, -- e.g., Active, Resolved, Ruled Out\n is_chronic boolean DEFAULT false, -- flag for chronic conditions\n PRIMARY KEY (diagnosis_id)\n)\nCREATE TABLE healthcare.patient_insurance ( patient_insurance_id.text, patient_id.text, plan_id.text, policy_number.text, group_number.text, subscriber_name.text, effective_date.date, expiration_date.date, is_primary.boolean )\n"} {"conversations": [{"role": "user", "content": "List all post IDs and their corresponding hashtag names for posts that include media."}, {"role": "assistant", "content": "SELECT ph.post_id, h.tag_name\nFROM social_media.post_hashtags ph\nJOIN social_media.hashtags h ON ph.hashtag_id = h.hashtag_id\nJOIN social_media.posts p ON ph.post_id = p.post_id\nWHERE p.media_url IS NOT NULL AND p.media_url != '';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE social_media.posts ( post_id text PRIMARY KEY, user_id text, content text, media_url text, media_type text, created_at timestamp, updated_at timestamp, visibility text, location_lat numeric, location_lon numeric )\nCREATE TABLE social_media.follows (\n follow_id character varying(64) NOT NULL, -- unique identifier for the follow relationship\n follower_user_id character varying(64) NOT NULL, -- identifier of the user who is following (FK to users.user_id)\n following_user_id character varying(64) NOT NULL, -- identifier of the user being followed (FK to users.user_id)\n created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of when the follow started\n PRIMARY KEY (follow_id),\n CONSTRAINT unique_follow UNIQUE (follower_user_id, following_user_id) -- prevent duplicate follows\n)\nCREATE TABLE social_media.hashtags ( hashtag_id character varying(64) NOT NULL, tag_name character varying(100) NOT NULL UNIQUE, created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, PRIMARY KEY (hashtag_id) )\nCREATE TABLE social_media.post_hashtags (\n post_hashtag_id character varying(64) NOT NULL, -- unique identifier for the post-hashtag link\n post_id character varying(64) NOT NULL, -- identifier of the post (FK to posts.post_id)\n hashtag_id character varying(64) NOT NULL, -- identifier of the hashtag (FK to hashtags.hashtag_id)\n PRIMARY KEY (post_hashtag_id),\n CONSTRAINT unique_post_hashtag UNIQUE (post_id, hashtag_id) -- prevent duplicate tags on a post\n)\nCREATE TABLE social_media.messages (\n message_id character varying(64) NOT NULL, -- unique identifier for the message\n conversation_id character varying(64) NOT NULL, -- identifier for the conversation thread (FK to conversations.conversation_id)\n sender_user_id character varying(64) NOT NULL, -- identifier of the sender (FK to users.user_id)\n content text, -- textual content of the message\n media_url text, -- URL to attached media (image/video)\n media_type character varying(20), -- type of media ('image', 'video', null)\n sent_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp when message was sent\n read_at timestamp, -- timestamp when message was read by recipient(s)\n PRIMARY KEY (message_id)\n)\nCREATE TABLE social_media.conversations ( conversation_id text PRIMARY KEY, created_at timestamp, last_message_at timestamp, is_group_chat bool, group_name text )\nCREATE TABLE social_media.conversation_participants (\n participant_id character varying(64) NOT NULL, -- unique identifier for the participant entry\n conversation_id character varying(64) NOT NULL, -- identifier of the conversation (FK to conversations.conversation_id)\n user_id character varying(64) NOT NULL, -- identifier of the user in the conversation (FK to users.user_id)\n joined_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp when user joined the conversation\n last_read_at timestamp, -- timestamp indicating up to when the user has read messages\n PRIMARY KEY (participant_id),\n CONSTRAINT unique_user_conversation UNIQUE (conversation_id, user_id) -- prevent user being added multiple times\n)\nCREATE TABLE social_media.notifications (\n notification_id character varying(64) NOT NULL, -- unique identifier for the notification\n recipient_user_id character varying(64) NOT NULL, -- user receiving the notification (FK to users.user_id)\n sender_user_id character varying(64), -- user triggering the notification (FK to users.user_id, can be null for system notifications)\n notification_type character varying(30) NOT NULL, -- type of notification ('like', 'comment', 'follow', 'mention', 'message')\n target_entity_id character varying(64), -- ID of the related entity (post_id, comment_id, user_id, conversation_id)\n target_entity_type character varying(20), -- type of the related entity ('post', 'comment', 'user', 'conversation')\n created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp notification was created\n read_at timestamp, -- timestamp notification was marked as read\n PRIMARY KEY (notification_id)\n)\nCREATE TABLE social_media.user_settings ( setting_id character varying(64) NOT NULL, user_id character varying(64) NOT NULL UNIQUE, theme character varying(20) DEFAULT 'light', email_notifications_enabled boolean DEFAULT true, push_notifications_enabled boolean DEFAULT true, private_profile boolean DEFAULT false, updated_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, PRIMARY KEY (setting_id) )\n"} {"conversations": [{"role": "user", "content": "Show me all lawyers' full names, their bar number, and if they are partners, the full name of another partner from their firm."}, {"role": "assistant", "content": "SELECT l1.first_name || ' ' || l1.last_name AS lawyer_full_name, l1.bar_number,\n CASE WHEN l1.is_partner = TRUE THEN (\n SELECT l2.first_name || ' ' || l2.last_name\n FROM legal_services.lawyers l2\n WHERE l2.firm_id = l1.firm_id AND l2.is_partner = TRUE AND l2.lawyer_id <> l1.lawyer_id\n LIMIT 1\n ) ELSE NULL END AS another_partner_full_name\nFROM legal_services.lawyers l1;"}, {"role": "user", "content": "Only include lawyers who have an email address specified."}, {"role": "assistant", "content": "SELECT l1.first_name || ' ' || l1.last_name AS lawyer_full_name, l1.bar_number,\n CASE WHEN l1.is_partner = TRUE THEN (\n SELECT l2.first_name || ' ' || l2.last_name\n FROM legal_services.lawyers l2\n WHERE l2.firm_id = l1.firm_id AND l2.is_partner = TRUE AND l2.lawyer_id <> l1.lawyer_id\n LIMIT 1\n ) ELSE NULL END AS another_partner_full_name\nFROM legal_services.lawyers l1\nWHERE l1.email IS NOT NULL AND l1.email <> '';"}, {"role": "user", "content": "Actually, restrict it to lawyers hired in or after 2023."}, {"role": "assistant", "content": "SELECT l1.first_name || ' ' || l1.last_name AS lawyer_full_name, l1.bar_number,\n CASE WHEN l1.is_partner = TRUE THEN (\n SELECT l2.first_name || ' ' || l2.last_name\n FROM legal_services.lawyers l2\n WHERE l2.firm_id = l1.firm_id AND l2.is_partner = TRUE AND l2.lawyer_id <> l1.lawyer_id\n LIMIT 1\n ) ELSE NULL END AS another_partner_full_name\nFROM legal_services.lawyers l1\nWHERE l1.email IS NOT NULL AND l1.email <> '' AND l1.hire_date >= '2023-01-01';"}, {"role": "user", "content": "Sort the results by the lawyer's last name in descending order."}, {"role": "assistant", "content": "SELECT l1.first_name || ' ' || l1.last_name AS lawyer_full_name, l1.bar_number,\n CASE WHEN l1.is_partner = TRUE THEN (\n SELECT l2.first_name || ' ' || l2.last_name\n FROM legal_services.lawyers l2\n WHERE l2.firm_id = l1.firm_id AND l2.is_partner = TRUE AND l2.lawyer_id <> l1.lawyer_id\n LIMIT 1\n ) ELSE NULL END AS another_partner_full_name\nFROM legal_services.lawyers l1\nWHERE l1.email IS NOT NULL AND l1.email <> '' AND l1.hire_date >= '2023-01-01'\nORDER BY l1.last_name DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.lawyers ( lawyer_id.text, first_name.text, last_name.text, bar_number.text, firm_id.text, email.text, phone.text, specialization.text, hire_date.timestamp, is_partner.boolean )\n"} {"conversations": [{"role": "user", "content": "What is the total USD value of all token outflows (type = 2) across all chains?"}, {"role": "assistant", "content": "SELECT SUM(usd_value) AS total_outflow_usd FROM smart_money_token_inflow WHERE type = 2;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE smart_money_token_inflow ( token_address character varying(100) NOT NULL, -- the token's address token_symbol character varying(100), -- the tokens's symbol token_amount numeric(38,2), -- the absolute value of the amount if user bought minus the amount user sold of this token usd_value numeric(38,2), -- the absolute usd value of the bought token minus sold token avg_price numeric(38,6), -- the average cost price of user spent on this token type int, -- the direction of the trade on this token. 1 means buying, 2 means selling address_amount integer, -- the amount of the user bought this token narrative character varying(100), -- the category or narrative of the token chain character varying(100), -- the chain that the token resides ,PRIMARY KEY (token_address, chain) )\n"} {"conversations": [{"role": "user", "content": "Show a list of all game developers with their name and founded year."}, {"role": "assistant", "content": "SELECT\n name,\n founded_year\nFROM gaming_technology.developers;"}, {"role": "user", "content": "Please filter the list to only include developers founded in the year 1998."}, {"role": "assistant", "content": "SELECT\n name,\n founded_year\nFROM gaming_technology.developers\nWHERE\n founded_year = 1998;"}, {"role": "user", "content": "Can you also include the number of games each of these developers has released?"}, {"role": "assistant", "content": "SELECT\n T1.name,\n T1.founded_year,\n COUNT(T2.game_id) AS game_count\nFROM gaming_technology.developers AS T1\nLEFT JOIN gaming_technology.games AS T2\n ON T1.developer_id = T2.developer_id\nWHERE\n T1.founded_year = 1998\nGROUP BY\n T1.developer_id,\n T1.name,\n T1.founded_year;"}, {"role": "user", "content": "Now, only show the developers who have released exactly 2 games."}, {"role": "assistant", "content": "SELECT\n T1.name,\n T1.founded_year,\n COUNT(T2.game_id) AS game_count\nFROM gaming_technology.developers AS T1\nJOIN gaming_technology.games AS T2\n ON T1.developer_id = T2.developer_id\nWHERE\n T1.founded_year = 1998\nGROUP BY\n T1.developer_id,\n T1.name,\n T1.founded_year\nHAVING\n COUNT(T2.game_id) = 2;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE gaming_technology.players (\n player_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for the player\n username character varying(100) NOT NULL UNIQUE, -- player's chosen display name\n email character varying(255) NOT NULL UNIQUE, -- player's email address for login/recovery\n password_hash text NOT NULL, -- securely hashed password\n registration_date timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP, -- when the player account was created\n last_login timestamp with time zone, -- timestamp of the last successful login\n country_code character(2), -- player's country (ISO 3166-1 alpha-2)\n status character varying(20) NOT NULL DEFAULT 'active', -- account status (e.g., active, banned, suspended)\n profile_data jsonb, -- flexible field for avatar url, bio, preferences etc.\n PRIMARY KEY (player_id)\n)\nCREATE TABLE gaming_technology.games (\n game_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for the game\n title character varying(200) NOT NULL, -- official title of the game\n developer_id uuid NOT NULL, -- FK linking to the developers table\n publisher_id uuid, -- FK linking to a potential publishers table (optional)\n genre character varying(100), -- primary genre (e.g., RPG, FPS, Strategy)\n release_date date, -- official release date\n description text, -- short description or synopsis of the game\n platform character varying(50) NOT NULL, -- primary platform (e.g., PC, PlayStation 5, Xbox Series X, Mobile)\n engine character varying(100), -- game engine used (e.g., Unreal Engine 5, Unity)\n website character varying(255), -- official website URL\n PRIMARY KEY (game_id)\n -- FOREIGN KEY (developer_id) REFERENCES gaming_technology.developers(developer_id) -- Example FK constraint\n)\nCREATE TABLE gaming_technology.developers (\n developer_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for the developer studio\n name character varying(150) NOT NULL UNIQUE, -- name of the development studio\n country character varying(100), -- country where the studio is based\n founded_year integer, -- year the studio was founded\n website character varying(255), -- developer's official website\n created_at timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP,\n PRIMARY KEY (developer_id)\n)\nCREATE TABLE gaming_technology.game_sessions (\n session_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for the game session\n player_id uuid NOT NULL, -- FK linking to the players table\n game_id uuid NOT NULL, -- FK linking to the games table\n server_id uuid, -- FK linking to the servers table (nullable for single-player)\n start_time timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP, -- when the session began\n end_time timestamp with time zone, -- when the session ended (null if ongoing)\n duration_seconds integer, -- calculated duration of the session in seconds\n score integer, -- player's score for the session, if applicable\n session_data jsonb, -- flexible field for session-specific info (e.g., map played, character used)\n PRIMARY KEY (session_id)\n -- FOREIGN KEY (player_id) REFERENCES gaming_technology.players(player_id),\n -- FOREIGN KEY (game_id) REFERENCES gaming_technology.games(game_id),\n -- FOREIGN KEY (server_id) REFERENCES gaming_technology.servers(server_id)\n)\nCREATE TABLE gaming_technology.servers (\n server_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for the game server instance\n game_id uuid NOT NULL, -- FK linking to the game this server hosts\n server_name character varying(150), -- display name for the server\n region character varying(50) NOT NULL, -- geographical region (e.g., us-east-1, eu-west-2)\n ip_address character varying(45), -- IP address (IPv4 or IPv6)\n port integer, -- network port number\n current_players integer NOT NULL DEFAULT 0, -- number of players currently connected\n max_players integer NOT NULL, -- maximum player capacity\n status character varying(30) NOT NULL DEFAULT 'offline', -- server status (e.g., online, offline, maintenance)\n last_heartbeat timestamp with time zone, -- last time the server reported its status\n PRIMARY KEY (server_id)\n -- FOREIGN KEY (game_id) REFERENCES gaming_technology.games(game_id)\n)\nCREATE TABLE gaming_technology.achievements (\n achievement_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for an achievement definition\n game_id uuid NOT NULL, -- FK linking to the game the achievement belongs to\n name character varying(150) NOT NULL, -- name of the achievement\n description text NOT NULL, -- how to unlock the achievement\n icon_url character varying(255), -- URL for the achievement's icon\n points integer DEFAULT 0, -- points awarded for unlocking (optional)\n hidden boolean DEFAULT false, -- whether the achievement details are hidden until unlocked\n PRIMARY KEY (achievement_id)\n -- FOREIGN KEY (game_id) REFERENCES gaming_technology.games(game_id)\n)\nCREATE TABLE gaming_technology.player_achievements (\n player_achievement_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for this unlock instance\n player_id uuid NOT NULL, -- FK linking to the player who unlocked it\n achievement_id uuid NOT NULL, -- FK linking to the achievement definition\n unlocked_at timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP, -- when the achievement was unlocked\n PRIMARY KEY (player_achievement_id),\n UNIQUE (player_id, achievement_id) -- Ensure a player can only unlock an achievement once\n -- FOREIGN KEY (player_id) REFERENCES gaming_technology.players(player_id),\n -- FOREIGN KEY (achievement_id) REFERENCES gaming_technology.achievements(achievement_id)\n)\n"} {"conversations": [{"role": "user", "content": "Show the document ID, document type, and upload timestamp for all documents uploaded by citizens who registered after January 1st, 2023."}, {"role": "assistant", "content": "SELECT d.document_id, d.document_type, d.upload_timestamp FROM government_services.documents d JOIN citizens c ON d.citizen_id = c.citizen_id WHERE c.registration_date > '2023-01-01';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.documents ( document_id text, application_id text, citizen_id text, document_type text, file_reference text, upload_timestamp timestamp, expiry_date date, verification_status text, verified_by_employee_id text, verification_timestamp timestamp )\n"} {"conversations": [{"role": "user", "content": "List group conversation names and the number of messages sent in each conversation after January 1, 2023."}, {"role": "assistant", "content": "SELECT c.group_name, COUNT(m.message_id) FROM social_media.conversations c JOIN social_media.messages m ON c.conversation_id = m.conversation_id WHERE c.is_group_chat = true AND m.sent_at >= '2023-01-01' GROUP BY c.conversation_id, c.group_name;"}, {"role": "user", "content": "Only show conversations that have more than 100 messages sent after that date."}, {"role": "assistant", "content": "SELECT c.group_name, COUNT(m.message_id) FROM social_media.conversations c JOIN social_media.messages m ON c.conversation_id = m.conversation_id WHERE c.is_group_chat = true AND m.sent_at >= '2023-01-01' GROUP BY c.conversation_id, c.group_name HAVING COUNT(m.message_id) > 100;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE social_media.users ( user_id text, username text, email text, password_hash text, full_name text, profile_picture_url text, bio text, location text, created_at timestamp, updated_at timestamp, is_verified boolean )\nCREATE TABLE social_media.posts ( post_id text, user_id text, content text, media_url text, media_type text, created_at timestamp, updated_at timestamp, visibility text, location_lat numeric, location_lon numeric )\nCREATE TABLE social_media.likes ( like_id text, user_id text, post_id text, comment_id text, created_at timestamp )\nCREATE TABLE social_media.follows ( follow_id text, follower_user_id text, following_user_id text, created_at timestamp )\nCREATE TABLE social_media.post_hashtags ( post_hashtag_id text, post_id text, hashtag_id text )\nCREATE TABLE social_media.messages ( message_id text, conversation_id text, sender_user_id text, content text, media_url text, media_type text, sent_at timestamp, read_at timestamp )\nCREATE TABLE social_media.conversations ( conversation_id text, created_at timestamp, last_message_at timestamp, is_group_chat boolean, group_name text )\nCREATE TABLE social_media.conversation_participants ( participant_id text, conversation_id text, user_id text, joined_at timestamp, last_read_at timestamp )\nCREATE TABLE social_media.notifications ( notification_id text, recipient_user_id text, sender_user_id text, notification_type text, target_entity_id text, target_entity_type text, created_at timestamp, read_at timestamp )\nCREATE TABLE social_media.user_settings ( setting_id text, user_id text, theme text, email_notifications_enabled boolean, push_notifications_enabled boolean, private_profile boolean, updated_at timestamp )\n"} {"conversations": [{"role": "user", "content": "What is the performance review score for employee with ID 'EMP456' for the last quarter?"}, {"role": "assistant", "content": "I'm sorry, but I can't assist with information about performance review scores as this data is not included in the employees table."}], "system": "You are an SQL statement expert and you can refuse the user's question if the question is not related to the table structure. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE manufacturing.employees ( employee_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, job_title character varying(128) NOT NULL, skill_certifications text, hire_date date NOT NULL, assigned_line_id character varying(64), employment_status character varying(50) NOT NULL, supervisor_employee_id character varying(64), PRIMARY KEY (employee_id) )\n"} {"conversations": [{"role": "user", "content": "Show the full names and contact emails of all citizens who have applied for services with a standard fee greater than 100."}, {"role": "assistant", "content": "SELECT c.first_name || ' ' || c.last_name AS full_name, c.contact_email\nFROM government_services.citizens c\nJOIN government_services.services s ON c.citizen_id IS NOT NULL -- Replace with actual application linking table if exists\nWHERE s.standard_fee > 100;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.citizens ( citizen_id character varying(64) NOT NULL, national_id_number character varying(128) NOT NULL UNIQUE, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, date_of_birth date NOT NULL, gender character varying(20), primary_address text NOT NULL, contact_email character varying(128) UNIQUE, contact_phone character varying(32), registration_date timestamp NOT NULL, is_verified boolean DEFAULT false, PRIMARY KEY (citizen_id) )\nCREATE TABLE government_services.services ( service_id.text, agency_id.text, service_name.text, description.text, category.text, eligibility_criteria.text, standard_fee.numeric, average_processing_time_days.integer, is_active.boolean, online_application_url.text )\n"} {"conversations": [{"role": "user", "content": "How many agents are currently active in each license state?"}, {"role": "assistant", "content": "SELECT license_state, COUNT(*) AS active_agent_count\nFROM insurance.agents\nWHERE status = 'Active'\nGROUP BY license_state;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.claims (\n claim_id character varying(64) NOT NULL, -- unique identifier for the claim\n policy_id character varying(64) NOT NULL, -- identifier of the policy under which the claim is made (FK to policies)\n customer_id character varying(64) NOT NULL, -- identifier of the customer making the claim (FK to customers)\n incident_date timestamp NOT NULL, -- date and time of the incident leading to the claim\n reported_date timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- date the claim was reported\n description text NOT NULL, -- detailed description of the incident and claim\n estimated_loss numeric(15, 2), -- initial estimated cost of the loss\n status character varying(30) NOT NULL, -- e.g., Filed, Processing, Under Review, Approved, Denied, Settled\n settlement_amount numeric(15, 2), -- final amount paid out\n settlement_date date,\n claim_handler_id character varying(64), -- identifier for the employee handling the claim (FK to employees/adjusters)\n police_report_number character varying(100),\n PRIMARY KEY (claim_id)\n)\nCREATE TABLE insurance.agents ( agent_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, agency_name character varying(150), license_number character varying(100) NOT NULL UNIQUE, license_state character varying(50) NOT NULL, contact_email character varying(128) UNIQUE, contact_phone character varying(30), hire_date date, termination_date date, status character varying(20) NOT NULL DEFAULT 'Active', commission_rate numeric(5, 4) NOT NULL DEFAULT 0.05, manager_id character varying(64), PRIMARY KEY (agent_id) )\n"} {"conversations": [{"role": "user", "content": "Show me all wallet addresses that hold more than 1000 of any ERC1155 token, along with the token ID and amount, from the nft_holders table."}, {"role": "assistant", "content": "SELECT wallet_address, token_id, amount FROM nft_holders WHERE contract_type = 'ERC1155' AND CAST(amount AS decimal) > 1000;"}, {"role": "user", "content": "Can you join this with the nft_metadata table to include the name and image_uri of each token?"}, {"role": "assistant", "content": "SELECT nh.wallet_address, nh.token_id, nh.amount, nm.name, nm.image_uri FROM nft_holders nh JOIN nft_metadata nm ON nh.contract_address = nm.contract_address AND nh.token_id = nm.token_id WHERE nh.contract_type = 'ERC1155' AND CAST(nh.amount AS decimal) > 1000;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE token_metas ( block_timestamp timestamp(6) NOT NULL, block_number bigint NOT NULL, transaction_hash varchar NOT NULL, transaction_index bigint NOT NULL, from_address varchar NOT NULL, contract_address varchar NOT NULL, symbol varchar NOT NULL, total_supply varchar NOT NULL, name varchar NOT NULL, decimals bigint NOT NULL, is_erc20 integer NOT NULL, is_erc721 integer NOT NULL, is_erc1155 integer NOT NULL, is_proxy integer NOT NULL, extra_info varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE erc1155_approval_for_all ( block_number bigint NOT NULL, block_timestamp timestamp(3) NOT NULL, transaction_index integer NOT NULL, transaction_hash varchar(66) NOT NULL, log_index integer NOT NULL, contract_address varchar(42) NOT NULL )\nCREATE TABLE erc20_balances_historical ( block_number bigint, contract_address text, wallet_address text, amount text, pk integer )\nCREATE TABLE nft_holders ( block_number bigint NOT NULL, contract_address varchar NOT NULL, wallet_address varchar NOT NULL, token_id varchar NOT NULL, contract_type varchar NOT NULL, amount varchar NOT NULL, pk varchar NOT NULL )\nCREATE TABLE nft_holder_historical ( block_number.bigint, contract_address.text, wallet_address.text, token_id.text, contract_type.text, amount.text, pk.integer )\nCREATE TABLE sui_coins ( object_id varchar NOT NULL, status varchar NOT NULL, coin_type varchar NOT NULL, balance varchar NOT NULL, owner varchar NOT NULL )\nCREATE TABLE sui_nfts ( object_id text, status text, collection_type text, package_id text, previous_transaction text, display text, owner text, name text )\nCREATE TABLE nft_metadata (\n blockchain varchar NOT NULL, -- blockchain fields for the functionType in contract\n contract_address varchar NOT NULL, -- Contract address(with bloom filter)\n token_id varchar NOT NULL, -- The number of the token\n contract_name varchar NOT NULL, -- contract_name fields for the functionType in contract\n erc_type varchar NOT NULL, -- The type of token\n amount bigint NOT NULL, -- amount fields for the functionType in contract\n minter varchar NOT NULL, -- minter fields for the functionType in contract\n owner varchar NOT NULL, -- owner fields for the functionType in contract\n mint_block_number bigint NOT NULL, -- mint_block_number fields for the functionType in contract\n mint_time bigint NOT NULL, -- mint_time fields for the functionType in contract\n mint_transaction_hash varchar NOT NULL, -- mint_transaction_hash fields for the functionType in contract\n mint_price varchar NOT NULL, -- mint_price fields for the functionType in contract\n token_uri varchar NOT NULL, -- token_uri fields for the functionType in contract\n metadata varchar NOT NULL, -- metadata fields for the functionType in contract\n name varchar NOT NULL, -- name fields for the functionType in contract\n image_uri varchar NOT NULL, -- image_uri fields for the functionType in contract\n traits varchar NOT NULL, -- traits fields for the functionType in contract\n updated_at bigint NOT NULL, -- updated_at fields for the functionType in contract\n status varchar NOT NULL, -- status fields for the functionType in contract\n rarity_score real NOT NULL, -- rarity_score fields for the functionType in contract\n rarity_rank integer NOT NULL, -- rarity_rank fields for the functionType in contract\n unique_attribute_count integer NOT NULL, -- unique_attribute_count fields for the functionType in contract\n pk integer NOT NULL -- Partition key for the table(floor(mint_time / 1000 / 86400 / 30))\n)\nCREATE TABLE token_prices ( uuid text, blockchain text, address text, decimals bigint, symbol text, price real, timestamp timestamp )\nCREATE TABLE erc20_approval ( block_number bigint, block_timestamp timestamp, transaction_index integer, transaction_hash varchar, log_index integer, contract_address varchar, pk integer )\nCREATE TABLE token_info ( block_timestamp timestamp(3) NOT NULL, block_number bigint NOT NULL, tx_index integer NOT NULL, tx_hash varchar(66) NOT NULL, tick varchar NOT NULL, max_supply decimal(38,0) NOT NULL, lim decimal(38,0) NOT NULL, wlim decimal(38,0) NOT NULL, dec integer NOT NULL, creator varchar(42) NOT NULL )\nCREATE TABLE token_activities ( block_timestamp.timestamp, block_number.bigint, tx_index.integer, tx_hash.text, log_index.integer, type.text, tick.text, id.text, amt.decimal, from_address.text, to_address.text )\nCREATE TABLE mud_holesky_redstone ( address varchar NOT NULL, table_id varchar NOT NULL, key_bytes varchar NOT NULL, key0 varchar NOT NULL, key1 varchar NOT NULL, static_data varchar NOT NULL, encoded_lengths varchar NOT NULL, dynamic_data varchar NOT NULL, is_deleted boolean NOT NULL, block_number bigint NOT NULL, log_index bigint NOT NULL )\nCREATE TABLE token_info_bitcoin (\n block_timestamp timestamp(3) NOT NULL, -- Timestamp of the block containing the inscription (matches block_timestamp in transactions table)\n block_number bigint NOT NULL, -- Block number containing the inscription (matches block_number in transactions table)\n tx_index integer NOT NULL, -- Index of the transaction containing the inscription (matches transaction_index in transactions table)\n tx_hash varchar(66) NOT NULL, -- Unique identifier of the transaction containing the inscription (matches hash in transactions table)\n tick varchar(255) NOT NULL, -- Ticker: Identifier of the inscription\n max_supply decimal(38,0) NOT NULL, -- Max supply: Set max supply of the inscription\n lim decimal(38,0) NOT NULL, -- Mint limit: limit per inscription\n wlim decimal(38,0) NOT NULL, -- Limit of each address can maximum mint\n dec integer NOT NULL, -- Decimal for minimum divie\n creator varchar(42) NOT NULL -- Address originating the inscription (matches from_address in transactions table)\n)\nCREATE TABLE token_activities_avalanche (\n block_timestamp timestamp(3) NOT NULL, -- Timestamp of the block containing the inscription (matches block_timestamp in transactions table)\n block_number bigint NOT NULL, -- Block number containing the inscription (matches block_number in transactions table)\n tx_index integer NOT NULL, -- Index of the transaction containing the inscription (matches transaction_index in transactions table)\n tx_hash varchar(66) NOT NULL, -- Unique identifier of the transaction containing the inscription (matches hash in transactions table)\n log_index integer NOT NULL, -- Index of the log within the transaction\n type varchar(20) NOT NULL, -- Operation: Type of event (deploy, mint, transfer, list)\n tick varchar(255) NOT NULL, -- Ticker: Identifier of the inscription\n id varchar(255) NOT NULL, -- Unique identifier of the inscription\n amt decimal(38,0) NOT NULL, -- Amount to mint: States the amount of the inscription to operation. When operation is mint, has to be less or equal to \"lim\"\n from_address varchar(42) NOT NULL, -- Address sending the inscription\n to_address varchar(42) NOT NULL -- Address receiving the inscription\n)\nCREATE TABLE token_balances_avalanche (\n block_number bigint NOT NULL, -- Block number containing the transaction\n block_timestamp timestamp(3) NOT NULL, -- Block timestamp containing the transaction\n tick varchar(20) NOT NULL, -- Ticker: Identifier of the inscription\n wallet_address varchar(42) NOT NULL, -- Address of owner\n total_supply decimal(38,0) NOT NULL, -- Max supply: Set max supply of the inscription\n amount decimal(38,0) NOT NULL -- The balance of wallet balance at the corresponding block height\n)\n"} {"conversations": [{"role": "user", "content": "Get a list of room types along with their property name and the count of rooms currently Available for each type."}, {"role": "assistant", "content": "SELECT rt.type_name, p.property_name, COUNT(r.room_id) AS available_rooms_count\nFROM hospitality_technology.room_types rt\nJOIN hospitality_technology.rooms r ON rt.room_type_id = r.room_type_id\n AND r.status = 'Available'\nJOIN hospitality_technology.properties p ON rt.property_id = p.property_id\nGROUP BY rt.type_name, p.property_name;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE hospitality_technology.properties ( property_id character varying(64) NOT NULL, property_name character varying(255) NOT NULL, address_line1 character varying(255) NOT NULL, address_line2 character varying(255), city character varying(100) NOT NULL, state_province character varying(100), postal_code character varying(20) NOT NULL, country_code character varying(3) NOT NULL, phone_number character varying(30), email_address character varying(255), property_type character varying(50) NOT NULL, star_rating numeric(2,1), timezone character varying(64) NOT NULL, manager_staff_id character varying(64), created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, updated_at timestamp with time zone NOT NULL DEFAULT current_timestamp, PRIMARY KEY (property_id) )\nCREATE TABLE hospitality_technology.rooms ( room_id character varying(64) NOT NULL, property_id character varying(64) NOT NULL, room_number character varying(10) NOT NULL, room_type_id character varying(64) NOT NULL, floor integer, status character varying(50) NOT NULL, is_smoking boolean NOT NULL DEFAULT false, features text, current_condition text, last_cleaned_at timestamp with time zone, PRIMARY KEY (room_id), FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id), FOREIGN KEY (room_type_id) REFERENCES hospitality_technology.room_types(room_type_id) )\nCREATE TABLE hospitality_technology.room_types ( room_type_id character varying(64) NOT NULL, property_id character varying(64) NOT NULL, type_name character varying(100) NOT NULL, description text, base_rate numeric(10, 2) NOT NULL, max_occupancy integer NOT NULL, bed_type character varying(50), area_sqft numeric(8,2), amenities text, PRIMARY KEY (room_type_id), FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id) )\nCREATE TABLE hospitality_technology.guests ( guest_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, email character varying(255) UNIQUE, phone_number character varying(30), date_of_birth date, address_line1 character varying(255), city character varying(100), state_province character varying(100), postal_code character varying(20), country_code character varying(3), preferences text, loyalty_member_id character varying(64) UNIQUE, communication_consent boolean DEFAULT true, created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, updated_at timestamp with time zone NOT NULL DEFAULT current_timestamp, PRIMARY KEY (guest_id) )\nCREATE TABLE hospitality_technology.reservations ( reservation_id character varying(64) NOT NULL, property_id character varying(64) NOT NULL, guest_id character varying(64) NOT NULL, room_id character varying(64), room_type_id character varying(64) NOT NULL, check_in_date date NOT NULL, check_out_date date NOT NULL, actual_check_in_ts timestamp with time zone, actual_check_out_ts timestamp with time zone, num_adults integer NOT NULL, num_children integer DEFAULT 0, status character varying(50) NOT NULL, booking_source character varying(100), rate_plan_id character varying(64), total_amount numeric(12, 2), amount_paid numeric(12, 2) DEFAULT 0.00, special_requests text, created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, updated_at timestamp with time zone NOT NULL DEFAULT current_timestamp, PRIMARY KEY (reservation_id), FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id), FOREIGN KEY (guest_id) REFERENCES hospitality_technology.guests(guest_id), FOREIGN KEY (room_id) REFERENCES hospitality_technology.rooms(room_id), FOREIGN KEY (room_type_id) REFERENCES hospitality_technology.room_types(room_type_id) )\nCREATE TABLE hospitality_technology.staff ( staff_id character varying(64) NOT NULL, property_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, position character varying(100) NOT NULL, work_email character varying(255) UNIQUE, work_phone character varying(30), hire_date date NOT NULL, termination_date date, is_active boolean NOT NULL DEFAULT true, access_level integer NOT NULL, manager_id character varying(64), created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, PRIMARY KEY (staff_id), FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id), FOREIGN KEY (manager_id) REFERENCES hospitality_technology.staff(staff_id) )\nCREATE TABLE hospitality_technology.services ( service_id character varying(64) NOT NULL, property_id character varying(64) NOT NULL, service_name character varying(150) NOT NULL, description text, category character varying(100), price numeric(10, 2) NOT NULL, unit character varying(30), is_available boolean NOT NULL DEFAULT true, department character varying(100), PRIMARY KEY (service_id), FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id) )\nCREATE TABLE hospitality_technology.service_orders ( order_id character varying(64) NOT NULL, reservation_id character varying(64), guest_id character varying(64) NOT NULL, service_id character varying(64) NOT NULL, staff_id_ordered character varying(64), staff_id_delivered character varying(64), order_timestamp timestamp with time zone NOT NULL DEFAULT current_timestamp, delivery_timestamp timestamp with time zone, quantity integer NOT NULL DEFAULT 1, unit_price numeric(10, 2) NOT NULL, total_price numeric(12, 2) NOT NULL, status character varying(50) NOT NULL, notes text, bill_id character varying(64), PRIMARY KEY (order_id), FOREIGN KEY (reservation_id) REFERENCES hospitality_technology.reservations(reservation_id), FOREIGN KEY (guest_id) REFERENCES hospitality_technology.guests(guest_id), FOREIGN KEY (service_id) REFERENCES hospitality_technology.services(service_id), FOREIGN KEY (staff_id_ordered) REFERENCES hospitality_technology.staff(staff_id), FOREIGN KEY (staff_id_delivered) REFERENCES hospitality_technology.staff(staff_id) )\nCREATE TABLE hospitality_technology.reviews ( review_id character varying(64) NOT NULL, property_id character varying(64) NOT NULL, reservation_id character varying(64) UNIQUE, guest_id character varying(64) NOT NULL, rating_overall integer, rating_cleanliness integer, rating_service integer, rating_location integer, rating_value integer, comment text, review_source character varying(100), review_date timestamp with time zone NOT NULL DEFAULT current_timestamp, is_public boolean DEFAULT true, staff_response text, response_staff_id character varying(64), response_date timestamp with time zone, PRIMARY KEY (review_id), FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id), FOREIGN KEY (reservation_id) REFERENCES hospitality_technology.reservations(reservation_id), FOREIGN KEY (guest_id) REFERENCES hospitality_technology.guests(guest_id), FOREIGN KEY (response_staff_id) REFERENCES hospitality_technology.staff(staff_id) )\n"} {"conversations": [{"role": "user", "content": "How many policies were canceled in the previous month, grouped by cancellation reason?"}, {"role": "assistant", "content": "SELECT cancellation_reason,\n COUNT(*) AS canceled_count\nFROM insurance.policies\nWHERE cancellation_date BETWEEN date_trunc('month', CURRENT_DATE) - INTERVAL '1 month'\n AND date_trunc('month', CURRENT_DATE) - INTERVAL '1 day'\nGROUP BY cancellation_reason;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.policies ( policy_id text, customer_id text, product_id text, agent_id text, policy_number text, start_date date, end_date date, premium_amount numeric, coverage_limit numeric, deductible numeric, status text, issued_at timestamp, cancellation_date date, cancellation_reason text )\n"} {"conversations": [{"role": "user", "content": "List the first_name, last_name, and email of all clients whose email domain is 'gmail.com'."}, {"role": "assistant", "content": "SELECT first_name, last_name, email FROM legal_services.clients WHERE SUBSTRING(email FROM POSITION('@' IN email) + 1) = 'gmail.com';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.clients ( client_id text, first_name text, last_name text, company_name text, email text, phone text, address text, date_registered timestamp, status text )\n"} {"conversations": [{"role": "user", "content": "Show the symbol, name, and total supply for all SUI coins with status 'active'."}, {"role": "assistant", "content": "SELECT scm.symbol, scm.name, scm.coin_type, scm.total_supply\nFROM sui_coins_metadata scm\nWHERE scm.status = 'active';"}, {"role": "user", "content": "I received an error that column 'total_supply' doesn't exist in sui_coins_metadata."}, {"role": "assistant", "content": "SELECT scm.symbol, scm.name, scm.coin_type\nFROM sui_coins_metadata scm\nWHERE scm.status = 'active';"}, {"role": "user", "content": "Now, join with sui_coins to add up the total balance across all owners for each coin_type."}, {"role": "assistant", "content": "SELECT scm.symbol, scm.name, scm.coin_type, SUM(CAST(sc.balance AS NUMERIC)) AS total_balance\nFROM sui_coins_metadata scm\nJOIN sui_coins sc ON scm.coin_type = sc.coin_type\nWHERE scm.status = 'active'\nGROUP BY scm.symbol, scm.name, scm.coin_type;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE token_metas ( block_timestamp timestamp, block_number bigint, transaction_hash text, transaction_index bigint, from_address text, contract_address text, symbol text, total_supply text, name text, decimals bigint, is_erc20 integer, is_erc721 integer, is_erc1155 integer, is_proxy integer, extra_info text, pk integer )\nCREATE TABLE erc1155_approval_for_all ( block_number bigint, block_timestamp timestamp, transaction_index integer, transaction_hash text, log_index integer, contract_address text )\nCREATE TABLE erc20_balances ( block_number bigint, contract_address text, wallet_address text, amount text, pk text )\nCREATE TABLE erc20_balances_historical ( block_number bigint, contract_address text, wallet_address text, amount text, pk integer )\nCREATE TABLE nft_holders ( block_number bigint, contract_address text, wallet_address text, token_id text, contract_type text, amount text, pk text )\nCREATE TABLE nft_holder_historical ( block_number bigint, contract_address text, wallet_address text, token_id text, contract_type text, amount text, pk integer )\nCREATE TABLE sui_coins ( object_id text, status text, coin_type text, balance text, owner text )\nCREATE TABLE sui_coins_metadata ( object_id text, coin_type text, status text, decimals bigint, description text, icon_url text, symbol text, name text )\nCREATE TABLE sui_nfts ( object_id text, status text, collection_type text, package_id text, previous_transaction text, display text, owner text, name text )\nCREATE TABLE nft_metadata ( blockchain text, contract_address text, token_id text, contract_name text, erc_type text, amount bigint, minter text, owner text, mint_block_number bigint, mint_time bigint, mint_transaction_hash text, mint_price text, token_uri text, metadata text, name text, image_uri text, traits text, updated_at bigint, status text, rarity_score real, rarity_rank integer, unique_attribute_count integer, pk integer )\nCREATE TABLE nft_collections ( blockchain text, contract_address text, name text, symbol text, deploy_block_number bigint, deploy_block_time bigint, erc_type text, owner text, traits text, description text, slug text, media_info text, image_url text, banner_image_url text, updated_at bigint, banner text, token_count bigint, floor_price text, floor_price_symbol text, floor_price_contract text, pk integer )\nCREATE TABLE token_prices ( uuid text, blockchain text, address text, decimals bigint, symbol text, price real, timestamp timestamp )\nCREATE TABLE token_prices_latest ( blockchain text, address text, decimals bigint, symbol text, price real, timestamp timestamp )\nCREATE TABLE erc20_approval ( block_number bigint, block_timestamp timestamp, transaction_index integer, transaction_hash text, log_index integer, contract_address text, pk integer )\nCREATE TABLE token_balances ( block_number bigint, block_timestamp timestamp, tick text, wallet_address text, total_supply decimal, amount decimal )\nCREATE TABLE token_info ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash text, tick text, max_supply decimal, lim decimal, wlim decimal, dec integer, creator text )\nCREATE TABLE token_activities ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash text, log_index integer, type text, tick text, id text, amt decimal, from_address text, to_address text )\nCREATE TABLE mud_holesky_redstone ( address text, table_id text, key_bytes text, key0 text, key1 text, static_data text, encoded_lengths text, dynamic_data text, is_deleted boolean, block_number bigint, log_index bigint )\nCREATE TABLE token_balances_bitcoin ( block_number bigint, block_timestamp timestamp, tick text, wallet_address text, total_supply text, amount text )\nCREATE TABLE token_info_bitcoin ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash text, tick text, max_supply decimal, lim decimal, wlim decimal, dec integer, creator text )\nCREATE TABLE token_activities_bitcoin ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash text, log_index integer, type text, tick text, id text, amt decimal, from_address text, to_address text )\nCREATE TABLE token_activities_avalanche ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash text, log_index integer, type text, tick text, id text, amt decimal, from_address text, to_address text )\nCREATE TABLE token_balances_avalanche ( block_number bigint, block_timestamp timestamp, tick text, wallet_address text, total_supply decimal, amount decimal )\n"} {"conversations": [{"role": "user", "content": "Show me the top 5 tokens by 24-hour trading volume on the Ethereum chain, along with their narrative and 7-day price change percentage."}, {"role": "assistant", "content": "SELECT t.token_symbol, t.narrative, t.price_change_percentage_7d FROM token_basic_info t WHERE t.chain = 'Ethereum' ORDER BY CAST(t.total_volume AS numeric) DESC LIMIT 5;"}, {"role": "user", "content": "Can you also include their liquidity from the token_dexpool_info table?"}, {"role": "assistant", "content": "SELECT t.token_symbol, t.narrative, t.price_change_percentage_7d, d.liquidity FROM token_basic_info t JOIN token_dexpool_info d ON t.token_symbol = d.token_symbol AND t.chain = d.chain WHERE t.chain = 'Ethereum' ORDER BY CAST(t.total_volume AS numeric) DESC LIMIT 5;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE token_basic_info ( coin_id character varying(100) NOT NULL, -- the id of the token token_name character varying(100) NOT NULL, -- the token's name token_symbol character varying(100) NOT NULL, -- the token's symbol token_address character varying(100) NOT NULL, -- the token's address chain text, -- the chain that the token resides price double precision, -- the current price of the token price_change_percentage_1h double precision, -- change in value divided by the absolute price value of the original token price in 1 hour price_change_percentage_24h double precision, -- change in value divided by the absolute price value of the original token price in 24 hours price_change_percentage_7d double precision, -- change in value divided by the absolute price value of the original token price in 7 days highest_price_24h double precision, -- the highest price of the token in 24 hours lowest_price_24h double precision, -- the lowest price of the token in 24 hours market_cap double precision, -- the market cap of the token market_cap_rank bigint, -- the rank of the token market cap in desc market_cap_change_percentage_24h text, -- the percentage of market cap changes in 24 hours total_volume text, -- the trade volum of the token both in decentralized exchange(DEX) and centralized exchange(CEX) narrative text, -- the category or narrative of the token trend_rank biging, -- the trending rank of the token, value 1 expresses the most popular token. ,PRIMARY KEY (coin_id, chain) )\nCREATE TABLE narrative_info ( narrative character varying(512) NOT NULL, -- the id of narrative top_3_coins text, -- the top 3 tokens in the narrative price_change_percentage_1h double precision, -- change in value divided by the absolute price value of the original token price in 1 hour in the narrative price_change_percentage_24h double precision, -- change in value divided by the absolute price value of the original token price in 24 hours in the narrative price_change_percentage_7d double precision, -- change in value divided by the absolute price value of the original token price in 7 days in the narrative market_cap double precision, -- the market cap of the narrative volume_24h double precision, -- the trade volume of the narrative trend_rank bigint, -- the trending rank of the narrative, value 1 expresses the most popular narrative token_num bigint, -- total token number in the narrative ,PRIMARY KEY (narrative) )\nCREATE TABLE token_dexpool_info ( pair_address character varying(512) NOT NULL, -- the id of dexpool token_name character varying(100) NOT NULL, -- the name of the token in the dexpool token_symbol character varying(100) NOT NULL, -- the token's symbol chain text, -- the chain that the dexpool resides price double precision, -- the current price of the token price_change_percentage_1h double precision, -- change in value divided by the absolute price value of the original token price in 1 hour price_change_percentage_6h double precision, -- change in value divided by the absolute price value of the original token price in 6 hours price_change_percentage_24h double precision, -- change in value divided by the absolute price value of the original token price in 24 hours makers_24h double precision, -- the makers of the dex pool in 24 hours volume_24h double precision, -- the trade volume of the dex pool in 24 hours liquidity double precision, -- the liquidity of the dex pool market_cap double precision, -- the market cap of the token trend_rank bigint, -- the rank of token in the dex pool of recent trending, value 1 expresses the most popular token. ,PRIMARY KEY (pair_address, chain) )\nCREATE TABLE smart_money_profit ( address character varying(100) NOT NULL, -- the user's address rank INT, -- the rank of the address in trade performance, value 1 expresses the best address. profit numeric(38,6), -- the profit user made in a month roi numeric(38,2), -- the roi of the user in a month realized_ratio numeric(38,2), -- the percentage of the user's realized profit most_profit_token character varying(100), -- the token symbol of the user's most profitable trade last_trade_time character varying(100), -- the last trade time of the user chain character varying(100), -- the chain that the address resides PRIMARY KEY (address, chain) )\nCREATE TABLE smart_money_token_performance ( token_address character varying(100) NOT NULL, -- the token's address token_symbol character varying(100), -- the tokens's symbol pnl numeric(38,2), -- the profit users made on this token net_flow numeric(38,2), -- the netflow of the token, means the money user spent minus the the money user sold of this token avg_cost numeric(38,16), -- the average cost price of user spent on this token price double precision, -- the current price of the token realized_ratio numeric(10,2), -- the ratio user sold of the token roi numeric(10,2), -- the roi users made of this token chain character varying(100), -- the chain that the token resides PRIMARY KEY (token_address, chain) )\nCREATE TABLE smart_money_token_inflow ( token_address character varying(100) NOT NULL, -- the token's address token_symbol character varying(100), -- the tokens's symbol token_amount numeric(38,2), -- the absolute value of the amount if user bought minus the amount user sold of this token usd_value numeric(38,2), -- the absolute usd value of the bought token minus sold token avg_price numeric(38,6), -- the average cost price of user spent on this token type int, -- the direction of the trade on this token. 1 means buying, 2 means selling address_amount integer, -- the amount of the user bought this token narrative character varying(100), -- the category or narrative of the token chain character varying(100), -- the chain that the token resides ,PRIMARY KEY (token_address, chain) )\n"} {"conversations": [{"role": "user", "content": "Show each policy number and the total amount paid for it across all premium payments received so far."}, {"role": "assistant", "content": "SELECT T1.policy_number, SUM(T2.amount_paid) FROM insurance.policies AS T1 JOIN insurance.premium_payments AS T2 ON T1.policy_id = T2.policy_id GROUP BY T1.policy_number;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.customers ( customer_id text PRIMARY KEY, first_name text, last_name text, date_of_birth date, ssn_hash text, address_line1 text, address_line2 text, city text, state text, zip_code text, country text, phone_number text, email text, created_at timestamp, updated_at timestamp, status text )\nCREATE TABLE insurance.policies ( policy_id text, customer_id text, product_id text, agent_id text, policy_number text, start_date date, end_date date, premium_amount numeric, coverage_limit numeric, deductible numeric, status text, issued_at timestamp, cancellation_date date, cancellation_reason text )\nCREATE TABLE insurance.claims (\n claim_id character varying(64) NOT NULL, -- unique identifier for the claim\n policy_id character varying(64) NOT NULL, -- identifier of the policy under which the claim is made (FK to policies)\n customer_id character varying(64) NOT NULL, -- identifier of the customer making the claim (FK to customers)\n incident_date timestamp NOT NULL, -- date and time of the incident leading to the claim\n reported_date timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- date the claim was reported\n description text NOT NULL, -- detailed description of the incident and claim\n estimated_loss numeric(15, 2), -- initial estimated cost of the loss\n status character varying(30) NOT NULL, -- e.g., Filed, Processing, Under Review, Approved, Denied, Settled\n settlement_amount numeric(15, 2), -- final amount paid out\n settlement_date date,\n claim_handler_id character varying(64), -- identifier for the employee handling the claim (FK to employees/adjusters)\n police_report_number character varying(100),\n PRIMARY KEY (claim_id)\n)\nCREATE TABLE insurance.insurance_products ( product_id text PRIMARY KEY, product_name text, product_type text, description text, base_premium numeric, coverage_details text, underwriting_rules text, is_active boolean, created_at timestamp, updated_at timestamp )\nCREATE TABLE insurance.agents ( agent_id text, first_name text, last_name text, agency_name text, license_number text, license_state text, contact_email text, contact_phone text, hire_date date, termination_date date, status text, commission_rate numeric, manager_id text )\nCREATE TABLE insurance.premium_payments (\n payment_id character varying(64) NOT NULL, -- unique identifier for the payment\n policy_id character varying(64) NOT NULL, -- identifier of the policy the payment is for (FK to policies)\n customer_id character varying(64) NOT NULL, -- identifier of the customer making the payment (FK to customers)\n payment_date timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- date the payment was received\n amount_paid numeric(12, 2) NOT NULL, -- amount of the payment\n payment_method character varying(50), -- e.g., Credit Card, Bank Transfer, Check\n transaction_reference character varying(128) UNIQUE, -- reference from payment processor\n due_date date, -- due date for this payment installment\n payment_period_start date, -- start date of the period this payment covers\n payment_period_end date, -- end date of the period this payment covers\n status character varying(30) NOT NULL DEFAULT 'Completed', -- e.g., Completed, Pending, Failed, Refunded\n PRIMARY KEY (payment_id)\n)\nCREATE TABLE insurance.claim_documents ( document_id character varying(64) NOT NULL, claim_id character varying(64) NOT NULL, document_type character varying(50) NOT NULL, file_name character varying(255) NOT NULL, file_path character varying(512) NOT NULL, file_size_bytes integer, mime_type character varying(100), uploaded_by character varying(64), uploaded_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, description text, PRIMARY KEY (document_id) )\n"} {"conversations": [{"role": "user", "content": "Show me all claims along with the related customer's full name and the policy number for incidents that occurred in 2024."}, {"role": "assistant", "content": "SELECT c.claim_id, c.incident_date, c.description, cu.first_name || ' ' || cu.last_name AS customer_full_name, p.policy_number\nFROM insurance.claims c\nJOIN insurance.customers cu ON c.customer_id = cu.customer_id\nJOIN insurance.policies p ON c.policy_id = p.policy_id\nWHERE EXTRACT(YEAR FROM c.incident_date) = 2024;"}, {"role": "user", "content": "Include the settlement amount and status of each claim in the results."}, {"role": "assistant", "content": "SELECT c.claim_id, c.incident_date, c.description, cu.first_name || ' ' || cu.last_name AS customer_full_name, p.policy_number, c.settlement_amount, c.status\nFROM insurance.claims c\nJOIN insurance.customers cu ON c.customer_id = cu.customer_id\nJOIN insurance.policies p ON c.policy_id = p.policy_id\nWHERE EXTRACT(YEAR FROM c.incident_date) = 2024;"}, {"role": "user", "content": "Actually, please filter only those claims with a settlement_amount that is not null."}, {"role": "assistant", "content": "SELECT c.claim_id, c.incident_date, c.description, cu.first_name || ' ' || cu.last_name AS customer_full_name, p.policy_number, c.settlement_amount, c.status\nFROM insurance.claims c\nJOIN insurance.customers cu ON c.customer_id = cu.customer_id\nJOIN insurance.policies p ON c.policy_id = p.policy_id\nWHERE EXTRACT(YEAR FROM c.incident_date) = 2024\n AND c.settlement_amount IS NOT NULL;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.customers (\n customer_id character varying(64) NOT NULL, -- unique identifier for the customer\n first_name character varying(100) NOT NULL, -- customer's first name\n last_name character varying(100) NOT NULL, -- customer's last name\n date_of_birth date NOT NULL, -- customer's date of birth\n ssn_hash character varying(128), -- Hashed social security number (or national ID)\n address_line1 character varying(255) NOT NULL,\n address_line2 character varying(255),\n city character varying(100) NOT NULL,\n state character varying(50) NOT NULL,\n zip_code character varying(20) NOT NULL,\n country character varying(50) NOT NULL DEFAULT 'USA',\n phone_number character varying(30),\n email character varying(128) UNIQUE, -- unique email address\n created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- when the customer record was created\n updated_at timestamp, -- when the customer record was last updated\n status character varying(20) NOT NULL DEFAULT 'Active', -- e.g., Active, Inactive, Prospect\n PRIMARY KEY (customer_id)\n)\nCREATE TABLE insurance.policies ( policy_id character varying(64) NOT NULL, customer_id character varying(64) NOT NULL, product_id character varying(64) NOT NULL, agent_id character varying(64), policy_number character varying(100) NOT NULL UNIQUE, start_date date NOT NULL, end_date date NOT NULL, premium_amount numeric(12, 2) NOT NULL, coverage_limit numeric(15, 2) NOT NULL, deductible numeric(10, 2) NOT NULL, status character varying(30) NOT NULL, issued_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, cancellation_date date, cancellation_reason text, PRIMARY KEY (policy_id) )\nCREATE TABLE insurance.claims ( claim_id character varying(64) NOT NULL, policy_id character varying(64) NOT NULL, customer_id character varying(64) NOT NULL, incident_date timestamp NOT NULL, reported_date timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, description text NOT NULL, estimated_loss numeric(15, 2), status character varying(30) NOT NULL, settlement_amount numeric(15, 2), settlement_date date, claim_handler_id character varying(64), police_report_number character varying(100), PRIMARY KEY (claim_id) )\nCREATE TABLE insurance.insurance_products ( product_id.text, product_name.text, product_type.text, description.text, base_premium.numeric, coverage_details.text, underwriting_rules.text, is_active.boolean, created_at.timestamp, updated_at.timestamp )\nCREATE TABLE insurance.premium_payments ( payment_id text, policy_id text, customer_id text, payment_date timestamp, amount_paid numeric, payment_method text, transaction_reference text, due_date date, payment_period_start date, payment_period_end date, status text )\nCREATE TABLE insurance.claim_documents ( document_id.text, claim_id.text, document_type.text, file_name.text, file_path.text, file_size_bytes.integer, mime_type.text, uploaded_by.text, uploaded_at.timestamp, description.text )\n"} {"conversations": [{"role": "user", "content": "Show me the content of all comments that have received at least one like."}, {"role": "assistant", "content": "SELECT DISTINCT T1.content FROM social_media.comments AS T1 JOIN social_media.likes AS T2 ON T1.comment_id = T2.comment_id;"}, {"role": "user", "content": "Also include the creation time of these comments and the user_id of the commenter?"}, {"role": "assistant", "content": "SELECT DISTINCT T1.comment_id, T1.content, T1.created_at, T1.user_id FROM social_media.comments AS T1 JOIN social_media.likes AS T2 ON T1.comment_id = T2.comment_id;"}, {"role": "user", "content": "Only show comments created before '2024-05-01'."}, {"role": "assistant", "content": "SELECT DISTINCT T1.comment_id, T1.content, T1.created_at, T1.user_id FROM social_media.comments AS T1 JOIN social_media.likes AS T2 ON T1.comment_id = T2.comment_id WHERE T1.created_at < '2024-05-01';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE social_media.comments (\n comment_id character varying(64) NOT NULL, -- unique identifier for the comment\n post_id character varying(64) NOT NULL, -- identifier of the post being commented on (FK to posts.post_id)\n user_id character varying(64) NOT NULL, -- identifier of the user who made the comment (FK to users.user_id)\n parent_comment_id character varying(64), -- identifier of the parent comment if it's a reply (FK to comments.comment_id)\n content text NOT NULL, -- textual content of the comment\n created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of comment creation\n updated_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of last comment edit\n PRIMARY KEY (comment_id)\n)\nCREATE TABLE social_media.likes ( like_id text, user_id text, post_id text, comment_id text, created_at timestamp )\nCREATE TABLE social_media.conversations ( conversation_id text PRIMARY KEY, created_at timestamp, last_message_at timestamp, is_group_chat bool, group_name text )\n"} {"conversations": [{"role": "user", "content": "Retrieve the product_id, product_name, base_premium, and created_at for all active insurance products with a base_premium greater than 1000, ordered by base_premium descending."}, {"role": "assistant", "content": "SELECT\n product_id,\n product_name,\n base_premium,\n created_at\nFROM insurance.insurance_products\nWHERE is_active = true\n AND base_premium > 1000\nORDER BY base_premium DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.insurance_products (\n product_id character varying(64) NOT NULL, -- unique identifier for the insurance product\n product_name character varying(150) NOT NULL, -- name of the insurance product (e.g., 'Comprehensive Auto Insurance')\n product_type character varying(50) NOT NULL, -- category like 'Auto', 'Home', 'Life', 'Health', 'Travel'\n description text, -- detailed description of the product\n base_premium numeric(10, 2) NOT NULL, -- starting premium before adjustments\n coverage_details text, -- details about what is covered (could be JSON or structured text)\n underwriting_rules text, -- rules used for assessing risk and eligibility\n is_active boolean NOT NULL DEFAULT true, -- whether the product is currently offered\n created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP,\n updated_at timestamp,\n PRIMARY KEY (product_id)\n)\n"} {"conversations": [{"role": "user", "content": "Show me all policies that expired in the last 60 days, along with their product IDs and premium amounts."}, {"role": "assistant", "content": "SELECT policy_id, product_id, premium_amount FROM insurance.policies WHERE status = 'expired' AND end_date >= CURRENT_DATE - INTERVAL '60 days' AND end_date <= CURRENT_DATE;"}, {"role": "user", "content": "Now include only policies that had a deductible of $1000 or more."}, {"role": "assistant", "content": "SELECT policy_id, product_id, premium_amount, deductible FROM insurance.policies WHERE status = 'expired' AND end_date >= CURRENT_DATE - INTERVAL '60 days' AND end_date <= CURRENT_DATE AND deductible >= 1000;"}, {"role": "user", "content": "I also want to see the count of such expired policies per product ID."}, {"role": "assistant", "content": "SELECT product_id, COUNT(*) as policy_count FROM insurance.policies WHERE status = 'expired' AND end_date >= CURRENT_DATE - INTERVAL '60 days' AND end_date <= CURRENT_DATE AND deductible >= 1000 GROUP BY product_id ORDER BY policy_count DESC;"}, {"role": "user", "content": "Finally, show me the average premium amount for these expired high-deductible policies grouped by product ID."}, {"role": "assistant", "content": "SELECT product_id, AVG(premium_amount) as avg_premium FROM insurance.policies WHERE status = 'expired' AND end_date >= CURRENT_DATE - INTERVAL '60 days' AND end_date <= CURRENT_DATE AND deductible >= 1000 GROUP BY product_id ORDER BY avg_premium DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.policies ( policy_id text PRIMARY KEY, customer_id text, product_id text, agent_id text, policy_number text, start_date date, end_date date, premium_amount numeric, coverage_limit numeric, deductible numeric, status text, issued_at timestamp, cancellation_date date, cancellation_reason text )\n"} {"conversations": [{"role": "user", "content": "List patient_id, full name, policy_number, plan_type, and insurance_provider for all active primary insurance policies."}, {"role": "assistant", "content": "SELECT pi.patient_id,\n p.first_name,\n p.last_name,\n pi.policy_number,\n ip.plan_type,\n ip.insurance_provider\nFROM healthcare.patient_insurance pi\nJOIN healthcare.patients p\n ON p.patient_id = pi.patient_id\nJOIN healthcare.insurance_plans ip\n ON ip.plan_id = pi.plan_id\nWHERE pi.is_primary = TRUE\n AND pi.effective_date <= CURRENT_DATE\n AND pi.expiration_date >= CURRENT_DATE;"}, {"role": "user", "content": "Now also restrict to policies expiring within the next 30 days."}, {"role": "assistant", "content": "SELECT pi.patient_id,\n p.first_name,\n p.last_name,\n pi.policy_number,\n ip.plan_type,\n ip.insurance_provider\nFROM healthcare.patient_insurance pi\nJOIN healthcare.patients p\n ON p.patient_id = pi.patient_id\nJOIN healthcare.insurance_plans ip\n ON ip.plan_id = pi.plan_id\nWHERE pi.is_primary = TRUE\n AND pi.effective_date <= CURRENT_DATE\n AND pi.expiration_date BETWEEN CURRENT_DATE AND CURRENT_DATE + INTERVAL '30 days';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.patients ( patient_id text, first_name text, last_name text, date_of_birth date, gender text, address text, phone_number text, email text, emergency_contact_name text, emergency_contact_phone text, created_at timestamp, updated_at timestamp )\nCREATE TABLE healthcare.appointments ( appointment_id text, patient_id text, doctor_id text, appointment_time timestamp, duration_minutes integer, reason text, status text, location_id text, notes text, created_at timestamp )\nCREATE TABLE healthcare.medical_records ( record_id text, patient_id text, appointment_id text, doctor_id text, record_date timestamp, chief_complaint text, present_illness_history text, past_medical_history text, physical_examination_notes text, assessment text, treatment_plan text, vitals text, created_at timestamp )\nCREATE TABLE healthcare.diagnoses ( diagnosis_id text, record_id text, patient_id text, doctor_id text, diagnosis_code text, code_type text, description text, diagnosis_date date, status text, is_chronic boolean )\nCREATE TABLE healthcare.medications ( medication_id text, medication_name text, generic_name text, manufacturer text, ndc_code text, description text )\nCREATE TABLE healthcare.prescriptions ( prescription_id text, record_id text, patient_id text, doctor_id text, medication_id text, dosage text, frequency text, route text, start_date date, end_date date, quantity_dispensed numeric, refills_allowed integer, prescription_date timestamp )\nCREATE TABLE healthcare.insurance_plans ( plan_id text, plan_name text, insurance_provider text, plan_type text, contact_phone text, website text )\nCREATE TABLE healthcare.patient_insurance ( patient_insurance_id text, patient_id text, plan_id text, policy_number text, group_number text, subscriber_name text, effective_date date, expiration_date date, is_primary boolean )\n"} {"conversations": [{"role": "user", "content": "Show me the top 5 users with the highest number of wallet addresses."}, {"role": "assistant", "content": "SELECT user_id, COUNT(*) AS wallet_count FROM blockchain.wallets WHERE user_id IS NOT NULL GROUP BY user_id ORDER BY wallet_count DESC LIMIT 5;"}, {"role": "user", "content": "Can you also include the earliest created wallet address for each of these top 5 users?"}, {"role": "assistant", "content": "SELECT w1.user_id, w1.address_id, w1.private_key FROM blockchain.wallets w1 INNER JOIN (SELECT user_id, MIN(wallet_id) AS oldest_wallet_id FROM blockchain.wallets WHERE user_id IS NOT NULL GROUP BY user_id ORDER BY COUNT(*) DESC LIMIT 5) w2 ON w1.user_id = w2.user_id AND w1.wallet_id = w2.oldest_wallet_id;"}, {"role": "user", "content": "This query seems incorrect as it's not showing the actual earliest wallet address. Can you modify it to show the wallet_id with the minimum creation timestamp?"}, {"role": "assistant", "content": "SELECT w1.user_id, w1.address_id, w1.private_key FROM blockchain.wallets w1 INNER JOIN (SELECT user_id FROM blockchain.wallets WHERE user_id IS NOT NULL GROUP BY user_id ORDER BY COUNT(*) DESC LIMIT 5) w2 ON w1.user_id = w2.user_id WHERE w1.wallet_id = (SELECT MIN(wallet_id) FROM blockchain.wallets w3 WHERE w3.user_id = w1.user_id);"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE blockchain.wallets ( wallet_id text, user_id text, address_id text, private_key text )\n"} {"conversations": [{"role": "user", "content": "For each claim handler, count the number of documents uploaded for the claims they handled. Return claim_handler_id and document_count."}, {"role": "assistant", "content": "SELECT c.claim_handler_id,\n COUNT(d.document_id) AS document_count\nFROM insurance.claims AS c\nJOIN insurance.claim_documents AS d\n ON c.claim_id = d.claim_id\nGROUP BY c.claim_handler_id;"}, {"role": "user", "content": "Now restrict to handlers who have uploaded more than 10 documents."}, {"role": "assistant", "content": "SELECT c.claim_handler_id,\n COUNT(d.document_id) AS document_count\nFROM insurance.claims AS c\nJOIN insurance.claim_documents AS d\n ON c.claim_id = d.claim_id\nGROUP BY c.claim_handler_id\nHAVING COUNT(d.document_id) > 10;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.claims ( claim_id.text, policy_id.text, customer_id.text, incident_date.timestamp, reported_date.timestamp, description.text, estimated_loss.numeric, status.text, settlement_amount.numeric, settlement_date.date, claim_handler_id.text, police_report_number.text )\nCREATE TABLE insurance.premium_payments ( payment_id character varying(64) NOT NULL, policy_id character varying(64) NOT NULL, customer_id character varying(64) NOT NULL, payment_date timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, amount_paid numeric(12, 2) NOT NULL, payment_method character varying(50), transaction_reference character varying(128) UNIQUE, due_date date, payment_period_start date, payment_period_end date, status character varying(30) NOT NULL DEFAULT 'Completed', PRIMARY KEY (payment_id) )\nCREATE TABLE insurance.claim_documents ( document_id text PRIMARY KEY, claim_id text, document_type text, file_name text, file_path text, file_size_bytes int, mime_type text, uploaded_by text, uploaded_at timestamp, description text )\n"} {"conversations": [{"role": "user", "content": "List the booking ID, the first name, and the last name of the passenger for all bookings."}, {"role": "assistant", "content": "SELECT T1.booking_id , T2.first_name , T2.last_name FROM transportation.bookings AS T1 JOIN transportation.passengers AS T2 ON T1.passenger_id = T2.passenger_id"}, {"role": "user", "content": "Now, only include bookings where the fare is greater than 100."}, {"role": "assistant", "content": "SELECT T1.booking_id , T2.first_name , T2.last_name FROM transportation.bookings AS T1 JOIN transportation.passengers AS T2 ON T1.passenger_id = T2.passenger_id WHERE T1.fare > 100"}, {"role": "user", "content": "For these bookings with fares over 100, also show the booking status and order the results by fare in descending order."}, {"role": "assistant", "content": "SELECT T1.booking_id , T2.first_name , T2.last_name , T1.status FROM transportation.bookings AS T1 JOIN transportation.passengers AS T2 ON T1.passenger_id = T2.passenger_id WHERE T1.fare > 100 ORDER BY T1.fare DESC"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.vehicles ( vehicle_id.text, license_plate.text, vin.text, make.text, model.text, year.integer, type.text, capacity.integer, fuel_type.text, status.text, depot_id.text, acquisition_date.date )\nCREATE TABLE transportation.drivers ( driver_id.text, employee_id.text, first_name.text, last_name.text, license_number.text, license_expiry_date.date, contact_number.text, email.text, hire_date.date, status.text )\nCREATE TABLE transportation.routes ( route_id.text, route_number.text, description.text, origin_location_id.text, destination_location_id.text, distance_km.numeric, estimated_duration_minutes.integer, type.text )\nCREATE TABLE transportation.trips ( trip_id.text, route_id.text, vehicle_id.text, driver_id.text, scheduled_departure.timestamp, actual_departure.timestamp, scheduled_arrival.timestamp, actual_arrival.timestamp, origin_location_id.text, destination_location_id.text, status.text, passenger_count.integer, cargo_manifest_id.text )\nCREATE TABLE transportation.maintenance_logs ( log_id.text, vehicle_id.text, service_date.date, odometer_reading.integer, service_type.text, description.text, cost.numeric, mechanic_name.text, next_service_due_date.date )\nCREATE TABLE transportation.fuel_logs ( fuel_log_id.text, vehicle_id.text, trip_id.text, log_timestamp.timestamp, fuel_type.text, quantity.numeric, unit.text, cost_per_unit.numeric, total_cost.numeric, odometer_reading.integer, location_id.text )\nCREATE TABLE transportation.passengers ( passenger_id.text, first_name.text, last_name.text, email.text, phone_number.text, date_of_birth.date, loyalty_program_id.text, created_at.timestamp )\nCREATE TABLE transportation.bookings ( booking_id.text, passenger_id.text, trip_id.text, seat_number.text, booking_time.timestamp, status.text, fare.numeric, payment_transaction_id.text, special_requests.text )\n"} {"conversations": [{"role": "user", "content": "Show each wallet address that has received token transfers of more than one type of token, along with the count of token types received."}, {"role": "assistant", "content": "SELECT tt.to_address, COUNT(DISTINCT tt.token_id) AS token_type_count\nFROM web3.token_transfers tt\nGROUP BY tt.to_address\nHAVING COUNT(DISTINCT tt.token_id) > 1;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE web3.contracts ( contract_id text PRIMARY KEY, address text, abi text, bytecode text, deployer_address text, deployed_at timestamp, network_id text, status text )\nCREATE TABLE web3.events ( event_id character varying(64) NOT NULL, contract_id character varying(64) NOT NULL, event_name character varying(128) NOT NULL, data text NOT NULL, emitted_at timestamp NOT NULL, transaction_id character varying(64) NOT NULL, log_index integer NOT NULL, PRIMARY KEY (event_id) )\nCREATE TABLE web3.tokens (\n token_id character varying(64) NOT NULL, -- unique identifier for the token\n contract_address character varying(128) NOT NULL, -- address of the token contract\n token_name character varying(128) NOT NULL, -- name of the token\n token_symbol character varying(32) NOT NULL, -- symbol of the token\n decimals integer NOT NULL, -- number of decimals for the token\n total_supply numeric(38,14) NOT NULL, -- total supply of the token\n PRIMARY KEY (token_id)\n)\nCREATE TABLE web3.token_transfers ( transfer_id character varying(64) NOT NULL, token_id character varying(64) NOT NULL, from_address character varying(128) NOT NULL, to_address character varying(128) NOT NULL, value numeric(38,14) NOT NULL, transaction_id character varying(64) NOT NULL, log_index integer NOT NULL, PRIMARY KEY (transfer_id) )\nCREATE TABLE web3.wallets (\n wallet_id character varying(64) NOT NULL, -- unique identifier for the wallet\n user_id character varying(64) NOT NULL, -- identifier of the user owning the wallet\n address character varying(128) NOT NULL, -- address of the wallet\n private_key text NOT NULL, -- private key of the wallet\n created_at timestamp NOT NULL, -- time when the wallet was created\n PRIMARY KEY (wallet_id)\n)\nCREATE TABLE web3.users (\n user_id character varying(64) NOT NULL, -- unique identifier for the user\n username character varying(128) NOT NULL, -- username of the user\n email character varying(128) NOT NULL, -- email address of the user\n password_hash text NOT NULL, -- hashed password of the user\n created_at timestamp NOT NULL, -- time when the user account was created\n PRIMARY KEY (user_id)\n)\n"} {"conversations": [{"role": "user", "content": "For each agency that is a parent, how many direct child agencies does it have? Show the parent agency name and the count."}, {"role": "assistant", "content": "SELECT parent.agency_name AS parent_agency_name, COUNT(child.agency_id) AS child_agency_count FROM government_services.agencies AS parent INNER JOIN government_services.agencies AS child ON parent.agency_id = child.parent_agency_id GROUP BY parent.agency_id, parent.agency_name;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.agencies ( agency_id character varying(64) NOT NULL, agency_name character varying(255) NOT NULL, jurisdiction_level character varying(50) NOT NULL, primary_contact_email character varying(128), main_phone_number character varying(32), website_url character varying(255), established_date date, parent_agency_id character varying(64), PRIMARY KEY (agency_id) )\n"} {"conversations": [{"role": "user", "content": "For each route, show the route_number, origin and destination location names with their cities, and the average departure delay (in minutes) for trips where actual_departure was later than scheduled_departure."}, {"role": "assistant", "content": "SELECT r.route_number,\n lo.name AS origin_name,\n lo.city AS origin_city,\n ld.name AS destination_name,\n ld.city AS destination_city,\n AVG(EXTRACT(EPOCH FROM (t.actual_departure - t.scheduled_departure)) / 60) AS avg_delay_minutes\nFROM transportation.routes r\nJOIN transportation.trips t\n ON r.route_id = t.route_id\nJOIN transportation.locations lo\n ON r.origin_location_id = lo.location_id\nJOIN transportation.locations ld\n ON r.destination_location_id = ld.location_id\nWHERE t.actual_departure > t.scheduled_departure\nGROUP BY r.route_number, origin_name, origin_city, destination_name, destination_city;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.vehicles (\n vehicle_id character varying(64) NOT NULL, -- unique identifier for the vehicle\n license_plate character varying(32) NOT NULL UNIQUE, -- vehicle license plate\n vin character varying(17) UNIQUE, -- vehicle identification number\n make character varying(64) NOT NULL, -- manufacturer of the vehicle\n model character varying(64) NOT NULL, -- model of the vehicle\n year integer NOT NULL, -- manufacturing year\n type character varying(32) NOT NULL, -- type of vehicle (e.g., Bus, Train, Truck, Car, Van)\n capacity integer, -- passenger or cargo capacity\n fuel_type character varying(32) NOT NULL, -- e.g., Diesel, Gasoline, Electric, Hydrogen\n status character varying(32) NOT NULL, -- e.g., Active, Maintenance, Decommissioned\n depot_id character varying(64), -- identifier of the home depot/base\n acquisition_date date, -- date the vehicle was acquired\n PRIMARY KEY (vehicle_id)\n)\nCREATE TABLE transportation.drivers ( driver_id character varying(64) NOT NULL, employee_id character varying(64) NOT NULL UNIQUE, first_name character varying(128) NOT NULL, last_name character varying(128) NOT NULL, license_number character varying(64) NOT NULL UNIQUE, license_expiry_date date NOT NULL, contact_number character varying(32), email character varying(128) UNIQUE, hire_date date NOT NULL, status character varying(32) NOT NULL, PRIMARY KEY (driver_id) )\nCREATE TABLE transportation.routes ( route_id text, route_number text, description text, origin_location_id text, destination_location_id text, distance_km numeric, estimated_duration_minutes integer, type text )\nCREATE TABLE transportation.trips (\n trip_id character varying(64) NOT NULL, -- unique identifier for a specific trip instance\n route_id character varying(64), -- identifier of the route being followed (can be null for ad-hoc trips)\n vehicle_id character varying(64) NOT NULL, -- identifier of the vehicle used\n driver_id character varying(64) NOT NULL, -- identifier of the driver operating\n scheduled_departure timestamp with time zone NOT NULL, -- planned departure time\n actual_departure timestamp with time zone, -- actual departure time\n scheduled_arrival timestamp with time zone NOT NULL, -- planned arrival time\n actual_arrival timestamp with time zone, -- actual arrival time\n origin_location_id character varying(64) NOT NULL, -- actual starting location (could differ from route origin)\n destination_location_id character varying(64) NOT NULL, -- actual ending location (could differ from route destination)\n status character varying(32) NOT NULL, -- e.g., Scheduled, In Progress, Completed, Delayed, Cancelled\n passenger_count integer, -- number of passengers (if applicable)\n cargo_manifest_id character varying(64), -- link to cargo details (if applicable)\n PRIMARY KEY (trip_id)\n)\nCREATE TABLE transportation.locations ( location_id.text, name.text, type.text, address_line1.text, city.text, state_province.text, postal_code.text, country.text, latitude.numeric, longitude.numeric, timezone.text )\nCREATE TABLE transportation.passengers ( passenger_id text PRIMARY KEY, first_name text, last_name text, email text, phone_number text, date_of_birth date, loyalty_program_id text, created_at timestamp )\nCREATE TABLE transportation.bookings (\n booking_id character varying(64) NOT NULL, -- unique identifier for the booking\n passenger_id character varying(64) NOT NULL, -- identifier of the passenger making the booking\n trip_id character varying(64) NOT NULL, -- identifier of the trip being booked\n seat_number character varying(16), -- assigned seat number (if applicable)\n booking_time timestamp with time zone NOT NULL, -- time when the booking was made\n status character varying(32) NOT NULL, -- e.g., Confirmed, Cancelled, Pending Payment\n fare numeric(10, 2) NOT NULL, -- price paid for the booking\n payment_transaction_id character varying(128), -- reference to the payment transaction\n special_requests text, -- any special requests from the passenger\n PRIMARY KEY (booking_id)\n)\n"} {"conversations": [{"role": "user", "content": "List all auto loans (loan_id, principal_amount, interest_rate) where the current principal balance is less than 40% of the original principal amount, along with the account_id and the difference between principal_amount and current_principal_balance."}, {"role": "assistant", "content": "SELECT loan_id, principal_amount, interest_rate, account_id, (principal_amount - current_principal_balance) AS amount_paid FROM financial_services.loans WHERE loan_type = 'Auto' AND current_principal_balance < (0.4 * principal_amount);"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE financial_services.loans ( loan_id character varying(64) NOT NULL, account_id character varying(64) NOT NULL UNIQUE, loan_type character varying(50) NOT NULL, principal_amount numeric(19, 4) NOT NULL, current_principal_balance numeric(19, 4) NOT NULL, interest_rate numeric(6, 4) NOT NULL, term_months integer NOT NULL, origination_date date NOT NULL, maturity_date date NOT NULL, monthly_payment numeric(12, 4), collateral_description text, status character varying(32) NOT NULL, PRIMARY KEY (loan_id), FOREIGN KEY (account_id) REFERENCES financial_services.accounts(account_id) )\n"} {"conversations": [{"role": "user", "content": "Show me all transactions where the description contains the word 'fee'."}, {"role": "assistant", "content": "SELECT * FROM financial_services.transactions WHERE description ILIKE '%fee%';"}, {"role": "user", "content": "Limit the results to transactions that occurred in the previous month."}, {"role": "assistant", "content": "SELECT * FROM financial_services.transactions WHERE description ILIKE '%fee%' AND transaction_date >= date_trunc('month', CURRENT_DATE - INTERVAL '1 month') AND transaction_date < date_trunc('month', CURRENT_DATE);"}, {"role": "user", "content": "Only include transactions with an amount greater than 20."}, {"role": "assistant", "content": "SELECT * FROM financial_services.transactions WHERE description ILIKE '%fee%' AND transaction_date >= date_trunc('month', CURRENT_DATE - INTERVAL '1 month') AND transaction_date < date_trunc('month', CURRENT_DATE) AND amount > 20;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE financial_services.transactions ( transaction_id text, account_id text, related_account_id text, transaction_type text, amount numeric, currency text, transaction_date timestamp, effective_date date, description text, status text, reference_number text )\n"} {"conversations": [{"role": "user", "content": "能否帮我统计特定车站(station_id 为 'station_xyz')的所有工作人员数量？"}, {"role": "assistant", "content": "MATCH (s:Station {station_id: 'station_xyz'})<-[:BASED_AT]-(staff:Staff)\nRETURN COUNT(staff) AS total_staff"}], "system": "You are an expert in writing database language. You can write a corresponding database language query to answer the user's question based on the table structure described by the table creation statement. \n##Table Structure\n// Node Label: :Station\n// Properties:\n// station_id: String (Constraint: UNIQUE)\n// station_name: String\n// city: String (Index recommended)\n// state_province: String\n// country_code: String\n// address: String\n// timezone: String\n// number_of_platforms: Integer\n// created_at: DateTime\n// last_updated_at: DateTime\n// Example Cypher CREATE:\n// CREATE (:Station {station_id: 'station_xyz', station_name: 'Grand Central Terminal', city: 'New York', ...})\n// Node Label: :Platform\n// Properties:\n// platform_id: String (Constraint: UNIQUE)\n// platform_number: String\n// track_number: String\n// status: String\n// length_meters: Float\n// accessible: Boolean\n// Relationship: (:Platform)-[:LOCATED_AT]->(:Station)\n// Example Cypher CREATE:\n// MATCH (s:Station {station_id: 'station_xyz'})\n// CREATE (p:Platform {platform_id: 'plat_123', ...})-[:LOCATED_AT]->(s)\n// Node Label: :Train\n// Properties:\n// train_id: String (Constraint: UNIQUE)\n// train_number: String (Constraint: UNIQUE)\n// model: String\n// manufacturer: String\n// year_manufactured: Integer\n// capacity: Integer\n// status: String\n// last_maintenance_date: Date\n// next_maintenance_date: Date\n// Example Cypher CREATE:\n// CREATE (:Train {train_id: 'train_789', train_number: 'Acela 2151', ...})\n// Node Label: :TrainCar\n// Properties:\n// car_id: String (Constraint: UNIQUE)\n// car_number: String\n// car_type: String\n// class: String\n// capacity: Integer\n// features: String (Or List if driver supports)\n// Relationship: (:TrainCar)-[:PART_OF_TRAIN]->(:Train)\n// Example Cypher CREATE:\n// MATCH (t:Train {train_id: 'train_789'})\n// CREATE (c:TrainCar {car_id: 'car_abc', ...})-[:PART_OF_TRAIN]->(t)\n// Node Label: :Route\n// Properties:\n// route_id: String (Constraint: UNIQUE)\n// route_name: String\n// description: String\n// is_active: Boolean\n// Relationships:\n// (:Route)-[:STARTS_AT]->(:Station)\n// (:Route)-[:ENDS_AT]->(:Station)\n// Example Cypher CREATE:\n// MATCH (origin:Station {station_id: 'station_bos'}), (dest:Station {station_id: 'station_was'})\n// CREATE (r:Route {route_id: 'route_ne_corr', ...})-[:STARTS_AT]->(origin), (r)-[:ENDS_AT]->(dest)\n// Relationship: (:Route)-[rel:HAS_STOP]->(:Station)\n// Relationship Properties on :HAS_STOP:\n// sequence_order: Integer\n// distance_from_previous_km: Float\n// typical_stop_duration_minutes: Integer\n// Example Cypher CREATE:\n// MATCH (r:Route {route_id: 'route_ne_corr'}), (s:Station {station_id: 'station_pvd'})\n// CREATE (r)-[:HAS_STOP {sequence_order: 2, distance_from_previous_km: 70.5, ...}]->(s)\n// Node Label: :ScheduledTrip (or just :Trip)\n// Properties:\n// schedule_id: String (Constraint: UNIQUE)\n// departure_datetime: DateTime\n// arrival_datetime: DateTime\n// status: String\n// notes: String\n// Relationships:\n// (:ScheduledTrip)-[:USES_TRAIN]->(:Train)\n// (:ScheduledTrip)-[:FOLLOWS_ROUTE]->(:Route)\n// Example Cypher CREATE:\n// MATCH (t:Train {train_id: 'train_789'}), (r:Route {route_id: 'route_ne_corr'})\n// CREATE (sched:ScheduledTrip {schedule_id: 'sched_1122', ...})-[:USES_TRAIN]->(t), (sched)-[:FOLLOWS_ROUTE]->(r)\n// Relationship: (:ScheduledTrip)-[rel:SCHEDULED_STOP]->(:Station)\n// Relationship Properties on :SCHEDULED_STOP:\n// sequence_order: Integer\n// platform_id: String (references Platform node if modeled, or just store ID)\n// scheduled_arrival_time: DateTime\n// scheduled_departure_time: DateTime\n// actual_arrival_time: DateTime\n// actual_departure_time: DateTime\n// status: String\n// Example Cypher CREATE:\n// MATCH (sched:ScheduledTrip {schedule_id: 'sched_1122'}), (s:Station {station_id: 'station_pvd'})\n// CREATE (sched)-[:SCHEDULED_STOP {sequence_order: 2, platform_id: 'plat_pvd_1', ...}]->(s)\n// Node Label: :Passenger\n// Properties:\n// passenger_id: String (Constraint: UNIQUE)\n// first_name: String\n// last_name: String\n// email: String (Constraint: UNIQUE, if not null)\n// phone_number: String (Constraint: UNIQUE, if not null)\n// date_of_birth: Date\n// loyalty_program_id: String\n// created_at: DateTime\n// Example Cypher CREATE:\n// CREATE (:Passenger {passenger_id: 'pass_pqr', first_name: 'Alice', ...})\n// Node Label: :Booking\n// Properties:\n// booking_id: String (Constraint: UNIQUE)\n// booking_datetime: DateTime\n// status: String\n// total_price: Float\n// currency_code: String\n// special_requests: String\n// Relationships:\n// (:Passenger)-[:MADE_BOOKING]->(:Booking)\n// (:Booking)-[:FOR_TRIP]->(:ScheduledTrip)\n// Example Cypher CREATE:\n// MATCH (p:Passenger {passenger_id: 'pass_pqr'}), (sched:ScheduledTrip {schedule_id: 'sched_1122'})\n// CREATE (p)-[:MADE_BOOKING]->(b:Booking {booking_id: 'book_zyx', ...})-[:FOR_TRIP]->(sched)\n// Node Label: :Ticket\n// Properties:\n// ticket_id: String (Constraint: UNIQUE)\n// seat_number: String\n// ticket_type: String\n// price: Float\n// is_checked_in: Boolean\n// qr_code_data: String\n// Relationships:\n// (:Ticket)-[:PART_OF_BOOKING]->(:Booking)\n// (:Ticket)-[:ASSIGNED_TO_CAR]->(:TrainCar)\n// Example Cypher CREATE:\n// MATCH (b:Booking {booking_id: 'book_zyx'}), (c:TrainCar {car_id: 'car_abc'})\n// CREATE (t:Ticket {ticket_id: 'tkt_1a2b', ...})-[:PART_OF_BOOKING]->(b), (t)-[:ASSIGNED_TO_CAR]->(c)\n// Node Label: :Staff\n// Properties:\n// staff_id: String (Constraint: UNIQUE)\n// first_name: String\n// last_name: String\n// role: String\n// employee_number: String (Constraint: UNIQUE)\n// hire_date: Date\n// contact_email: String (Constraint: UNIQUE, if not null)\n// contact_phone: String\n// is_active: Boolean\n// Relationship (Optional):\n// (:Staff)-[:BASED_AT]->(:Station)\n// Example Cypher CREATE:\n// CREATE (:Staff {staff_id: 'staff_mno', first_name: 'Bob', ...})\n// OPTIONAL MATCH (s:Station {station_id: 'station_xyz'}) // If primary_station_id exists\n// WITH s, staff_mno // Need to get the created staff node reference\n// WHERE s IS NOT NULL\n// CREATE (staff_mno)-[:BASED_AT]->(s)\n"} {"conversations": [{"role": "user", "content": "For each state, count the number of customers and display state as state and the count as customer_count, ordered by customer_count descending."}, {"role": "assistant", "content": "SELECT state,\n COUNT(*) AS customer_count\nFROM insurance.customers\nGROUP BY state\nORDER BY customer_count DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.customers ( customer_id text PRIMARY KEY, first_name text, last_name text, date_of_birth date, ssn_hash text, address_line1 text, address_line2 text, city text, state text, zip_code text, country text, phone_number text, email text, created_at timestamp, updated_at timestamp, status text )\n"} {"conversations": [{"role": "user", "content": "Show me the document name and the date worked for time entries logged by the same lawyer."}, {"role": "assistant", "content": "SELECT T1.document_name , T2.date_worked FROM documents AS T1 JOIN time_entries AS T2 ON T1.uploaded_by_lawyer_id = T2.lawyer_id"}, {"role": "user", "content": "Only show pairs where the time entry is billable."}, {"role": "assistant", "content": "SELECT T1.document_name , T2.date_worked FROM documents AS T1 JOIN time_entries AS T2 ON T1.uploaded_by_lawyer_id = T2.lawyer_id WHERE T2.is_billable = true"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.documents ( document_id text, case_id text, document_name text, document_type text, storage_path text, uploaded_by_lawyer_id text, upload_timestamp timestamp, version integer, description text )\nCREATE TABLE legal_services.time_entries (\n entry_id character varying(64) NOT NULL, -- unique identifier for the time entry\n case_id character varying(64) NOT NULL, -- FK to cases table\n lawyer_id character varying(64) NOT NULL, -- FK to lawyers table (who performed the work)\n date_worked date NOT NULL, -- date the work was performed\n hours_spent numeric(5, 2) NOT NULL CHECK (hours_spent > 0), -- duration of work in hours (e.g., 1.5 for 1h 30m)\n billing_rate numeric(10, 2) NOT NULL, -- hourly rate applied for this entry\n description text NOT NULL, -- detailed description of the work performed\n is_billable boolean DEFAULT true, -- whether this time entry is billable to the client\n is_billed boolean DEFAULT false, -- whether this entry has been included in an invoice\n invoice_id character varying(64), -- FK to invoices table (once billed)\n created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- when the entry was recorded\n PRIMARY KEY (entry_id)\n)\n"} {"conversations": [{"role": "user", "content": "List the citizen IDs for individuals who have both uploaded documents and made payments."}, {"role": "assistant", "content": "SELECT DISTINCT T1.citizen_id FROM documents AS T1 JOIN payments AS T2 ON T1.citizen_id = T2.citizen_id"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.documents ( document_id character varying(64) NOT NULL, application_id character varying(64), citizen_id character varying(64) NOT NULL, document_type character varying(100) NOT NULL, file_reference text NOT NULL, upload_timestamp timestamp NOT NULL, expiry_date date, verification_status character varying(30) DEFAULT 'Pending', verified_by_employee_id character varying(64), verification_timestamp timestamp, PRIMARY KEY (document_id) )\nCREATE TABLE government_services.payments ( payment_id character varying(64) NOT NULL, application_id character varying(64), citizen_id character varying(64) NOT NULL, service_id character varying(64), amount numeric(12, 2) NOT NULL, currency character varying(3) NOT NULL DEFAULT 'USD', payment_method character varying(50), payment_provider_reference character varying(128), payment_timestamp timestamp NOT NULL, status character varying(30) NOT NULL, notes text, PRIMARY KEY (payment_id) )\n"} {"conversations": [{"role": "user", "content": "List all tokens with a price below $1 and a 24-hour trading volume over $10 million."}, {"role": "assistant", "content": "SELECT token_name, token_symbol, price, total_volume FROM token_basic_info WHERE price < 1 AND CAST(total_volume AS double precision) > 10000000;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE token_basic_info ( coin_id character varying(100) NOT NULL, token_name character varying(100) NOT NULL, token_symbol character varying(100) NOT NULL, token_address character varying(100) NOT NULL, chain text, price double precision, price_change_percentage_1h double precision, price_change_percentage_24h double precision, price_change_percentage_7d double precision, highest_price_24h double precision, lowest_price_24h double precision, market_cap double precision, market_cap_rank bigint, market_cap_change_percentage_24h text, total_volume text, narrative text, trend_rank bigint )\n"} {"conversations": [{"role": "user", "content": "Show all rooms that are on floor 3."}, {"role": "assistant", "content": "SELECT room_id, property_id, room_number FROM hospitality_technology.rooms WHERE floor = 3;"}, {"role": "user", "content": "For these rooms, include the property name and room number."}, {"role": "assistant", "content": "SELECT r.room_number, p.property_name FROM hospitality_technology.rooms AS r JOIN hospitality_technology.properties AS p ON r.property_id = p.property_id WHERE r.floor = 3;"}, {"role": "user", "content": "Also, include the type name and current status for each room."}, {"role": "assistant", "content": "SELECT r.room_number, p.property_name, rt.type_name, r.status FROM hospitality_technology.rooms AS r JOIN hospitality_technology.properties AS p ON r.property_id = p.property_id JOIN hospitality_technology.room_types AS rt ON r.room_type_id = rt.room_type_id AND r.property_id = rt.property_id WHERE r.floor = 3;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE hospitality_technology.properties ( property_id text, property_name text, address_line1 text, address_line2 text, city text, state_province text, postal_code text, country_code text, phone_number text, email_address text, property_type text, star_rating numeric, timezone text, manager_staff_id text, created_at timestamp, updated_at timestamp )\nCREATE TABLE hospitality_technology.rooms ( room_id text, property_id text, room_number text, room_type_id text, floor integer, status text, is_smoking boolean, features text, current_condition text, last_cleaned_at timestamp )\nCREATE TABLE hospitality_technology.room_types ( room_type_id text, property_id text, type_name text, description text, base_rate numeric, max_occupancy integer, bed_type text, area_sqft numeric, amenities text )\n"} {"conversations": [{"role": "user", "content": "Show smart money addresses with an ROI greater than 3 and a realized ratio greater than 0.7. Display the address, chain, ROI, realized ratio, and most profitable token."}, {"role": "assistant", "content": "SELECT address, chain, roi, realized_ratio, most_profit_token FROM smart_money_profit WHERE roi > 3 AND realized_ratio > 0.7;"}, {"role": "user", "content": "For these tokens (`most_profit_token` from the previous result), what is the total USD value held by CEXes across all chains? Show the token symbol and the total CEX USD value."}, {"role": "assistant", "content": "WITH HighlyPerformingTokens AS (SELECT DISTINCT most_profit_token FROM smart_money_profit WHERE roi > 3 AND realized_ratio > 0.7 AND most_profit_token IS NOT NULL) SELECT c.token_symbol, SUM(c.usd_value) AS total_cex_usd_value FROM cex_token_balance c JOIN HighlyPerformingTokens h ON c.token_symbol = h.most_profit_token WHERE c.usd_value IS NOT NULL GROUP BY c.token_symbol ORDER BY total_cex_usd_value DESC;"}, {"role": "user", "content": "Filter the previous results to only include tokens where the `average_smart_money_roi` is greater than 10 (1000%) and the `average_smart_money_realized_ratio` is greater than 0.8."}, {"role": "assistant", "content": "WITH CexHeldTokens AS (SELECT DISTINCT token_symbol FROM cex_token_balance WHERE token_symbol IS NOT NULL AND token_symbol != ''), TokenPerformance AS (SELECT s.most_profit_token AS token_symbol, AVG(s.roi) AS average_smart_money_roi, AVG(s.realized_ratio) AS average_smart_money_realized_ratio FROM smart_money_profit s JOIN CexHeldTokens c ON s.most_profit_token = c.token_symbol WHERE s.roi IS NOT NULL AND s.realized_ratio IS NOT NULL GROUP BY s.most_profit_token) SELECT token_symbol, average_smart_money_roi, average_smart_money_realized_ratio FROM TokenPerformance WHERE average_smart_money_roi > 10 AND average_smart_money_realized_ratio > 0.8 ORDER BY average_smart_money_roi DESC;"}, {"role": "user", "content": "For these filtered tokens, add the total USD value held by CEXes (`usd_value` from `cex_token_balance`) to the results. Show token symbol, total CEX USD value, average ROI, and average realized ratio."}, {"role": "assistant", "content": "WITH CexHeldTokens AS (SELECT DISTINCT token_symbol FROM cex_token_balance WHERE token_symbol IS NOT NULL AND token_symbol != ''), TokenPerformance AS (SELECT s.most_profit_token AS token_symbol, AVG(s.roi) AS average_smart_money_roi, AVG(s.realized_ratio) AS average_smart_money_realized_ratio FROM smart_money_profit s JOIN CexHeldTokens c ON s.most_profit_token = c.token_symbol WHERE s.roi IS NOT NULL AND s.realized_ratio IS NOT NULL GROUP BY s.most_profit_token), FilteredPerformance AS (SELECT token_symbol, average_smart_money_roi, average_smart_money_realized_ratio FROM TokenPerformance WHERE average_smart_money_roi > 10 AND average_smart_money_realized_ratio > 0.8) SELECT fp.token_symbol, SUM(c.usd_value) AS total_cex_usd_value, fp.average_smart_money_roi, fp.average_smart_money_realized_ratio FROM FilteredPerformance fp JOIN cex_token_balance c ON fp.token_symbol = c.token_symbol WHERE c.usd_value IS NOT NULL GROUP BY fp.token_symbol, fp.average_smart_money_roi, fp.average_smart_money_realized_ratio ORDER BY fp.average_smart_money_roi DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\n \"CREATE TABLE cex_token_balance (\",\n \"snapshot_time character varying(32) NOT NULL, -- the snapshot time of record, converted from original timestamp\",\n \"chain character varying(128) NOT NULL, -- the chain that the token resides\",\n \"address character varying(128) NOT NULL, -- the address that holds the assets, owned by a CEX\",\n \"exchange character varying(512) NOT NULL, -- a centralized exchange name\",\n \"token_address character varying(128) NOT NULL, -- token contract address\",\n \"token_symbol character varying(512), --token symbol\",\n \"balance numeric(38,10), -- token balance\",\n \"usd_value numeric(38,14), -- value of the token held in USD\",\n \"price double precision, --price of the token in USD\",\n \",PRIMARY KEY (snapshot_time, exchange, address, chain, token_address));\"\n\nCREATE TABLE smart_money_profit ( address character varying(100) NOT NULL, -- the user's address rank INT, -- the rank of the address in trade performance, value 1 expresses the best address. profit numeric(38,6), -- the profit user made in a month roi numeric(38,2), -- the roi of the user in a month realized_ratio numeric(38,2), -- the percentage of the user's realized profit most_profit_token character varying(100), -- the token symbol of the user's most profitable trade last_trade_time character varying(100), -- the last trade time of the user chain character varying(100), -- the chain that the address resides PRIMARY KEY (address, chain) )\n"} {"conversations": [{"role": "user", "content": "List all claim IDs that have both an 'Accident Report' and a 'Damage Assessment' document, and show the earliest upload timestamp for each type."}, {"role": "assistant", "content": "SELECT a.claim_id,\n MIN(a.uploaded_at) AS accident_report_date,\n MIN(d.uploaded_at) AS damage_assessment_date\nFROM insurance.claim_documents AS a\nJOIN insurance.claim_documents AS d\n ON a.claim_id = d.claim_id\nWHERE a.document_type = 'Accident Report'\n AND d.document_type = 'Damage Assessment'\nGROUP BY a.claim_id;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.claim_documents ( document_id.text, claim_id.text, document_type.text, file_name.text, file_path.text, file_size_bytes.integer, mime_type.text, uploaded_by.text, uploaded_at.timestamp, description.text )\n"} {"conversations": [{"role": "user", "content": "List all pairs of tokens (show token_id for both) that share the same contract address, excluding pairs where the token_id is the same."}, {"role": "assistant", "content": "SELECT t1.token_id AS token_id1, t2.token_id AS token_id2, t1.contract_address FROM web3.tokens AS t1 JOIN web3.tokens AS t2 ON t1.contract_address = t2.contract_address WHERE t1.token_id < t2.token_id;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE web3.tokens ( token_id character varying(64) NOT NULL, contract_address character varying(128) NOT NULL, token_name character varying(128) NOT NULL, token_symbol character varying(32) NOT NULL, decimals integer NOT NULL, total_supply numeric(38,14) NOT NULL, PRIMARY KEY (token_id) )\n"} {"conversations": [{"role": "user", "content": "List all patients who do not have an email address on file, showing their patient_id, first_name, last_name, and phone_number."}, {"role": "assistant", "content": "SELECT patient_id,\n first_name,\n last_name,\n phone_number\nFROM healthcare.patients\nWHERE email IS NULL;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.patients ( patient_id text, first_name text, last_name text, date_of_birth date, gender text, address text, phone_number text, email text, emergency_contact_name text, emergency_contact_phone text, created_at timestamp, updated_at timestamp )\n"} {"conversations": [{"role": "user", "content": "How many active insurance policies does each patient have? Return patient_id and active_policy_count."}, {"role": "assistant", "content": "SELECT patient_id,\n COUNT(*) AS active_policy_count\nFROM healthcare.patient_insurance\nWHERE expiration_date IS NULL\n OR expiration_date >= CURRENT_DATE\nGROUP BY patient_id;"}, {"role": "user", "content": "Actually, only include patients who have more than one active insurance policy."}, {"role": "assistant", "content": "SELECT patient_id,\n COUNT(*) AS active_policy_count\nFROM healthcare.patient_insurance\nWHERE expiration_date IS NULL\n OR expiration_date >= CURRENT_DATE\nGROUP BY patient_id\nHAVING COUNT(*) > 1;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.patients (\n patient_id character varying(64) NOT NULL, -- unique identifier for the patient\n first_name character varying(100) NOT NULL, -- patient's first name\n last_name character varying(100) NOT NULL, -- patient's last name\n date_of_birth date NOT NULL, -- patient's date of birth\n gender character varying(10), -- patient's gender (e.g., Male, Female, Other)\n address text, -- patient's home address\n phone_number character varying(20), -- patient's phone number\n email character varying(128) UNIQUE, -- patient's email address\n emergency_contact_name character varying(200), -- name of emergency contact\n emergency_contact_phone character varying(20), -- phone number of emergency contact\n created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, -- record creation time\n updated_at timestamp with time zone NOT NULL DEFAULT current_timestamp, -- record last update time\n PRIMARY KEY (patient_id)\n)\nCREATE TABLE healthcare.doctors (\n doctor_id character varying(64) NOT NULL, -- unique identifier for the doctor\n first_name character varying(100) NOT NULL, -- doctor's first name\n last_name character varying(100) NOT NULL, -- doctor's last name\n specialty character varying(100) NOT NULL, -- doctor's medical specialty\n license_number character varying(50) UNIQUE NOT NULL, -- doctor's medical license number\n phone_number character varying(20), -- doctor's contact phone\n email character varying(128) UNIQUE, -- doctor's contact email\n hospital_affiliation_id character varying(64), -- FK to hospitals table (optional)\n created_at timestamp with time zone NOT NULL DEFAULT current_timestamp,\n updated_at timestamp with time zone NOT NULL DEFAULT current_timestamp,\n PRIMARY KEY (doctor_id)\n)\nCREATE TABLE healthcare.appointments (\n appointment_id character varying(64) NOT NULL, -- unique identifier for the appointment\n patient_id character varying(64) NOT NULL, -- FK to patients table\n doctor_id character varying(64) NOT NULL, -- FK to doctors table\n appointment_time timestamp with time zone NOT NULL, -- date and time of the appointment\n duration_minutes integer NOT NULL, -- expected duration in minutes\n reason text, -- reason for the visit\n status character varying(32) NOT NULL, -- e.g., Scheduled, Completed, Cancelled, No-show\n location_id character varying(64), -- FK to a potential locations/clinics table\n notes text, -- notes related to scheduling\n created_at timestamp with time zone NOT NULL DEFAULT current_timestamp,\n PRIMARY KEY (appointment_id)\n)\nCREATE TABLE healthcare.medical_records (\n record_id character varying(64) NOT NULL, -- unique identifier for the medical record entry\n patient_id character varying(64) NOT NULL, -- FK to patients table\n appointment_id character varying(64) UNIQUE, -- FK to appointments table (can be null if record not tied to specific appt)\n doctor_id character varying(64) NOT NULL, -- FK to doctors table (doctor creating the record)\n record_date timestamp with time zone NOT NULL, -- date the record/observation was made\n chief_complaint text, -- patient's primary reason for visit\n present_illness_history text, -- detailed history of the current issue\n past_medical_history text, -- relevant past conditions/surgeries\n physical_examination_notes text, -- findings from the physical exam\n assessment text, -- doctor's assessment/diagnosis summary\n treatment_plan text, -- planned course of action\n vitals jsonb, -- store vitals like BP, HR, Temp as structured JSON\n created_at timestamp with time zone NOT NULL DEFAULT current_timestamp,\n PRIMARY KEY (record_id)\n)\nCREATE TABLE healthcare.medications (\n medication_id character varying(64) NOT NULL, -- unique identifier for the medication type\n medication_name character varying(255) NOT NULL, -- common or brand name\n generic_name character varying(255), -- generic chemical name\n manufacturer character varying(100), -- drug manufacturer\n ndc_code character varying(20) UNIQUE, -- National Drug Code (optional but useful)\n description text, -- description of the medication\n PRIMARY KEY (medication_id)\n)\nCREATE TABLE healthcare.insurance_plans (\n plan_id character varying(64) NOT NULL, -- unique identifier for the insurance plan\n plan_name character varying(200) NOT NULL, -- name of the insurance plan\n insurance_provider character varying(100) NOT NULL, -- name of the insurance company\n plan_type character varying(50), -- e.g., PPO, HMO, EPO\n contact_phone character varying(20), -- provider contact number\n website character varying(255), -- provider website\n PRIMARY KEY (plan_id)\n)\nCREATE TABLE healthcare.patient_insurance (\n patient_insurance_id character varying(64) NOT NULL, -- unique identifier for this patient-plan link\n patient_id character varying(64) NOT NULL, -- FK to patients table\n plan_id character varying(64) NOT NULL, -- FK to insurance_plans table\n policy_number character varying(100) NOT NULL, -- patient's policy number\n group_number character varying(100), -- group number, if applicable\n subscriber_name character varying(200), -- name of the primary policy holder\n effective_date date NOT NULL, -- date the coverage begins\n expiration_date date, -- date the coverage ends (if known)\n is_primary boolean NOT NULL DEFAULT true, -- indicates if this is the primary insurance\n PRIMARY KEY (patient_insurance_id),\n UNIQUE (patient_id, plan_id, policy_number) -- ensure a patient doesn't have the same policy twice\n)\n"} {"conversations": [{"role": "user", "content": "Can you list each server along with its game title and how many players it can still accommodate (max_players - current_players)?"}, {"role": "assistant", "content": "SELECT s.server_id,\n s.server_name,\n g.title AS game_title,\n (s.max_players - s.current_players) AS available_slots\nFROM gaming_technology.servers s\nJOIN gaming_technology.games g ON s.game_id = g.game_id;"}, {"role": "user", "content": "Only include servers that are currently 'online' or 'idle'."}, {"role": "assistant", "content": "SELECT s.server_id,\n s.server_name,\n g.title AS game_title,\n (s.max_players - s.current_players) AS available_slots\nFROM gaming_technology.servers s\nJOIN gaming_technology.games g ON s.game_id = g.game_id\nWHERE s.status IN ('online', 'idle');"}, {"role": "user", "content": "Now show only those with available_slots greater than 10, sorted by available_slots descending."}, {"role": "assistant", "content": "SELECT s.server_id,\n s.server_name,\n g.title AS game_title,\n (s.max_players - s.current_players) AS available_slots\nFROM gaming_technology.servers s\nJOIN gaming_technology.games g ON s.game_id = g.game_id\nWHERE s.status IN ('online', 'idle')\n AND (s.max_players - s.current_players) > 10\nORDER BY available_slots DESC;"}, {"role": "user", "content": "Finally, include the game's release_date and only for games released after 2022-01-01."}, {"role": "assistant", "content": "SELECT s.server_id,\n s.server_name,\n g.title AS game_title,\n g.release_date,\n (s.max_players - s.current_players) AS available_slots\nFROM gaming_technology.servers s\nJOIN gaming_technology.games g ON s.game_id = g.game_id\nWHERE s.status IN ('online', 'idle')\n AND (s.max_players - s.current_players) > 10\n AND g.release_date > '2022-01-01'\nORDER BY available_slots DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE gaming_technology.games ( game_id uuid NOT NULL DEFAULT gen_random_uuid(), title character varying(200) NOT NULL, developer_id uuid NOT NULL, publisher_id uuid, genre character varying(100), release_date date, description text, platform character varying(50) NOT NULL, engine character varying(100), website character varying(255), PRIMARY KEY (game_id) )\nCREATE TABLE gaming_technology.servers ( server_id.uuid, game_id.uuid, server_name.text, region.text, ip_address.text, port.integer, current_players.integer, max_players.integer, status.text, last_heartbeat.timestamptz )\nCREATE TABLE gaming_technology.player_achievements ( player_achievement_id uuid NOT NULL DEFAULT gen_random_uuid(), player_id uuid NOT NULL, achievement_id uuid NOT NULL, unlocked_at timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP, PRIMARY KEY (player_achievement_id), UNIQUE (player_id, achievement_id) )\nCREATE TABLE gaming_technology.player_inventory ( inventory_id uuid NOT NULL DEFAULT gen_random_uuid(), player_id uuid NOT NULL, item_id uuid NOT NULL, quantity integer NOT NULL DEFAULT 1, acquired_at timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP, instance_data jsonb, PRIMARY KEY (inventory_id) )\n"} {"conversations": [{"role": "user", "content": "List document names and versions for documents that share the same case_id, showing each pair of versions."}, {"role": "assistant", "content": "SELECT d1.case_id, d1.document_name AS doc_name_v1, d1.version AS version1, d2.document_name AS doc_name_v2, d2.version AS version2 FROM legal_services.documents d1 JOIN legal_services.documents d2 ON d1.case_id = d2.case_id AND d1.version < d2.version;"}, {"role": "user", "content": "Actually, I only want to compare the highest version against the second highest version per case."}, {"role": "assistant", "content": "SELECT d_prev.case_id, d_prev.document_name AS prev_doc, d_prev.version AS prev_version, d_latest.document_name AS latest_doc, d_latest.version AS latest_version FROM legal_services.documents d_latest JOIN legal_services.documents d_prev ON d_latest.case_id = d_prev.case_id AND d_prev.version = d_latest.version - 1 WHERE d_latest.version = (SELECT MAX(version) FROM legal_services.documents d WHERE d.case_id = d_latest.case_id);"}, {"role": "user", "content": "Also include the upload timestamps and restrict to cases with at least three versions."}, {"role": "assistant", "content": "SELECT d_latest.case_id, d_prev.document_name AS prev_doc, d_prev.upload_timestamp AS prev_upload, d_latest.document_name AS latest_doc, d_latest.upload_timestamp AS latest_upload FROM legal_services.documents d_latest JOIN legal_services.documents d_prev ON d_latest.case_id = d_prev.case_id AND d_prev.version = d_latest.version - 1 WHERE d_latest.version = (SELECT MAX(version) FROM legal_services.documents d WHERE d.case_id = d_latest.case_id) AND (SELECT COUNT(*) FROM legal_services.documents d2 WHERE d2.case_id = d_latest.case_id) >= 3;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.documents (\n document_id character varying(64) NOT NULL, -- unique identifier for the document\n case_id character varying(64) NOT NULL, -- FK to cases table\n document_name character varying(255) NOT NULL, -- name of the document file\n document_type character varying(100), -- e.g., Pleading, Contract, Evidence, Correspondence\n storage_path text NOT NULL, -- path or reference to the document storage location\n uploaded_by_lawyer_id character varying(64), -- FK to lawyers table (who uploaded it)\n upload_timestamp timestamp NOT NULL, -- time the document was uploaded\n version integer DEFAULT 1, -- document version number\n description text, -- brief description or notes about the document\n PRIMARY KEY (document_id)\n)\n"} {"conversations": [{"role": "user", "content": "List all claim documents that are police reports and were uploaded in the last 30 days, along with their file sizes."}, {"role": "assistant", "content": "SELECT cd.document_id, cd.claim_id, cd.file_size_bytes FROM insurance.claim_documents cd WHERE cd.document_type = 'Police Report' AND cd.uploaded_at >= CURRENT_DATE - INTERVAL '30 days';"}, {"role": "user", "content": "Now include only documents that are larger than 1MB and sort them by file size in descending order."}, {"role": "assistant", "content": "SELECT cd.document_id, cd.claim_id, cd.file_size_bytes FROM insurance.claim_documents cd WHERE cd.document_type = 'Police Report' AND cd.uploaded_at >= CURRENT_DATE - INTERVAL '30 days' AND cd.file_size_bytes > 1000000 ORDER BY cd.file_size_bytes DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.policies ( policy_id character varying(64) NOT NULL, customer_id character varying(64) NOT NULL, product_id character varying(64) NOT NULL, agent_id character varying(64), policy_number character varying(100) NOT NULL UNIQUE, start_date date NOT NULL, end_date date NOT NULL, premium_amount numeric(12, 2) NOT NULL, coverage_limit numeric(15, 2) NOT NULL, deductible numeric(10, 2) NOT NULL, status character varying(30) NOT NULL, issued_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, cancellation_date date, cancellation_reason text, PRIMARY KEY (policy_id) )\nCREATE TABLE insurance.claims ( claim_id character varying(64) NOT NULL, policy_id character varying(64) NOT NULL, customer_id character varying(64) NOT NULL, incident_date timestamp NOT NULL, reported_date timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, description text NOT NULL, estimated_loss numeric(15, 2), status character varying(30) NOT NULL, settlement_amount numeric(15, 2), settlement_date date, claim_handler_id character varying(64), police_report_number character varying(100), PRIMARY KEY (claim_id) )\nCREATE TABLE insurance.agents ( agent_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, agency_name character varying(150), license_number character varying(100) NOT NULL UNIQUE, license_state character varying(50) NOT NULL, contact_email character varying(128) UNIQUE, contact_phone character varying(30), hire_date date, termination_date date, status character varying(20) NOT NULL DEFAULT 'Active', commission_rate numeric(5, 4) NOT NULL DEFAULT 0.05, manager_id character varying(64), PRIMARY KEY (agent_id) )\nCREATE TABLE insurance.premium_payments ( payment_id character varying(64) NOT NULL, policy_id character varying(64) NOT NULL, customer_id character varying(64) NOT NULL, payment_date timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, amount_paid numeric(12, 2) NOT NULL, payment_method character varying(50), transaction_reference character varying(128) UNIQUE, due_date date, payment_period_start date, payment_period_end date, status character varying(30) NOT NULL DEFAULT 'Completed', PRIMARY KEY (payment_id) )\nCREATE TABLE insurance.claim_documents ( document_id character varying(64) NOT NULL, claim_id character varying(64) NOT NULL, document_type character varying(50) NOT NULL, file_name character varying(255) NOT NULL, file_path character varying(512) NOT NULL, file_size_bytes integer, mime_type character varying(100), uploaded_by character varying(64), uploaded_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, description text, PRIMARY KEY (document_id) )\nCREATE TABLE insurance.policy_beneficiaries ( beneficiary_id character varying(64) NOT NULL, policy_id character varying(64) NOT NULL, customer_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, relationship character varying(50) NOT NULL, percentage_share numeric(5, 2) NOT NULL CHECK (percentage_share > 0 AND percentage_share <= 100), contact_info text, added_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, PRIMARY KEY (beneficiary_id), UNIQUE (policy_id, customer_id) )\n"} {"conversations": [{"role": "user", "content": "Retrieve each agent's ID, full name, and the count of 'Pending' policies they have sold with a premium_amount greater than 2000. Order the results by the policy count descending."}, {"role": "assistant", "content": "SELECT a.agent_id,\n a.first_name || ' ' || a.last_name AS agent_name,\n COUNT(p.policy_id) AS pending_policy_count\nFROM insurance.agents a\nJOIN insurance.policies p ON a.agent_id = p.agent_id\nWHERE p.status = 'Pending'\n AND p.premium_amount > 2000\nGROUP BY a.agent_id, agent_name\nORDER BY pending_policy_count DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.policies ( policy_id text, customer_id text, product_id text, agent_id text, policy_number text, start_date date, end_date date, premium_amount numeric, coverage_limit numeric, deductible numeric, status text, issued_at timestamp, cancellation_date date, cancellation_reason text )\nCREATE TABLE insurance.claims (\n claim_id character varying(64) NOT NULL, -- unique identifier for the claim\n policy_id character varying(64) NOT NULL, -- identifier of the policy under which the claim is made (FK to policies)\n customer_id character varying(64) NOT NULL, -- identifier of the customer making the claim (FK to customers)\n incident_date timestamp NOT NULL, -- date and time of the incident leading to the claim\n reported_date timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- date the claim was reported\n description text NOT NULL, -- detailed description of the incident and claim\n estimated_loss numeric(15, 2), -- initial estimated cost of the loss\n status character varying(30) NOT NULL, -- e.g., Filed, Processing, Under Review, Approved, Denied, Settled\n settlement_amount numeric(15, 2), -- final amount paid out\n settlement_date date,\n claim_handler_id character varying(64), -- identifier for the employee handling the claim (FK to employees/adjusters)\n police_report_number character varying(100),\n PRIMARY KEY (claim_id)\n)\nCREATE TABLE insurance.agents ( agent_id text, first_name text, last_name text, agency_name text, license_number text, license_state text, contact_email text, contact_phone text, hire_date date, termination_date date, status text, commission_rate numeric, manager_id text )\nCREATE TABLE insurance.policy_beneficiaries ( beneficiary_id text, policy_id text, customer_id text, first_name text, last_name text, relationship text, percentage_share numeric, contact_info text, added_at timestamp )\n"} {"conversations": [{"role": "user", "content": "What is the total investment_value per fundraising round for the year 2023? Order by total investment descending."}, {"role": "assistant", "content": "SELECT\n substr(investment_date,1,7) AS month,\n rounds_name,\n SUM(investment_value) AS total_investment\nFROM project_fundraising_record\nWHERE investment_date LIKE '2023-%'\nGROUP BY substr(investment_date,1,7), rounds_name\nORDER BY total_investment DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE project_fundraising_record ( id.text, project_id.text, project_name.text, rounds_name.text, investment_value.numeric, investment_date.text, introduction.text, valuation.numeric )\n"} {"conversations": [{"role": "user", "content": "List pairs of citizens who share the same email domain."}, {"role": "assistant", "content": "SELECT c1.first_name AS first1,\n c1.last_name AS last1,\n c2.first_name AS first2,\n c2.last_name AS last2,\n SPLIT_PART(c1.contact_email, '@', 2) AS domain\nFROM government_services.citizens c1\nJOIN government_services.citizens c2\n ON SPLIT_PART(c1.contact_email, '@', 2) = SPLIT_PART(c2.contact_email, '@', 2)\n AND c1.citizen_id < c2.citizen_id\nWHERE c1.contact_email IS NOT NULL\n AND c2.contact_email IS NOT NULL;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.citizens (\n citizen_id character varying(64) NOT NULL, -- unique identifier for the citizen\n national_id_number character varying(128) NOT NULL UNIQUE, -- official national identification number\n first_name character varying(100) NOT NULL,\n last_name character varying(100) NOT NULL,\n date_of_birth date NOT NULL,\n gender character varying(20),\n primary_address text NOT NULL, -- full primary residential address\n contact_email character varying(128) UNIQUE,\n contact_phone character varying(32),\n registration_date timestamp NOT NULL, -- when the citizen profile was created\n is_verified boolean DEFAULT false, -- whether identity has been officially verified\n PRIMARY KEY (citizen_id)\n)\n"} {"conversations": [{"role": "user", "content": "Show a list of all DApps together with the total number of unique assets linked to each via the metadata table."}, {"role": "assistant", "content": "SELECT d.dapp_id, d.name, d.url, COUNT(DISTINCT m.asset_id) AS unique_asset_count\nFROM trading_platform.dapps d\nLEFT JOIN trading_platform.metadata m ON m.asset_id IS NOT NULL\nGROUP BY d.dapp_id, d.name, d.url;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE trading_platform.orders ( order_id text PRIMARY KEY, user_id text, wallet_id text, asset_id text, order_type text, quantity numeric, price numeric, status text, created_at timestamp )\nCREATE TABLE trading_platform.trades ( trade_id text PRIMARY KEY, order_id text, buyer_id text, seller_id text, asset_id text, quantity numeric, price numeric, traded_at timestamp )\nCREATE TABLE trading_platform.utxos ( utxo_id text PRIMARY KEY, transaction_id text, output_index int, address text, amount numeric, spent boolean )\nCREATE TABLE trading_platform.dapps ( dapp_id text PRIMARY KEY, name text, description text, url text )\nCREATE TABLE trading_platform.peers ( peer_id text PRIMARY KEY, ip_address text, port int, last_seen timestamp )\nCREATE TABLE trading_platform.metadata ( metadata_id text PRIMARY KEY, asset_id text, key text, value text )\nCREATE TABLE trading_platform.kyc_audit ( kyc_audit_id text PRIMARY KEY, user_id text, status text, reviewed_at timestamp )\nCREATE TABLE trading_platform.logs ( log_id text PRIMARY KEY, user_id text, action text, details text, logged_at timestamp )\n"} {"conversations": [{"role": "user", "content": "Show me each department in each property, along with the total number of available services and their combined price."}, {"role": "assistant", "content": "SELECT property_id, department, COUNT(*) AS service_count, SUM(price) AS total_price FROM hospitality_technology.services WHERE is_available = true GROUP BY property_id, department;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE hospitality_technology.services ( service_id character varying(64) NOT NULL, property_id character varying(64) NOT NULL, service_name character varying(150) NOT NULL, description text, category character varying(100), price numeric(10, 2) NOT NULL, unit character varying(30), is_available boolean NOT NULL DEFAULT true, department character varying(100), PRIMARY KEY (service_id), FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id) )\n"} {"conversations": [{"role": "user", "content": "For each vehicle, count how many maintenance logs exist."}, {"role": "assistant", "content": "SELECT v.vehicle_id, v.make, v.model, COUNT(ml.log_id) AS maintenance_log_count FROM transportation.vehicles v JOIN transportation.maintenance_logs ml ON v.vehicle_id = ml.vehicle_id GROUP BY v.vehicle_id, v.make, v.model ORDER BY maintenance_log_count DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.vehicles ( vehicle_id character varying(64) NOT NULL, license_plate character varying(32) NOT NULL UNIQUE, vin character varying(17) UNIQUE, make character varying(64) NOT NULL, model character varying(64) NOT NULL, year integer NOT NULL, type character varying(32) NOT NULL, capacity integer, fuel_type character varying(32) NOT NULL, status character varying(32) NOT NULL, depot_id character varying(64), acquisition_date date, PRIMARY KEY (vehicle_id) )\nCREATE TABLE transportation.drivers ( driver_id character varying(64) NOT NULL, employee_id character varying(64) NOT NULL UNIQUE, first_name character varying(128) NOT NULL, last_name character varying(128) NOT NULL, license_number character varying(64) NOT NULL UNIQUE, license_expiry_date date NOT NULL, contact_number character varying(32), email character varying(128) UNIQUE, hire_date date NOT NULL, status character varying(32) NOT NULL, PRIMARY KEY (driver_id) )\nCREATE TABLE transportation.trips ( trip_id character varying(64) NOT NULL, route_id character varying(64), vehicle_id character varying(64) NOT NULL, driver_id character varying(64) NOT NULL, scheduled_departure timestamp with time zone NOT NULL, actual_departure timestamp with time zone, scheduled_arrival timestamp with time zone NOT NULL, actual_arrival timestamp with time zone, origin_location_id character varying(64) NOT NULL, destination_location_id character varying(64) NOT NULL, status character varying(32) NOT NULL, passenger_count integer, cargo_manifest_id character varying(64), PRIMARY KEY (trip_id) )\nCREATE TABLE transportation.locations ( location_id character varying(64) NOT NULL, name character varying(255) NOT NULL, type character varying(64) NOT NULL, address_line1 character varying(255), city character varying(128), state_province character varying(128), postal_code character varying(32), country character varying(64) NOT NULL, latitude numeric(9, 6), longitude numeric(9, 6), timezone character varying(64), PRIMARY KEY (location_id) )\nCREATE TABLE transportation.maintenance_logs ( log_id character varying(64) NOT NULL, vehicle_id character varying(64) NOT NULL, service_date date NOT NULL, odometer_reading integer, service_type character varying(128) NOT NULL, description text NOT NULL, cost numeric(10, 2), mechanic_name character varying(128), next_service_due_date date, PRIMARY KEY (log_id) )\nCREATE TABLE transportation.passengers ( passenger_id character varying(64) NOT NULL, first_name character varying(128) NOT NULL, last_name character varying(128) NOT NULL, email character varying(128) UNIQUE, phone_number character varying(32) UNIQUE, date_of_birth date, loyalty_program_id character varying(64), created_at timestamp with time zone NOT NULL, PRIMARY KEY (passenger_id) )\n"} {"conversations": [{"role": "user", "content": "For Sui coins owned by address '0xabc...xyz', list the balance and their symbol by joining the coins and metadata tables."}, {"role": "assistant", "content": "SELECT T1.balance, T2.symbol FROM sui_coins AS T1 JOIN sui_coins_metadata AS T2 ON T1.coin_type = T2.coin_type WHERE T1.owner = '0xabc...xyz';"}, {"role": "user", "content": "Filter the results to only include coins with the symbol 'USDC'."}, {"role": "assistant", "content": "SELECT T1.balance, T2.symbol FROM sui_coins AS T1 JOIN sui_coins_metadata AS T2 ON T1.coin_type = T2.coin_type WHERE T1.owner = '0xabc...xyz' AND T2.symbol = 'USDC';"}, {"role": "user", "content": "Instead of listing all, just tell me the total balance of 'USDC' for that owner."}, {"role": "assistant", "content": "SELECT SUM(CAST(T1.balance AS DECIMAL)) FROM sui_coins AS T1 JOIN sui_coins_metadata AS T2 ON T1.coin_type = T2.coin_type WHERE T1.owner = '0xabc...xyz' AND T2.symbol = 'USDC';"}], "system": "You are an expert in writing database language. You can write a corresponding database language query to answer the user's question based on the table structure described by the table creation statement. \n##Table Structure\nCREATE TABLE token_metas ( block_timestamp timestamp(6) NOT NULL, block_number bigint NOT NULL, transaction_hash varchar NOT NULL, transaction_index bigint NOT NULL, from_address varchar NOT NULL, contract_address varchar NOT NULL, symbol varchar NOT NULL, total_supply varchar NOT NULL, name varchar NOT NULL, decimals bigint NOT NULL, is_erc20 integer NOT NULL, is_erc721 integer NOT NULL, is_erc1155 integer NOT NULL, is_proxy integer NOT NULL, extra_info varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE erc1155_approval_for_all ( block_number bigint NOT NULL, block_timestamp timestamp(3) NOT NULL, transaction_index integer NOT NULL, transaction_hash varchar(66) NOT NULL, log_index integer NOT NULL, contract_address varchar(42) NOT NULL )\nCREATE TABLE erc20_balances ( block_number bigint NOT NULL, contract_address varchar NOT NULL, wallet_address varchar NOT NULL, amount varchar NOT NULL, pk varchar NOT NULL )\nCREATE TABLE erc20_balances_historical ( block_number bigint NOT NULL, contract_address varchar NOT NULL, wallet_address varchar NOT NULL, amount varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE sui_coins ( object_id varchar NOT NULL, status varchar NOT NULL, coin_type varchar NOT NULL, balance varchar NOT NULL, owner varchar NOT NULL )\nCREATE TABLE sui_coins_metadata ( object_id varchar NOT NULL, coin_type varchar NOT NULL, status varchar NOT NULL, decimals bigint NOT NULL, description varchar NOT NULL, icon_url varchar NOT NULL, symbol varchar NOT NULL, name varchar NOT NULL )\nCREATE TABLE nft_metadata ( blockchain varchar NOT NULL, contract_address varchar NOT NULL, token_id varchar NOT NULL, contract_name varchar NOT NULL, erc_type varchar NOT NULL, amount bigint NOT NULL, minter varchar NOT NULL, owner varchar NOT NULL, mint_block_number bigint NOT NULL, mint_time bigint NOT NULL, mint_transaction_hash varchar NOT NULL, mint_price varchar NOT NULL, token_uri varchar NOT NULL, metadata varchar NOT NULL, name varchar NOT NULL, image_uri varchar NOT NULL, traits varchar NOT NULL, updated_at bigint NOT NULL, status varchar NOT NULL, rarity_score real NOT NULL, rarity_rank integer NOT NULL, unique_attribute_count integer NOT NULL, pk integer NOT NULL )\nCREATE TABLE token_prices ( uuid varchar(36) NOT NULL, blockchain varchar(36) NOT NULL, address varchar(42) NOT NULL, decimals bigint NOT NULL, symbol varchar(36) NOT NULL, price real NOT NULL, timestamp timestamp(6) NOT NULL )\nCREATE TABLE token_prices_latest ( blockchain varchar(36) NOT NULL, address varchar(42) NOT NULL, decimals bigint NOT NULL, symbol varchar(36) NOT NULL, price real NOT NULL, timestamp timestamp(6) NOT NULL )\nCREATE TABLE token_balances ( block_number bigint NOT NULL, block_timestamp timestamp(3) NOT NULL, tick varchar NOT NULL, wallet_address varchar(42) NOT NULL, total_supply decimal(38,0) NOT NULL, amount decimal(38,0) NOT NULL )\nCREATE TABLE token_activities ( block_timestamp timestamp(3) NOT NULL, block_number bigint NOT NULL, tx_index integer NOT NULL, tx_hash varchar(66) NOT NULL, log_index integer NOT NULL, type varchar NOT NULL, tick varchar NOT NULL, id varchar(255) NOT NULL, amt decimal(38,0) NOT NULL, from_address varchar(42) NOT NULL, to_address varchar(42) NOT NULL )\nCREATE TABLE token_activities_avalanche ( block_timestamp timestamp(3) NOT NULL, block_number bigint NOT NULL, tx_index integer NOT NULL, tx_hash varchar(66) NOT NULL, log_index integer NOT NULL, type varchar(20) NOT NULL, tick varchar(255) NOT NULL, id varchar(255) NOT NULL, amt decimal(38,0) NOT NULL, from_address varchar(42) NOT NULL, to_address varchar(42) NOT NULL )\nCREATE TABLE token_balances_avalanche ( block_number bigint NOT NULL, block_timestamp timestamp(3) NOT NULL, tick varchar(20) NOT NULL, wallet_address varchar(42) NOT NULL, total_supply decimal(38,0) NOT NULL, amount decimal(38,0) NOT NULL )\nCREATE TABLE token_info_avalanche ( block_timestamp timestamp(3) NOT NULL, block_number bigint NOT NULL, tx_index integer NOT NULL, tx_hash varchar(66) NOT NULL, tick varchar(20) NOT NULL, max_supply decimal(38,0) NOT NULL, lim decimal(38,0) NOT NULL, wlim decimal(38,0) NOT NULL, dec integer NOT NULL, creator varchar(42) NOT NULL, minted decimal(38,0) NOT NULL, holders decimal(38,0) NOT NULL, txs decimal(38,0) NOT NULL, updated_timestamp timestamp(3) NOT NULL, completed_timestamp timestamp(3) NOT NULL, id varchar(255) NOT NULL )\n"} {"conversations": [{"role": "user", "content": "Find all medical records where the treatment plan includes 'physical therapy' and the patient has an active primary insurance plan, showing the patient ID, record date, and insurance provider details."}, {"role": "assistant", "content": "SELECT mr.patient_id, mr.record_date, ip.insurance_provider, ip.plan_name, pi.policy_number FROM healthcare.medical_records mr JOIN healthcare.patients p ON mr.patient_id = p.patient_id JOIN healthcare.patient_insurance pi ON p.patient_id = pi.patient_id AND pi.is_primary = true JOIN healthcare.insurance_plans ip ON pi.plan_id = ip.plan_id WHERE mr.treatment_plan LIKE '%physical therapy%' AND (pi.expiration_date IS NULL OR pi.expiration_date > CURRENT_DATE);"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.patients ( patient_id text, first_name text, last_name text, date_of_birth date, gender text, address text, phone_number text, email text, emergency_contact_name text, emergency_contact_phone text, created_at timestamp, updated_at timestamp )\nCREATE TABLE healthcare.appointments ( appointment_id text, patient_id text, doctor_id text, appointment_time timestamp, duration_minutes integer, reason text, status text, location_id text, notes text, created_at timestamp )\nCREATE TABLE healthcare.medical_records ( record_id text PRIMARY KEY, patient_id text, appointment_id text, doctor_id text, record_date timestamp, chief_complaint text, present_illness_history text, past_medical_history text, physical_examination_notes text, assessment text, treatment_plan text, vitals text, created_at timestamp )\nCREATE TABLE healthcare.diagnoses ( diagnosis_id text PRIMARY KEY, record_id text, patient_id text, doctor_id text, diagnosis_code text, code_type text, description text, diagnosis_date date, status text, is_chronic boolean )\nCREATE TABLE healthcare.medications ( medication_id text, medication_name text, generic_name text, manufacturer text, ndc_code text, description text )\nCREATE TABLE healthcare.insurance_plans (\n plan_id character varying(64) NOT NULL, -- unique identifier for the insurance plan\n plan_name character varying(200) NOT NULL, -- name of the insurance plan\n insurance_provider character varying(100) NOT NULL, -- name of the insurance company\n plan_type character varying(50), -- e.g., PPO, HMO, EPO\n contact_phone character varying(20), -- provider contact number\n website character varying(255), -- provider website\n PRIMARY KEY (plan_id)\n)\nCREATE TABLE healthcare.patient_insurance ( patient_insurance_id character varying(64) NOT NULL, patient_id character varying(64) NOT NULL, plan_id character varying(64) NOT NULL, policy_number character varying(100) NOT NULL, group_number character varying(100), subscriber_name character varying(200), effective_date date NOT NULL, expiration_date date, is_primary boolean NOT NULL DEFAULT true, PRIMARY KEY (patient_insurance_id), UNIQUE (patient_id, plan_id, policy_number) )\n"} {"conversations": [{"role": "user", "content": "How many group chats have been created since January 1, 2024?"}, {"role": "assistant", "content": "SELECT COUNT(*) AS group_chat_count\nFROM social_media.conversations\nWHERE is_group_chat = TRUE\n AND created_at >= '2024-01-01';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE social_media.posts ( post_id text, user_id text, content text, media_url text, media_type text, created_at timestamp, updated_at timestamp, visibility text, location_lat numeric, location_lon numeric )\nCREATE TABLE social_media.likes ( like_id text, user_id text, post_id text, comment_id text, created_at timestamp )\nCREATE TABLE social_media.hashtags ( hashtag_id text, tag_name text, created_at timestamp )\nCREATE TABLE social_media.conversations ( conversation_id text, created_at timestamp, last_message_at timestamp, is_group_chat boolean, group_name text )\n"} {"conversations": [{"role": "user", "content": "Show me all doctors who have prescribed medications with a dosage greater than 200mg, along with their specialties and the count of such prescriptions per doctor."}, {"role": "assistant", "content": "SELECT d.doctor_id, d.first_name, d.last_name, d.specialty, COUNT(p.prescription_id) AS prescription_count FROM healthcare.doctors d JOIN healthcare.prescriptions p ON d.doctor_id = p.doctor_id WHERE CAST(SUBSTRING(p.dosage FROM '[0-9]+') AS INTEGER) > 200 GROUP BY d.doctor_id, d.first_name, d.last_name, d.specialty ORDER BY prescription_count DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.doctors ( doctor_id.text, first_name.text, last_name.text, specialty.text, license_number.text, phone_number.text, email.text, hospital_affiliation_id.text, created_at.timestamp, updated_at.timestamp )\nCREATE TABLE healthcare.diagnoses ( diagnosis_id.text, record_id.text, patient_id.text, doctor_id.text, diagnosis_code.text, code_type.text, description.text, diagnosis_date.date, status.text, is_chronic.boolean )\nCREATE TABLE healthcare.prescriptions ( prescription_id.text, record_id.text, patient_id.text, doctor_id.text, medication_id.text, dosage.text, frequency.text, route.text, start_date.date, end_date.date, quantity_dispensed.numeric, refills_allowed.integer, prescription_date.timestamp )\nCREATE TABLE healthcare.patient_insurance ( patient_insurance_id.text, patient_id.text, plan_id.text, policy_number.text, group_number.text, subscriber_name.text, effective_date.date, expiration_date.date, is_primary.boolean )\n"} {"conversations": [{"role": "user", "content": "For each agent, show the total number of policies they have sold and the sum of the premium amounts. Include the agent_id."}, {"role": "assistant", "content": "SELECT agent_id, COUNT(*) AS policy_count, SUM(premium_amount) AS total_premium\nFROM insurance.policies\nWHERE agent_id IS NOT NULL\nGROUP BY agent_id;"}, {"role": "user", "content": "Can you filter to only include agents who have sold more than 20 policies?"}, {"role": "assistant", "content": "SELECT agent_id, COUNT(*) AS policy_count, SUM(premium_amount) AS total_premium\nFROM insurance.policies\nWHERE agent_id IS NOT NULL\nGROUP BY agent_id\nHAVING COUNT(*) > 20;"}, {"role": "user", "content": "Actually, could you also show the average premium amount per policy for each qualifying agent?"}, {"role": "assistant", "content": "SELECT agent_id, COUNT(*) AS policy_count, SUM(premium_amount) AS total_premium, AVG(premium_amount) AS avg_premium\nFROM insurance.policies\nWHERE agent_id IS NOT NULL\nGROUP BY agent_id\nHAVING COUNT(*) > 20;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.policies ( policy_id character varying(64) NOT NULL, customer_id character varying(64) NOT NULL, product_id character varying(64) NOT NULL, agent_id character varying(64), policy_number character varying(100) NOT NULL UNIQUE, start_date date NOT NULL, end_date date NOT NULL, premium_amount numeric(12, 2) NOT NULL, coverage_limit numeric(15, 2) NOT NULL, deductible numeric(10, 2) NOT NULL, status character varying(30) NOT NULL, issued_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, cancellation_date date, cancellation_reason text, PRIMARY KEY (policy_id) )\n"} {"conversations": [{"role": "user", "content": "Find all wallets that were created on the same day and list their wallet IDs, addresses, and the creation date."}, {"role": "assistant", "content": "SELECT w1.wallet_id, w1.address, w1.created_at::date AS creation_date FROM web3.wallets w1 JOIN (SELECT created_at::date AS creation_date FROM web3.wallets GROUP BY created_at::date HAVING COUNT(*) > 1) w2 ON w1.created_at::date = w2.creation_date ORDER BY creation_date, w1.wallet_id;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE web3.wallets (\n wallet_id character varying(64) NOT NULL, -- unique identifier for the wallet\n user_id character varying(64) NOT NULL, -- identifier of the user owning the wallet\n address character varying(128) NOT NULL, -- address of the wallet\n private_key text NOT NULL, -- private key of the wallet\n created_at timestamp NOT NULL, -- time when the wallet was created\n PRIMARY KEY (wallet_id)\n)\n"} {"conversations": [{"role": "user", "content": "What is the average ROI for smart money addresses on the Ethereum chain?"}, {"role": "assistant", "content": "SELECT AVG(roi) FROM smart_money_token_performance WHERE chain = 'Ethereum';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\n \"CREATE TABLE project_fundraising_record (\",\n \"id character varying(32) NOT NULL, -- fundraising record id\",\n \"project_id character varying(32) NOT NULL, -- the invested project's id\",\n \"project_name character varying(128) NOT NULL, -- name of the invested project\",\n \"rounds_name character varying(32), -- name of the fundraising round\",\n \"investment_value numeric(38,14), -- amount of the fundraising in USD\",\n \"investment_date character varying(128), -- the date of the investment happened\",\n \"introduction character varying(128), -- the introduction of the invested project\",\n \"valuation numeric(38,14), -- the valuation of the project in USD when invested\",\n\n \"CREATE TABLE token_basic_info (\",\n \"coin_id character varying(100) NOT NULL, -- the id of the token\",\n \"token_name character varying(100) NOT NULL, -- the token's name\",\n \"token_symbol character varying(100) NOT NULL, -- the token's symbol\",\n \"token_address character varying(100) NOT NULL, -- the token's address\",\n \"chain text, -- the chain that the token resides\",\n \"price double precision, -- the current price of the token\",\n \"price_change_percentage_1h double precision, -- change in value divided by the absolute price value of the original token price in 1 hour\",\n \"price_change_percentage_24h double precision, -- change in value divided by the absolute price value of the original token price in 24 hours\",\n \"price_change_percentage_7d double precision, -- change in value divided by the absolute price value of the original token price in 7 days\",\n \"highest_price_24h double precision, -- the highest price of the token in 24 hours\",\n \"lowest_price_24h double precision, -- the lowest price of the token in 24 hours\",\n \"market_cap double precision, -- the market cap of the token\",\n \"market_cap_rank bigint, -- the rank of the token market cap in desc\",\n \"market_cap_change_percentage_24h text, -- the percentage of market cap changes in 24 hours\",\n \"total_volume text, -- the trade volum of the token both in decentralized exchange(DEX) and centralized exchange(CEX)\", \n \"narrative text, -- the category or narrative of the token\",\n \"trend_rank biging, -- the trending rank of the token, value 1 expresses the most popular token.\",\n \",PRIMARY KEY (coin_id, chain));\",\n\n \"CREATE TABLE narrative_info (\",\n \"narrative character varying(512) NOT NULL, -- the id of narrative\",\n \"top_3_coins text, -- the top 3 tokens in the narrative\",\n \"price_change_percentage_1h double precision, -- change in value divided by the absolute price value of the original token price in 1 hour in the narrative\",\n \"price_change_percentage_24h double precision, -- change in value divided by the absolute price value of the original token price in 24 hours in the narrative\",\n \"price_change_percentage_7d double precision, -- change in value divided by the absolute price value of the original token price in 7 days in the narrative\",\n \"market_cap double precision, -- the market cap of the narrative\",\n \"volume_24h double precision, -- the trade volume of the narrative\",\n \"trend_rank bigint, -- the trending rank of the narrative, value 1 expresses the most popular narrative\",\n \"token_num bigint, -- total token number in the narrative\",\n \",PRIMARY KEY (narrative));\"\n\n \"CREATE TABLE cex_token_balance (\",\n \"snapshot_time character varying(32) NOT NULL, -- the snapshot time of record, converted from original timestamp\",\n \"chain character varying(128) NOT NULL, -- the chain that the token resides\",\n \"address character varying(128) NOT NULL, -- the address that holds the assets, owned by a CEX\",\n \"exchange character varying(512) NOT NULL, -- a centralized exchange name\",\n \"token_address character varying(128) NOT NULL, -- token contract address\",\n \"token_symbol character varying(512), --token symbol\",\n \"balance numeric(38,10), -- token balance\",\n \"usd_value numeric(38,14), -- value of the token held in USD\",\n \"price double precision, --price of the token in USD\",\n \",PRIMARY KEY (snapshot_time, exchange, address, chain, token_address));\"\n\n \"CREATE TABLE smart_money_token_performance (\",\n \"token_address character varying(100) NOT NULL, -- the token's address\",\n \"token_symbol character varying(100), -- the tokens's symbol\",\n \"pnl numeric(38,2), -- the profit users made on this token\",\n \"net_flow numeric(38,2), -- the netflow of the token, means the money user spent minus the the money user sold of this token\",\n \"avg_cost numeric(38,16), -- the average cost price of user spent on this token\",\n \"price double precision, -- the current price of the token\",\n \"realized_ratio numeric(10,2), -- the ratio user sold of the token\",\n \"roi numeric(10,2), -- the roi users made of this token\",\n \"chain character varying(100), -- the chain that the token resides\",\n \"PRIMARY KEY (token_address, chain));\",\n\n"} {"conversations": [{"role": "user", "content": "For each Bitcoin token tick, show me the creator address from the token_info_bitcoin table and the number of unique wallets currently holding that token."}, {"role": "assistant", "content": "SELECT ti.tick, ti.creator, COUNT(DISTINCT tb.wallet_address) AS unique_wallets FROM token_info_bitcoin ti JOIN token_balances_bitcoin tb ON ti.tick = tb.tick GROUP BY ti.tick, ti.creator;"}, {"role": "user", "content": "Now, only include ticks where there are more than 5 unique wallets, and order the result by the number of unique wallets descending."}, {"role": "assistant", "content": "SELECT ti.tick, ti.creator, COUNT(DISTINCT tb.wallet_address) AS unique_wallets FROM token_info_bitcoin ti JOIN token_balances_bitcoin tb ON ti.tick = tb.tick GROUP BY ti.tick, ti.creator HAVING COUNT(DISTINCT tb.wallet_address) > 5 ORDER BY unique_wallets DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE erc1155_approval_for_all (\n block_number bigint NOT NULL, -- Block number containing the transaction\n block_timestamp timestamp(3) NOT NULL, -- Timestamp of the block containing the transaction\n transaction_index integer NOT NULL, -- Index of the transaction within the block\n transaction_hash varchar(66) NOT NULL, -- Transaction hash\n log_index integer NOT NULL, -- Log index\n contract_address varchar(42) NOT NULL -- Event contract address\n)\nCREATE TABLE erc20_balances ( block_number bigint, contract_address varchar, wallet_address varchar, amount varchar, pk varchar )\nCREATE TABLE erc20_balances_historical ( block_number bigint, contract_address text, wallet_address text, amount text, pk integer )\nCREATE TABLE nft_holders ( block_number.bigint, contract_address.text, wallet_address.text, token_id.text, contract_type.text, amount.text, pk.text )\nCREATE TABLE sui_coins ( object_id varchar NOT NULL, status varchar NOT NULL, coin_type varchar NOT NULL, balance varchar NOT NULL, owner varchar NOT NULL )\nCREATE TABLE sui_coins_metadata (\n object_id varchar NOT NULL, -- object id of the coin metadata object\n coin_type varchar NOT NULL, -- coin type, eg. 0x...66::reap_token::REAP_TOKEN\n status varchar NOT NULL, -- coin status, eg. exists, deleted\n decimals bigint NOT NULL, -- decimals of the coin\n description varchar NOT NULL, -- description of the coin\n icon_url varchar NOT NULL, -- icon url of the coin\n symbol varchar NOT NULL, -- symbol of the coin\n name varchar NOT NULL -- name of the coin\n)\nCREATE TABLE sui_nfts ( object_id.text, status.text, collection_type.text, package_id.text, previous_transaction.text, display.text, owner.text, name.text )\nCREATE TABLE nft_collections ( blockchain varchar NOT NULL, contract_address varchar NOT NULL, name varchar NOT NULL, symbol varchar NOT NULL, deploy_block_number bigint NOT NULL, deploy_block_time bigint NOT NULL, erc_type varchar NOT NULL, owner varchar NOT NULL, traits varchar NOT NULL, description varchar NOT NULL, slug varchar NOT NULL, media_info varchar NOT NULL, image_url varchar NOT NULL, banner_image_url varchar NOT NULL, updated_at bigint NOT NULL, banner varchar NOT NULL, token_count bigint NOT NULL, floor_price varchar NOT NULL, floor_price_symbol varchar NOT NULL, floor_price_contract varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE token_prices ( uuid.text, blockchain.text, address.text, decimals.bigint, symbol.text, price.real, timestamp.timestamp )\nCREATE TABLE token_prices_latest ( blockchain.text, address.text, decimals.bigint, symbol.text, price.real, timestamp.timestamp )\nCREATE TABLE erc20_approval ( block_number.bigint, block_timestamp.timestamp, transaction_index.integer, transaction_hash.text, log_index.integer, contract_address.text, pk.integer )\nCREATE TABLE token_balances (\n block_number bigint NOT NULL, -- Block number containing the transaction\n block_timestamp timestamp(3) NOT NULL, -- Block timestamp containing the transaction\n tick varchar NOT NULL, -- Token tick\n wallet_address varchar(42) NOT NULL, -- Address of owner\n total_supply decimal(38,0) NOT NULL, -- Max supply\n amount decimal(38,0) NOT NULL -- The balance of wallet balance at the corresponding block height\n)\nCREATE TABLE token_info ( block_timestamp timestamp(3) NOT NULL, block_number bigint NOT NULL, tx_index integer NOT NULL, tx_hash varchar(66) NOT NULL, tick varchar NOT NULL, max_supply decimal(38,0) NOT NULL, lim decimal(38,0) NOT NULL, wlim decimal(38,0) NOT NULL, dec integer NOT NULL, creator varchar(42) NOT NULL )\nCREATE TABLE token_activities ( block_timestamp.timestamp, block_number.bigint, tx_index.integer, tx_hash.text, log_index.integer, type.text, tick.text, id.text, amt.decimal, from_address.text, to_address.text )\nCREATE TABLE mud_holesky_redstone ( address text, table_id text, key_bytes text, key0 text, key1 text, static_data text, encoded_lengths text, dynamic_data text, is_deleted boolean, block_number bigint, log_index bigint )\nCREATE TABLE token_balances_bitcoin (\n block_number bigint NOT NULL, -- Block number containing the transaction\n block_timestamp timestamp(3) NOT NULL, -- Block timestamp containing the transaction\n tick varchar(255) NOT NULL, -- Ticker: Identifier of the inscription\n wallet_address varchar(42) NOT NULL, -- Address of owner\n total_supply varchar NOT NULL, -- Max supply: Set max supply of the inscription\n amount varchar NOT NULL -- The balance of wallet balance at the corresponding block height\n)\nCREATE TABLE token_info_bitcoin ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash text, tick text, max_supply decimal, lim decimal, wlim decimal, dec integer, creator text )\nCREATE TABLE token_activities_bitcoin ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash text, log_index integer, type text, tick text, id text, amt decimal, from_address text, to_address text )\nCREATE TABLE token_activities_avalanche ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash varchar, log_index integer, type varchar, tick varchar, id varchar, amt decimal, from_address varchar, to_address varchar )\nCREATE TABLE token_balances_avalanche (\n block_number bigint NOT NULL, -- Block number containing the transaction\n block_timestamp timestamp(3) NOT NULL, -- Block timestamp containing the transaction\n tick varchar(20) NOT NULL, -- Ticker: Identifier of the inscription\n wallet_address varchar(42) NOT NULL, -- Address of owner\n total_supply decimal(38,0) NOT NULL, -- Max supply: Set max supply of the inscription\n amount decimal(38,0) NOT NULL -- The balance of wallet balance at the corresponding block height\n)\nCREATE TABLE token_info_avalanche ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash varchar, tick varchar, max_supply decimal, lim decimal, wlim decimal, dec integer, creator varchar, minted decimal, holders decimal, txs decimal, updated_timestamp timestamp, completed_timestamp timestamp, id varchar )\n"} {"conversations": [{"role": "user", "content": "Find all wallet addresses that don't have an associated user_id."}, {"role": "assistant", "content": "SELECT address_id FROM blockchain.wallets WHERE user_id IS NULL;"}, {"role": "user", "content": "Now show me these addresses along with their private_key, and join with another table to see if they have any transactions."}, {"role": "assistant", "content": "SELECT w.address_id, w.private_key FROM blockchain.wallets w WHERE w.user_id IS NULL;"}, {"role": "user", "content": "Actually, I want to see the count of such wallet addresses grouped by the first 3 characters of their address_id."}, {"role": "assistant", "content": "SELECT SUBSTRING(address_id, 1, 3) as address_prefix, COUNT(*) as address_count FROM blockchain.wallets WHERE user_id IS NULL GROUP BY SUBSTRING(address_id, 1, 3);"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE blockchain.wallets ( wallet_id.text, user_id.text, address_id.text, private_key.text )\n"} {"conversations": [{"role": "user", "content": "For each transaction ID, provide a count of unspent UTXOs."}, {"role": "assistant", "content": "SELECT transaction_id, COUNT(*) FROM utxos WHERE spent = FALSE GROUP BY transaction_id;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE trading_platform.utxos (\n utxo_id character varying(64) NOT NULL, -- unique identifier for the UTXO\n transaction_id character varying(64) NOT NULL, -- identifier of the transaction that created the UTXO\n output_index integer NOT NULL, -- index of the output in the transaction\n address character varying(128) NOT NULL, -- address that can spend the UTXO\n amount numeric(38,14) NOT NULL, -- amount of the asset in the UTXO\n spent boolean NOT NULL, -- whether the UTXO has been spent\n PRIMARY KEY (utxo_id)\n)\n"} {"conversations": [{"role": "user", "content": "List all pairs of token IDs that share the same decimals value, and show the shared decimals."}, {"role": "assistant", "content": "SELECT t1.token_id AS token1_id,\n t2.token_id AS token2_id,\n t1.decimals\nFROM web3.tokens t1\nJOIN web3.tokens t2\n ON t1.decimals = t2.decimals\n AND t1.token_id < t2.token_id;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE web3.tokens (\n token_id character varying(64) NOT NULL, -- unique identifier for the token\n contract_address character varying(128) NOT NULL, -- address of the token contract\n token_name character varying(128) NOT NULL, -- name of the token\n token_symbol character varying(32) NOT NULL, -- symbol of the token\n decimals integer NOT NULL, -- number of decimals for the token\n total_supply numeric(38,14) NOT NULL, -- total supply of the token\n PRIMARY KEY (token_id)\n)\n"} {"conversations": [{"role": "user", "content": "List all properties and the room types they offer, including the base rate for each room type."}, {"role": "assistant", "content": "SELECT T1.property_name, T2.type_name, T2.base_rate FROM hospitality_technology.properties AS T1 JOIN hospitality_technology.room_types AS T2 ON T1.property_id = T2.property_id;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE hospitality_technology.rooms (\n room_id character varying(64) NOT NULL, -- unique identifier for the room\n property_id character varying(64) NOT NULL, -- FK to properties table\n room_number character varying(10) NOT NULL, -- room number identifier (e.g., '101', 'Suite 2B')\n room_type_id character varying(64) NOT NULL, -- FK to room_types table\n floor integer, -- floor number the room is on\n status character varying(50) NOT NULL, -- e.g., Available, Occupied, Cleaning, OutOfOrder, Maintenance\n is_smoking boolean NOT NULL DEFAULT false, -- smoking allowed flag\n features text, -- description of features (e.g., Balcony, Sea View, Jacuzzi)\n current_condition text, -- notes on room condition\n last_cleaned_at timestamp with time zone, -- timestamp of last cleaning\n PRIMARY KEY (room_id),\n FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id),\n FOREIGN KEY (room_type_id) REFERENCES hospitality_technology.room_types(room_type_id)\n)\nCREATE TABLE hospitality_technology.guests ( guest_id text PRIMARY KEY, first_name text, last_name text, email text, phone_number text, date_of_birth date, address_line1 text, city text, state_province text, postal_code text, country_code text, preferences text, loyalty_member_id text, communication_consent boolean, created_at timestamp, updated_at timestamp )\nCREATE TABLE hospitality_technology.reservations ( reservation_id character varying(64) NOT NULL, property_id character varying(64) NOT NULL, guest_id character varying(64) NOT NULL, room_id character varying(64), room_type_id character varying(64) NOT NULL, check_in_date date NOT NULL, check_out_date date NOT NULL, actual_check_in_ts timestamp with time zone, actual_check_out_ts timestamp with time zone, num_adults integer NOT NULL, num_children integer DEFAULT 0, status character varying(50) NOT NULL, booking_source character varying(100), rate_plan_id character varying(64), total_amount numeric(12, 2), amount_paid numeric(12, 2) DEFAULT 0.00, special_requests text, created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, updated_at timestamp with time zone NOT NULL DEFAULT current_timestamp, PRIMARY KEY (reservation_id), FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id), FOREIGN KEY (guest_id) REFERENCES hospitality_technology.guests(guest_id), FOREIGN KEY (room_id) REFERENCES hospitality_technology.rooms(room_id), FOREIGN KEY (room_type_id) REFERENCES hospitality_technology.room_types(room_type_id) )\nCREATE TABLE hospitality_technology.staff ( staff_id text PRIMARY KEY, property_id text, first_name text, last_name text, position text, work_email text, work_phone text, hire_date date, termination_date date, is_active boolean, access_level int, manager_id text, created_at timestamp )\nCREATE TABLE hospitality_technology.services ( service_id character varying(64) NOT NULL, property_id character varying(64) NOT NULL, service_name character varying(150) NOT NULL, description text, category character varying(100), price numeric(10, 2) NOT NULL, unit character varying(30), is_available boolean NOT NULL DEFAULT true, department character varying(100), PRIMARY KEY (service_id), FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id) )\nCREATE TABLE hospitality_technology.payments ( payment_id.text, reservation_id.text, guest_id.text, bill_id.text, amount.numeric, currency_code.text, payment_method.text, card_type.text, card_last_four.text, transaction_ref.text, payment_timestamp.timestamp, status.text, staff_id_processed.text, notes.text )\nCREATE TABLE hospitality_technology.reviews ( review_id text PRIMARY KEY, property_id text, reservation_id text, guest_id text, rating_overall int, rating_cleanliness int, rating_service int, rating_location int, rating_value int, comment text, review_source text, review_date timestamp, is_public boolean, staff_response text, response_staff_id text, response_date timestamp )\n"} {"conversations": [{"role": "user", "content": "Count the number of law firms founded in each decade. Show the decade (e.g., 1990s, 2000s) and the count."}, {"role": "assistant", "content": "SELECT CONCAT(FLOOR(EXTRACT(YEAR FROM founded_date) / 10) * 10, 's') AS decade, COUNT(*) AS firm_count FROM law_firms WHERE founded_date IS NOT NULL GROUP BY decade ORDER BY decade;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.clients ( client_id text PRIMARY KEY, first_name text, last_name text, company_name text, email text UNIQUE, phone text, address text, date_registered timestamp, status text )\nCREATE TABLE legal_services.law_firms ( firm_id text PRIMARY KEY, firm_name text, address text, phone text, website text, founded_date date, managing_partner_id text )\nCREATE TABLE legal_services.documents ( document_id text PRIMARY KEY, case_id text, document_name text, document_type text, storage_path text, uploaded_by_lawyer_id text, upload_timestamp timestamp, version int, description text )\n"} {"conversations": [{"role": "user", "content": "Show me the top 5 projects by valuation that completed fundraising rounds in the last 6 months, along with their narrative information if available."}, {"role": "assistant", "content": "SELECT pfr.project_name, pfr.rounds_name, pfr.valuation, pfr.investment_date, ni.narrative, ni.trend_rank\nFROM project_fundraising_record pfr\nLEFT JOIN narrative_info ni ON pfr.project_name = ni.narrative\nWHERE pfr.investment_date >= date_sub(now(), interval 6 month)\nORDER BY pfr.valuation DESC\nLIMIT 5;"}, {"role": "user", "content": "Can you filter these results to only include projects with valuation over $50 million and add their 24-hour trading volume from the narrative?"}, {"role": "assistant", "content": "SELECT pfr.project_name, pfr.rounds_name, pfr.valuation, ni.volume_24h\nFROM project_fundraising_record pfr\nLEFT JOIN narrative_info ni ON pfr.project_name = ni.narrative\nWHERE pfr.investment_date >= date_sub(now(), interval 6 month)\nAND pfr.valuation > 50000000\nORDER BY pfr.valuation DESC\nLIMIT 5;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE project_fundraising_record ( id character varying(32) NOT NULL, -- fundraising record id project_id character varying(32) NOT NULL, -- the invested project's id project_name character varying(128) NOT NULL, -- name of the invested project rounds_name character varying(32), -- name of the fundraising round investment_value numeric(38,14), -- amount of the fundraising in USD investment_date character varying(128), -- the date of the investment happened introduction character varying(128), -- the introduction of the invested project valuation numeric(38,14), -- the valuation of the project in USD when invested )\nCREATE TABLE narrative_info ( narrative character varying(512) NOT NULL, -- the id of narrative top_3_coins text, -- the top 3 tokens in the narrative price_change_percentage_1h double precision, -- change in value divided by the absolute price value of the original token price in 1 hour in the narrative price_change_percentage_24h double precision, -- change in value divided by the absolute price value of the original token price in 24 hours in the narrative price_change_percentage_7d double precision, -- change in value divided by the absolute price value of the original token price in 7 days in the narrative market_cap double precision, -- the market cap of the narrative volume_24h double precision, -- the trade volume of the narrative trend_rank bigint, -- the trending rank of the narrative, value 1 expresses the most popular narrative token_num bigint, -- total token number in the narrative ,PRIMARY KEY (narrative) )\nCREATE TABLE smart_money_profit ( address character varying(100) NOT NULL, -- the user's address rank INT, -- the rank of the address in trade performance, value 1 expresses the best address. profit numeric(38,6), -- the profit user made in a month roi numeric(38,2), -- the roi of the user in a month realized_ratio numeric(38,2), -- the percentage of the user's realized profit most_profit_token character varying(100), -- the token symbol of the user's most profitable trade last_trade_time character varying(100), -- the last trade time of the user chain character varying(100), -- the chain that the address resides PRIMARY KEY (address, chain) )\n"} {"conversations": [{"role": "user", "content": "What is the detailed repair history of the equipment used by the staff with staff_id 'STAFF123' during maintenance tasks?"}, {"role": "assistant", "content": "I'm sorry, but I can't provide information on the detailed repair history of equipment used by staff members. The data in the maintenance_records table only includes information about maintenance tasks, such as record_id, asset_id, maintenance type, and staff_id, but does not cover equipment repair histories."}], "system": "You are an SQL statement expert and you can refuse the user's question if the question is not related to the table structure. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE train_station_management.maintenance_records ( record_id.text, asset_id.text, asset_type.text, maintenance_type.text, staff_id.text, start_datetime.timestamp, end_datetime.timestamp, description.text, cost.numeric, status.text )\n"} {"conversations": [{"role": "user", "content": "Show me the top 5 projects by valuation that completed fundraising rounds in the last 12 months, along with their token symbol and price from the token_basic_info table."}, {"role": "assistant", "content": "SELECT pfr.project_name, pfr.valuation, tbi.token_symbol, tbi.price FROM project_fundraising_record pfr LEFT JOIN token_basic_info tbi ON pfr.project_name = tbi.token_name WHERE pfr.investment_date >= DATE_SUB(CURRENT_DATE, INTERVAL 12 MONTH) ORDER BY pfr.valuation DESC LIMIT 5;"}, {"role": "user", "content": "Can you also include the 24-hour trading volume for these projects' tokens and filter to only include projects with valuation over $100 million?"}, {"role": "assistant", "content": "SELECT pfr.project_name, pfr.valuation, tbi.token_symbol, tbi.price, tbi.total_volume FROM project_fundraising_record pfr LEFT JOIN token_basic_info tbi ON pfr.project_name = tbi.token_name WHERE pfr.investment_date >= DATE_SUB(CURRENT_DATE, INTERVAL 12 MONTH) AND pfr.valuation > 100000000 ORDER BY pfr.valuation DESC LIMIT 5;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\n \"CREATE TABLE project_fundraising_record (\",\n \"id character varying(32) NOT NULL, -- fundraising record id\",\n \"project_id character varying(32) NOT NULL, -- the invested project's id\",\n \"project_name character varying(128) NOT NULL, -- name of the invested project\",\n \"rounds_name character varying(32), -- name of the fundraising round\",\n \"investment_value numeric(38,14), -- amount of the fundraising in USD\",\n \"investment_date character varying(128), -- the date of the investment happened\",\n \"introduction character varying(128), -- the introduction of the invested project\",\n \"valuation numeric(38,14), -- the valuation of the project in USD when invested\",\n\nCREATE TABLE token_basic_info ( coin_id character varying(100) NOT NULL, -- the id of the token token_name character varying(100) NOT NULL, -- the token's name token_symbol character varying(100) NOT NULL, -- the token's symbol token_address character varying(100) NOT NULL, -- the token's address chain text, -- the chain that the token resides price double precision, -- the current price of the token price_change_percentage_1h double precision, -- change in value divided by the absolute price value of the original token price in 1 hour price_change_percentage_24h double precision, -- change in value divided by the absolute price value of the original token price in 24 hours price_change_percentage_7d double precision, -- change in value divided by the absolute price value of the original token price in 7 days highest_price_24h double precision, -- the highest price of the token in 24 hours lowest_price_24h double precision, -- the lowest price of the token in 24 hours market_cap double precision, -- the market cap of the token market_cap_rank bigint, -- the rank of the token market cap in desc market_cap_change_percentage_24h text, -- the percentage of market cap changes in 24 hours total_volume text, -- the trade volum of the token both in decentralized exchange(DEX) and centralized exchange(CEX) narrative text, -- the category or narrative of the token trend_rank biging, -- the trending rank of the token, value 1 expresses the most popular token. ,PRIMARY KEY (coin_id, chain) )\nCREATE TABLE narrative_info ( narrative character varying(512) NOT NULL, -- the id of narrative top_3_coins text, -- the top 3 tokens in the narrative price_change_percentage_1h double precision, -- change in value divided by the absolute price value of the original token price in 1 hour in the narrative price_change_percentage_24h double precision, -- change in value divided by the absolute price value of the original token price in 24 hours in the narrative price_change_percentage_7d double precision, -- change in value divided by the absolute price value of the original token price in 7 days in the narrative market_cap double precision, -- the market cap of the narrative volume_24h double precision, -- the trade volume of the narrative trend_rank bigint, -- the trending rank of the narrative, value 1 expresses the most popular narrative token_num bigint, -- total token number in the narrative ,PRIMARY KEY (narrative) )\nCREATE TABLE token_dexpool_info ( pair_address character varying(512) NOT NULL, token_name character varying(100) NOT NULL, token_symbol character varying(100) NOT NULL, chain text, price double precision, price_change_percentage_1h double precision, price_change_percentage_6h double precision, price_change_percentage_24h double precision, makers_24h double precision, volume_24h double precision, liquidity double precision, market_cap double precision, trend_rank bigint )\nCREATE TABLE smart_money_profit ( address character varying(100) NOT NULL, rank INT, profit numeric(38,6), roi numeric(38,2), realized_ratio numeric(38,2), most_profit_token character varying(100), last_trade_time character varying(100), chain character varying(100) )\n \"CREATE TABLE smart_money_token_performance (\",\n \"token_address character varying(100) NOT NULL, -- the token's address\",\n \"token_symbol character varying(100), -- the tokens's symbol\",\n \"pnl numeric(38,2), -- the profit users made on this token\",\n \"net_flow numeric(38,2), -- the netflow of the token, means the money user spent minus the the money user sold of this token\",\n \"avg_cost numeric(38,16), -- the average cost price of user spent on this token\",\n \"price double precision, -- the current price of the token\",\n \"realized_ratio numeric(10,2), -- the ratio user sold of the token\",\n \"roi numeric(10,2), -- the roi users made of this token\",\n \"chain character varying(100), -- the chain that the token resides\",\n \"PRIMARY KEY (token_address, chain));\",\n\n \"CREATE TABLE smart_money_token_inflow (\",\n \"token_address character varying(100) NOT NULL, -- the token's address\",\n \"token_symbol character varying(100), -- the tokens's symbol\",\n \"token_amount numeric(38,2), -- the absolute value of the amount if user bought minus the amount user sold of this token\",\n \"usd_value numeric(38,2), -- the absolute usd value of the bought token minus sold token\",\n \"avg_price numeric(38,6), -- the average cost price of user spent on this token\",\n \"type int, -- the direction of the trade on this token. 1 means buying, 2 means selling\",\n \"address_amount integer, -- the amount of the user bought this token\",\n \"narrative character varying(100), -- the category or narrative of the token\",\n \"chain character varying(100), -- the chain that the token resides\",\n \",PRIMARY KEY (token_address, chain)\",\n\n"} {"conversations": [{"role": "user", "content": "What is the average number of days by which paid invoices were paid late? Calculate the average of (payment_date - due_date) for invoices with status 'Paid'."}, {"role": "assistant", "content": "SELECT AVG((payment_date::date - due_date)) AS average_late_days\nFROM legal_services.invoices\nWHERE status = 'Paid';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.invoices ( invoice_id character varying(64) NOT NULL, invoice_number character varying(100) UNIQUE NOT NULL, client_id character varying(64) NOT NULL, case_id character varying(64), issue_date date NOT NULL, due_date date NOT NULL, total_amount numeric(12, 2) NOT NULL, amount_paid numeric(12, 2) DEFAULT 0.00, status character varying(50) NOT NULL, payment_date timestamp, notes text, created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, PRIMARY KEY (invoice_id) )\n"} {"conversations": [{"role": "user", "content": "Show me the latest uploaded document (name and version) for each invoice that is linked to a case, including the invoice number and total amount."}, {"role": "assistant", "content": "SELECT i.invoice_number, i.total_amount, d.document_name, d.version AS latest_version\nFROM legal_services.invoices i\nJOIN legal_services.documents d ON i.case_id = d.case_id\nWHERE d.upload_timestamp = (\n SELECT MAX(d2.upload_timestamp)\n FROM legal_services.documents d2\n WHERE d2.case_id = d.case_id\n)\nAND i.case_id IS NOT NULL;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.lawyers ( lawyer_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, bar_number character varying(64) UNIQUE NOT NULL, firm_id character varying(64), email character varying(128) UNIQUE NOT NULL, phone character varying(32), specialization text, hire_date timestamp NOT NULL, is_partner boolean DEFAULT false, PRIMARY KEY (lawyer_id) )\nCREATE TABLE legal_services.documents ( document_id character varying(64) NOT NULL, case_id character varying(64) NOT NULL, document_name character varying(255) NOT NULL, document_type character varying(100), storage_path text NOT NULL, uploaded_by_lawyer_id character varying(64), upload_timestamp timestamp NOT NULL, version integer DEFAULT 1, description text, PRIMARY KEY (document_id) )\nCREATE TABLE legal_services.invoices ( invoice_id character varying(64) NOT NULL, invoice_number character varying(100) UNIQUE NOT NULL, client_id character varying(64) NOT NULL, case_id character varying(64), issue_date date NOT NULL, due_date date NOT NULL, total_amount numeric(12, 2) NOT NULL, amount_paid numeric(12, 2) DEFAULT 0.00, status character varying(50) NOT NULL, payment_date timestamp, notes text, created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, PRIMARY KEY (invoice_id) )\n"} {"conversations": [{"role": "user", "content": "For each vehicle, show the vehicle_id, license_plate, date of its most recent trip (actual_arrival), and the odometer_reading at its latest maintenance service."}, {"role": "assistant", "content": "SELECT\n v.vehicle_id,\n v.license_plate,\n (\n SELECT MAX(t.actual_arrival)\n FROM transportation.trips t\n WHERE t.vehicle_id = v.vehicle_id\n ) AS last_trip_arrival,\n ml.odometer_reading\nFROM transportation.vehicles v\nLEFT JOIN LATERAL (\n SELECT odometer_reading\n FROM transportation.maintenance_logs ml\n WHERE ml.vehicle_id = v.vehicle_id\n ORDER BY ml.service_date DESC\n LIMIT 1\n) ml ON TRUE;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.vehicles ( vehicle_id text PRIMARY KEY, license_plate text, vin text, make text, model text, year int, type text, capacity int, fuel_type text, status text, depot_id text, acquisition_date date )\nCREATE TABLE transportation.drivers ( driver_id text, employee_id text, first_name text, last_name text, license_number text, license_expiry_date date, contact_number text, email text, hire_date date, status text )\nCREATE TABLE transportation.routes ( route_id text PRIMARY KEY, route_number text, description text, origin_location_id text, destination_location_id text, distance_km numeric, estimated_duration_minutes int, type text )\nCREATE TABLE transportation.trips ( trip_id text PRIMARY KEY, route_id text, vehicle_id text, driver_id text, scheduled_departure timestamp, actual_departure timestamp, scheduled_arrival timestamp, actual_arrival timestamp, origin_location_id text, destination_location_id text, status text, passenger_count int, cargo_manifest_id text )\nCREATE TABLE transportation.locations ( location_id text PRIMARY KEY, name text, type text, address_line1 text, city text, state_province text, postal_code text, country text, latitude numeric, longitude numeric, timezone text )\nCREATE TABLE transportation.maintenance_logs ( log_id.text, vehicle_id.text, service_date.date, odometer_reading.integer, service_type.text, description.text, cost.numeric, mechanic_name.text, next_service_due_date.date )\nCREATE TABLE transportation.passengers (\n passenger_id character varying(64) NOT NULL, -- unique identifier for the passenger\n first_name character varying(128) NOT NULL, -- passenger's first name\n last_name character varying(128) NOT NULL, -- passenger's last name\n email character varying(128) UNIQUE, -- email address\n phone_number character varying(32) UNIQUE, -- phone number\n date_of_birth date, -- passenger's date of birth\n loyalty_program_id character varying(64), -- identifier for loyalty program membership\n created_at timestamp with time zone NOT NULL, -- time when the passenger record was created\n PRIMARY KEY (passenger_id)\n)\nCREATE TABLE transportation.bookings ( booking_id text, passenger_id text, trip_id text, seat_number text, booking_time timestamp, status text, fare numeric, payment_transaction_id text, special_requests text )\n"} {"conversations": [{"role": "user", "content": "List all ERC20 tokens with their names and symbols where the price is greater than $100, sorted by price in descending order."}, {"role": "assistant", "content": "SELECT scm.name, scm.symbol, tpl.price FROM sui_coins_metadata scm JOIN token_prices_latest tpl ON scm.coin_type = tpl.address WHERE tpl.price > 100 ORDER BY tpl.price DESC;"}, {"role": "user", "content": "I think there's an error in your query - it should be joining on address not coin_type. Also, can you add the decimals to the results?"}, {"role": "assistant", "content": "SELECT scm.name, scm.symbol, scm.decimals, tpl.price FROM sui_coins_metadata scm JOIN token_prices_latest tpl ON scm.object_id = tpl.address WHERE tpl.price > 100 ORDER BY tpl.price DESC;"}, {"role": "user", "content": "Now filter these results to only show tokens with decimals equal to 18 and limit to the top 10."}, {"role": "assistant", "content": "SELECT scm.name, scm.symbol, scm.decimals, tpl.price FROM sui_coins_metadata scm JOIN token_prices_latest tpl ON scm.object_id = tpl.address WHERE tpl.price > 100 AND scm.decimals = 18 ORDER BY tpl.price DESC LIMIT 10;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE nft_holder_historical ( block_number.bigint, contract_address.text, wallet_address.text, token_id.text, contract_type.text, amount.text, pk.integer )\nCREATE TABLE sui_coins_metadata ( object_id.text, coin_type.text, status.text, decimals.bigint, description.text, icon_url.text, symbol.text, name.text )\nCREATE TABLE sui_nfts ( object_id.text, status.text, collection_type.text, package_id.text, previous_transaction.text, display.text, owner.text, name.text )\nCREATE TABLE nft_metadata ( blockchain.text, contract_address.text, token_id.text, contract_name.text, erc_type.text, amount.bigint, minter.text, owner.text, mint_block_number.bigint, mint_time.bigint, mint_transaction_hash.text, mint_price.text, token_uri.text, metadata.text, name.text, image_uri.text, traits.text, updated_at.bigint, status.text, rarity_score.real, rarity_rank.integer, unique_attribute_count.integer, pk.integer )\nCREATE TABLE token_prices_latest ( blockchain.text, address.text, decimals.bigint, symbol.text, price.real, timestamp.timestamp )\nCREATE TABLE erc20_approval ( block_number.bigint, block_timestamp.timestamp, transaction_index.integer, transaction_hash.text, log_index.integer, contract_address.text, pk.integer )\nCREATE TABLE token_activities ( block_timestamp.timestamp, block_number.bigint, tx_index.integer, tx_hash.text, log_index.integer, type.text, tick.text, id.text, amt.decimal, from_address.text, to_address.text )\nCREATE TABLE token_info_bitcoin ( block_timestamp.timestamp, block_number.bigint, tx_index.integer, tx_hash.text, tick.text, max_supply.decimal, lim.decimal, wlim.decimal, dec.integer, creator.text )\nCREATE TABLE token_activities_avalanche ( block_timestamp.timestamp, block_number.bigint, tx_index.integer, tx_hash.text, log_index.integer, type.text, tick.text, id.text, amt.decimal, from_address.text, to_address.text )\nCREATE TABLE token_balances_avalanche ( block_number.bigint, block_timestamp.timestamp, tick.text, wallet_address.text, total_supply.decimal, amount.decimal )\nCREATE TABLE token_info_avalanche ( block_timestamp.timestamp, block_number.bigint, tx_index.integer, tx_hash.text, tick.text, max_supply.decimal, lim.decimal, wlim.decimal, dec.integer, creator.text, minted.decimal, holders.decimal, txs.decimal, updated_timestamp.timestamp, completed_timestamp.timestamp, id.text )\n"} {"conversations": [{"role": "user", "content": "For each player, show the timestamp of their first achievement unlock. Include player_id and the timestamp."}, {"role": "assistant", "content": "SELECT player_id, MIN(unlocked_at) as first_unlock_at FROM gaming_technology.player_achievements GROUP BY player_id ORDER BY first_unlock_at;"}, {"role": "user", "content": "For each player, show the timestamp of their second earliest achievement unlock, if they have at least two. Include player_id and the timestamp."}, {"role": "assistant", "content": "WITH RankedUnlocks AS ( SELECT player_id, unlocked_at, ROW_NUMBER() OVER(PARTITION BY player_id ORDER BY unlocked_at) as rn FROM gaming_technology.player_achievements ) SELECT player_id, unlocked_at as second_unlock_at FROM RankedUnlocks WHERE rn = 2 ORDER BY player_id, second_unlock_at;"}, {"role": "user", "content": "List the player_id for players who unlocked their second achievement within 10 minutes of their first."}, {"role": "assistant", "content": "WITH PlayerFirstUnlock AS ( SELECT player_id, MIN(unlocked_at) as first_unlock_at FROM gaming_technology.player_achievements GROUP BY player_id ), RankedUnlocks AS ( SELECT player_id, unlocked_at, ROW_NUMBER() OVER(PARTITION BY player_id ORDER BY unlocked_at) as rn FROM gaming_technology.player_achievements ) SELECT pfu.player_id FROM PlayerFirstUnlock pfu JOIN RankedUnlocks ru ON pfu.player_id = ru.player_id WHERE ru.rn = 2 AND ru.unlocked_at <= pfu.first_unlock_at + INTERVAL '10 minute' ORDER BY pfu.player_id;"}, {"role": "user", "content": "For the players identified in the previous query (those whose second unlock was within 10 minutes of the first), list the achievement_id of their first and second unlocks."}, {"role": "assistant", "content": "WITH PlayerFirstUnlock AS ( SELECT player_id, MIN(unlocked_at) as first_unlock_at FROM gaming_technology.player_achievements GROUP BY player_id ), RankedUnlocks AS ( SELECT player_id, achievement_id, unlocked_at, ROW_NUMBER() OVER(PARTITION BY player_id ORDER BY unlocked_at) as rn FROM gaming_technology.player_achievements ), PlayersWithFastSecondUnlock AS ( SELECT pfu.player_id FROM PlayerFirstUnlock pfu JOIN RankedUnlocks ru ON pfu.player_id = ru.player_id WHERE ru.rn = 2 AND ru.unlocked_at <= pfu.first_unlock_at + INTERVAL '10 minute' ) SELECT pfl.player_id, ru_first.achievement_id as first_achievement_id, ru_second.achievement_id as second_achievement_id FROM PlayersWithFastSecondUnlock pfl JOIN RankedUnlocks ru_first ON pfl.player_id = ru_first.player_id AND ru_first.rn = 1 JOIN RankedUnlocks ru_second ON pfl.player_id = ru_second.player_id AND ru_second.rn = 2 ORDER BY pfl.player_id;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE gaming_technology.player_achievements ( player_achievement_id uuid NOT NULL DEFAULT gen_random_uuid(), player_id uuid NOT NULL, achievement_id uuid NOT NULL, unlocked_at timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP, PRIMARY KEY (player_achievement_id), UNIQUE (player_id, achievement_id) )\n"} {"conversations": [{"role": "user", "content": "For each premium payment, list all previous payments made by the same customer. Show customer_id, previous_payment_id, previous_payment_date, current_payment_id, current_payment_date, and amount difference."}, {"role": "assistant", "content": "SELECT p1.customer_id,\n p1.payment_id AS previous_payment_id,\n p1.payment_date AS previous_payment_date,\n p2.payment_id AS current_payment_id,\n p2.payment_date AS current_payment_date,\n p2.amount_paid - p1.amount_paid AS amount_diff\nFROM insurance.premium_payments p1\nJOIN insurance.premium_payments p2\n ON p1.customer_id = p2.customer_id\n AND p1.payment_date < p2.payment_date;"}, {"role": "user", "content": "Actually, only include pairs where the current payment date is in 2024."}, {"role": "assistant", "content": "SELECT p1.customer_id,\n p1.payment_id AS previous_payment_id,\n p1.payment_date AS previous_payment_date,\n p2.payment_id AS current_payment_id,\n p2.payment_date AS current_payment_date,\n p2.amount_paid - p1.amount_paid AS amount_diff\nFROM insurance.premium_payments p1\nJOIN insurance.premium_payments p2\n ON p1.customer_id = p2.customer_id\n AND p1.payment_date < p2.payment_date\nWHERE p2.payment_date BETWEEN '2024-01-01' AND '2024-12-31';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.premium_payments ( payment_id text, policy_id text, customer_id text, payment_date timestamp, amount_paid numeric, payment_method text, transaction_reference text, due_date date, payment_period_start date, payment_period_end date, status text )\n"} {"conversations": [{"role": "user", "content": "For each recipient address, count how many token transfers they have received."}, {"role": "assistant", "content": "SELECT to_address, COUNT(*) AS received_transfer_count FROM web3.token_transfers GROUP BY to_address;"}, {"role": "user", "content": "Only show addresses that have received more than 100 transfers."}, {"role": "assistant", "content": "SELECT to_address, COUNT(*) AS received_transfer_count FROM web3.token_transfers GROUP BY to_address HAVING COUNT(*) > 100;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE web3.token_transfers ( transfer_id text PRIMARY KEY, token_id text, from_address text, to_address text, value numeric, transaction_id text, log_index int )\n"} {"conversations": [{"role": "user", "content": "List all ERC20 tokens where the total supply is between 1 million and 10 million, including their names, symbols, and contract addresses."}, {"role": "assistant", "content": "SELECT ti.tick as name, ti.tick as symbol, tb.tick as contract_address FROM token_info ti JOIN token_balances tb ON ti.tick = tb.tick WHERE CAST(tb.total_supply AS decimal) BETWEEN 1000000 AND 10000000;"}, {"role": "user", "content": "I think there's an error in your query - it should be tb.total_supply not ti.total_supply. Also, can you add the current price of each token from the token_prices_latest table?"}, {"role": "assistant", "content": "SELECT ti.tick as name, ti.tick as symbol, tb.tick as contract_address, tpl.price FROM token_info ti JOIN token_balances tb ON ti.tick = tb.tick LEFT JOIN token_prices_latest tpl ON ti.tick = tpl.tick WHERE CAST(tb.total_supply AS decimal) BETWEEN 1000000 AND 10000000;"}, {"role": "user", "content": "Now sort these results by price in descending order and limit to the top 10."}, {"role": "assistant", "content": "SELECT ti.tick as name, ti.tick as symbol, tb.tick as contract_address, tpl.price FROM token_info ti JOIN token_balances tb ON ti.tick = tb.tick LEFT JOIN token_prices_latest tpl ON ti.tick = tpl.tick WHERE CAST(tb.total_supply AS decimal) BETWEEN 1000000 AND 10000000 ORDER BY tpl.price DESC LIMIT 10;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE erc1155_approval_for_all ( block_number.bigint, block_timestamp.timestamp, transaction_index.integer, transaction_hash.text, log_index.integer, contract_address.text )\nCREATE TABLE erc20_balances ( block_number.bigint, contract_address.text, wallet_address.text, amount.text, pk.text )\nCREATE TABLE nft_holders ( block_number.bigint, contract_address.text, wallet_address.text, token_id.text, contract_type.text, amount.text, pk.text )\nCREATE TABLE nft_holder_historical ( block_number.bigint, contract_address.text, wallet_address.text, token_id.text, contract_type.text, amount.text, pk.integer )\nCREATE TABLE sui_coins_metadata ( object_id.text, coin_type.text, status.text, decimals.bigint, description.text, icon_url.text, symbol.text, name.text )\nCREATE TABLE nft_metadata ( blockchain.text, contract_address.text, token_id.text, contract_name.text, erc_type.text, amount.bigint, minter.text, owner.text, mint_block_number.bigint, mint_time.bigint, mint_transaction_hash.text, mint_price.text, token_uri.text, metadata.text, name.text, image_uri.text, traits.text, updated_at.bigint, status.text, rarity_score.real, rarity_rank.integer, unique_attribute_count.integer, pk.integer )\nCREATE TABLE nft_collections ( blockchain.text, contract_address.text, name.text, symbol.text, deploy_block_number.bigint, deploy_block_time.bigint, erc_type.text, owner.text, traits.text, description.text, slug.text, media_info.text, image_url.text, banner_image_url.text, updated_at.bigint, banner.text, token_count.bigint, floor_price.text, floor_price_symbol.text, floor_price_contract.text, pk.integer )\nCREATE TABLE erc20_approval ( block_number.bigint, block_timestamp.timestamp, transaction_index.integer, transaction_hash.text, log_index.integer, contract_address.text, pk.integer )\nCREATE TABLE token_balances ( block_number.bigint, block_timestamp.timestamp, tick.text, wallet_address.text, total_supply.decimal, amount.decimal )\nCREATE TABLE token_info ( block_timestamp.timestamp, block_number.bigint, tx_index.integer, tx_hash.text, tick.text, max_supply.decimal, lim.decimal, wlim.decimal, dec.integer, creator.text )\nCREATE TABLE token_activities ( block_timestamp.timestamp, block_number.bigint, tx_index.integer, tx_hash.text, log_index.integer, type.text, tick.text, id.text, amt.decimal, from_address.text, to_address.text )\nCREATE TABLE mud_holesky_redstone ( address.text, table_id.text, key_bytes.text, key0.text, key1.text, static_data.text, encoded_lengths.text, dynamic_data.text, is_deleted.boolean, block_number.bigint, log_index.bigint )\nCREATE TABLE token_activities_avalanche ( block_timestamp.timestamp, block_number.bigint, tx_index.integer, tx_hash.text, log_index.integer, type.text, tick.text, id.text, amt.decimal, from_address.text, to_address.text )\nCREATE TABLE token_balances_avalanche ( block_number.bigint, block_timestamp.timestamp, tick.text, wallet_address.text, total_supply.decimal, amount.decimal )\nCREATE TABLE token_info_avalanche ( block_timestamp.timestamp, block_number.bigint, tx_index.integer, tx_hash.text, tick.text, max_supply.decimal, lim.decimal, wlim.decimal, dec.integer, creator.text, minted.decimal, holders.decimal, txs.decimal, updated_timestamp.timestamp, completed_timestamp.timestamp, id.text )\n"} {"conversations": [{"role": "user", "content": "Count the total number of invoices issued in each calendar year and month. Show the year, month, and the count, ordered chronologically."}, {"role": "assistant", "content": "SELECT EXTRACT(YEAR FROM issue_date) AS issue_year, EXTRACT(MONTH FROM issue_date) AS issue_month, COUNT(*) AS invoice_count FROM legal_services.invoices GROUP BY issue_year, issue_month ORDER BY issue_year, issue_month;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.invoices ( invoice_id.text, invoice_number.text, client_id.text, case_id.text, issue_date.date, due_date.date, total_amount.numeric, amount_paid.numeric, status.text, payment_date.timestamp, notes.text, created_at.timestamp )\n"} {"conversations": [{"role": "user", "content": "Show me assets along with their associated 'symbol' metadata value. Assume an assets table with asset_id exists."}, {"role": "assistant", "content": "SELECT a.asset_id, m.value FROM assets a JOIN metadata m ON a.asset_id = m.asset_id WHERE m.key = 'symbol'"}, {"role": "user", "content": "Now, also include the 'name' metadata value for these assets in the same result."}, {"role": "assistant", "content": "SELECT a.asset_id, m_symbol.value AS symbol, m_name.value AS name FROM assets a LEFT JOIN metadata m_symbol ON a.asset_id = m_symbol.asset_id AND m_symbol.key = 'symbol' LEFT JOIN metadata m_name ON a.asset_id = m_name.asset_id AND m_name.key = 'name'"}, {"role": "user", "content": "For assets that have both 'symbol' and 'name' metadata, list the asset ID and the count of *all* metadata entries they have."}, {"role": "assistant", "content": "SELECT a.asset_id, COUNT(m_all.metadata_id) FROM assets a JOIN metadata m_symbol ON a.asset_id = m_symbol.asset_id AND m_symbol.key = 'symbol' JOIN metadata m_name ON a.asset_id = m_name.asset_id AND m_name.key = 'name' JOIN metadata m_all ON a.asset_id = m_all.asset_id GROUP BY a.asset_id"}], "system": "You are an expert in writing database language. You can write a corresponding database language query to answer the user's question based on the table structure described by the table creation statement. \n##Table Structure\nCREATE TABLE trading_platform.utxos ( utxo_id text PRIMARY KEY, transaction_id text, output_index int, address text, amount numeric, spent boolean )\nCREATE TABLE trading_platform.dapps ( dapp_id text PRIMARY KEY, name text, description text, url text )\nCREATE TABLE trading_platform.peers ( peer_id text PRIMARY KEY, ip_address text, port int, last_seen timestamp )\nCREATE TABLE trading_platform.metadata ( metadata_id text PRIMARY KEY, asset_id text, key text, value text )\nCREATE TABLE trading_platform.notifications ( notification_id text PRIMARY KEY, user_id text, message text, sent_at timestamp, read_at timestamp )\n"} {"conversations": [{"role": "user", "content": "Show me wallet addresses that hold more than 1000 of any ERC1155 token, along with the token ID and contract address, from the nft_holders table."}, {"role": "assistant", "content": "SELECT wallet_address, token_id, contract_address FROM nft_holders WHERE contract_type = 'ERC1155' AND CAST(amount AS decimal) > 1000;"}, {"role": "user", "content": "Can you also include the name of each token from the nft_collections table?"}, {"role": "assistant", "content": "SELECT nh.wallet_address, nh.token_id, nh.contract_address, nc.name FROM nft_holders nh JOIN nft_collections nc ON nh.contract_address = nc.contract_address WHERE nh.contract_type = 'ERC1155' AND CAST(nh.amount AS decimal) > 1000;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE token_metas (\n block_timestamp timestamp(6) NOT NULL, -- Timestamp of the block when token metadata was recorded\n block_number bigint NOT NULL, -- Block number uniquely identifying the block\n transaction_hash varchar NOT NULL, -- Hash value of the transaction\n transaction_index bigint NOT NULL, -- Index of the transaction within the block\n from_address varchar NOT NULL, -- Address from which the transaction originated\n contract_address varchar NOT NULL, -- Address of the token contract\n symbol varchar NOT NULL, -- Symbol of the token\n total_supply varchar NOT NULL, -- erc20 contract total supply\n name varchar NOT NULL, -- Name of the token\n decimals bigint NOT NULL, -- Number of decimal places for the token\n is_erc20 integer NOT NULL, -- Flag indicating if the token is an ERC-20 token (0 or 1)\n is_erc721 integer NOT NULL, -- Flag indicating if the token is an ERC-721 token (0 or 1)\n is_erc1155 integer NOT NULL, -- Flag indicating if the token is an ERC-1155 token (0 or 1)\n is_proxy integer NOT NULL, -- Flag indicating if the token is a proxy (0 or 1)\n extra_info varchar NOT NULL, -- Additional information about the token\n pk integer NOT NULL -- Partition key for the table(floor(block_number / 5760))\n)\nCREATE TABLE erc20_balances ( block_number bigint NOT NULL, contract_address varchar NOT NULL, wallet_address varchar NOT NULL, amount varchar NOT NULL, pk varchar NOT NULL )\nCREATE TABLE nft_holders (\n block_number bigint NOT NULL, -- Block number containing the transaction\n contract_address varchar NOT NULL, -- Event contract address\n wallet_address varchar NOT NULL, -- The wallet address for the contract(with bloom filter)\n token_id varchar NOT NULL, -- NFT token id\n contract_type varchar NOT NULL, -- NFT contract type\n amount varchar NOT NULL, -- Number of held NFTs\n pk varchar NOT NULL -- The last string partition of the contract.\n)\nCREATE TABLE sui_coins ( object_id varchar NOT NULL, status varchar NOT NULL, coin_type varchar NOT NULL, balance varchar NOT NULL, owner varchar NOT NULL )\nCREATE TABLE sui_coins_metadata ( object_id.text, coin_type.text, status.text, decimals.bigint, description.text, icon_url.text, symbol.text, name.text )\nCREATE TABLE sui_nfts ( object_id text, status text, collection_type text, package_id text, previous_transaction text, display text, owner text, name text )\nCREATE TABLE token_prices_latest ( blockchain.text, address.text, decimals.bigint, symbol.text, price.real, timestamp.timestamp )\nCREATE TABLE mud_holesky_redstone ( address varchar, table_id varchar, key_bytes varchar, key0 varchar, key1 varchar, static_data varchar, encoded_lengths varchar, dynamic_data varchar, is_deleted boolean, block_number bigint, log_index bigint )\nCREATE TABLE token_info_bitcoin ( block_timestamp timestamp(3) NOT NULL, block_number bigint NOT NULL, tx_index integer NOT NULL, tx_hash varchar(66) NOT NULL, tick varchar(255) NOT NULL, max_supply decimal(38,0) NOT NULL, lim decimal(38,0) NOT NULL, wlim decimal(38,0) NOT NULL, dec integer NOT NULL, creator varchar(42) NOT NULL )\nCREATE TABLE token_activities_bitcoin ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash text, log_index integer, type text, tick text, id text, amt decimal, from_address text, to_address text )\nCREATE TABLE token_activities_avalanche ( block_timestamp.timestamp, block_number.bigint, tx_index.integer, tx_hash.text, log_index.integer, type.text, tick.text, id.text, amt.decimal, from_address.text, to_address.text )\nCREATE TABLE token_balances_avalanche ( block_number bigint NOT NULL, block_timestamp timestamp(3) NOT NULL, tick varchar(20) NOT NULL, wallet_address varchar(42) NOT NULL, total_supply decimal(38,0) NOT NULL, amount decimal(38,0) NOT NULL )\n"} {"conversations": [{"role": "user", "content": "Show me all properties in California with their star ratings and the total number of rooms they have, ordered by the room count in descending order."}, {"role": "assistant", "content": "SELECT p.property_id, p.property_name, p.star_rating, COUNT(r.room_id) AS room_count FROM hospitality_technology.properties p LEFT JOIN hospitality_technology.rooms r ON p.property_id = r.property_id WHERE p.state_province = 'California' GROUP BY p.property_id, p.property_name, p.star_rating ORDER BY room_count DESC;"}, {"role": "user", "content": "Now, include only properties with a star rating of 4.0 or higher and show the average base rate of their room types."}, {"role": "assistant", "content": "SELECT p.property_id, p.property_name, p.star_rating, COUNT(r.room_id) AS room_count, AVG(rt.base_rate) AS avg_base_rate FROM hospitality_technology.properties p LEFT JOIN hospitality_technology.rooms r ON p.property_id = r.property_id LEFT JOIN hospitality_technology.room_types rt ON p.property_id = rt.property_id WHERE p.state_province = 'California' AND p.star_rating >= 4.0 GROUP BY p.property_id, p.property_name, p.star_rating ORDER BY room_count DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE hospitality_technology.properties ( property_id character varying(64) NOT NULL, property_name character varying(255) NOT NULL, address_line1 character varying(255) NOT NULL, address_line2 character varying(255), city character varying(100) NOT NULL, state_province character varying(100), postal_code character varying(20) NOT NULL, country_code character varying(3) NOT NULL, phone_number character varying(30), email_address character varying(255), property_type character varying(50) NOT NULL, star_rating numeric(2,1), timezone character varying(64) NOT NULL, manager_staff_id character varying(64), created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, updated_at timestamp with time zone NOT NULL DEFAULT current_timestamp, PRIMARY KEY (property_id) )\nCREATE TABLE hospitality_technology.rooms ( room_id character varying(64) NOT NULL, property_id character varying(64) NOT NULL, room_number character varying(10) NOT NULL, room_type_id character varying(64) NOT NULL, floor integer, status character varying(50) NOT NULL, is_smoking boolean NOT NULL DEFAULT false, features text, current_condition text, last_cleaned_at timestamp with time zone, PRIMARY KEY (room_id), FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id), FOREIGN KEY (room_type_id) REFERENCES hospitality_technology.room_types(room_type_id) )\nCREATE TABLE hospitality_technology.room_types ( room_type_id character varying(64) NOT NULL, property_id character varying(64) NOT NULL, type_name character varying(100) NOT NULL, description text, base_rate numeric(10, 2) NOT NULL, max_occupancy integer NOT NULL, bed_type character varying(50), area_sqft numeric(8,2), amenities text, PRIMARY KEY (room_type_id), FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id) )\nCREATE TABLE hospitality_technology.reservations (\n reservation_id character varying(64) NOT NULL, -- unique identifier for the booking\n property_id character varying(64) NOT NULL, -- FK to properties table\n guest_id character varying(64) NOT NULL, -- FK to guests table (primary guest)\n room_id character varying(64), -- FK to rooms table (assigned room, might be null initially)\n room_type_id character varying(64) NOT NULL, -- FK to room_types table (booked room type)\n check_in_date date NOT NULL, -- scheduled check-in date\n check_out_date date NOT NULL, -- scheduled check-out date\n actual_check_in_ts timestamp with time zone, -- actual check-in time\n actual_check_out_ts timestamp with time zone, -- actual check-out time\n num_adults integer NOT NULL, -- number of adults\n num_children integer DEFAULT 0, -- number of children\n status character varying(50) NOT NULL, -- e.g., Pending, Confirmed, CheckedIn, CheckedOut, Cancelled, NoShow\n booking_source character varying(100), -- e.g., Website, OTA (Expedia, Booking.com), Phone, WalkIn\n rate_plan_id character varying(64), -- FK to rate_plans table (optional)\n total_amount numeric(12, 2), -- estimated or final total cost\n amount_paid numeric(12, 2) DEFAULT 0.00, -- amount already paid\n special_requests text, -- specific guest requests for this booking\n created_at timestamp with time zone NOT NULL DEFAULT current_timestamp,\n updated_at timestamp with time zone NOT NULL DEFAULT current_timestamp,\n PRIMARY KEY (reservation_id),\n FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id),\n FOREIGN KEY (guest_id) REFERENCES hospitality_technology.guests(guest_id),\n FOREIGN KEY (room_id) REFERENCES hospitality_technology.rooms(room_id),\n FOREIGN KEY (room_type_id) REFERENCES hospitality_technology.room_types(room_type_id)\n)\nCREATE TABLE hospitality_technology.staff ( staff_id text PRIMARY KEY, property_id text, first_name text, last_name text, position text, work_email text, work_phone text, hire_date date, termination_date date, is_active boolean, access_level int, manager_id text, created_at timestamp )\nCREATE TABLE hospitality_technology.services (\n service_id character varying(64) NOT NULL, -- unique identifier for a chargeable service\n property_id character varying(64) NOT NULL, -- FK to properties table\n service_name character varying(150) NOT NULL, -- e.g., Room Service - Burger, Spa - Massage 60min, Laundry - Shirt\n description text,\n category character varying(100), -- e.g., Food & Beverage, Wellness, Business Center, Activities\n price numeric(10, 2) NOT NULL, -- price per unit/instance\n unit character varying(30), -- e.g., Per Item, Per Hour, Per Day\n is_available boolean NOT NULL DEFAULT true, -- is the service currently offered?\n department character varying(100), -- department responsible (e.g., F&B, Spa, Housekeeping)\n PRIMARY KEY (service_id),\n FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id)\n)\nCREATE TABLE hospitality_technology.payments ( payment_id text PRIMARY KEY, reservation_id text, guest_id text, bill_id text, amount numeric, currency_code text, payment_method text, card_type text, card_last_four text, transaction_ref text, payment_timestamp timestamp, status text, staff_id_processed text, notes text )\nCREATE TABLE hospitality_technology.reviews ( review_id character varying(64) NOT NULL, property_id character varying(64) NOT NULL, reservation_id character varying(64) UNIQUE, guest_id character varying(64) NOT NULL, rating_overall integer, rating_cleanliness integer, rating_service integer, rating_location integer, rating_value integer, comment text, review_source character varying(100), review_date timestamp with time zone NOT NULL DEFAULT current_timestamp, is_public boolean DEFAULT true, staff_response text, response_staff_id character varying(64), response_date timestamp with time zone, PRIMARY KEY (review_id), FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id), FOREIGN KEY (reservation_id) REFERENCES hospitality_technology.reservations(reservation_id), FOREIGN KEY (guest_id) REFERENCES hospitality_technology.guests(guest_id), FOREIGN KEY (response_staff_id) REFERENCES hospitality_technology.staff(staff_id) )\n"} {"conversations": [{"role": "user", "content": "Show me the top 5 addresses with the highest balances, along with their public keys."}, {"role": "assistant", "content": "SELECT address_id, public_key, balance FROM blockchain.addresses ORDER BY balance DESC LIMIT 5;"}, {"role": "user", "content": "Now, filter these results to only show addresses where the public_key starts with '0x1'."}, {"role": "assistant", "content": "SELECT address_id, public_key, balance FROM blockchain.addresses WHERE public_key LIKE '0x1%' ORDER BY balance DESC LIMIT 5;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE blockchain.addresses ( address_id text PRIMARY KEY, public_key text, balance numeric )\n"} {"conversations": [{"role": "user", "content": "Retrieve all prescriptions linked to chronic diagnoses. Show prescription_id, diagnosis_id, diagnosis_code, and prescription_date."}, {"role": "assistant", "content": "SELECT pr.prescription_id,\n d.diagnosis_id,\n d.diagnosis_code,\n pr.prescription_date\nFROM healthcare.prescriptions pr\nJOIN healthcare.diagnoses d\n ON pr.record_id = d.record_id\nWHERE d.is_chronic = true;"}, {"role": "user", "content": "Include the patient's full name and the prescribing doctor's last name, and sort by prescription_date ascending."}, {"role": "assistant", "content": "SELECT pr.prescription_id,\n d.diagnosis_id,\n d.diagnosis_code,\n pr.prescription_date,\n p.first_name || ' ' || p.last_name AS patient_name,\n doc.last_name AS doctor_last_name\nFROM healthcare.prescriptions pr\nJOIN healthcare.diagnoses d\n ON pr.record_id = d.record_id\nJOIN healthcare.patients p\n ON pr.patient_id = p.patient_id\nJOIN healthcare.doctors doc\n ON pr.doctor_id = doc.doctor_id\nWHERE d.is_chronic = true\nORDER BY pr.prescription_date ASC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.patients ( patient_id.text, first_name.text, last_name.text, date_of_birth.date, gender.text, address.text, phone_number.text, email.text, emergency_contact_name.text, emergency_contact_phone.text, created_at.timestamp, updated_at.timestamp )\nCREATE TABLE healthcare.doctors (\n doctor_id character varying(64) NOT NULL, -- unique identifier for the doctor\n first_name character varying(100) NOT NULL, -- doctor's first name\n last_name character varying(100) NOT NULL, -- doctor's last name\n specialty character varying(100) NOT NULL, -- doctor's medical specialty\n license_number character varying(50) UNIQUE NOT NULL, -- doctor's medical license number\n phone_number character varying(20), -- doctor's contact phone\n email character varying(128) UNIQUE, -- doctor's contact email\n hospital_affiliation_id character varying(64), -- FK to hospitals table (optional)\n created_at timestamp with time zone NOT NULL DEFAULT current_timestamp,\n updated_at timestamp with time zone NOT NULL DEFAULT current_timestamp,\n PRIMARY KEY (doctor_id)\n)\nCREATE TABLE healthcare.appointments ( appointment_id.text, patient_id.text, doctor_id.text, appointment_time.timestamp, duration_minutes.integer, reason.text, status.text, location_id.text, notes.text, created_at.timestamp )\nCREATE TABLE healthcare.medical_records (\n record_id character varying(64) NOT NULL, -- unique identifier for the medical record entry\n patient_id character varying(64) NOT NULL, -- FK to patients table\n appointment_id character varying(64) UNIQUE, -- FK to appointments table (can be null if record not tied to specific appt)\n doctor_id character varying(64) NOT NULL, -- FK to doctors table (doctor creating the record)\n record_date timestamp with time zone NOT NULL, -- date the record/observation was made\n chief_complaint text, -- patient's primary reason for visit\n present_illness_history text, -- detailed history of the current issue\n past_medical_history text, -- relevant past conditions/surgeries\n physical_examination_notes text, -- findings from the physical exam\n assessment text, -- doctor's assessment/diagnosis summary\n treatment_plan text, -- planned course of action\n vitals jsonb, -- store vitals like BP, HR, Temp as structured JSON\n created_at timestamp with time zone NOT NULL DEFAULT current_timestamp,\n PRIMARY KEY (record_id)\n)\nCREATE TABLE healthcare.diagnoses (\n diagnosis_id character varying(64) NOT NULL, -- unique identifier for the diagnosis entry\n record_id character varying(64) NOT NULL, -- FK linking to the specific medical record entry\n patient_id character varying(64) NOT NULL, -- FK to patients table\n doctor_id character varying(64) NOT NULL, -- FK to doctors table (diagnosing doctor)\n diagnosis_code character varying(20) NOT NULL, -- standard code (e.g., ICD-10)\n code_type character varying(10) NOT NULL DEFAULT 'ICD-10', -- type of code used\n description text, -- textual description of the diagnosis\n diagnosis_date date NOT NULL, -- date the diagnosis was made\n status character varying(32) NOT NULL, -- e.g., Active, Resolved, Ruled Out\n is_chronic boolean DEFAULT false, -- flag for chronic conditions\n PRIMARY KEY (diagnosis_id)\n)\nCREATE TABLE healthcare.medications ( medication_id text, medication_name text, generic_name text, manufacturer text, ndc_code text, description text )\nCREATE TABLE healthcare.prescriptions ( prescription_id text, record_id text, patient_id text, doctor_id text, medication_id text, dosage text, frequency text, route text, start_date date, end_date date, quantity_dispensed numeric, refills_allowed integer, prescription_date timestamp )\nCREATE TABLE healthcare.insurance_plans ( plan_id text, plan_name text, insurance_provider text, plan_type text, contact_phone text, website text )\n"} {"conversations": [{"role": "user", "content": "List all depots (location type 'Depot') and the number of vehicles assigned to each. Include the depot name and city."}, {"role": "assistant", "content": "SELECT T1.name , T1.city , COUNT(T2.vehicle_id) FROM transportation.locations AS T1 LEFT JOIN transportation.vehicles AS T2 ON T1.location_id = T2.depot_id WHERE T1.type = 'Depot' GROUP BY T1.location_id , T1.name , T1.city"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.vehicles (\n vehicle_id character varying(64) NOT NULL, -- unique identifier for the vehicle\n license_plate character varying(32) NOT NULL UNIQUE, -- vehicle license plate\n vin character varying(17) UNIQUE, -- vehicle identification number\n make character varying(64) NOT NULL, -- manufacturer of the vehicle\n model character varying(64) NOT NULL, -- model of the vehicle\n year integer NOT NULL, -- manufacturing year\n type character varying(32) NOT NULL, -- type of vehicle (e.g., Bus, Train, Truck, Car, Van)\n capacity integer, -- passenger or cargo capacity\n fuel_type character varying(32) NOT NULL, -- e.g., Diesel, Gasoline, Electric, Hydrogen\n status character varying(32) NOT NULL, -- e.g., Active, Maintenance, Decommissioned\n depot_id character varying(64), -- identifier of the home depot/base\n acquisition_date date, -- date the vehicle was acquired\n PRIMARY KEY (vehicle_id)\n)\nCREATE TABLE transportation.drivers (\n driver_id character varying(64) NOT NULL, -- unique identifier for the driver\n employee_id character varying(64) NOT NULL UNIQUE, -- employee reference number\n first_name character varying(128) NOT NULL, -- driver's first name\n last_name character varying(128) NOT NULL, -- driver's last name\n license_number character varying(64) NOT NULL UNIQUE, -- driving license number\n license_expiry_date date NOT NULL, -- expiry date of the license\n contact_number character varying(32), -- phone number\n email character varying(128) UNIQUE, -- email address\n hire_date date NOT NULL, -- date the driver was hired\n status character varying(32) NOT NULL, -- e.g., Active, On Leave, Terminated\n PRIMARY KEY (driver_id)\n)\nCREATE TABLE transportation.routes (\n route_id character varying(64) NOT NULL, -- unique identifier for the route\n route_number character varying(32) NOT NULL UNIQUE, -- public-facing route number/name\n description text, -- description of the route\n origin_location_id character varying(64) NOT NULL, -- identifier of the starting location\n destination_location_id character varying(64) NOT NULL, -- identifier of the ending location\n distance_km numeric(10, 2), -- estimated distance in kilometers\n estimated_duration_minutes integer, -- estimated travel time in minutes\n type character varying(32) NOT NULL, -- e.g., City Bus, Intercity Train, Cargo Delivery\n PRIMARY KEY (route_id)\n)\nCREATE TABLE transportation.locations (\n location_id character varying(64) NOT NULL, -- unique identifier for the location\n name character varying(255) NOT NULL, -- name of the location (e.g., Central Station, Depot Alpha, Pier 7)\n type character varying(64) NOT NULL, -- e.g., Station, Stop, Depot, Port, Airport, Customer Address\n address_line1 character varying(255), -- street address\n city character varying(128), -- city name\n state_province character varying(128), -- state or province\n postal_code character varying(32), -- postal code\n country character varying(64) NOT NULL, -- country name\n latitude numeric(9, 6), -- geographic latitude\n longitude numeric(9, 6), -- geographic longitude\n timezone character varying(64), -- IANA timezone name (e.g., America/New_York)\n PRIMARY KEY (location_id)\n)\nCREATE TABLE transportation.fuel_logs (\n fuel_log_id character varying(64) NOT NULL, -- unique identifier for the fuel log entry\n vehicle_id character varying(64) NOT NULL, -- identifier of the vehicle fueled\n trip_id character varying(64), -- optional: identifier of the trip during which fueling occurred\n log_timestamp timestamp with time zone NOT NULL, -- time when fueling occurred\n fuel_type character varying(32) NOT NULL, -- type of fuel added (matches vehicle's fuel type)\n quantity numeric(10, 3) NOT NULL, -- amount of fuel added (e.g., Liters, Gallons, kWh)\n unit character varying(16) NOT NULL, -- unit of quantity (e.g., L, gal, kWh)\n cost_per_unit numeric(8, 4), -- price per unit of fuel\n total_cost numeric(10, 2) NOT NULL, -- total cost of the fuel purchase\n odometer_reading integer, -- vehicle mileage at time of fueling\n location_id character varying(64), -- identifier of the fueling station/location\n PRIMARY KEY (fuel_log_id)\n)\n"} {"conversations": [{"role": "user", "content": "Find cases where an address received tokens in one transfer and then sent tokens in another. List the receive transfer_id, the send transfer_id, the address, and both transfer values."}, {"role": "assistant", "content": "SELECT recv.transfer_id AS receive_transfer_id,\n send.transfer_id AS send_transfer_id,\n recv.to_address AS address,\n recv.value AS received_value,\n send.value AS sent_value\nFROM web3.token_transfers recv\nJOIN web3.token_transfers send\n ON recv.to_address = send.from_address;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE web3.token_transfers (\n transfer_id character varying(64) NOT NULL, -- unique identifier for the transfer\n token_id character varying(64) NOT NULL, -- identifier of the token being transferred\n from_address character varying(128) NOT NULL, -- address of the sender\n to_address character varying(128) NOT NULL, -- address of the receiver\n value numeric(38,14) NOT NULL, -- amount of tokens transferred\n transaction_id character varying(64) NOT NULL, -- identifier of the transaction containing the transfer\n log_index integer NOT NULL, -- index of the transfer log in the transaction\n PRIMARY KEY (transfer_id)\n)\n"} {"conversations": [{"role": "user", "content": "Show the number of active agents in each license state."}, {"role": "assistant", "content": "SELECT license_state,\n COUNT(*) AS active_agent_count\nFROM insurance.agents\nWHERE status = 'active'\nGROUP BY license_state;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.agents ( agent_id text PRIMARY KEY, first_name text, last_name text, agency_name text, license_number text, license_state text, contact_email text, contact_phone text, hire_date date, termination_date date, status text, commission_rate numeric, manager_id text )\n"} {"conversations": [{"role": "user", "content": "List the usernames and user IDs of all users whose bio contains the word 'developer'."}, {"role": "assistant", "content": "SELECT user_id, username\nFROM social_media.users\nWHERE bio ILIKE '%developer%';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE social_media.users (\n user_id character varying(64) NOT NULL, -- unique identifier for the user\n username character varying(50) NOT NULL UNIQUE, -- user's unique handle\n email character varying(128) NOT NULL UNIQUE, -- user's email address\n password_hash text NOT NULL, -- hashed password\n full_name character varying(100), -- user's full name\n profile_picture_url text, -- URL to the profile picture\n bio text, -- short user biography\n location character varying(100), -- user's location\n created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of account creation\n updated_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of last profile update\n is_verified boolean NOT NULL DEFAULT false, -- verification status\n PRIMARY KEY (user_id)\n)\nCREATE TABLE social_media.comments (\n comment_id character varying(64) NOT NULL, -- unique identifier for the comment\n post_id character varying(64) NOT NULL, -- identifier of the post being commented on (FK to posts.post_id)\n user_id character varying(64) NOT NULL, -- identifier of the user who made the comment (FK to users.user_id)\n parent_comment_id character varying(64), -- identifier of the parent comment if it's a reply (FK to comments.comment_id)\n content text NOT NULL, -- textual content of the comment\n created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of comment creation\n updated_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of last comment edit\n PRIMARY KEY (comment_id)\n)\nCREATE TABLE social_media.likes (\n like_id character varying(64) NOT NULL, -- unique identifier for the like\n user_id character varying(64) NOT NULL, -- identifier of the user who liked (FK to users.user_id)\n post_id character varying(64), -- identifier of the post being liked (FK to posts.post_id, nullable)\n comment_id character varying(64), -- identifier of the comment being liked (FK to comments.comment_id, nullable)\n created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of when the like occurred\n PRIMARY KEY (like_id),\n CONSTRAINT unique_user_like UNIQUE (user_id, post_id, comment_id), -- prevent duplicate likes\n CONSTRAINT check_like_target CHECK (post_id IS NOT NULL OR comment_id IS NOT NULL) -- ensure it likes something\n)\nCREATE TABLE social_media.follows (\n follow_id character varying(64) NOT NULL, -- unique identifier for the follow relationship\n follower_user_id character varying(64) NOT NULL, -- identifier of the user who is following (FK to users.user_id)\n following_user_id character varying(64) NOT NULL, -- identifier of the user being followed (FK to users.user_id)\n created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of when the follow started\n PRIMARY KEY (follow_id),\n CONSTRAINT unique_follow UNIQUE (follower_user_id, following_user_id) -- prevent duplicate follows\n)\nCREATE TABLE social_media.hashtags (\n hashtag_id character varying(64) NOT NULL, -- unique identifier for the hashtag\n tag_name character varying(100) NOT NULL UNIQUE, -- the actual hashtag text (without '#')\n created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp when the hashtag was first used\n PRIMARY KEY (hashtag_id)\n)\nCREATE TABLE social_media.conversations (\n conversation_id character varying(64) NOT NULL, -- unique identifier for the conversation\n created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp when conversation was initiated\n last_message_at timestamp, -- timestamp of the last message in the conversation\n is_group_chat boolean NOT NULL DEFAULT false, -- indicates if it's a group chat or direct message\n group_name character varying(100), -- name of the group chat (if applicable)\n PRIMARY KEY (conversation_id)\n)\nCREATE TABLE social_media.conversation_participants (\n participant_id character varying(64) NOT NULL, -- unique identifier for the participant entry\n conversation_id character varying(64) NOT NULL, -- identifier of the conversation (FK to conversations.conversation_id)\n user_id character varying(64) NOT NULL, -- identifier of the user in the conversation (FK to users.user_id)\n joined_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp when user joined the conversation\n last_read_at timestamp, -- timestamp indicating up to when the user has read messages\n PRIMARY KEY (participant_id),\n CONSTRAINT unique_user_conversation UNIQUE (conversation_id, user_id) -- prevent user being added multiple times\n)\nCREATE TABLE social_media.notifications (\n notification_id character varying(64) NOT NULL, -- unique identifier for the notification\n recipient_user_id character varying(64) NOT NULL, -- user receiving the notification (FK to users.user_id)\n sender_user_id character varying(64), -- user triggering the notification (FK to users.user_id, can be null for system notifications)\n notification_type character varying(30) NOT NULL, -- type of notification ('like', 'comment', 'follow', 'mention', 'message')\n target_entity_id character varying(64), -- ID of the related entity (post_id, comment_id, user_id, conversation_id)\n target_entity_type character varying(20), -- type of the related entity ('post', 'comment', 'user', 'conversation')\n created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp notification was created\n read_at timestamp, -- timestamp notification was marked as read\n PRIMARY KEY (notification_id)\n)\nCREATE TABLE social_media.user_settings (\n setting_id character varying(64) NOT NULL, -- unique identifier for the setting entry\n user_id character varying(64) NOT NULL UNIQUE, -- user the settings belong to (FK to users.user_id)\n theme character varying(20) DEFAULT 'light', -- UI theme ('light', 'dark')\n email_notifications_enabled boolean DEFAULT true, -- enable/disable email notifications\n push_notifications_enabled boolean DEFAULT true, -- enable/disable push notifications\n private_profile boolean DEFAULT false, -- is the user profile private\n updated_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of last setting change\n PRIMARY KEY (setting_id)\n)\n"} {"conversations": [{"role": "user", "content": "List all invoices that were paid within 7 days of their issue date. Show invoice number, issue date, payment date, and total amount."}, {"role": "assistant", "content": "SELECT invoice_number, issue_date, payment_date, total_amount FROM legal_services.invoices WHERE status = 'Paid' AND payment_date IS NOT NULL AND (payment_date::DATE - issue_date) <= 7;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.lawyers ( lawyer_id.text, first_name.text, last_name.text, bar_number.text, firm_id.text, email.text, phone.text, specialization.text, hire_date.timestamp, is_partner.boolean )\nCREATE TABLE legal_services.invoices ( invoice_id text, invoice_number text, client_id text, case_id text, issue_date date, due_date date, total_amount numeric, amount_paid numeric, status text, payment_date timestamp, notes text, created_at timestamp )\n"} {"conversations": [{"role": "user", "content": "Show me the notification ID, recipient user ID, and notification type for notifications received by users that user 'user123' is following."}, {"role": "assistant", "content": "SELECT n.notification_id, n.recipient_user_id, n.notification_type FROM social_media.notifications AS n JOIN social_media.follows AS f ON n.recipient_user_id = f.following_user_id WHERE f.follower_user_id = 'user123';"}, {"role": "user", "content": "Filter this list to only include notifications created after '2024-06-01' and also show the notification creation time."}, {"role": "assistant", "content": "SELECT n.notification_id, n.recipient_user_id, n.notification_type, n.created_at FROM social_media.notifications AS n JOIN social_media.follows AS f ON n.recipient_user_id = f.following_user_id WHERE f.follower_user_id = 'user123' AND n.created_at >= '2024-06-01';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE social_media.comments ( comment_id.text, post_id.text, user_id.text, parent_comment_id.text, content.text, created_at.timestamp, updated_at.timestamp )\nCREATE TABLE social_media.follows ( follow_id.text, follower_user_id.text, following_user_id.text, created_at.timestamp )\nCREATE TABLE social_media.conversations ( conversation_id.text, created_at.timestamp, last_message_at.timestamp, is_group_chat.boolean, group_name.text )\nCREATE TABLE social_media.notifications ( notification_id.text, recipient_user_id.text, sender_user_id.text, notification_type.text, target_entity_id.text, target_entity_type.text, created_at.timestamp, read_at.timestamp )\n"} {"conversations": [{"role": "user", "content": "List all claims and the first and last name of the agent who handled each claim."}, {"role": "assistant", "content": "SELECT T1.claim_id, T1.estimated_loss, T2.first_name, T2.last_name FROM claims AS T1 JOIN agents AS T2 ON T1.claim_handler_id = T2.agent_id"}, {"role": "user", "content": "Can you also include the policy ID and customer ID for each claim?"}, {"role": "assistant", "content": "SELECT T1.claim_id, T1.policy_id, T1.customer_id, T1.estimated_loss, T2.first_name, T2.last_name FROM claims AS T1 JOIN agents AS T2 ON T1.claim_handler_id = T2.agent_id"}, {"role": "user", "content": "Filter the results to only show claims where the status is 'Open' and the agent is currently 'active'."}, {"role": "assistant", "content": "SELECT T1.claim_id, T1.policy_id, T1.customer_id, T1.estimated_loss, T2.first_name, T2.last_name FROM claims AS T1 JOIN agents AS T2 ON T1.claim_handler_id = T2.agent_id WHERE T1.status = 'Open' AND T2.status = 'active'"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.claims ( claim_id.text, policy_id.text, customer_id.text, incident_date.timestamp, reported_date.timestamp, description.text, estimated_loss.numeric, status.text, settlement_amount.numeric, settlement_date.date, claim_handler_id.text, police_report_number.text )\nCREATE TABLE insurance.agents ( agent_id.text, first_name.text, last_name.text, agency_name.text, license_number.text, license_state.text, contact_email.text, contact_phone.text, hire_date.date, termination_date.date, status.text, commission_rate.numeric, manager_id.text )\nCREATE TABLE insurance.premium_payments ( payment_id.text, policy_id.text, customer_id.text, payment_date.timestamp, amount_paid.numeric, payment_method.text, transaction_reference.text, due_date.date, payment_period_start.date, payment_period_end.date, status.text )\nCREATE TABLE insurance.claim_documents ( document_id.text, claim_id.text, document_type.text, file_name.text, file_path.text, file_size_bytes.integer, mime_type.text, uploaded_by.text, uploaded_at.timestamp, description.text )\nCREATE TABLE insurance.policy_beneficiaries ( beneficiary_id.text, policy_id.text, customer_id.text, first_name.text, last_name.text, relationship.text, percentage_share.numeric, contact_info.text, added_at.timestamp )\n"} {"conversations": [{"role": "user", "content": "List the names of services for which documents are set to expire in the next 90 days."}, {"role": "assistant", "content": "SELECT DISTINCT T1.service_name FROM government_services.services AS T1 JOIN applications AS T2 ON T1.service_id = T2.service_id JOIN government_services.documents AS T3 ON T2.application_id = T3.application_id WHERE T3.expiry_date IS NOT NULL AND T3.expiry_date BETWEEN CURRENT_DATE AND CURRENT_DATE + INTERVAL '90 days'"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.services ( service_id text PRIMARY KEY, agency_id text, service_name text, description text, category text, eligibility_criteria text, standard_fee numeric, average_processing_time_days int, is_active boolean, online_application_url text )\nCREATE TABLE government_services.documents ( document_id text PRIMARY KEY, application_id text, citizen_id text, document_type text, file_reference text, upload_timestamp timestamp, expiry_date date, verification_status text, verified_by_employee_id text, verification_timestamp timestamp )\n"} {"conversations": [{"role": "user", "content": "Find all smart contracts where the code length is greater than 1000 characters."}, {"role": "assistant", "content": "SELECT contract_id, creator_address, timestamp FROM blockchain.smart_contracts WHERE LENGTH(code) > 1000;"}, {"role": "user", "content": "Now group these by creator_address and show the count of such contracts per creator."}, {"role": "assistant", "content": "SELECT creator_address, COUNT(*) AS long_code_contracts FROM blockchain.smart_contracts WHERE LENGTH(code) > 1000 GROUP BY creator_address;"}, {"role": "user", "content": "Can you order the results by the count in descending order?"}, {"role": "assistant", "content": "SELECT creator_address, COUNT(*) AS long_code_contracts FROM blockchain.smart_contracts WHERE LENGTH(code) > 1000 GROUP BY creator_address ORDER BY long_code_contracts DESC;"}, {"role": "user", "content": "Now show only creators who have more than 3 such contracts."}, {"role": "assistant", "content": "SELECT creator_address, COUNT(*) AS long_code_contracts FROM blockchain.smart_contracts WHERE LENGTH(code) > 1000 GROUP BY creator_address HAVING COUNT(*) > 3 ORDER BY long_code_contracts DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE blockchain.smart_contracts ( contract_id text PRIMARY KEY, creator_address text, code text, timestamp timestamp )\n"} {"conversations": [{"role": "user", "content": "For each type of entity a notification can be related to, how many notifications have been successfully sent?"}, {"role": "assistant", "content": "SELECT related_entity_type, COUNT(*) AS sent_notification_count FROM government_services.notifications WHERE status = 'Sent' GROUP BY related_entity_type;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.services ( service_id text PRIMARY KEY, agency_id text, service_name text, description text, category text, eligibility_criteria text, standard_fee numeric, average_processing_time_days int, is_active boolean, online_application_url text )\nCREATE TABLE government_services.documents (\n document_id character varying(64) NOT NULL, -- unique identifier for the document instance\n application_id character varying(64), -- FK to applications table (optional, could be linked to citizen directly)\n citizen_id character varying(64) NOT NULL, -- FK to citizens table\n document_type character varying(100) NOT NULL, -- e.g., Passport Scan, Proof of Address, Birth Certificate\n file_reference text NOT NULL, -- reference to the stored file (e.g., S3 URL, internal path)\n upload_timestamp timestamp NOT NULL,\n expiry_date date,\n verification_status character varying(30) DEFAULT 'Pending', -- e.g., Pending, Verified, Rejected\n verified_by_employee_id character varying(64), -- FK to employees table\n verification_timestamp timestamp,\n PRIMARY KEY (document_id)\n)\nCREATE TABLE government_services.payments ( payment_id text PRIMARY KEY, application_id text, citizen_id text, service_id text, amount numeric, currency text, payment_method text, payment_provider_reference text, payment_timestamp timestamp, status text, notes text )\nCREATE TABLE government_services.employees (\n employee_id character varying(64) NOT NULL, -- unique identifier for the government employee\n agency_id character varying(64) NOT NULL, -- FK to agencies table\n first_name character varying(100) NOT NULL,\n last_name character varying(100) NOT NULL,\n job_title character varying(150) NOT NULL,\n department character varying(100),\n work_email character varying(128) NOT NULL UNIQUE,\n work_phone character varying(32),\n hire_date date NOT NULL,\n termination_date date, -- null if currently employed\n access_level character varying(50), -- Role or permission level\n manager_employee_id character varying(64), -- FK to self for reporting structure\n PRIMARY KEY (employee_id)\n)\nCREATE TABLE government_services.appointments ( appointment_id character varying(64) NOT NULL, citizen_id character varying(64) NOT NULL, employee_id character varying(64), location_id character varying(64), service_id character varying(64), scheduled_start_time timestamp NOT NULL, scheduled_end_time timestamp, purpose text NOT NULL, status character varying(30) NOT NULL, booking_method character varying(50), created_at timestamp NOT NULL, notes text, PRIMARY KEY (appointment_id) )\nCREATE TABLE government_services.notifications ( notification_id character varying(64) NOT NULL, citizen_id character varying(64) NOT NULL, application_id character varying(64), message_subject character varying(255), message_body text NOT NULL, channel character varying(30) NOT NULL, sent_at timestamp NOT NULL, status character varying(30) NOT NULL, related_entity_type character varying(50), related_entity_id character varying(64), PRIMARY KEY (notification_id) )\n"} {"conversations": [{"role": "user", "content": "Show me the make and model of vehicles along with the route number and distance for all routes that are serviced by vehicles with a fuel_type of 'Electric'."}, {"role": "assistant", "content": "SELECT v.make, v.model, r.route_number, r.distance_km\nFROM transportation.vehicles v\nJOIN transportation.routes r ON v.vehicle_id = r.route_id\nWHERE v.fuel_type = 'Electric';"}, {"role": "user", "content": "Oops, I want to include the estimated duration for each route as well, and only show routes where the estimated duration is less than 90 minutes."}, {"role": "assistant", "content": "SELECT v.make, v.model, r.route_number, r.distance_km, r.estimated_duration_minutes\nFROM transportation.vehicles v\nJOIN transportation.routes r ON v.vehicle_id = r.route_id\nWHERE v.fuel_type = 'Electric' AND r.estimated_duration_minutes < 90;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.vehicles ( vehicle_id text, license_plate text, vin text, make text, model text, year integer, type text, capacity integer, fuel_type text, status text, depot_id text, acquisition_date date )\nCREATE TABLE transportation.drivers (\n driver_id character varying(64) NOT NULL, -- unique identifier for the driver\n employee_id character varying(64) NOT NULL UNIQUE, -- employee reference number\n first_name character varying(128) NOT NULL, -- driver's first name\n last_name character varying(128) NOT NULL, -- driver's last name\n license_number character varying(64) NOT NULL UNIQUE, -- driving license number\n license_expiry_date date NOT NULL, -- expiry date of the license\n contact_number character varying(32), -- phone number\n email character varying(128) UNIQUE, -- email address\n hire_date date NOT NULL, -- date the driver was hired\n status character varying(32) NOT NULL, -- e.g., Active, On Leave, Terminated\n PRIMARY KEY (driver_id)\n)\nCREATE TABLE transportation.routes ( route_id text PRIMARY KEY, route_number text, description text, origin_location_id text, destination_location_id text, distance_km numeric, estimated_duration_minutes int, type text )\nCREATE TABLE transportation.maintenance_logs ( log_id.text, vehicle_id.text, service_date.date, odometer_reading.integer, service_type.text, description.text, cost.numeric, mechanic_name.text, next_service_due_date.date )\nCREATE TABLE transportation.fuel_logs ( fuel_log_id text, vehicle_id text, trip_id text, log_timestamp timestamp, fuel_type text, quantity numeric, unit text, cost_per_unit numeric, total_cost numeric, odometer_reading integer, location_id text )\n"} {"conversations": [{"role": "user", "content": "For each group chat, can you show me each participant's username and the date they joined the chat?"}, {"role": "assistant", "content": "SELECT u.username, c.group_name, cp.joined_at\nFROM social_media.conversation_participants cp\nJOIN social_media.users u ON cp.user_id = u.user_id\nJOIN social_media.conversations c ON cp.conversation_id = c.conversation_id\nWHERE c.is_group_chat = true;"}, {"role": "user", "content": "Can you also include the total number of participants for each group chat in the result?"}, {"role": "assistant", "content": "SELECT u.username, c.group_name, cp.joined_at, COUNT(cp2.participant_id) AS total_participants\nFROM social_media.conversation_participants cp\nJOIN social_media.users u ON cp.user_id = u.user_id\nJOIN social_media.conversations c ON cp.conversation_id = c.conversation_id\nJOIN social_media.conversation_participants cp2 ON cp2.conversation_id = cp.conversation_id\nWHERE c.is_group_chat = true\nGROUP BY u.username, c.group_name, cp.joined_at;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE social_media.users ( user_id text, username text, email text, password_hash text, full_name text, profile_picture_url text, bio text, location text, created_at timestamp, updated_at timestamp, is_verified boolean )\nCREATE TABLE social_media.posts ( post_id text, user_id text, content text, media_url text, media_type text, created_at timestamp, updated_at timestamp, visibility text, location_lat numeric, location_lon numeric )\nCREATE TABLE social_media.comments ( comment_id text, post_id text, user_id text, parent_comment_id text, content text, created_at timestamp, updated_at timestamp )\nCREATE TABLE social_media.follows ( follow_id text, follower_user_id text, following_user_id text, created_at timestamp )\nCREATE TABLE social_media.post_hashtags ( post_hashtag_id text, post_id text, hashtag_id text )\nCREATE TABLE social_media.messages ( message_id text, conversation_id text, sender_user_id text, content text, media_url text, media_type text, sent_at timestamp, read_at timestamp )\nCREATE TABLE social_media.conversation_participants ( participant_id text, conversation_id text, user_id text, joined_at timestamp, last_read_at timestamp )\nCREATE TABLE social_media.notifications ( notification_id text, recipient_user_id text, sender_user_id text, notification_type text, target_entity_id text, target_entity_type text, created_at timestamp, read_at timestamp )\nCREATE TABLE social_media.user_settings ( setting_id text, user_id text, theme text, email_notifications_enabled boolean, push_notifications_enabled boolean, private_profile boolean, updated_at timestamp )\n"} {"conversations": [{"role": "user", "content": "Return the number of top-level comments and the number of replies in the comments table."}, {"role": "assistant", "content": "SELECT\n SUM(CASE WHEN parent_comment_id IS NULL THEN 1 ELSE 0 END) AS top_level_comments,\n SUM(CASE WHEN parent_comment_id IS NOT NULL THEN 1 ELSE 0 END) AS reply_comments\nFROM social_media.comments;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE social_media.users ( user_id text, username text, email text, password_hash text, full_name text, profile_picture_url text, bio text, location text, created_at timestamp, updated_at timestamp, is_verified boolean )\nCREATE TABLE social_media.posts ( post_id text, user_id text, content text, media_url text, media_type text, created_at timestamp, updated_at timestamp, visibility text, location_lat numeric, location_lon numeric )\nCREATE TABLE social_media.comments ( comment_id text, post_id text, user_id text, parent_comment_id text, content text, created_at timestamp, updated_at timestamp )\nCREATE TABLE social_media.follows ( follow_id text, follower_user_id text, following_user_id text, created_at timestamp )\nCREATE TABLE social_media.post_hashtags ( post_hashtag_id text, post_id text, hashtag_id text )\nCREATE TABLE social_media.conversations ( conversation_id text, created_at timestamp, last_message_at timestamp, is_group_chat boolean, group_name text )\nCREATE TABLE social_media.notifications ( notification_id text, recipient_user_id text, sender_user_id text, notification_type text, target_entity_id text, target_entity_type text, created_at timestamp, read_at timestamp )\n"} {"conversations": [{"role": "user", "content": "What is the reason behind the cost variation for maintenance of asset_id 'ASSET456' over the past year?"}, {"role": "assistant", "content": "I'm sorry, but I can't provide information on the reasons behind cost variations for maintenance. The data in the maintenance_records table includes only the cost amount and other basic details of each maintenance record, but it does not contain explanations or factors influencing cost changes."}], "system": "You are an SQL statement expert and you can refuse the user's question if the question is not related to the table structure. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE train_station_management.maintenance_records ( record_id character varying(64) NOT NULL, asset_id character varying(64) NOT NULL, asset_type character varying(32) NOT NULL, maintenance_type character varying(128) NOT NULL, staff_id character varying(64), start_datetime timestamp NOT NULL, end_datetime timestamp, description text NOT NULL, cost numeric(12, 2), status character varying(32) NOT NULL DEFAULT 'Completed', PRIMARY KEY (record_id), FOREIGN KEY (staff_id) REFERENCES train_station_management.staff(staff_id) )\n"} {"conversations": [{"role": "user", "content": "Show me all events emitted by contracts where the event name contains 'Approval', along with the contract ID and transaction ID, sorted by emitted timestamp in descending order."}, {"role": "assistant", "content": "SELECT event_id, contract_id, event_name, transaction_id, emitted_at FROM web3.events WHERE event_name LIKE '%Approval%' ORDER BY emitted_at DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE web3.events (\n event_id character varying(64) NOT NULL, -- unique identifier for the event\n contract_id character varying(64) NOT NULL, -- identifier of the contract emitting the event\n event_name character varying(128) NOT NULL, -- name of the event\n data text NOT NULL, -- data payload of the event\n emitted_at timestamp NOT NULL, -- time when the event was emitted\n transaction_id character varying(64) NOT NULL, -- identifier of the transaction that triggered the event\n log_index integer NOT NULL, -- index of the event log in the transaction\n PRIMARY KEY (event_id)\n)\n"} {"conversations": [{"role": "user", "content": "How many documents were uploaded in the year 2023?"}, {"role": "assistant", "content": "SELECT count(*) FROM government_services.documents WHERE date_part('year', upload_timestamp) = 2023;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.documents ( document_id character varying(64) NOT NULL, application_id character varying(64), citizen_id character varying(64) NOT NULL, document_type character varying(100) NOT NULL, file_reference text NOT NULL, upload_timestamp timestamp NOT NULL, expiry_date date, verification_status character varying(30) DEFAULT 'Pending', verified_by_employee_id character varying(64), verification_timestamp timestamp, PRIMARY KEY (document_id) )\n"} {"conversations": [{"role": "user", "content": "What are the fuel consumption rates per hour for the Boeing 747-8 model?"}, {"role": "assistant", "content": "I'm sorry, but I can't provide information on the fuel consumption rates for the Boeing 747-8 model as this data is not included in the aircraft_models table. The table contains details such as model name, manufacturer, passenger capacity, and other specifications, but fuel consumption data is not available. If you have another question or need assistance with something else related to the table, I'm happy to help."}], "system": "You are an SQL statement expert and you can refuse the user's question if the question is not related to the table structure. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE manufacturing.aircraft_models ( model_id.text, model_name.text, manufacturer.text, passenger_capacity.integer, max_range_km.integer, engine_type.text, wingspan_m.numeric, status.text, first_flight_date.date )\n"} {"conversations": [{"role": "user", "content": "List all pairs of locations that are in the same city. Include their names and the city they are in."}, {"role": "assistant", "content": "SELECT\n l1.name AS location1_name,\n l2.name AS location2_name,\n l1.city\nFROM transportation.locations AS l1\nJOIN transportation.locations AS l2\n ON l1.city = l2.city AND l1.location_id < l2.location_id;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.locations ( location_id.text, name.text, type.text, address_line1.text, city.text, state_province.text, postal_code.text, country.text, latitude.numeric, longitude.numeric, timezone.text )\n"} {"conversations": [{"role": "user", "content": "Find currently employed employees whose direct manager has been terminated. Display the employee's full name, hire date, manager's full name, and manager's termination date."}, {"role": "assistant", "content": "SELECT e.employee_id,\n CONCAT(e.first_name, ' ', e.last_name) AS employee_full_name,\n e.hire_date,\n CONCAT(m.first_name, ' ', m.last_name) AS manager_full_name,\n m.termination_date\nFROM government_services.employees e\nJOIN government_services.employees m ON e.manager_employee_id = m.employee_id\nWHERE e.termination_date IS NULL\n AND m.termination_date IS NOT NULL;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.citizens ( citizen_id text, national_id_number text, first_name text, last_name text, date_of_birth date, gender text, primary_address text, contact_email text, contact_phone text, registration_date timestamp, is_verified boolean )\nCREATE TABLE government_services.agencies ( agency_id character varying(64) NOT NULL, agency_name character varying(255) NOT NULL, jurisdiction_level character varying(50) NOT NULL, primary_contact_email character varying(128), main_phone_number character varying(32), website_url character varying(255), established_date date, parent_agency_id character varying(64), PRIMARY KEY (agency_id) )\nCREATE TABLE government_services.payments ( payment_id text PRIMARY KEY, application_id text, citizen_id text, service_id text, amount numeric, currency text, payment_method text, payment_provider_reference text, payment_timestamp timestamp, status text, notes text )\nCREATE TABLE government_services.employees (\n employee_id character varying(64) NOT NULL, -- unique identifier for the government employee\n agency_id character varying(64) NOT NULL, -- FK to agencies table\n first_name character varying(100) NOT NULL,\n last_name character varying(100) NOT NULL,\n job_title character varying(150) NOT NULL,\n department character varying(100),\n work_email character varying(128) NOT NULL UNIQUE,\n work_phone character varying(32),\n hire_date date NOT NULL,\n termination_date date, -- null if currently employed\n access_level character varying(50), -- Role or permission level\n manager_employee_id character varying(64), -- FK to self for reporting structure\n PRIMARY KEY (employee_id)\n)\nCREATE TABLE government_services.service_locations ( location_id text PRIMARY KEY, agency_id text, location_name text, address text, city text, state text, postal_code text, latitude numeric, longitude numeric, operating_hours text, contact_phone text, is_accessible boolean )\nCREATE TABLE government_services.appointments ( appointment_id character varying(64) NOT NULL, citizen_id character varying(64) NOT NULL, employee_id character varying(64), location_id character varying(64), service_id character varying(64), scheduled_start_time timestamp NOT NULL, scheduled_end_time timestamp, purpose text NOT NULL, status character varying(30) NOT NULL, booking_method character varying(50), created_at timestamp NOT NULL, notes text, PRIMARY KEY (appointment_id) )\nCREATE TABLE government_services.notifications ( notification_id character varying(64) NOT NULL, citizen_id character varying(64) NOT NULL, application_id character varying(64), message_subject character varying(255), message_body text NOT NULL, channel character varying(30) NOT NULL, sent_at timestamp NOT NULL, status character varying(30) NOT NULL, related_entity_type character varying(50), related_entity_id character varying(64), PRIMARY KEY (notification_id) )\n"} {"conversations": [{"role": "user", "content": "List the first and last name of each citizen along with the city and state of the service location for their agency."}, {"role": "assistant", "content": "SELECT c.first_name, c.last_name, sl.city, sl.state\nFROM government_services.citizens c\nJOIN government_services.payments p ON c.citizen_id = p.citizen_id\nJOIN government_services.employees e ON p.application_id IS NOT NULL AND e.agency_id IS NOT NULL\nJOIN government_services.service_locations sl ON e.agency_id = sl.agency_id;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.citizens ( citizen_id text, national_id_number text, first_name text, last_name text, date_of_birth date, gender text, primary_address text, contact_email text, contact_phone text, registration_date timestamp, is_verified boolean )\nCREATE TABLE government_services.payments ( payment_id text, application_id text, citizen_id text, service_id text, amount numeric, currency text, payment_method text, payment_provider_reference text, payment_timestamp timestamp, status text, notes text )\nCREATE TABLE government_services.employees ( employee_id text, agency_id text, first_name text, last_name text, job_title text, department text, work_email text, work_phone text, hire_date date, termination_date date, access_level text, manager_employee_id text )\nCREATE TABLE government_services.service_locations ( location_id text, agency_id text, location_name text, address text, city text, state text, postal_code text, latitude numeric, longitude numeric, operating_hours text, contact_phone text, is_accessible boolean )\n"} {"conversations": [{"role": "user", "content": "Show me all properties in California with a star rating above 4.0, along with their room types and base rates."}, {"role": "assistant", "content": "SELECT p.property_name, p.star_rating, rt.type_name, rt.base_rate FROM hospitality_technology.properties p JOIN hospitality_technology.room_types rt ON p.property_id = rt.property_id WHERE p.state_province = 'California' AND p.star_rating > 4.0;"}, {"role": "user", "content": "Now, filter the results to only include room types with a max occupancy of at least 4 people."}, {"role": "assistant", "content": "SELECT p.property_name, p.star_rating, rt.type_name, rt.base_rate FROM hospitality_technology.properties p JOIN hospitality_technology.room_types rt ON p.property_id = rt.property_id WHERE p.state_province = 'California' AND p.star_rating > 4.0 AND rt.max_occupancy >= 4;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE hospitality_technology.properties ( property_id.text, property_name.text, address_line1.text, address_line2.text, city.text, state_province.text, postal_code.text, country_code.text, phone_number.text, email_address.text, property_type.text, star_rating.numeric, timezone.text, manager_staff_id.text, created_at.timestamp, updated_at.timestamp )\nCREATE TABLE hospitality_technology.room_types ( room_type_id character varying(64) NOT NULL, property_id character varying(64) NOT NULL, type_name character varying(100) NOT NULL, description text, base_rate numeric(10, 2) NOT NULL, max_occupancy integer NOT NULL, bed_type character varying(50), area_sqft numeric(8,2), amenities text, PRIMARY KEY (room_type_id), FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id) )\nCREATE TABLE hospitality_technology.staff (\n staff_id character varying(64) NOT NULL, -- unique identifier for the staff member\n property_id character varying(64) NOT NULL, -- FK to properties table (primary property)\n first_name character varying(100) NOT NULL,\n last_name character varying(100) NOT NULL,\n position character varying(100) NOT NULL, -- e.g., Front Desk Agent, Housekeeper, Manager, Concierge\n work_email character varying(255) UNIQUE, -- staff member's work email\n work_phone character varying(30),\n hire_date date NOT NULL,\n termination_date date, -- date employment ended (if applicable)\n is_active boolean NOT NULL DEFAULT true, -- currently employed flag\n access_level integer NOT NULL, -- permission level within systems (e.g., 1=basic, 5=admin)\n manager_id character varying(64), -- FK to staff table (self-referencing for supervisor)\n created_at timestamp with time zone NOT NULL DEFAULT current_timestamp,\n PRIMARY KEY (staff_id),\n FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id),\n FOREIGN KEY (manager_id) REFERENCES hospitality_technology.staff(staff_id)\n)\nCREATE TABLE hospitality_technology.services ( service_id text PRIMARY KEY, property_id text, service_name text, description text, category text, price numeric, unit text, is_available boolean, department text )\nCREATE TABLE hospitality_technology.service_orders ( order_id character varying(64) NOT NULL, reservation_id character varying(64), guest_id character varying(64) NOT NULL, service_id character varying(64) NOT NULL, staff_id_ordered character varying(64), staff_id_delivered character varying(64), order_timestamp timestamp with time zone NOT NULL DEFAULT current_timestamp, delivery_timestamp timestamp with time zone, quantity integer NOT NULL DEFAULT 1, unit_price numeric(10, 2) NOT NULL, total_price numeric(12, 2) NOT NULL, status character varying(50) NOT NULL, notes text, bill_id character varying(64), PRIMARY KEY (order_id), FOREIGN KEY (reservation_id) REFERENCES hospitality_technology.reservations(reservation_id), FOREIGN KEY (guest_id) REFERENCES hospitality_technology.guests(guest_id), FOREIGN KEY (service_id) REFERENCES hospitality_technology.services(service_id), FOREIGN KEY (staff_id_ordered) REFERENCES hospitality_technology.staff(staff_id), FOREIGN KEY (staff_id_delivered) REFERENCES hospitality_technology.staff(staff_id) )\nCREATE TABLE hospitality_technology.payments ( payment_id text, reservation_id text, guest_id text, bill_id text, amount numeric, currency_code text, payment_method text, card_type text, card_last_four text, transaction_ref text, payment_timestamp timestamp, status text, staff_id_processed text, notes text )\n"} {"conversations": [{"role": "user", "content": "For each route that originates from a location of type 'Port', list the route number, the name of the origin location, and the total distance accumulated from all completed trips on this route."}, {"role": "assistant", "content": "SELECT\n r.route_number,\n l_origin.name AS origin_location_name,\n SUM(t.distance_km) AS total_accumulated_distance\nFROM transportation.routes AS r\nJOIN transportation.locations AS l_origin\n ON r.origin_location_id = l_origin.location_id\nJOIN transportation.trips AS t\n ON r.route_id = t.route_id\nWHERE\n l_origin.type = 'Port' AND t.status = 'Completed'\nGROUP BY\n r.route_id,\n r.route_number,\n l_origin.name;"}, {"role": "user", "content": "Now, only include routes where the accumulated distance is greater than 5000 kilometers and order the results by accumulated distance descending."}, {"role": "assistant", "content": "SELECT\n r.route_number,\n l_origin.name AS origin_location_name,\n SUM(t.distance_km) AS total_accumulated_distance\nFROM transportation.routes AS r\nJOIN transportation.locations AS l_origin\n ON r.origin_location_id = l_origin.location_id\nJOIN transportation.trips AS t\n ON r.route_id = t.route_id\nWHERE\n l_origin.type = 'Port' AND t.status = 'Completed'\nGROUP BY\n r.route_id,\n r.route_number,\n l_origin.name\nHAVING\n SUM(t.distance_km) > 5000\nORDER BY\n total_accumulated_distance DESC;"}, {"role": "user", "content": "Also include the number of completed trips for each of these routes and filter further to only show routes that have had more than 5 completed trips."}, {"role": "assistant", "content": "SELECT\n r.route_number,\n l_origin.name AS origin_location_name,\n SUM(t.distance_km) AS total_accumulated_distance,\n COUNT(t.trip_id) AS completed_trip_count\nFROM transportation.routes AS r\nJOIN transportation.locations AS l_origin\n ON r.origin_location_id = l_origin.location_id\nJOIN transportation.trips AS t\n ON r.route_id = t.route_id\nWHERE\n l_origin.type = 'Port' AND t.status = 'Completed'\nGROUP BY\n r.route_id,\n r.route_number,\n l_origin.name\nHAVING\n SUM(t.distance_km) > 5000 AND COUNT(t.trip_id) > 5\nORDER BY\n total_accumulated_distance DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.vehicles ( vehicle_id text PRIMARY KEY, license_plate text, vin text, make text, model text, year int, type text, capacity int, fuel_type text, status text, depot_id text, acquisition_date date )\nCREATE TABLE transportation.drivers ( driver_id text PRIMARY KEY, employee_id text, first_name text, last_name text, license_number text, license_expiry_date date, contact_number text, email text, hire_date date, status text )\nCREATE TABLE transportation.routes ( route_id text PRIMARY KEY, route_number text, description text, origin_location_id text, destination_location_id text, distance_km numeric, estimated_duration_minutes int, type text )\nCREATE TABLE transportation.trips ( trip_id text PRIMARY KEY, route_id text, vehicle_id text, driver_id text, scheduled_departure timestamp, actual_departure timestamp, scheduled_arrival timestamp, actual_arrival timestamp, origin_location_id text, destination_location_id text, status text, passenger_count int, cargo_manifest_id text )\nCREATE TABLE transportation.locations ( location_id text PRIMARY KEY, name text, type text, address_line1 text, city text, state_province text, postal_code text, country text, latitude numeric, longitude numeric, timezone text )\nCREATE TABLE transportation.maintenance_logs ( log_id text PRIMARY KEY, vehicle_id text, service_date date, odometer_reading int, service_type text, description text, cost numeric, mechanic_name text, next_service_due_date date )\nCREATE TABLE transportation.bookings ( booking_id text PRIMARY KEY, passenger_id text, trip_id text, seat_number text, booking_time timestamp, status text, fare numeric, payment_transaction_id text, special_requests text )\n"} {"conversations": [{"role": "user", "content": "List all agencies that do not have a website URL specified. Return their agency_id, agency_name, and main_phone_number."}, {"role": "assistant", "content": "SELECT agency_id, agency_name, main_phone_number FROM government_services.agencies WHERE website_url IS NULL OR website_url = '';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.agencies ( agency_id character varying(64) NOT NULL, agency_name character varying(255) NOT NULL, jurisdiction_level character varying(50) NOT NULL, primary_contact_email character varying(128), main_phone_number character varying(32), website_url character varying(255), established_date date, parent_agency_id character varying(64), PRIMARY KEY (agency_id) )\n"} {"conversations": [{"role": "user", "content": "List each employee's first and last name along with the count of active services offered by their agency."}, {"role": "assistant", "content": "SELECT e.first_name, e.last_name, COUNT(s.service_id) AS active_service_count\nFROM government_services.employees e\nJOIN government_services.services s ON e.agency_id = s.agency_id AND s.is_active = TRUE\nGROUP BY e.employee_id, e.first_name, e.last_name;"}, {"role": "user", "content": "Actually, only include employees whose service count is greater than 5."}, {"role": "assistant", "content": "SELECT e.first_name, e.last_name, COUNT(s.service_id) AS active_service_count\nFROM government_services.employees e\nJOIN government_services.services s ON e.agency_id = s.agency_id AND s.is_active = TRUE\nGROUP BY e.employee_id, e.first_name, e.last_name\nHAVING COUNT(s.service_id) > 5;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.citizens ( citizen_id character varying(64) NOT NULL, national_id_number character varying(128) NOT NULL UNIQUE, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, date_of_birth date NOT NULL, gender character varying(20), primary_address text NOT NULL, contact_email character varying(128) UNIQUE, contact_phone character varying(32), registration_date timestamp NOT NULL, is_verified boolean DEFAULT false, PRIMARY KEY (citizen_id) )\nCREATE TABLE government_services.agencies ( agency_id character varying(64) NOT NULL, agency_name character varying(255) NOT NULL, jurisdiction_level character varying(50) NOT NULL, primary_contact_email character varying(128), main_phone_number character varying(32), website_url character varying(255), established_date date, parent_agency_id character varying(64), PRIMARY KEY (agency_id) )\nCREATE TABLE government_services.services ( service_id character varying(64) NOT NULL, agency_id character varying(64) NOT NULL, service_name character varying(255) NOT NULL, description text, category character varying(100), eligibility_criteria text, standard_fee numeric(10, 2) DEFAULT 0.00, average_processing_time_days integer, is_active boolean DEFAULT true, online_application_url character varying(255), PRIMARY KEY (service_id) )\nCREATE TABLE government_services.applications ( application_id character varying(64) NOT NULL, citizen_id character varying(64) NOT NULL, service_id character varying(64) NOT NULL, submitted_at timestamp NOT NULL, status character varying(50) NOT NULL, last_updated_at timestamp NOT NULL, assigned_employee_id character varying(64), decision_date date, notes text, reference_number character varying(100) UNIQUE, PRIMARY KEY (application_id) )\nCREATE TABLE government_services.payments ( payment_id character varying(64) NOT NULL, application_id character varying(64), citizen_id character varying(64) NOT NULL, service_id character varying(64), amount numeric(12, 2) NOT NULL, currency character varying(3) NOT NULL DEFAULT 'USD', payment_method character varying(50), payment_provider_reference character varying(128), payment_timestamp timestamp NOT NULL, status character varying(30) NOT NULL, notes text, PRIMARY KEY (payment_id) )\nCREATE TABLE government_services.employees ( employee_id character varying(64) NOT NULL, agency_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, job_title character varying(150) NOT NULL, department character varying(100), work_email character varying(128) NOT NULL UNIQUE, work_phone character varying(32), hire_date date NOT NULL, termination_date date, access_level character varying(50), manager_employee_id character varying(64), PRIMARY KEY (employee_id) )\nCREATE TABLE government_services.service_locations ( location_id character varying(64) NOT NULL, agency_id character varying(64) NOT NULL, location_name character varying(200), address text NOT NULL, city character varying(100), state character varying(50), postal_code character varying(20), latitude numeric(9, 6), longitude numeric(9, 6), operating_hours text, contact_phone character varying(32), is_accessible boolean, PRIMARY KEY (location_id) )\nCREATE TABLE government_services.appointments ( appointment_id character varying(64) NOT NULL, citizen_id character varying(64) NOT NULL, employee_id character varying(64), location_id character varying(64), service_id character varying(64), scheduled_start_time timestamp NOT NULL, scheduled_end_time timestamp, purpose text NOT NULL, status character varying(30) NOT NULL, booking_method character varying(50), created_at timestamp NOT NULL, notes text, PRIMARY KEY (appointment_id) )\nCREATE TABLE government_services.notifications ( notification_id character varying(64) NOT NULL, citizen_id character varying(64) NOT NULL, application_id character varying(64), message_subject character varying(255), message_body text NOT NULL, channel character varying(30) NOT NULL, sent_at timestamp NOT NULL, status character varying(30) NOT NULL, related_entity_type character varying(50), related_entity_id character varying(64), PRIMARY KEY (notification_id) )\n"} {"conversations": [{"role": "user", "content": "Show each citizen's first and last notification IDs based on sent_at."}, {"role": "assistant", "content": "WITH bounds AS (\n SELECT citizen_id,\n MIN(sent_at) AS first_sent,\n MAX(sent_at) AS last_sent\n FROM government_services.notifications\n GROUP BY citizen_id\n)\nSELECT n1.citizen_id,\n n1.notification_id AS first_notification_id,\n n2.notification_id AS last_notification_id\nFROM bounds b\nJOIN government_services.notifications n1\n ON n1.citizen_id = b.citizen_id\n AND n1.sent_at = b.first_sent\nJOIN government_services.notifications n2\n ON n2.citizen_id = b.citizen_id\n AND n2.sent_at = b.last_sent;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.notifications ( notification_id text PRIMARY KEY, citizen_id text, application_id text, message_subject text, message_body text, channel text, sent_at timestamp, status text, related_entity_type text, related_entity_id text )\n"} {"conversations": [{"role": "user", "content": "List all applications that have at least one document with a verification status of 'Verified'. Show the application reference number and the name of the service associated with the application."}, {"role": "assistant", "content": "SELECT\n T1.reference_number,\n T2.service_name\nFROM government_services.applications AS T1\nINNER JOIN government_services.services AS T2\n ON T1.service_id = T2.service_id\nWHERE EXISTS (\n SELECT\n 1\n FROM government_services.documents AS T3\n WHERE\n T3.application_id = T1.application_id AND T3.verification_status = 'Verified'\n);"}, {"role": "user", "content": "Now, only include applications that were submitted in the year 2024."}, {"role": "assistant", "content": "SELECT\n T1.reference_number,\n T2.service_name\nFROM government_services.applications AS T1\nINNER JOIN government_services.services AS T2\n ON T1.service_id = T2.service_id\nWHERE EXISTS (\n SELECT\n 1\n FROM government_services.documents AS T3\n WHERE\n T3.application_id = T1.application_id AND T3.verification_status = 'Verified'\n)\nAND EXTRACT(YEAR FROM T1.submitted_at) = 2024;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.citizens (\n citizen_id character varying(64) NOT NULL, -- unique identifier for the citizen\n national_id_number character varying(128) NOT NULL UNIQUE, -- official national identification number\n first_name character varying(100) NOT NULL,\n last_name character varying(100) NOT NULL,\n date_of_birth date NOT NULL,\n gender character varying(20),\n primary_address text NOT NULL, -- full primary residential address\n contact_email character varying(128) UNIQUE,\n contact_phone character varying(32),\n registration_date timestamp NOT NULL, -- when the citizen profile was created\n is_verified boolean DEFAULT false, -- whether identity has been officially verified\n PRIMARY KEY (citizen_id)\n)\nCREATE TABLE government_services.agencies (\n agency_id character varying(64) NOT NULL, -- unique identifier for the agency\n agency_name character varying(255) NOT NULL, -- full name of the government agency\n jurisdiction_level character varying(50) NOT NULL, -- e.g., Federal, State, County, City\n primary_contact_email character varying(128),\n main_phone_number character varying(32),\n website_url character varying(255),\n established_date date,\n parent_agency_id character varying(64), -- FK to self for hierarchical structure\n PRIMARY KEY (agency_id)\n)\nCREATE TABLE government_services.services (\n service_id character varying(64) NOT NULL, -- unique identifier for the service\n agency_id character varying(64) NOT NULL, -- FK to agencies table\n service_name character varying(255) NOT NULL, -- name of the service (e.g., Driver's License Renewal)\n description text,\n category character varying(100), -- e.g., Licensing, Benefits, Taxation, Permits\n eligibility_criteria text, -- description of who is eligible\n standard_fee numeric(10, 2) DEFAULT 0.00, -- typical fee for the service\n average_processing_time_days integer, -- estimated processing time\n is_active boolean DEFAULT true, -- whether the service is currently offered\n online_application_url character varying(255),\n PRIMARY KEY (service_id)\n)\nCREATE TABLE government_services.documents (\n document_id character varying(64) NOT NULL, -- unique identifier for the document instance\n application_id character varying(64), -- FK to applications table (optional, could be linked to citizen directly)\n citizen_id character varying(64) NOT NULL, -- FK to citizens table\n document_type character varying(100) NOT NULL, -- e.g., Passport Scan, Proof of Address, Birth Certificate\n file_reference text NOT NULL, -- reference to the stored file (e.g., S3 URL, internal path)\n upload_timestamp timestamp NOT NULL,\n expiry_date date,\n verification_status character varying(30) DEFAULT 'Pending', -- e.g., Pending, Verified, Rejected\n verified_by_employee_id character varying(64), -- FK to employees table\n verification_timestamp timestamp,\n PRIMARY KEY (document_id)\n)\nCREATE TABLE government_services.appointments (\n appointment_id character varying(64) NOT NULL, -- unique identifier for the appointment\n citizen_id character varying(64) NOT NULL, -- FK to citizens table\n employee_id character varying(64), -- FK to employees table (optional, if assigned)\n location_id character varying(64), -- FK to service_locations table (if physical)\n service_id character varying(64), -- FK to services table (optional, if related to specific service)\n scheduled_start_time timestamp NOT NULL,\n scheduled_end_time timestamp,\n purpose text NOT NULL, -- reason for the appointment\n status character varying(30) NOT NULL, -- e.g., Scheduled, Completed, Cancelled, No-Show\n booking_method character varying(50), -- e.g., Online, Phone, In-Person\n created_at timestamp NOT NULL, -- when the appointment was booked\n notes text,\n PRIMARY KEY (appointment_id)\n)\nCREATE TABLE government_services.notifications (\n notification_id character varying(64) NOT NULL, -- unique identifier for the notification\n citizen_id character varying(64) NOT NULL, -- FK to citizens table\n application_id character varying(64), -- FK to applications table (optional)\n message_subject character varying(255),\n message_body text NOT NULL,\n channel character varying(30) NOT NULL, -- e.g., Email, SMS, Portal Message, Mail\n sent_at timestamp NOT NULL,\n status character varying(30) NOT NULL, -- e.g., Queued, Sent, Delivered, Failed, Read\n related_entity_type character varying(50), -- e.g., Application, Appointment, Document Request\n related_entity_id character varying(64), -- ID of the related entity\n PRIMARY KEY (notification_id)\n)\n"} {"conversations": [{"role": "user", "content": "Show the full names and contact emails of all citizens who have made a payment for an application that is currently in 'Pending' status."}, {"role": "assistant", "content": "SELECT DISTINCT c.first_name || ' ' || c.last_name AS full_name, c.contact_email\nFROM government_services.citizens c\nJOIN government_services.payments p ON c.citizen_id = p.citizen_id\nJOIN government_services.applications a ON p.application_id = a.application_id\nWHERE a.status = 'Pending';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.citizens ( citizen_id text PRIMARY KEY, national_id_number text, first_name text, last_name text, date_of_birth date, gender text, primary_address text, contact_email text, contact_phone text, registration_date timestamp, is_verified boolean )\nCREATE TABLE government_services.applications ( application_id text PRIMARY KEY, citizen_id text, service_id text, submitted_at timestamp, status text, last_updated_at timestamp, assigned_employee_id text, decision_date date, notes text, reference_number text )\nCREATE TABLE government_services.payments ( payment_id text PRIMARY KEY, application_id text, citizen_id text, service_id text, amount numeric, currency text, payment_method text, payment_provider_reference text, payment_timestamp timestamp, status text, notes text )\nCREATE TABLE government_services.service_locations ( location_id text PRIMARY KEY, agency_id text, location_name text, address text, city text, state text, postal_code text, latitude numeric, longitude numeric, operating_hours text, contact_phone text, is_accessible boolean )\nCREATE TABLE government_services.appointments ( appointment_id text PRIMARY KEY, citizen_id text, employee_id text, location_id text, service_id text, scheduled_start_time timestamp, scheduled_end_time timestamp, purpose text, status text, booking_method text, created_at timestamp, notes text )\nCREATE TABLE government_services.notifications ( notification_id text PRIMARY KEY, citizen_id text, application_id text, message_subject text, message_body text, channel text, sent_at timestamp, status text, related_entity_type text, related_entity_id text )\n"} {"conversations": [{"role": "user", "content": "List all DApps along with the number of metadata entries linked to each, even if the DApp has no linked metadata."}, {"role": "assistant", "content": "SELECT d.name, d.url, COUNT(m.metadata_id) AS metadata_count\nFROM trading_platform.dapps d\nLEFT JOIN trading_platform.metadata m ON d.dapp_id = m.asset_id\nGROUP BY d.dapp_id, d.name, d.url;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE trading_platform.users ( user_id.text, username.text, email.text, password_hash.text, created_at.timestamp )\nCREATE TABLE trading_platform.orders ( order_id text, user_id text, wallet_id text, asset_id text, order_type text, quantity numeric, price numeric, status text, created_at timestamp )\nCREATE TABLE trading_platform.assets ( asset_id text, name text, symbol text, type text )\nCREATE TABLE trading_platform.dapps ( dapp_id text, name text, description text, url text )\nCREATE TABLE trading_platform.peers ( peer_id.text, ip_address.text, port.integer, last_seen.timestamp )\nCREATE TABLE trading_platform.metadata ( metadata_id character varying(64) NOT NULL, asset_id character varying(64) NOT NULL, key character varying(128) NOT NULL, value text NOT NULL, PRIMARY KEY (metadata_id) )\nCREATE TABLE trading_platform.logs ( log_id text PRIMARY KEY, user_id text, action text, details text, logged_at timestamp )\nCREATE TABLE trading_platform.notifications ( notification_id text, user_id text, message text, sent_at timestamp, read_at timestamp )\n"} {"conversations": [{"role": "user", "content": "Which vehicles have a total maintenance cost exceeding 10000 across all their maintenance logs?"}, {"role": "assistant", "content": "SELECT vehicle_id, SUM(cost) AS total_maintenance_cost FROM transportation.maintenance_logs GROUP BY vehicle_id HAVING SUM(cost) > 10000;"}, {"role": "user", "content": "For these vehicles, also show the count of maintenance logs and the average cost per log."}, {"role": "assistant", "content": "SELECT vehicle_id, COUNT(log_id) AS maintenance_log_count, AVG(cost) AS average_maintenance_cost FROM transportation.maintenance_logs GROUP BY vehicle_id HAVING SUM(cost) > 10000;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.vehicles ( vehicle_id character varying(64) NOT NULL, license_plate character varying(32) NOT NULL UNIQUE, vin character varying(17) UNIQUE, make character varying(64) NOT NULL, model character varying(64) NOT NULL, year integer NOT NULL, type character varying(32) NOT NULL, capacity integer, fuel_type character varying(32) NOT NULL, status character varying(32) NOT NULL, depot_id character varying(64), acquisition_date date, PRIMARY KEY (vehicle_id) )\nCREATE TABLE transportation.trips ( trip_id character varying(64) NOT NULL, route_id character varying(64), vehicle_id character varying(64) NOT NULL, driver_id character varying(64) NOT NULL, scheduled_departure timestamp with time zone NOT NULL, actual_departure timestamp with time zone, scheduled_arrival timestamp with time zone NOT NULL, actual_arrival timestamp with time zone, origin_location_id character varying(64) NOT NULL, destination_location_id character varying(64) NOT NULL, status character varying(32) NOT NULL, passenger_count integer, cargo_manifest_id character varying(64), PRIMARY KEY (trip_id) )\nCREATE TABLE transportation.locations ( location_id character varying(64) NOT NULL, name character varying(255) NOT NULL, type character varying(64) NOT NULL, address_line1 character varying(255), city character varying(128), state_province character varying(128), postal_code character varying(32), country character varying(64) NOT NULL, latitude numeric(9, 6), longitude numeric(9, 6), timezone character varying(64), PRIMARY KEY (location_id) )\nCREATE TABLE transportation.maintenance_logs ( log_id character varying(64) NOT NULL, vehicle_id character varying(64) NOT NULL, service_date date NOT NULL, odometer_reading integer, service_type character varying(128) NOT NULL, description text NOT NULL, cost numeric(10, 2), mechanic_name character varying(128), next_service_due_date date, PRIMARY KEY (log_id) )\nCREATE TABLE transportation.fuel_logs ( fuel_log_id character varying(64) NOT NULL, vehicle_id character varying(64) NOT NULL, trip_id character varying(64), log_timestamp timestamp with time zone NOT NULL, fuel_type character varying(32) NOT NULL, quantity numeric(10, 3) NOT NULL, unit character varying(16) NOT NULL, cost_per_unit numeric(8, 4), total_cost numeric(10, 2) NOT NULL, odometer_reading integer, location_id character varying(64), PRIMARY KEY (fuel_log_id) )\nCREATE TABLE transportation.passengers ( passenger_id character varying(64) NOT NULL, first_name character varying(128) NOT NULL, last_name character varying(128) NOT NULL, email character varying(128) UNIQUE, phone_number character varying(32) UNIQUE, date_of_birth date, loyalty_program_id character varying(64), created_at timestamp with time zone NOT NULL, PRIMARY KEY (passenger_id) )\n"} {"conversations": [{"role": "user", "content": "Show me all home loans (loan_id, principal_amount, interest_rate) where the current principal balance is more than 75% of the original principal amount, along with the account_id and employee details (first_name, last_name) of the employee who processed the loan application."}, {"role": "assistant", "content": "SELECT l.loan_id, l.principal_amount, l.interest_rate, l.account_id, e.first_name, e.last_name FROM financial_services.loans l JOIN financial_services.employees e ON l.account_id = e.employee_id WHERE l.loan_type = 'Home' AND l.current_principal_balance > (l.principal_amount * 0.75)"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE financial_services.transactions ( transaction_id.text, account_id.text, related_account_id.text, transaction_type.text, amount.numeric, currency.text, transaction_date.timestamp, effective_date.date, description.text, status.text, reference_number.text )\nCREATE TABLE financial_services.securities ( security_id.text, ticker_symbol.text, isin_code.text, cusip_code.text, security_name.text, security_type.text, exchange.text, currency.text, issuer_name.text, sector.text, last_updated.timestamp )\nCREATE TABLE financial_services.market_data ( data_point_id.bigint, security_id.text, data_timestamp.timestamp, open_price.numeric, high_price.numeric, low_price.numeric, close_price.numeric, adjusted_close_price.numeric, volume.bigint, source.text )\nCREATE TABLE financial_services.employees ( employee_id.text, first_name.text, last_name.text, job_title.text, department.text, branch_id.text, email.text, phone_extension.text, hire_date.date, termination_date.date, manager_id.text, status.text )\nCREATE TABLE financial_services.loans ( loan_id.text, account_id.text, loan_type.text, principal_amount.numeric, current_principal_balance.numeric, interest_rate.numeric, term_months.integer, origination_date.date, maturity_date.date, monthly_payment.numeric, collateral_description.text, status.text )\n"} {"conversations": [{"role": "user", "content": "Show all insurance plans where the plan name includes the word 'Care'."}, {"role": "assistant", "content": "SELECT plan_id, plan_name, insurance_provider, plan_type\nFROM healthcare.insurance_plans\nWHERE plan_name ILIKE '%Care%';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.diagnoses ( diagnosis_id.text, record_id.text, patient_id.text, doctor_id.text, diagnosis_code.text, code_type.text, description.text, diagnosis_date.date, status.text, is_chronic.boolean )\nCREATE TABLE healthcare.insurance_plans ( plan_id.text, plan_name.text, insurance_provider.text, plan_type.text, contact_phone.text, website.text )\n"} {"conversations": [{"role": "user", "content": "List all employees who are currently active and were hired before 2022. Show employee_id, first_name, last_name, job_title, department, and hire_date."}, {"role": "assistant", "content": "SELECT\n employee_id,\n first_name,\n last_name,\n job_title,\n department,\n hire_date\nFROM financial_services.employees\nWHERE\n status = 'Active' AND hire_date < '2022-01-01';"}, {"role": "user", "content": "Also, only include employees from the 'IT' or 'Operations' departments."}, {"role": "assistant", "content": "SELECT\n employee_id,\n first_name,\n last_name,\n job_title,\n department,\n hire_date\nFROM financial_services.employees\nWHERE\n status = 'Active' AND hire_date < '2022-01-01' AND department IN ('IT', 'Operations');"}, {"role": "user", "content": "Sort the results by hire date ascending and limit to the first 5."}, {"role": "assistant", "content": "SELECT\n employee_id,\n first_name,\n last_name,\n job_title,\n department,\n hire_date\nFROM financial_services.employees\nWHERE\n status = 'Active' AND hire_date < '2022-01-01' AND department IN ('IT', 'Operations')\nORDER BY\n hire_date ASC\nLIMIT 5;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE financial_services.customers ( customer_id text, first_name text, last_name text, date_of_birth date, ssn_hash text, address text, city text, state text, zip_code text, country text, email text, phone_number text, created_at timestamp, status text, risk_profile text )\nCREATE TABLE financial_services.accounts ( account_id text, customer_id text, account_number text, account_type text, balance numeric, currency text, opened_date date, status text, interest_rate numeric, last_updated_at timestamp )\nCREATE TABLE financial_services.transactions (\n transaction_id character varying(64) NOT NULL, -- unique identifier for the transaction\n account_id character varying(64) NOT NULL, -- account involved in the transaction\n related_account_id character varying(64), -- counterpart account for transfers\n transaction_type character varying(50) NOT NULL, -- e.g., Deposit, Withdrawal, Transfer, Payment, Fee, Interest\n amount numeric(19, 4) NOT NULL, -- transaction amount\n currency character varying(3) NOT NULL, -- transaction currency\n transaction_date timestamp NOT NULL, -- exact time of the transaction\n effective_date date NOT NULL, -- date the transaction affects the balance\n description text, -- description or memo of the transaction\n status character varying(32) NOT NULL, -- e.g., Pending, Completed, Failed, Reversed\n reference_number character varying(128), -- external reference if applicable (e.g., check number)\n PRIMARY KEY (transaction_id),\n FOREIGN KEY (account_id) REFERENCES financial_services.accounts(account_id),\n FOREIGN KEY (related_account_id) REFERENCES financial_services.accounts(account_id)\n)\nCREATE TABLE financial_services.securities ( security_id.text, ticker_symbol.text, isin_code.text, cusip_code.text, security_name.text, security_type.text, exchange.text, currency.text, issuer_name.text, sector.text, last_updated.timestamp )\nCREATE TABLE financial_services.trades ( trade_id text PRIMARY KEY, account_id text, security_id text, order_id text, trade_type text, quantity numeric, price_per_unit numeric, total_amount numeric, commission numeric, trade_timestamp timestamp, settlement_date date, status text, execution_venue text )\nCREATE TABLE financial_services.market_data ( data_point_id.bigint, security_id.text, data_timestamp.timestamp, open_price.numeric, high_price.numeric, low_price.numeric, close_price.numeric, adjusted_close_price.numeric, volume.bigint, source.text )\nCREATE TABLE financial_services.employees (\n employee_id character varying(64) NOT NULL, -- unique identifier for the employee\n first_name character varying(100) NOT NULL,\n last_name character varying(100) NOT NULL,\n job_title character varying(100) NOT NULL, -- e.g., Teller, Branch Manager, Financial Advisor, Analyst\n department character varying(100), -- e.g., Retail Banking, Wealth Management, IT\n branch_id character varying(64), -- Identifier for the branch they work at (if applicable)\n email character varying(128) NOT NULL UNIQUE,\n phone_extension character varying(20),\n hire_date date NOT NULL,\n termination_date date, -- Date of termination, null if currently employed\n manager_id character varying(64), -- Self-referencing key for manager relationship\n status character varying(32) NOT NULL, -- e.g., Active, Terminated, On Leave\n PRIMARY KEY (employee_id),\n FOREIGN KEY (branch_id) REFERENCES financial_services.branches(branch_id), -- Assuming a branches table exists\n FOREIGN KEY (manager_id) REFERENCES financial_services.employees(employee_id)\n)\n"} {"conversations": [{"role": "user", "content": "Show me the top 5 most recent medical records with a fever recorded. Return record_id, patient_id, record_date, and the temperature value from vitals."}, {"role": "assistant", "content": "SELECT record_id,\n patient_id,\n record_date,\n vitals->>'temperature' AS temperature\nFROM healthcare.medical_records\nWHERE (vitals->>'temperature')::numeric > 38\nORDER BY record_date DESC\nLIMIT 5;"}, {"role": "user", "content": "Actually, include only records where assessment is not empty."}, {"role": "assistant", "content": "SELECT record_id,\n patient_id,\n record_date,\n vitals->>'temperature' AS temperature\nFROM healthcare.medical_records\nWHERE (vitals->>'temperature')::numeric > 38\n AND assessment IS NOT NULL\n AND assessment <> ''\nORDER BY record_date DESC\nLIMIT 5;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.patients ( patient_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, date_of_birth date NOT NULL, gender character varying(10), address text, phone_number character varying(20), email character varying(128) UNIQUE, emergency_contact_name character varying(200), emergency_contact_phone character varying(20), created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, updated_at timestamp with time zone NOT NULL DEFAULT current_timestamp, PRIMARY KEY (patient_id) )\nCREATE TABLE healthcare.appointments ( appointment_id text, patient_id text, doctor_id text, appointment_time timestamp, duration_minutes integer, reason text, status text, location_id text, notes text, created_at timestamp )\nCREATE TABLE healthcare.medical_records ( record_id character varying(64) NOT NULL, patient_id character varying(64) NOT NULL, appointment_id character varying(64) UNIQUE, doctor_id character varying(64) NOT NULL, record_date timestamp with time zone NOT NULL, chief_complaint text, present_illness_history text, past_medical_history text, physical_examination_notes text, assessment text, treatment_plan text, vitals jsonb, created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, PRIMARY KEY (record_id) )\nCREATE TABLE healthcare.diagnoses ( diagnosis_id text PRIMARY KEY, record_id text, patient_id text, doctor_id text, diagnosis_code text, code_type text, description text, diagnosis_date date, status text, is_chronic boolean )\nCREATE TABLE healthcare.medications ( medication_id text, medication_name text, generic_name text, manufacturer text, ndc_code text, description text )\nCREATE TABLE healthcare.prescriptions ( prescription_id.text, record_id.text, patient_id.text, doctor_id.text, medication_id.text, dosage.text, frequency.text, route.text, start_date.date, end_date.date, quantity_dispensed.numeric, refills_allowed.integer, prescription_date.timestamp )\nCREATE TABLE healthcare.insurance_plans ( plan_id.text, plan_name.text, insurance_provider.text, plan_type.text, contact_phone.text, website.text )\nCREATE TABLE healthcare.patient_insurance ( patient_insurance_id character varying(64) NOT NULL, patient_id character varying(64) NOT NULL, plan_id character varying(64) NOT NULL, policy_number character varying(100) NOT NULL, group_number character varying(100), subscriber_name character varying(200), effective_date date NOT NULL, expiration_date date, is_primary boolean NOT NULL DEFAULT true, PRIMARY KEY (patient_insurance_id), UNIQUE (patient_id, plan_id, policy_number) )\n"} {"conversations": [{"role": "user", "content": "List each transaction along with its status and the names of any events that were emitted during that transaction."}, {"role": "assistant", "content": "SELECT tr.transaction_id, tr.status, e.event_name\nFROM web3.transactions tr\nLEFT JOIN web3.events e ON tr.transaction_id = e.transaction_id;"}, {"role": "user", "content": "Only show transactions that had more than one event emitted, and list the number of events for each such transaction."}, {"role": "assistant", "content": "SELECT tr.transaction_id, tr.status, COUNT(e.event_id) AS event_count\nFROM web3.transactions tr\nJOIN web3.events e ON tr.transaction_id = e.transaction_id\nGROUP BY tr.transaction_id, tr.status\nHAVING COUNT(e.event_id) > 1;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE web3.contracts ( contract_id character varying(64) NOT NULL, address character varying(128) NOT NULL, abi text NOT NULL, bytecode text NOT NULL, deployer_address character varying(128) NOT NULL, deployed_at timestamp NOT NULL, network_id character varying(64) NOT NULL, status character varying(32) NOT NULL, PRIMARY KEY (contract_id) )\nCREATE TABLE web3.events ( event_id.text, contract_id.text, event_name.text, data.text, emitted_at.timestamp, transaction_id.text, log_index.integer )\nCREATE TABLE web3.transactions ( transaction_id character varying(64) NOT NULL, from_address character varying(128) NOT NULL, to_address character varying(128), value numeric(38,14) NOT NULL, gas_used integer NOT NULL, gas_price numeric(38,14) NOT NULL, block_number integer NOT NULL, timestamp timestamp NOT NULL, input_data text, status character varying(32) NOT NULL, nonce integer NOT NULL, PRIMARY KEY (transaction_id) )\nCREATE TABLE web3.tokens (\n token_id character varying(64) NOT NULL, -- unique identifier for the token\n contract_address character varying(128) NOT NULL, -- address of the token contract\n token_name character varying(128) NOT NULL, -- name of the token\n token_symbol character varying(32) NOT NULL, -- symbol of the token\n decimals integer NOT NULL, -- number of decimals for the token\n total_supply numeric(38,14) NOT NULL, -- total supply of the token\n PRIMARY KEY (token_id)\n)\nCREATE TABLE web3.token_transfers ( transfer_id text PRIMARY KEY, token_id text, from_address text, to_address text, value numeric, transaction_id text, log_index int )\nCREATE TABLE web3.wallets ( wallet_id text, user_id text, address text, private_key text, created_at timestamp )\n"} {"conversations": [{"role": "user", "content": "Provide each pair of plans that share the same plan_type but are offered by different providers."}, {"role": "assistant", "content": "SELECT p1.plan_type,\n p1.plan_id AS plan1_id,\n p1.plan_name AS plan1_name,\n p1.insurance_provider AS provider1,\n p2.plan_id AS plan2_id,\n p2.plan_name AS plan2_name,\n p2.insurance_provider AS provider2\nFROM healthcare.insurance_plans p1\nJOIN healthcare.insurance_plans p2\n ON p1.plan_type = p2.plan_type\n AND p1.insurance_provider < p2.insurance_provider;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.insurance_plans ( plan_id text PRIMARY KEY, plan_name text, insurance_provider text, plan_type text, contact_phone text, website text )\n"} {"conversations": [{"role": "user", "content": "Show me all business center services (category = 'Business Center') along with their property IDs and descriptions, where the service is available."}, {"role": "assistant", "content": "SELECT service_name, property_id, description FROM hospitality_technology.services WHERE category = 'Business Center' AND is_available = true;"}, {"role": "user", "content": "Now, join this with another query to include the property names from the properties table (assuming properties table has property_id and property_name columns)."}, {"role": "assistant", "content": "SELECT s.service_name, s.property_id, s.description, p.property_name FROM hospitality_technology.services s JOIN hospitality_technology.properties p ON s.property_id = p.property_id WHERE s.category = 'Business Center' AND s.is_available = true;"}, {"role": "user", "content": "The query is missing the price information. Can you include that as well?"}, {"role": "assistant", "content": "SELECT s.service_name, s.property_id, s.description, p.property_name, s.price FROM hospitality_technology.services s JOIN hospitality_technology.properties p ON s.property_id = p.property_id WHERE s.category = 'Business Center' AND s.is_available = true;"}, {"role": "user", "content": "Actually, I need to see only services priced per hour (unit = 'Per Hour'), and order them by property name in alphabetical order."}, {"role": "assistant", "content": "SELECT s.service_name, s.property_id, s.description, p.property_name, s.price FROM hospitality_technology.services s JOIN hospitality_technology.properties p ON s.property_id = p.property_id WHERE s.category = 'Business Center' AND s.is_available = true AND s.unit = 'Per Hour' ORDER BY p.property_name ASC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE hospitality_technology.services (\n service_id character varying(64) NOT NULL, -- unique identifier for a chargeable service\n property_id character varying(64) NOT NULL, -- FK to properties table\n service_name character varying(150) NOT NULL, -- e.g., Room Service - Burger, Spa - Massage 60min, Laundry - Shirt\n description text,\n category character varying(100), -- e.g., Food & Beverage, Wellness, Business Center, Activities\n price numeric(10, 2) NOT NULL, -- price per unit/instance\n unit character varying(30), -- e.g., Per Item, Per Hour, Per Day\n is_available boolean NOT NULL DEFAULT true, -- is the service currently offered?\n department character varying(100), -- department responsible (e.g., F&B, Spa, Housekeeping)\n PRIMARY KEY (service_id),\n FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id)\n)\n"} {"conversations": [{"role": "user", "content": "List all claims along with the first and last names of the agent who is currently handling each claim."}, {"role": "assistant", "content": "SELECT c.claim_id, c.policy_id, c.incident_date, a.first_name AS agent_first_name, a.last_name AS agent_last_name\nFROM insurance.claims c\nJOIN insurance.agents a ON c.claim_handler_id = a.agent_id;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.claims (\n claim_id character varying(64) NOT NULL, -- unique identifier for the claim\n policy_id character varying(64) NOT NULL, -- identifier of the policy under which the claim is made (FK to policies)\n customer_id character varying(64) NOT NULL, -- identifier of the customer making the claim (FK to customers)\n incident_date timestamp NOT NULL, -- date and time of the incident leading to the claim\n reported_date timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- date the claim was reported\n description text NOT NULL, -- detailed description of the incident and claim\n estimated_loss numeric(15, 2), -- initial estimated cost of the loss\n status character varying(30) NOT NULL, -- e.g., Filed, Processing, Under Review, Approved, Denied, Settled\n settlement_amount numeric(15, 2), -- final amount paid out\n settlement_date date,\n claim_handler_id character varying(64), -- identifier for the employee handling the claim (FK to employees/adjusters)\n police_report_number character varying(100),\n PRIMARY KEY (claim_id)\n)\nCREATE TABLE insurance.agents ( agent_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, agency_name character varying(150), license_number character varying(100) NOT NULL UNIQUE, license_state character varying(50) NOT NULL, contact_email character varying(128) UNIQUE, contact_phone character varying(30), hire_date date, termination_date date, status character varying(20) NOT NULL DEFAULT 'Active', commission_rate numeric(5, 4) NOT NULL DEFAULT 0.05, manager_id character varying(64), PRIMARY KEY (agent_id) )\n"} {"conversations": [{"role": "user", "content": "What is the current salary of employee with ID 'EMP123'?"}, {"role": "assistant", "content": "I'm sorry, but I can't provide information about an employee's salary as it is not included in the data available in the 'employees' table."}], "system": "You are an SQL statement expert and you can refuse the user's question if the question is not related to the table structure. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE manufacturing.employees (\n employee_id character varying(64) NOT NULL, -- unique identifier for the employee\n first_name character varying(100) NOT NULL,\n last_name character varying(100) NOT NULL,\n job_title character varying(128) NOT NULL, -- e.g., 'Aircraft Mechanic', 'Quality Inspector', 'Assembly Technician'\n skill_certifications text, -- comma-separated list or JSON of certifications\n hire_date date NOT NULL,\n assigned_line_id character varying(64), -- FK to the assembly line the employee is currently assigned to (can be null)\n employment_status character varying(50) NOT NULL, -- e.g., 'Active', 'On Leave', 'Terminated'\n supervisor_employee_id character varying(64), -- FK to the employee's supervisor (self-reference, nullable)\n PRIMARY KEY (employee_id)\n)\n"} {"conversations": [{"role": "user", "content": "List the first name, last name, and firm name for all lawyers who are partners."}, {"role": "assistant", "content": "SELECT T1.first_name , T1.last_name , T2.firm_name FROM legal_services.lawyers AS T1 JOIN law_firms AS T2 ON T1.firm_id = T2.firm_id WHERE T1.is_partner = TRUE"}, {"role": "user", "content": "Only show partners from law firms founded before 2010."}, {"role": "assistant", "content": "SELECT T1.first_name , T1.last_name , T2.firm_name FROM legal_services.lawyers AS T1 JOIN law_firms AS T2 ON T1.firm_id = T2.firm_id WHERE T1.is_partner = TRUE AND T2.founded_date < '2010-01-01'"}, {"role": "user", "content": "Sort the results by firm name and then by the lawyer's last name."}, {"role": "assistant", "content": "SELECT T1.first_name , T1.last_name , T2.firm_name FROM legal_services.lawyers AS T1 JOIN law_firms AS T2 ON T1.firm_id = T2.firm_id WHERE T1.is_partner = TRUE AND T2.founded_date < '2010-01-01' ORDER BY T2.firm_name , T1.last_name"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.lawyers (\n lawyer_id character varying(64) NOT NULL, -- unique identifier for the lawyer\n first_name character varying(100) NOT NULL, -- lawyer's first name\n last_name character varying(100) NOT NULL, -- lawyer's last name\n bar_number character varying(64) UNIQUE NOT NULL, -- lawyer's bar association number\n firm_id character varying(64), -- FK to law_firms table\n email character varying(128) UNIQUE NOT NULL, -- lawyer's professional email\n phone character varying(32), -- lawyer's contact phone number\n specialization text, -- areas of legal expertise\n hire_date timestamp NOT NULL, -- date the lawyer was hired or joined\n is_partner boolean DEFAULT false, -- flag indicating if the lawyer is a partner\n PRIMARY KEY (lawyer_id)\n)\n"} {"conversations": [{"role": "user", "content": "Can you narrow this down to only show cases where the case type is 'Criminal'?"}, {"role": "assistant", "content": "SELECT case_name, case_number, date_opened FROM legal_services.cases WHERE lead_lawyer_id = 'lawyer_abc' AND status = 'Open' AND case_type = 'Criminal';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.cases ( case_id.text, case_number.text, case_name.text, client_id.text, lead_lawyer_id.text, case_type.text, status.text, date_opened.timestamp, date_closed.timestamp, description.text, court_jurisdiction.text )\n"} {"conversations": [{"role": "user", "content": "Show each asset's symbol and the number of unique addresses that have UTXOs associated with it."}, {"role": "assistant", "content": "SELECT a.symbol, COUNT(DISTINCT u.address) AS unique_addresses\nFROM trading_platform.assets a\nJOIN trading_platform.utxos u ON a.asset_id = u.transaction_id\nGROUP BY a.asset_id, a.symbol;"}, {"role": "user", "content": "Now show only assets with more than 5 unique addresses."}, {"role": "assistant", "content": "SELECT a.symbol, COUNT(DISTINCT u.address) AS unique_addresses\nFROM trading_platform.assets a\nJOIN trading_platform.utxos u ON a.asset_id = u.transaction_id\nGROUP BY a.asset_id, a.symbol\nHAVING COUNT(DISTINCT u.address) > 5;"}, {"role": "user", "content": "Please also include the total amount for each asset in the result."}, {"role": "assistant", "content": "SELECT a.symbol, COUNT(DISTINCT u.address) AS unique_addresses, COALESCE(SUM(u.amount), 0) AS total_amount\nFROM trading_platform.assets a\nJOIN trading_platform.utxos u ON a.asset_id = u.transaction_id\nGROUP BY a.asset_id, a.symbol\nHAVING COUNT(DISTINCT u.address) > 5;"}, {"role": "user", "content": "Order the results by total_amount ascending and limit to the top 3."}, {"role": "assistant", "content": "SELECT a.symbol, COUNT(DISTINCT u.address) AS unique_addresses, COALESCE(SUM(u.amount), 0) AS total_amount\nFROM trading_platform.assets a\nJOIN trading_platform.utxos u ON a.asset_id = u.transaction_id\nGROUP BY a.asset_id, a.symbol\nHAVING COUNT(DISTINCT u.address) > 5\nORDER BY total_amount ASC\nLIMIT 3;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE trading_platform.users (\n user_id character varying(64) NOT NULL, -- unique identifier for the user\n username character varying(128) NOT NULL, -- username of the user\n email character varying(128) NOT NULL, -- email address of the user\n password_hash text NOT NULL, -- hashed password of the user\n created_at timestamp NOT NULL, -- time when the user account was created\n PRIMARY KEY (user_id)\n)\nCREATE TABLE trading_platform.assets ( asset_id text, name text, symbol text, type text )\nCREATE TABLE trading_platform.utxos ( utxo_id text PRIMARY KEY, transaction_id text, output_index int, address text, amount numeric, spent boolean )\nCREATE TABLE trading_platform.metadata ( metadata_id character varying(64) NOT NULL, asset_id character varying(64) NOT NULL, key character varying(128) NOT NULL, value text NOT NULL, PRIMARY KEY (metadata_id) )\n"} {"conversations": [{"role": "user", "content": "List all claims that are still pending (status = 'pending') and were reported more than 30 days ago."}, {"role": "assistant", "content": "SELECT claim_id, policy_id, customer_id, reported_date FROM insurance.claims WHERE status = 'pending' AND reported_date < CURRENT_DATE - INTERVAL '30 days';"}, {"role": "user", "content": "Now include only claims with estimated loss values and sort them by the oldest reported date first."}, {"role": "assistant", "content": "SELECT claim_id, policy_id, customer_id, reported_date, estimated_loss FROM insurance.claims WHERE status = 'pending' AND reported_date < CURRENT_DATE - INTERVAL '30 days' AND estimated_loss IS NOT NULL ORDER BY reported_date ASC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.claims ( claim_id character varying(64) NOT NULL, policy_id character varying(64) NOT NULL, customer_id character varying(64) NOT NULL, incident_date timestamp NOT NULL, reported_date timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, description text NOT NULL, estimated_loss numeric(15, 2), status character varying(30) NOT NULL, settlement_amount numeric(15, 2), settlement_date date, claim_handler_id character varying(64), police_report_number character varying(100), PRIMARY KEY (claim_id) )\n"} {"conversations": [{"role": "user", "content": "Count the total number of premium payments made in the year 2024."}, {"role": "assistant", "content": "SELECT COUNT(*) FROM premium_payments WHERE EXTRACT(YEAR FROM payment_date) = 2024"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.customers ( customer_id text PRIMARY KEY, first_name text, last_name text, date_of_birth date, ssn_hash text, address_line1 text, address_line2 text, city text, state text, zip_code text, country text, phone_number text, email text, created_at timestamp, updated_at timestamp, status text )\nCREATE TABLE insurance.policies ( policy_id character varying(64) NOT NULL, customer_id character varying(64) NOT NULL, product_id character varying(64) NOT NULL, agent_id character varying(64), policy_number character varying(100) NOT NULL UNIQUE, start_date date NOT NULL, end_date date NOT NULL, premium_amount numeric(12, 2) NOT NULL, coverage_limit numeric(15, 2) NOT NULL, deductible numeric(10, 2) NOT NULL, status character varying(30) NOT NULL, issued_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, cancellation_date date, cancellation_reason text, PRIMARY KEY (policy_id) )\nCREATE TABLE insurance.claims ( claim_id character varying(64) NOT NULL, policy_id character varying(64) NOT NULL, customer_id character varying(64) NOT NULL, incident_date timestamp NOT NULL, reported_date timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, description text NOT NULL, estimated_loss numeric(15, 2), status character varying(30) NOT NULL, settlement_amount numeric(15, 2), settlement_date date, claim_handler_id character varying(64), police_report_number character varying(100), PRIMARY KEY (claim_id) )\nCREATE TABLE insurance.agents ( agent_id text PRIMARY KEY, first_name text, last_name text, agency_name text, license_number text, license_state text, contact_email text, contact_phone text, hire_date date, termination_date date, status text, commission_rate numeric, manager_id text )\nCREATE TABLE insurance.premium_payments ( payment_id text PRIMARY KEY, policy_id text, customer_id text, payment_date timestamp, amount_paid numeric, payment_method text, transaction_reference text, due_date date, payment_period_start date, payment_period_end date, status text )\n"} {"conversations": [{"role": "user", "content": "List game titles released on the 'PC' platform along with the count of servers currently hosting each game."}, {"role": "assistant", "content": "SELECT T1.title, count(T2.server_id) FROM games AS T1 JOIN servers AS T2 ON T1.game_id = T2.game_id WHERE T1.platform = 'PC' GROUP BY T1.title;"}, {"role": "user", "content": "Now, only show games with more than 3 servers and sort the results by the server count in descending order."}, {"role": "assistant", "content": "SELECT T1.title, count(T2.server_id) AS server_count FROM games AS T1 JOIN servers AS T2 ON T1.game_id = T2.game_id WHERE T1.platform = 'PC' GROUP BY T1.title HAVING count(T2.server_id) > 3 ORDER BY server_count DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE gaming_technology.players (\n player_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for the player\n username character varying(100) NOT NULL UNIQUE, -- player's chosen display name\n email character varying(255) NOT NULL UNIQUE, -- player's email address for login/recovery\n password_hash text NOT NULL, -- securely hashed password\n registration_date timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP, -- when the player account was created\n last_login timestamp with time zone, -- timestamp of the last successful login\n country_code character(2), -- player's country (ISO 3166-1 alpha-2)\n status character varying(20) NOT NULL DEFAULT 'active', -- account status (e.g., active, banned, suspended)\n profile_data jsonb, -- flexible field for avatar url, bio, preferences etc.\n PRIMARY KEY (player_id)\n)\nCREATE TABLE gaming_technology.games (\n game_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for the game\n title character varying(200) NOT NULL, -- official title of the game\n developer_id uuid NOT NULL, -- FK linking to the developers table\n publisher_id uuid, -- FK linking to a potential publishers table (optional)\n genre character varying(100), -- primary genre (e.g., RPG, FPS, Strategy)\n release_date date, -- official release date\n description text, -- short description or synopsis of the game\n platform character varying(50) NOT NULL, -- primary platform (e.g., PC, PlayStation 5, Xbox Series X, Mobile)\n engine character varying(100), -- game engine used (e.g., Unreal Engine 5, Unity)\n website character varying(255), -- official website URL\n PRIMARY KEY (game_id)\n -- FOREIGN KEY (developer_id) REFERENCES gaming_technology.developers(developer_id) -- Example FK constraint\n)\nCREATE TABLE gaming_technology.game_sessions (\n session_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for the game session\n player_id uuid NOT NULL, -- FK linking to the players table\n game_id uuid NOT NULL, -- FK linking to the games table\n server_id uuid, -- FK linking to the servers table (nullable for single-player)\n start_time timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP, -- when the session began\n end_time timestamp with time zone, -- when the session ended (null if ongoing)\n duration_seconds integer, -- calculated duration of the session in seconds\n score integer, -- player's score for the session, if applicable\n session_data jsonb, -- flexible field for session-specific info (e.g., map played, character used)\n PRIMARY KEY (session_id)\n -- FOREIGN KEY (player_id) REFERENCES gaming_technology.players(player_id),\n -- FOREIGN KEY (game_id) REFERENCES gaming_technology.games(game_id),\n -- FOREIGN KEY (server_id) REFERENCES gaming_technology.servers(server_id)\n)\nCREATE TABLE gaming_technology.servers (\n server_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for the game server instance\n game_id uuid NOT NULL, -- FK linking to the game this server hosts\n server_name character varying(150), -- display name for the server\n region character varying(50) NOT NULL, -- geographical region (e.g., us-east-1, eu-west-2)\n ip_address character varying(45), -- IP address (IPv4 or IPv6)\n port integer, -- network port number\n current_players integer NOT NULL DEFAULT 0, -- number of players currently connected\n max_players integer NOT NULL, -- maximum player capacity\n status character varying(30) NOT NULL DEFAULT 'offline', -- server status (e.g., online, offline, maintenance)\n last_heartbeat timestamp with time zone, -- last time the server reported its status\n PRIMARY KEY (server_id)\n -- FOREIGN KEY (game_id) REFERENCES gaming_technology.games(game_id)\n)\nCREATE TABLE gaming_technology.achievements (\n achievement_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for an achievement definition\n game_id uuid NOT NULL, -- FK linking to the game the achievement belongs to\n name character varying(150) NOT NULL, -- name of the achievement\n description text NOT NULL, -- how to unlock the achievement\n icon_url character varying(255), -- URL for the achievement's icon\n points integer DEFAULT 0, -- points awarded for unlocking (optional)\n hidden boolean DEFAULT false, -- whether the achievement details are hidden until unlocked\n PRIMARY KEY (achievement_id)\n -- FOREIGN KEY (game_id) REFERENCES gaming_technology.games(game_id)\n)\nCREATE TABLE gaming_technology.player_achievements (\n player_achievement_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for this unlock instance\n player_id uuid NOT NULL, -- FK linking to the player who unlocked it\n achievement_id uuid NOT NULL, -- FK linking to the achievement definition\n unlocked_at timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP, -- when the achievement was unlocked\n PRIMARY KEY (player_achievement_id),\n UNIQUE (player_id, achievement_id) -- Ensure a player can only unlock an achievement once\n -- FOREIGN KEY (player_id) REFERENCES gaming_technology.players(player_id),\n -- FOREIGN KEY (achievement_id) REFERENCES gaming_technology.achievements(achievement_id)\n)\nCREATE TABLE gaming_technology.in_game_items (\n item_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for the item definition\n game_id uuid NOT NULL, -- FK linking to the game this item belongs to\n item_name character varying(150) NOT NULL, -- name of the item\n item_type character varying(50) NOT NULL, -- type (e.g., Cosmetic, Consumable, Weapon, Armor)\n description text, -- description of the item\n rarity character varying(30), -- item rarity (e.g., Common, Rare, Epic, Legendary)\n cost_currency character varying(10), -- currency code if purchasable (e.g., USD, EUR, GOLD)\n cost_amount numeric(12, 2), -- price if purchasable\n attributes jsonb, -- flexible field for item stats or properties\n PRIMARY KEY (item_id)\n -- FOREIGN KEY (game_id) REFERENCES gaming_technology.games(game_id)\n)\nCREATE TABLE gaming_technology.player_inventory (\n inventory_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for an inventory entry\n player_id uuid NOT NULL, -- FK linking to the player owning the item\n item_id uuid NOT NULL, -- FK linking to the item definition\n quantity integer NOT NULL DEFAULT 1, -- number of items held (for stackable items)\n acquired_at timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP, -- when the item was acquired\n instance_data jsonb, -- data specific to this instance (e.g., weapon mods, durability)\n PRIMARY KEY (inventory_id),\n -- Optional unique constraint if items are non-stackable or unique instances\n -- UNIQUE (player_id, item_id) -- Use if quantity is always 1\n -- FOREIGN KEY (player_id) REFERENCES gaming_technology.players(player_id),\n -- FOREIGN KEY (item_id) REFERENCES gaming_technology.in_game_items(item_id)\n)\n"} {"conversations": [{"role": "user", "content": "List each lawyer's full name with the full name of the partner at the same firm."}, {"role": "assistant", "content": "SELECT l.lawyer_id,\n CONCAT(l.first_name, ' ', l.last_name) AS lawyer_name,\n CONCAT(p.first_name, ' ', p.last_name) AS partner_name\nFROM legal_services.lawyers l\nJOIN legal_services.lawyers p\n ON l.firm_id = p.firm_id\n AND p.is_partner = true;"}, {"role": "user", "content": "Actually, I only want those lawyers whose specialization includes 'Corporate Law'. Could you update the query?"}, {"role": "assistant", "content": "SELECT l.lawyer_id,\n CONCAT(l.first_name, ' ', l.last_name) AS lawyer_name,\n CONCAT(p.first_name, ' ', p.last_name) AS partner_name\nFROM legal_services.lawyers l\nJOIN legal_services.lawyers p\n ON l.firm_id = p.firm_id\n AND p.is_partner = true\nWHERE l.specialization ILIKE '%Corporate Law%';"}, {"role": "user", "content": "Also only show those who were hired after 2020-01-01."}, {"role": "assistant", "content": "SELECT l.lawyer_id,\n CONCAT(l.first_name, ' ', l.last_name) AS lawyer_name,\n CONCAT(p.first_name, ' ', p.last_name) AS partner_name\nFROM legal_services.lawyers l\nJOIN legal_services.lawyers p\n ON l.firm_id = p.firm_id\n AND p.is_partner = true\nWHERE l.specialization ILIKE '%Corporate Law%'\n AND l.hire_date > '2020-01-01';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.lawyers (\n lawyer_id character varying(64) NOT NULL, -- unique identifier for the lawyer\n first_name character varying(100) NOT NULL, -- lawyer's first name\n last_name character varying(100) NOT NULL, -- lawyer's last name\n bar_number character varying(64) UNIQUE NOT NULL, -- lawyer's bar association number\n firm_id character varying(64), -- FK to law_firms table\n email character varying(128) UNIQUE NOT NULL, -- lawyer's professional email\n phone character varying(32), -- lawyer's contact phone number\n specialization text, -- areas of legal expertise\n hire_date timestamp NOT NULL, -- date the lawyer was hired or joined\n is_partner boolean DEFAULT false, -- flag indicating if the lawyer is a partner\n PRIMARY KEY (lawyer_id)\n)\n"} {"conversations": [{"role": "user", "content": "List the username and email of users whose first wallet creation date is the same day as their user registration date."}, {"role": "assistant", "content": "SELECT u.username, u.email FROM web3.users u JOIN (SELECT user_id, MIN(created_at) as first_wallet_created_at FROM web3.wallets GROUP BY user_id) w ON u.user_id = w.user_id WHERE DATE(u.created_at) = DATE(w.first_wallet_created_at);"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE web3.events (\n event_id character varying(64) NOT NULL, -- unique identifier for the event\n contract_id character varying(64) NOT NULL, -- identifier of the contract emitting the event\n event_name character varying(128) NOT NULL, -- name of the event\n data text NOT NULL, -- data payload of the event\n emitted_at timestamp NOT NULL, -- time when the event was emitted\n transaction_id character varying(64) NOT NULL, -- identifier of the transaction that triggered the event\n log_index integer NOT NULL, -- index of the event log in the transaction\n PRIMARY KEY (event_id)\n)\nCREATE TABLE web3.tokens (\n token_id character varying(64) NOT NULL, -- unique identifier for the token\n contract_address character varying(128) NOT NULL, -- address of the token contract\n token_name character varying(128) NOT NULL, -- name of the token\n token_symbol character varying(32) NOT NULL, -- symbol of the token\n decimals integer NOT NULL, -- number of decimals for the token\n total_supply numeric(38,14) NOT NULL, -- total supply of the token\n PRIMARY KEY (token_id)\n)\nCREATE TABLE web3.wallets (\n wallet_id character varying(64) NOT NULL, -- unique identifier for the wallet\n user_id character varying(64) NOT NULL, -- identifier of the user owning the wallet\n address character varying(128) NOT NULL, -- address of the wallet\n private_key text NOT NULL, -- private key of the wallet\n created_at timestamp NOT NULL, -- time when the wallet was created\n PRIMARY KEY (wallet_id)\n)\nCREATE TABLE web3.users (\n user_id character varying(64) NOT NULL, -- unique identifier for the user\n username character varying(128) NOT NULL, -- username of the user\n email character varying(128) NOT NULL, -- email address of the user\n password_hash text NOT NULL, -- hashed password of the user\n created_at timestamp NOT NULL, -- time when the user account was created\n PRIMARY KEY (user_id)\n)\n"} {"conversations": [{"role": "user", "content": "Find all non-smoking rooms that have not been cleaned in the last 7 days."}, {"role": "assistant", "content": "SELECT room_id, room_number, last_cleaned_at\nFROM hospitality_technology.rooms\nWHERE is_smoking = false\n AND last_cleaned_at < NOW() - INTERVAL '7 days';"}, {"role": "user", "content": "Now also include only those rooms with 'Balcony' in the features."}, {"role": "assistant", "content": "SELECT room_id, room_number, last_cleaned_at, features\nFROM hospitality_technology.rooms\nWHERE is_smoking = false\n AND last_cleaned_at < NOW() - INTERVAL '7 days'\n AND features ILIKE '%Balcony%';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE hospitality_technology.rooms (\n room_id character varying(64) NOT NULL, -- unique identifier for the room\n property_id character varying(64) NOT NULL, -- FK to properties table\n room_number character varying(10) NOT NULL, -- room number identifier (e.g., '101', 'Suite 2B')\n room_type_id character varying(64) NOT NULL, -- FK to room_types table\n floor integer, -- floor number the room is on\n status character varying(50) NOT NULL, -- e.g., Available, Occupied, Cleaning, OutOfOrder, Maintenance\n is_smoking boolean NOT NULL DEFAULT false, -- smoking allowed flag\n features text, -- description of features (e.g., Balcony, Sea View, Jacuzzi)\n current_condition text, -- notes on room condition\n last_cleaned_at timestamp with time zone, -- timestamp of last cleaning\n PRIMARY KEY (room_id),\n FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id),\n FOREIGN KEY (room_type_id) REFERENCES hospitality_technology.room_types(room_type_id)\n)\nCREATE TABLE hospitality_technology.payments ( payment_id text, reservation_id text, guest_id text, bill_id text, amount numeric, currency_code text, payment_method text, card_type text, card_last_four text, transaction_ref text, payment_timestamp timestamp, status text, staff_id_processed text, notes text )\n"} {"conversations": [{"role": "user", "content": "Give me the total billed amount for each invoice in 2024."}, {"role": "assistant", "content": "SELECT invoice_id, SUM(hours_spent * billing_rate) AS total_billed_amount FROM legal_services.time_entries WHERE is_billed = TRUE AND EXTRACT(YEAR FROM date_worked) = 2024 GROUP BY invoice_id;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.time_entries ( entry_id text PRIMARY KEY, case_id text, lawyer_id text, date_worked date, hours_spent numeric, billing_rate numeric, description text, is_billable bool, is_billed bool, invoice_id text, created_at timestamp )\n"} {"conversations": [{"role": "user", "content": "What is the total number of drivers hired each year? Provide the hire_year and driver_count."}, {"role": "assistant", "content": "SELECT EXTRACT(YEAR FROM hire_date) AS hire_year,\n COUNT(*) AS driver_count\nFROM transportation.drivers\nGROUP BY EXTRACT(YEAR FROM hire_date);"}, {"role": "user", "content": "Now only include years where driver_count > 3 and order the results by driver_count DESC."}, {"role": "assistant", "content": "SELECT hire_year, driver_count\nFROM (\n SELECT EXTRACT(YEAR FROM hire_date) AS hire_year,\n COUNT(*) AS driver_count\n FROM transportation.drivers\n GROUP BY EXTRACT(YEAR FROM hire_date)\n) sub\nWHERE driver_count > 3\nORDER BY driver_count DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.drivers ( driver_id text, employee_id text, first_name text, last_name text, license_number text, license_expiry_date date, contact_number text, email text, hire_date date, status text )\n"} {"conversations": [{"role": "user", "content": "List all users whose password hash contains the substring 'abc'."}, {"role": "assistant", "content": "SELECT user_id, username, password_hash FROM blockchain.users WHERE password_hash LIKE '%abc%';"}, {"role": "user", "content": "Also include their email address."}, {"role": "assistant", "content": "SELECT user_id, username, password_hash, email FROM blockchain.users WHERE password_hash LIKE '%abc%';"}, {"role": "user", "content": "Filter to only show users whose username does *not* contain 'test'."}, {"role": "assistant", "content": "SELECT user_id, username, password_hash, email FROM blockchain.users WHERE password_hash LIKE '%abc%' AND username NOT LIKE '%test%';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE blockchain.wallets ( wallet_id.text, user_id.text, address_id.text, private_key.text )\nCREATE TABLE blockchain.users ( user_id.text, username.text, email.text, password_hash.text )\n"} {"conversations": [{"role": "user", "content": "List each driver along with the driver_id of the driver who was hired immediately after them."}, {"role": "assistant", "content": "SELECT d1.driver_id AS current_driver_id, d2.driver_id AS next_driver_id FROM transportation.drivers d1 LEFT JOIN transportation.drivers d2 ON d2.hire_date = (SELECT MIN(hire_date) FROM transportation.drivers WHERE hire_date > d1.hire_date);"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.drivers ( driver_id.text, employee_id.text, first_name.text, last_name.text, license_number.text, license_expiry_date.date, contact_number.text, email.text, hire_date.date, status.text )\n"} {"conversations": [{"role": "user", "content": "Which NFTs minted in the past 14 days on Ethereum have a rarity_score above 70? For each, show contract address, token ID, name, and minter."}, {"role": "assistant", "content": "SELECT contract_address, token_id, name, minter\nFROM nft_metadata\nWHERE blockchain = 'Ethereum'\n AND mint_time >= (extract(epoch from now()) - 14*24*60*60)\n AND rarity_score > 70;"}, {"role": "user", "content": "For these NFTs, can you also include the collection name and symbol by joining with the nft_collections table?"}, {"role": "assistant", "content": "SELECT nm.contract_address, nm.token_id, nm.name, nm.minter, nc.name AS collection_name, nc.symbol\nFROM nft_metadata nm\nJOIN nft_collections nc\n ON nm.blockchain = nc.blockchain AND nm.contract_address = nc.contract_address\nWHERE nm.blockchain = 'Ethereum'\n AND nm.mint_time >= (extract(epoch from now()) - 14*24*60*60)\n AND nm.rarity_score > 70;"}, {"role": "user", "content": "Can you filter only those collections where the erc_type is 'ERC1155'?"}, {"role": "assistant", "content": "SELECT nm.contract_address, nm.token_id, nm.name, nm.minter, nc.name AS collection_name, nc.symbol\nFROM nft_metadata nm\nJOIN nft_collections nc\n ON nm.blockchain = nc.blockchain AND nm.contract_address = nc.contract_address\nWHERE nm.blockchain = 'Ethereum'\n AND nm.mint_time >= (extract(epoch from now()) - 14*24*60*60)\n AND nm.rarity_score > 70\n AND nc.erc_type = 'ERC1155';"}, {"role": "user", "content": "Now, also include the owner for each NFT, and order the results by rarity_rank ascending."}, {"role": "assistant", "content": "SELECT nm.contract_address, nm.token_id, nm.name, nm.minter, nm.owner, nc.name AS collection_name, nc.symbol\nFROM nft_metadata nm\nJOIN nft_collections nc\n ON nm.blockchain = nc.blockchain AND nm.contract_address = nc.contract_address\nWHERE nm.blockchain = 'Ethereum'\n AND nm.mint_time >= (extract(epoch from now()) - 14*24*60*60)\n AND nm.rarity_score > 70\n AND nc.erc_type = 'ERC1155'\nORDER BY nm.rarity_rank ASC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE nft_holders ( block_number bigint NOT NULL, contract_address varchar NOT NULL, wallet_address varchar NOT NULL, token_id varchar NOT NULL, contract_type varchar NOT NULL, amount varchar NOT NULL, pk varchar NOT NULL )\nCREATE TABLE sui_coins ( object_id varchar NOT NULL, status varchar NOT NULL, coin_type varchar NOT NULL, balance varchar NOT NULL, owner varchar NOT NULL )\nCREATE TABLE sui_coins_metadata (\n object_id varchar NOT NULL, -- object id of the coin metadata object\n coin_type varchar NOT NULL, -- coin type, eg. 0x...66::reap_token::REAP_TOKEN\n status varchar NOT NULL, -- coin status, eg. exists, deleted\n decimals bigint NOT NULL, -- decimals of the coin\n description varchar NOT NULL, -- description of the coin\n icon_url varchar NOT NULL, -- icon url of the coin\n symbol varchar NOT NULL, -- symbol of the coin\n name varchar NOT NULL -- name of the coin\n)\nCREATE TABLE sui_nfts ( object_id text, status text, collection_type text, package_id text, previous_transaction text, display text, owner text, name text )\nCREATE TABLE nft_metadata ( blockchain text, contract_address text, token_id text, contract_name text, erc_type text, amount bigint, minter text, owner text, mint_block_number bigint, mint_time bigint, mint_transaction_hash text, mint_price text, token_uri text, metadata text, name text, image_uri text, traits text, updated_at bigint, status text, rarity_score real, rarity_rank integer, unique_attribute_count integer, pk integer )\nCREATE TABLE nft_collections ( blockchain varchar NOT NULL, contract_address varchar NOT NULL, name varchar NOT NULL, symbol varchar NOT NULL, deploy_block_number bigint NOT NULL, deploy_block_time bigint NOT NULL, erc_type varchar NOT NULL, owner varchar NOT NULL, traits varchar NOT NULL, description varchar NOT NULL, slug varchar NOT NULL, media_info varchar NOT NULL, image_url varchar NOT NULL, banner_image_url varchar NOT NULL, updated_at bigint NOT NULL, banner varchar NOT NULL, token_count bigint NOT NULL, floor_price varchar NOT NULL, floor_price_symbol varchar NOT NULL, floor_price_contract varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE token_prices ( uuid text, blockchain text, address text, decimals bigint, symbol text, price real, timestamp timestamp )\nCREATE TABLE token_prices_latest (\n blockchain varchar(36) NOT NULL, -- blockchain fields for the functionType in contract\n address varchar(42) NOT NULL, -- address fields for the functionType in contract\n decimals bigint NOT NULL, -- decimals fields for the functionType in contract\n symbol varchar(36) NOT NULL, -- symbol fields for the functionType in contract\n price real NOT NULL, -- price fields for the functionType in contract\n timestamp timestamp(6) NOT NULL -- timestamp fields for the functionType in contract\n)\nCREATE TABLE erc20_approval ( block_number bigint NOT NULL, block_timestamp timestamp(6) NOT NULL, transaction_index integer NOT NULL, transaction_hash varchar NOT NULL, log_index integer NOT NULL, contract_address varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE token_balances ( block_number.bigint, block_timestamp.timestamp, tick.text, wallet_address.text, total_supply.decimal, amount.decimal )\nCREATE TABLE token_info (\n block_timestamp timestamp(3) NOT NULL, -- Timestamp of the block containing the inscription (matches block_timestamp in transactions table)\n block_number bigint NOT NULL, -- Block number containing the inscription (matches block_number in transactions table)\n tx_index integer NOT NULL, -- Index of the transaction containing the inscription (matches transaction_index in transactions table)\n tx_hash varchar(66) NOT NULL, -- Unique identifier of the transaction containing the inscription (matches hash in transactions table)\n tick varchar NOT NULL, -- Token tick\n max_supply decimal(38,0) NOT NULL, -- Max supply\n lim decimal(38,0) NOT NULL, -- Limit of each mint\n wlim decimal(38,0) NOT NULL, -- Limit of each address can maximum mint\n dec integer NOT NULL, -- Decimal for minimum divie\n creator varchar(42) NOT NULL -- Address originating the inscription (matches from_address in transactions table)\n)\nCREATE TABLE mud_holesky_redstone (\n address varchar NOT NULL, -- address fields for the functionType in contract\n table_id varchar NOT NULL, -- table_id fields for the functionType in contract\n key_bytes varchar NOT NULL, -- key_bytes fields for the functionType in contract\n key0 varchar NOT NULL, -- key0 fields for the functionType in contract\n key1 varchar NOT NULL, -- key1 fields for the functionType in contract\n static_data varchar NOT NULL, -- static_data fields for the functionType in contract\n encoded_lengths varchar NOT NULL, -- encoded_lengths fields for the functionType in contract\n dynamic_data varchar NOT NULL, -- dynamic_data fields for the functionType in contract\n is_deleted boolean NOT NULL, -- is_deleted fields for the functionType in contract\n block_number bigint NOT NULL, -- Block number uniquely identifying the block\n log_index bigint NOT NULL -- Index of the log within the transaction\n)\nCREATE TABLE token_info_bitcoin ( block_timestamp.timestamp, block_number.bigint, tx_index.integer, tx_hash.text, tick.text, max_supply.decimal, lim.decimal, wlim.decimal, dec.integer, creator.text )\nCREATE TABLE token_activities_avalanche (\n block_timestamp timestamp(3) NOT NULL, -- Timestamp of the block containing the inscription (matches block_timestamp in transactions table)\n block_number bigint NOT NULL, -- Block number containing the inscription (matches block_number in transactions table)\n tx_index integer NOT NULL, -- Index of the transaction containing the inscription (matches transaction_index in transactions table)\n tx_hash varchar(66) NOT NULL, -- Unique identifier of the transaction containing the inscription (matches hash in transactions table)\n log_index integer NOT NULL, -- Index of the log within the transaction\n type varchar(20) NOT NULL, -- Operation: Type of event (deploy, mint, transfer, list)\n tick varchar(255) NOT NULL, -- Ticker: Identifier of the inscription\n id varchar(255) NOT NULL, -- Unique identifier of the inscription\n amt decimal(38,0) NOT NULL, -- Amount to mint: States the amount of the inscription to operation. When operation is mint, has to be less or equal to \"lim\"\n from_address varchar(42) NOT NULL, -- Address sending the inscription\n to_address varchar(42) NOT NULL -- Address receiving the inscription\n)\nCREATE TABLE token_balances_avalanche ( block_number bigint, block_timestamp timestamp, tick varchar, wallet_address varchar, total_supply decimal, amount decimal )\n"} {"conversations": [{"role": "user", "content": "List the names of services and the total number of times each service has been ordered. Only include services that have been ordered at least once."}, {"role": "assistant", "content": "SELECT T1.service_name, count(T2.order_id) AS order_count FROM hospitality_technology.services AS T1 JOIN hospitality_technology.service_orders AS T2 ON T1.service_id = T2.service_id GROUP BY T1.service_name;"}, {"role": "user", "content": "Now, filter this list to only show services from the 'Food & Beverage' or 'Activities' categories, and sort by the order count in descending order."}, {"role": "assistant", "content": "SELECT T1.service_name, count(T2.order_id) AS order_count FROM hospitality_technology.services AS T1 JOIN hospitality_technology.service_orders AS T2 ON T1.service_id = T2.service_id WHERE T1.category IN ('Food & Beverage', 'Activities') GROUP BY T1.service_name ORDER BY order_count DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE hospitality_technology.properties ( property_id character varying(64) NOT NULL, property_name character varying(255) NOT NULL, address_line1 character varying(255) NOT NULL, address_line2 character varying(255), city character varying(100) NOT NULL, state_province character varying(100), postal_code character varying(20) NOT NULL, country_code character varying(3) NOT NULL, phone_number character varying(30), email_address character varying(255), property_type character varying(50) NOT NULL, star_rating numeric(2,1), timezone character varying(64) NOT NULL, manager_staff_id character varying(64), created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, updated_at timestamp with time zone NOT NULL DEFAULT current_timestamp, PRIMARY KEY (property_id) )\nCREATE TABLE hospitality_technology.rooms ( room_id character varying(64) NOT NULL, property_id character varying(64) NOT NULL, room_number character varying(10) NOT NULL, room_type_id character varying(64) NOT NULL, floor integer, status character varying(50) NOT NULL, is_smoking boolean NOT NULL DEFAULT false, features text, current_condition text, last_cleaned_at timestamp with time zone, PRIMARY KEY (room_id), FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id), FOREIGN KEY (room_type_id) REFERENCES hospitality_technology.room_types(room_type_id) )\nCREATE TABLE hospitality_technology.room_types ( room_type_id character varying(64) NOT NULL, property_id character varying(64) NOT NULL, type_name character varying(100) NOT NULL, description text, base_rate numeric(10, 2) NOT NULL, max_occupancy integer NOT NULL, bed_type character varying(50), area_sqft numeric(8,2), amenities text, PRIMARY KEY (room_type_id), FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id) )\nCREATE TABLE hospitality_technology.guests ( guest_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, email character varying(255) UNIQUE, phone_number character varying(30), date_of_birth date, address_line1 character varying(255), city character varying(100), state_province character varying(100), postal_code character varying(20), country_code character varying(3), preferences text, loyalty_member_id character varying(64) UNIQUE, communication_consent boolean DEFAULT true, created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, updated_at timestamp with time zone NOT NULL DEFAULT current_timestamp, PRIMARY KEY (guest_id) )\nCREATE TABLE hospitality_technology.reservations ( reservation_id character varying(64) NOT NULL, property_id character varying(64) NOT NULL, guest_id character varying(64) NOT NULL, room_id character varying(64), room_type_id character varying(64) NOT NULL, check_in_date date NOT NULL, check_out_date date NOT NULL, actual_check_in_ts timestamp with time zone, actual_check_out_ts timestamp with time zone, num_adults integer NOT NULL, num_children integer DEFAULT 0, status character varying(50) NOT NULL, booking_source character varying(100), rate_plan_id character varying(64), total_amount numeric(12, 2), amount_paid numeric(12, 2) DEFAULT 0.00, special_requests text, created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, updated_at timestamp with time zone NOT NULL DEFAULT current_timestamp, PRIMARY KEY (reservation_id), FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id), FOREIGN KEY (guest_id) REFERENCES hospitality_technology.guests(guest_id), FOREIGN KEY (room_id) REFERENCES hospitality_technology.rooms(room_id), FOREIGN KEY (room_type_id) REFERENCES hospitality_technology.room_types(room_type_id) )\nCREATE TABLE hospitality_technology.services ( service_id character varying(64) NOT NULL, property_id character varying(64) NOT NULL, service_name character varying(150) NOT NULL, description text, category character varying(100), price numeric(10, 2) NOT NULL, unit character varying(30), is_available boolean NOT NULL DEFAULT true, department character varying(100), PRIMARY KEY (service_id), FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id) )\nCREATE TABLE hospitality_technology.service_orders ( order_id character varying(64) NOT NULL, reservation_id character varying(64), guest_id character varying(64) NOT NULL, service_id character varying(64) NOT NULL, staff_id_ordered character varying(64), staff_id_delivered character varying(64), order_timestamp timestamp with time zone NOT NULL DEFAULT current_timestamp, delivery_timestamp timestamp with time zone, quantity integer NOT NULL DEFAULT 1, unit_price numeric(10, 2) NOT NULL, total_price numeric(12, 2) NOT NULL, status character varying(50) NOT NULL, notes text, bill_id character varying(64), PRIMARY KEY (order_id), FOREIGN KEY (reservation_id) REFERENCES hospitality_technology.reservations(reservation_id), FOREIGN KEY (guest_id) REFERENCES hospitality_technology.guests(guest_id), FOREIGN KEY (service_id) REFERENCES hospitality_technology.services(service_id), FOREIGN KEY (staff_id_ordered) REFERENCES hospitality_technology.staff(staff_id), FOREIGN KEY (staff_id_delivered) REFERENCES hospitality_technology.staff(staff_id) )\nCREATE TABLE hospitality_technology.payments ( payment_id character varying(64) NOT NULL, reservation_id character varying(64), guest_id character varying(64) NOT NULL, bill_id character varying(64), amount numeric(12,2) NOT NULL, currency_code character varying(3) NOT NULL, payment_method character varying(50) NOT NULL, card_type character varying(50), card_last_four character varying(4), transaction_ref character varying(128), payment_timestamp timestamp with time zone NOT NULL DEFAULT current_timestamp, status character varying(50) NOT NULL, staff_id_processed character varying(64), notes text, PRIMARY KEY (payment_id), FOREIGN KEY (reservation_id) REFERENCES hospitality_technology.reservations(reservation_id), FOREIGN KEY (guest_id) REFERENCES hospitality_technology.guests(guest_id), FOREIGN KEY (staff_id_processed) REFERENCES hospitality_technology.staff(staff_id) )\nCREATE TABLE hospitality_technology.reviews ( review_id character varying(64) NOT NULL, property_id character varying(64) NOT NULL, reservation_id character varying(64) UNIQUE, guest_id character varying(64) NOT NULL, rating_overall integer, rating_cleanliness integer, rating_service integer, rating_location integer, rating_value integer, comment text, review_source character varying(100), review_date timestamp with time zone NOT NULL DEFAULT current_timestamp, is_public boolean DEFAULT true, staff_response text, response_staff_id character varying(64), response_date timestamp with time zone, PRIMARY KEY (review_id), FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id), FOREIGN KEY (reservation_id) REFERENCES hospitality_technology.reservations(reservation_id), FOREIGN KEY (guest_id) REFERENCES hospitality_technology.guests(guest_id), FOREIGN KEY (response_staff_id) REFERENCES hospitality_technology.staff(staff_id) )\n"} {"conversations": [{"role": "user", "content": "List all ERC20 tokens where the price is between $1 and $10, including their names, symbols, and contract addresses."}, {"role": "assistant", "content": "SELECT tm.name, tm.symbol, tm.contract_address FROM token_metas tm JOIN token_prices_latest tpl ON tm.contract_address = tpl.contract_address WHERE tm.is_erc20 = 1 AND tpl.price BETWEEN 1 AND 10;"}, {"role": "user", "content": "I think there's an error in your query - the token_prices_latest table isn't in the schema. Can you modify it to use the token_balances table instead?"}, {"role": "assistant", "content": "SELECT tm.name, tm.symbol, tm.contract_address FROM token_metas tm JOIN token_balances tb ON tm.contract_address = tb.wallet_address WHERE tm.is_erc20 = 1 AND CAST(tb.amount AS decimal) BETWEEN 1 AND 10;"}, {"role": "user", "content": "That doesn't seem right either. Let's just get the basic ERC20 token information without price filtering for now."}, {"role": "assistant", "content": "SELECT name, symbol, contract_address FROM token_metas WHERE is_erc20 = 1 LIMIT 100;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE token_metas ( block_timestamp.timestamp, block_number.bigint, transaction_hash.text, transaction_index.bigint, from_address.text, contract_address.text, symbol.text, total_supply.text, name.text, decimals.bigint, is_erc20.integer, is_erc721.integer, is_erc1155.integer, is_proxy.integer, extra_info.text, pk.integer )\nCREATE TABLE erc1155_approval_for_all ( block_number bigint NOT NULL, block_timestamp timestamp(3) NOT NULL, transaction_index integer NOT NULL, transaction_hash varchar(66) NOT NULL, log_index integer NOT NULL, contract_address varchar(42) NOT NULL )\nCREATE TABLE erc20_balances ( block_number bigint NOT NULL, contract_address varchar NOT NULL, wallet_address varchar NOT NULL, amount varchar NOT NULL, pk varchar NOT NULL )\nCREATE TABLE erc20_balances_historical ( block_number bigint, contract_address text, wallet_address text, amount text, pk integer )\nCREATE TABLE nft_holders ( block_number bigint, contract_address text, wallet_address text, token_id text, contract_type text, amount text, pk text )\nCREATE TABLE nft_holder_historical ( block_number.bigint, contract_address.text, wallet_address.text, token_id.text, contract_type.text, amount.text, pk.integer )\nCREATE TABLE sui_nfts ( object_id text, status text, collection_type text, package_id text, previous_transaction text, display text, owner text, name text )\nCREATE TABLE nft_collections ( blockchain text, contract_address text, name text, symbol text, deploy_block_number bigint, deploy_block_time bigint, erc_type text, owner text, traits text, description text, slug text, media_info text, image_url text, banner_image_url text, updated_at bigint, banner text, token_count bigint, floor_price text, floor_price_symbol text, floor_price_contract text, pk integer )\nCREATE TABLE erc20_approval ( block_number bigint NOT NULL, block_timestamp timestamp(6) NOT NULL, transaction_index integer NOT NULL, transaction_hash varchar NOT NULL, log_index integer NOT NULL, contract_address varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE token_balances ( block_number bigint, block_timestamp timestamp, tick text, wallet_address text, total_supply decimal, amount decimal )\nCREATE TABLE token_info (\n block_timestamp timestamp(3) NOT NULL, -- Timestamp of the block containing the inscription (matches block_timestamp in transactions table)\n block_number bigint NOT NULL, -- Block number containing the inscription (matches block_number in transactions table)\n tx_index integer NOT NULL, -- Index of the transaction containing the inscription (matches transaction_index in transactions table)\n tx_hash varchar(66) NOT NULL, -- Unique identifier of the transaction containing the inscription (matches hash in transactions table)\n tick varchar NOT NULL, -- Token tick\n max_supply decimal(38,0) NOT NULL, -- Max supply\n lim decimal(38,0) NOT NULL, -- Limit of each mint\n wlim decimal(38,0) NOT NULL, -- Limit of each address can maximum mint\n dec integer NOT NULL, -- Decimal for minimum divie\n creator varchar(42) NOT NULL -- Address originating the inscription (matches from_address in transactions table)\n)\nCREATE TABLE token_activities ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash varchar, log_index integer, type varchar, tick varchar, id varchar, amt decimal, from_address varchar, to_address varchar )\nCREATE TABLE mud_holesky_redstone ( address varchar NOT NULL, table_id varchar NOT NULL, key_bytes varchar NOT NULL, key0 varchar NOT NULL, key1 varchar NOT NULL, static_data varchar NOT NULL, encoded_lengths varchar NOT NULL, dynamic_data varchar NOT NULL, is_deleted boolean NOT NULL, block_number bigint NOT NULL, log_index bigint NOT NULL )\nCREATE TABLE token_balances_bitcoin ( block_number bigint, block_timestamp timestamp, tick varchar, wallet_address varchar, total_supply varchar, amount varchar )\nCREATE TABLE token_info_bitcoin ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash varchar, tick varchar, max_supply decimal, lim decimal, wlim decimal, dec integer, creator varchar )\nCREATE TABLE token_activities_avalanche ( block_timestamp.timestamp, block_number.bigint, tx_index.integer, tx_hash.text, log_index.integer, type.text, tick.text, id.text, amt.decimal, from_address.text, to_address.text )\nCREATE TABLE token_balances_avalanche (\n block_number bigint NOT NULL, -- Block number containing the transaction\n block_timestamp timestamp(3) NOT NULL, -- Block timestamp containing the transaction\n tick varchar(20) NOT NULL, -- Ticker: Identifier of the inscription\n wallet_address varchar(42) NOT NULL, -- Address of owner\n total_supply decimal(38,0) NOT NULL, -- Max supply: Set max supply of the inscription\n amount decimal(38,0) NOT NULL -- The balance of wallet balance at the corresponding block height\n)\nCREATE TABLE token_info_avalanche ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash varchar, tick varchar, max_supply decimal, lim decimal, wlim decimal, dec integer, creator varchar, minted decimal, holders decimal, txs decimal, updated_timestamp timestamp, completed_timestamp timestamp, id varchar )\n"} {"conversations": [{"role": "user", "content": "List the names of employees and the agency they work for who have scheduled at least one appointment. Show the employee's first name, last name, and agency_id."}, {"role": "assistant", "content": "SELECT DISTINCT e.first_name, e.last_name, e.agency_id\nFROM government_services.employees e\nJOIN government_services.appointments a ON e.employee_id = a.employee_id;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.services ( service_id text, agency_id text, service_name text, description text, category text, eligibility_criteria text, standard_fee numeric, average_processing_time_days integer, is_active boolean, online_application_url text )\nCREATE TABLE government_services.applications ( application_id text, citizen_id text, service_id text, submitted_at timestamp, status text, last_updated_at timestamp, assigned_employee_id text, decision_date date, notes text, reference_number text )\nCREATE TABLE government_services.payments ( payment_id text, application_id text, citizen_id text, service_id text, amount numeric, currency text, payment_method text, payment_provider_reference text, payment_timestamp timestamp, status text, notes text )\nCREATE TABLE government_services.employees ( employee_id text, agency_id text, first_name text, last_name text, job_title text, department text, work_email text, work_phone text, hire_date date, termination_date date, access_level text, manager_employee_id text )\nCREATE TABLE government_services.appointments ( appointment_id text, citizen_id text, employee_id text, location_id text, service_id text, scheduled_start_time timestamp, scheduled_end_time timestamp, purpose text, status text, booking_method text, created_at timestamp, notes text )\nCREATE TABLE government_services.notifications ( notification_id text, citizen_id text, application_id text, message_subject text, message_body text, channel text, sent_at timestamp, status text, related_entity_type text, related_entity_id text )\n"} {"conversations": [{"role": "user", "content": "Show me wallet addresses that hold more than 1000 of any ERC20 token, along with the token symbol and amount, sorted by amount in descending order."}, {"role": "assistant", "content": "SELECT b.wallet_address, t.symbol, b.amount FROM erc20_balances b JOIN sui_coins_metadata t ON b.contract_address = t.coin_type WHERE CAST(b.amount AS decimal) > 1000 ORDER BY CAST(b.amount AS decimal) DESC;"}, {"role": "user", "content": "Can you also include the current price of each token from the token_prices_latest table?"}, {"role": "assistant", "content": "SELECT b.wallet_address, t.symbol, b.amount, p.price FROM erc20_balances b JOIN sui_coins_metadata t ON b.contract_address = t.coin_type JOIN token_prices_latest p ON b.contract_address = p.address WHERE CAST(b.amount AS decimal) > 1000 ORDER BY CAST(b.amount AS decimal) DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE erc1155_approval_for_all (\n block_number bigint NOT NULL, -- Block number containing the transaction\n block_timestamp timestamp(3) NOT NULL, -- Timestamp of the block containing the transaction\n transaction_index integer NOT NULL, -- Index of the transaction within the block\n transaction_hash varchar(66) NOT NULL, -- Transaction hash\n log_index integer NOT NULL, -- Log index\n contract_address varchar(42) NOT NULL -- Event contract address\n)\nCREATE TABLE erc20_balances ( block_number.bigint, contract_address.text, wallet_address.text, amount.text, pk.text )\nCREATE TABLE erc20_balances_historical ( block_number bigint NOT NULL, contract_address varchar NOT NULL, wallet_address varchar NOT NULL, amount varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE nft_holders ( block_number bigint, contract_address varchar, wallet_address varchar, token_id varchar, contract_type varchar, amount varchar, pk varchar )\nCREATE TABLE sui_coins_metadata ( object_id varchar, coin_type varchar, status varchar, decimals bigint, description varchar, icon_url varchar, symbol varchar, name varchar )\nCREATE TABLE nft_metadata (\n blockchain varchar NOT NULL, -- blockchain fields for the functionType in contract\n contract_address varchar NOT NULL, -- Contract address(with bloom filter)\n token_id varchar NOT NULL, -- The number of the token\n contract_name varchar NOT NULL, -- contract_name fields for the functionType in contract\n erc_type varchar NOT NULL, -- The type of token\n amount bigint NOT NULL, -- amount fields for the functionType in contract\n minter varchar NOT NULL, -- minter fields for the functionType in contract\n owner varchar NOT NULL, -- owner fields for the functionType in contract\n mint_block_number bigint NOT NULL, -- mint_block_number fields for the functionType in contract\n mint_time bigint NOT NULL, -- mint_time fields for the functionType in contract\n mint_transaction_hash varchar NOT NULL, -- mint_transaction_hash fields for the functionType in contract\n mint_price varchar NOT NULL, -- mint_price fields for the functionType in contract\n token_uri varchar NOT NULL, -- token_uri fields for the functionType in contract\n metadata varchar NOT NULL, -- metadata fields for the functionType in contract\n name varchar NOT NULL, -- name fields for the functionType in contract\n image_uri varchar NOT NULL, -- image_uri fields for the functionType in contract\n traits varchar NOT NULL, -- traits fields for the functionType in contract\n updated_at bigint NOT NULL, -- updated_at fields for the functionType in contract\n status varchar NOT NULL, -- status fields for the functionType in contract\n rarity_score real NOT NULL, -- rarity_score fields for the functionType in contract\n rarity_rank integer NOT NULL, -- rarity_rank fields for the functionType in contract\n unique_attribute_count integer NOT NULL, -- unique_attribute_count fields for the functionType in contract\n pk integer NOT NULL -- Partition key for the table(floor(mint_time / 1000 / 86400 / 30))\n)\nCREATE TABLE token_prices_latest ( blockchain varchar, address varchar, decimals bigint, symbol varchar, price real, timestamp timestamp )\nCREATE TABLE token_info ( block_timestamp timestamp(3) NOT NULL, block_number bigint NOT NULL, tx_index integer NOT NULL, tx_hash varchar(66) NOT NULL, tick varchar NOT NULL, max_supply decimal(38,0) NOT NULL, lim decimal(38,0) NOT NULL, wlim decimal(38,0) NOT NULL, dec integer NOT NULL, creator varchar(42) NOT NULL )\nCREATE TABLE mud_holesky_redstone (\n address varchar NOT NULL, -- address fields for the functionType in contract\n table_id varchar NOT NULL, -- table_id fields for the functionType in contract\n key_bytes varchar NOT NULL, -- key_bytes fields for the functionType in contract\n key0 varchar NOT NULL, -- key0 fields for the functionType in contract\n key1 varchar NOT NULL, -- key1 fields for the functionType in contract\n static_data varchar NOT NULL, -- static_data fields for the functionType in contract\n encoded_lengths varchar NOT NULL, -- encoded_lengths fields for the functionType in contract\n dynamic_data varchar NOT NULL, -- dynamic_data fields for the functionType in contract\n is_deleted boolean NOT NULL, -- is_deleted fields for the functionType in contract\n block_number bigint NOT NULL, -- Block number uniquely identifying the block\n log_index bigint NOT NULL -- Index of the log within the transaction\n)\nCREATE TABLE token_activities_bitcoin ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash varchar, log_index integer, type varchar, tick varchar, id varchar, amt decimal, from_address varchar, to_address varchar )\nCREATE TABLE token_balances_avalanche (\n block_number bigint NOT NULL, -- Block number containing the transaction\n block_timestamp timestamp(3) NOT NULL, -- Block timestamp containing the transaction\n tick varchar(20) NOT NULL, -- Ticker: Identifier of the inscription\n wallet_address varchar(42) NOT NULL, -- Address of owner\n total_supply decimal(38,0) NOT NULL, -- Max supply: Set max supply of the inscription\n amount decimal(38,0) NOT NULL -- The balance of wallet balance at the corresponding block height\n)\nCREATE TABLE token_info_avalanche ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash text, tick text, max_supply decimal, lim decimal, wlim decimal, dec integer, creator text, minted decimal, holders decimal, txs decimal, updated_timestamp timestamp, completed_timestamp timestamp, id text )\n"} {"conversations": [{"role": "user", "content": "Could you provide the total number of game sessions and the number of distinct players for each game genre? Display the genre, session count, and player count."}, {"role": "assistant", "content": "SELECT g.genre, COUNT(gs.session_id) AS session_count, COUNT(DISTINCT gs.player_id) AS player_count FROM gaming_technology.game_sessions AS gs JOIN gaming_technology.games AS g ON gs.game_id = g.game_id WHERE g.genre IS NOT NULL GROUP BY g.genre ORDER BY g.genre;"}, {"role": "user", "content": "Thanks. Can you modify the query to only include games that were released after the year 2020?"}, {"role": "assistant", "content": "SELECT g.genre, COUNT(gs.session_id) AS session_count, COUNT(DISTINCT gs.player_id) AS player_count FROM gaming_technology.game_sessions AS gs JOIN gaming_technology.games AS g ON gs.game_id = g.game_id WHERE g.genre IS NOT NULL AND g.release_date >= '2021-01-01' GROUP BY g.genre ORDER BY g.genre;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE gaming_technology.players (\n player_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for the player\n username character varying(100) NOT NULL UNIQUE, -- player's chosen display name\n email character varying(255) NOT NULL UNIQUE, -- player's email address for login/recovery\n password_hash text NOT NULL, -- securely hashed password\n registration_date timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP, -- when the player account was created\n last_login timestamp with time zone, -- timestamp of the last successful login\n country_code character(2), -- player's country (ISO 3166-1 alpha-2)\n status character varying(20) NOT NULL DEFAULT 'active', -- account status (e.g., active, banned, suspended)\n profile_data jsonb, -- flexible field for avatar url, bio, preferences etc.\n PRIMARY KEY (player_id)\n)\nCREATE TABLE gaming_technology.games (\n game_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for the game\n title character varying(200) NOT NULL, -- official title of the game\n developer_id uuid NOT NULL, -- FK linking to the developers table\n publisher_id uuid, -- FK linking to a potential publishers table (optional)\n genre character varying(100), -- primary genre (e.g., RPG, FPS, Strategy)\n release_date date, -- official release date\n description text, -- short description or synopsis of the game\n platform character varying(50) NOT NULL, -- primary platform (e.g., PC, PlayStation 5, Xbox Series X, Mobile)\n engine character varying(100), -- game engine used (e.g., Unreal Engine 5, Unity)\n website character varying(255), -- official website URL\n PRIMARY KEY (game_id)\n -- FOREIGN KEY (developer_id) REFERENCES gaming_technology.developers(developer_id) -- Example FK constraint\n)\nCREATE TABLE gaming_technology.game_sessions (\n session_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for the game session\n player_id uuid NOT NULL, -- FK linking to the players table\n game_id uuid NOT NULL, -- FK linking to the games table\n server_id uuid, -- FK linking to the servers table (nullable for single-player)\n start_time timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP, -- when the session began\n end_time timestamp with time zone, -- when the session ended (null if ongoing)\n duration_seconds integer, -- calculated duration of the session in seconds\n score integer, -- player's score for the session, if applicable\n session_data jsonb, -- flexible field for session-specific info (e.g., map played, character used)\n PRIMARY KEY (session_id)\n -- FOREIGN KEY (player_id) REFERENCES gaming_technology.players(player_id),\n -- FOREIGN KEY (game_id) REFERENCES gaming_technology.games(game_id),\n -- FOREIGN KEY (server_id) REFERENCES gaming_technology.servers(server_id)\n)\nCREATE TABLE gaming_technology.servers (\n server_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for the game server instance\n game_id uuid NOT NULL, -- FK linking to the game this server hosts\n server_name character varying(150), -- display name for the server\n region character varying(50) NOT NULL, -- geographical region (e.g., us-east-1, eu-west-2)\n ip_address character varying(45), -- IP address (IPv4 or IPv6)\n port integer, -- network port number\n current_players integer NOT NULL DEFAULT 0, -- number of players currently connected\n max_players integer NOT NULL, -- maximum player capacity\n status character varying(30) NOT NULL DEFAULT 'offline', -- server status (e.g., online, offline, maintenance)\n last_heartbeat timestamp with time zone, -- last time the server reported its status\n PRIMARY KEY (server_id)\n -- FOREIGN KEY (game_id) REFERENCES gaming_technology.games(game_id)\n)\nCREATE TABLE gaming_technology.achievements (\n achievement_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for an achievement definition\n game_id uuid NOT NULL, -- FK linking to the game the achievement belongs to\n name character varying(150) NOT NULL, -- name of the achievement\n description text NOT NULL, -- how to unlock the achievement\n icon_url character varying(255), -- URL for the achievement's icon\n points integer DEFAULT 0, -- points awarded for unlocking (optional)\n hidden boolean DEFAULT false, -- whether the achievement details are hidden until unlocked\n PRIMARY KEY (achievement_id)\n -- FOREIGN KEY (game_id) REFERENCES gaming_technology.games(game_id)\n)\nCREATE TABLE gaming_technology.player_achievements (\n player_achievement_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for this unlock instance\n player_id uuid NOT NULL, -- FK linking to the player who unlocked it\n achievement_id uuid NOT NULL, -- FK linking to the achievement definition\n unlocked_at timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP, -- when the achievement was unlocked\n PRIMARY KEY (player_achievement_id),\n UNIQUE (player_id, achievement_id) -- Ensure a player can only unlock an achievement once\n -- FOREIGN KEY (player_id) REFERENCES gaming_technology.players(player_id),\n -- FOREIGN KEY (achievement_id) REFERENCES gaming_technology.achievements(achievement_id)\n)\n"} {"conversations": [{"role": "user", "content": "What is the average ROI for smart money addresses on the Ethereum chain with a realized ratio above 70%?"}, {"role": "assistant", "content": "SELECT AVG(roi) FROM smart_money_profit WHERE chain = 'Ethereum' AND realized_ratio > 70;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE token_basic_info ( coin_id character varying(100) NOT NULL, -- the id of the token token_name character varying(100) NOT NULL, -- the token's name token_symbol character varying(100) NOT NULL, -- the token's symbol token_address character varying(100) NOT NULL, -- the token's address chain text, -- the chain that the token resides price double precision, -- the current price of the token price_change_percentage_1h double precision, -- change in value divided by the absolute price value of the original token price in 1 hour price_change_percentage_24h double precision, -- change in value divided by the absolute price value of the original token price in 24 hours price_change_percentage_7d double precision, -- change in value divided by the absolute price value of the original token price in 7 days highest_price_24h double precision, -- the highest price of the token in 24 hours lowest_price_24h double precision, -- the lowest price of the token in 24 hours market_cap double precision, -- the market cap of the token market_cap_rank bigint, -- the rank of the token market cap in desc market_cap_change_percentage_24h text, -- the percentage of market cap changes in 24 hours total_volume text, -- the trade volum of the token both in decentralized exchange(DEX) and centralized exchange(CEX) narrative text, -- the category or narrative of the token trend_rank biging, -- the trending rank of the token, value 1 expresses the most popular token. ,PRIMARY KEY (coin_id, chain) )\nCREATE TABLE narrative_info ( narrative character varying(512) NOT NULL, -- the id of narrative top_3_coins text, -- the top 3 tokens in the narrative price_change_percentage_1h double precision, -- change in value divided by the absolute price value of the original token price in 1 hour in the narrative price_change_percentage_24h double precision, -- change in value divided by the absolute price value of the original token price in 24 hours in the narrative price_change_percentage_7d double precision, -- change in value divided by the absolute price value of the original token price in 7 days in the narrative market_cap double precision, -- the market cap of the narrative volume_24h double precision, -- the trade volume of the narrative trend_rank bigint, -- the trending rank of the narrative, value 1 expresses the most popular narrative token_num bigint, -- total token number in the narrative ,PRIMARY KEY (narrative) )\nCREATE TABLE token_dexpool_info ( pair_address character varying(512) NOT NULL, -- the id of dexpool token_name character varying(100) NOT NULL, -- the name of the token in the dexpool token_symbol character varying(100) NOT NULL, -- the token's symbol chain text, -- the chain that the dexpool resides price double precision, -- the current price of the token price_change_percentage_1h double precision, -- change in value divided by the absolute price value of the original token price in 1 hour price_change_percentage_6h double precision, -- change in value divided by the absolute price value of the original token price in 6 hours price_change_percentage_24h double precision, -- change in value divided by the absolute price value of the original token price in 24 hours makers_24h double precision, -- the makers of the dex pool in 24 hours volume_24h double precision, -- the trade volume of the dex pool in 24 hours liquidity double precision, -- the liquidity of the dex pool market_cap double precision, -- the market cap of the token trend_rank bigint, -- the rank of token in the dex pool of recent trending, value 1 expresses the most popular token. ,PRIMARY KEY (pair_address, chain) )\nCREATE TABLE smart_money_profit ( address character varying(100) NOT NULL, -- the user's address rank INT, -- the rank of the address in trade performance, value 1 expresses the best address. profit numeric(38,6), -- the profit user made in a month roi numeric(38,2), -- the roi of the user in a month realized_ratio numeric(38,2), -- the percentage of the user's realized profit most_profit_token character varying(100), -- the token symbol of the user's most profitable trade last_trade_time character varying(100), -- the last trade time of the user chain character varying(100), -- the chain that the address resides PRIMARY KEY (address, chain) )\nCREATE TABLE smart_money_token_performance ( token_address character varying(100) NOT NULL, -- the token's address token_symbol character varying(100), -- the tokens's symbol pnl numeric(38,2), -- the profit users made on this token net_flow numeric(38,2), -- the netflow of the token, means the money user spent minus the the money user sold of this token avg_cost numeric(38,16), -- the average cost price of user spent on this token price double precision, -- the current price of the token realized_ratio numeric(10,2), -- the ratio user sold of the token roi numeric(10,2), -- the roi users made of this token chain character varying(100), -- the chain that the token resides PRIMARY KEY (token_address, chain) )\nCREATE TABLE smart_money_token_inflow ( token_address character varying(100) NOT NULL, -- the token's address token_symbol character varying(100), -- the tokens's symbol token_amount numeric(38,2), -- the absolute value of the amount if user bought minus the amount user sold of this token usd_value numeric(38,2), -- the absolute usd value of the bought token minus sold token avg_price numeric(38,6), -- the average cost price of user spent on this token type int, -- the direction of the trade on this token. 1 means buying, 2 means selling address_amount integer, -- the amount of the user bought this token narrative character varying(100), -- the category or narrative of the token chain character varying(100), -- the chain that the token resides ,PRIMARY KEY (token_address, chain) )\n"} {"conversations": [{"role": "user", "content": "Show me pairs of passengers who share the same loyalty program, including their IDs, first and last names, and the loyalty_program_id."}, {"role": "assistant", "content": "SELECT p1.passenger_id AS passenger1_id, p1.first_name AS first1, p1.last_name AS last1, p2.passenger_id AS passenger2_id, p2.first_name AS first2, p2.last_name AS last2, p1.loyalty_program_id FROM transportation.passengers p1 JOIN transportation.passengers p2 ON p1.loyalty_program_id = p2.loyalty_program_id AND p1.passenger_id < p2.passenger_id;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.passengers ( passenger_id text PRIMARY KEY, first_name text, last_name text, email text, phone_number text, date_of_birth date, loyalty_program_id text, created_at timestamp )\n"} {"conversations": [{"role": "user", "content": "Can you list the number of citizens registered each month in 2024? Please show the month and the citizen count."}, {"role": "assistant", "content": "SELECT TO_CHAR(registration_date, 'YYYY-MM') AS registration_month, COUNT(*) AS citizen_count FROM government_services.citizens WHERE registration_date >= '2024-01-01' AND registration_date < '2025-01-01' GROUP BY registration_month ORDER BY registration_month;"}, {"role": "user", "content": "Now, can you also show the number of verified citizens for each month?"}, {"role": "assistant", "content": "SELECT TO_CHAR(registration_date, 'YYYY-MM') AS registration_month, COUNT(*) AS citizen_count, SUM(CASE WHEN is_verified = true THEN 1 ELSE 0 END) AS verified_citizen_count FROM government_services.citizens WHERE registration_date >= '2024-01-01' AND registration_date < '2025-01-01' GROUP BY registration_month ORDER BY registration_month;"}, {"role": "user", "content": "I see some months with zero verified citizens, but they still show up. Can you exclude months with zero verified citizens from the result?"}, {"role": "assistant", "content": "SELECT registration_month, citizen_count, verified_citizen_count FROM (SELECT TO_CHAR(registration_date, 'YYYY-MM') AS registration_month, COUNT(*) AS citizen_count, SUM(CASE WHEN is_verified = true THEN 1 ELSE 0 END) AS verified_citizen_count FROM government_services.citizens WHERE registration_date >= '2024-01-01' AND registration_date < '2025-01-01' GROUP BY registration_month) sub WHERE verified_citizen_count > 0 ORDER BY registration_month;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.citizens ( citizen_id character varying(64) NOT NULL, national_id_number character varying(128) NOT NULL UNIQUE, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, date_of_birth date NOT NULL, gender character varying(20), primary_address text NOT NULL, contact_email character varying(128) UNIQUE, contact_phone character varying(32), registration_date timestamp NOT NULL, is_verified boolean DEFAULT false, PRIMARY KEY (citizen_id) )\n"} {"conversations": [{"role": "user", "content": "How many employees work in each department? List the department name and the count."}, {"role": "assistant", "content": "SELECT department, COUNT(*) FROM government_services.employees GROUP BY department"}, {"role": "user", "content": "Only show departments with more than 5 employees."}, {"role": "assistant", "content": "SELECT department, COUNT(*) FROM government_services.employees GROUP BY department HAVING COUNT(*) > 5"}, {"role": "user", "content": "For these departments, also list the job titles present."}, {"role": "assistant", "content": "SELECT department, COUNT(*), STRING_AGG(DISTINCT job_title, ', ') FROM government_services.employees GROUP BY department HAVING COUNT(*) > 5"}, {"role": "user", "content": "Add the total number of employees hired in 2023 for each of these departments."}, {"role": "assistant", "content": "SELECT department, COUNT(*), STRING_AGG(DISTINCT job_title, ', '), SUM(CASE WHEN EXTRACT(YEAR FROM hire_date) = 2023 THEN 1 ELSE 0 END) AS employees_hired_in_2023 FROM government_services.employees GROUP BY department HAVING COUNT(*) > 5"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.citizens ( citizen_id text, national_id_number text, first_name text, last_name text, date_of_birth date, gender text, primary_address text, contact_email text, contact_phone text, registration_date timestamp, is_verified boolean )\nCREATE TABLE government_services.agencies ( agency_id text, agency_name text, jurisdiction_level text, primary_contact_email text, main_phone_number text, website_url text, established_date date, parent_agency_id text )\nCREATE TABLE government_services.services (\n service_id character varying(64) NOT NULL, -- unique identifier for the service\n agency_id character varying(64) NOT NULL, -- FK to agencies table\n service_name character varying(255) NOT NULL, -- name of the service (e.g., Driver's License Renewal)\n description text,\n category character varying(100), -- e.g., Licensing, Benefits, Taxation, Permits\n eligibility_criteria text, -- description of who is eligible\n standard_fee numeric(10, 2) DEFAULT 0.00, -- typical fee for the service\n average_processing_time_days integer, -- estimated processing time\n is_active boolean DEFAULT true, -- whether the service is currently offered\n online_application_url character varying(255),\n PRIMARY KEY (service_id)\n)\nCREATE TABLE government_services.employees ( employee_id text, agency_id text, first_name text, last_name text, job_title text, department text, work_email text, work_phone text, hire_date date, termination_date date, access_level text, manager_employee_id text )\nCREATE TABLE government_services.service_locations ( location_id character varying(64) NOT NULL, agency_id character varying(64) NOT NULL, location_name character varying(200), address text NOT NULL, city character varying(100), state character varying(50), postal_code character varying(20), latitude numeric(9, 6), longitude numeric(9, 6), operating_hours text, contact_phone character varying(32), is_accessible boolean, PRIMARY KEY (location_id) )\nCREATE TABLE government_services.appointments ( appointment_id.text, citizen_id.text, employee_id.text, location_id.text, service_id.text, scheduled_start_time.timestamp, scheduled_end_time.timestamp, purpose.text, status.text, booking_method.text, created_at.timestamp, notes.text )\n"} {"conversations": [{"role": "user", "content": "List all SUI coins that have the status 'inactive', including their owner address and coin_type."}, {"role": "assistant", "content": "SELECT coin_type, owner FROM sui_coins WHERE status = 'inactive';"}, {"role": "user", "content": "Add the name and symbol for each coin by joining with sui_coins_metadata."}, {"role": "assistant", "content": "SELECT sc.coin_type, sc.owner, scm.name, scm.symbol FROM sui_coins sc JOIN sui_coins_metadata scm ON sc.coin_type = scm.coin_type WHERE sc.status = 'inactive';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE token_metas ( block_timestamp timestamp, block_number bigint, transaction_hash varchar, transaction_index bigint, from_address varchar, contract_address varchar, symbol varchar, total_supply varchar, name varchar, decimals bigint, is_erc20 integer, is_erc721 integer, is_erc1155 integer, is_proxy integer, extra_info varchar, pk integer )\nCREATE TABLE erc1155_approval_for_all ( block_number bigint NOT NULL, block_timestamp timestamp(3) NOT NULL, transaction_index integer NOT NULL, transaction_hash varchar(66) NOT NULL, log_index integer NOT NULL, contract_address varchar(42) NOT NULL )\nCREATE TABLE erc20_balances ( block_number.bigint, contract_address.text, wallet_address.text, amount.text, pk.text )\nCREATE TABLE erc20_balances_historical (\n block_number bigint NOT NULL, -- Block number containing the transaction\n contract_address varchar NOT NULL, -- Event contract address\n wallet_address varchar NOT NULL, -- The wallet address for the contract\n amount varchar NOT NULL, -- Wallet's on-chain balance at the corresponding block height\n pk integer NOT NULL -- Partition key for the table(floor(block_number / 7200))\n)\nCREATE TABLE nft_holders (\n block_number bigint NOT NULL, -- Block number containing the transaction\n contract_address varchar NOT NULL, -- Event contract address\n wallet_address varchar NOT NULL, -- The wallet address for the contract(with bloom filter)\n token_id varchar NOT NULL, -- NFT token id\n contract_type varchar NOT NULL, -- NFT contract type\n amount varchar NOT NULL, -- Number of held NFTs\n pk varchar NOT NULL -- The last string partition of the contract.\n)\nCREATE TABLE nft_holder_historical ( block_number.bigint, contract_address.text, wallet_address.text, token_id.text, contract_type.text, amount.text, pk.integer )\nCREATE TABLE sui_coins ( object_id text, status text, coin_type text, balance text, owner text )\nCREATE TABLE sui_coins_metadata ( object_id varchar, coin_type varchar, status varchar, decimals bigint, description varchar, icon_url varchar, symbol varchar, name varchar )\nCREATE TABLE sui_nfts ( object_id varchar, status varchar, collection_type varchar, package_id varchar, previous_transaction varchar, display varchar, owner varchar, name varchar )\nCREATE TABLE nft_collections (\n blockchain varchar NOT NULL, -- blockchain fields for the functionType in contract\n contract_address varchar NOT NULL, -- Contract address(with bloom filter)\n name varchar NOT NULL, -- name fields for the functionType in contract\n symbol varchar NOT NULL, -- symbol fields for the functionType in contract\n deploy_block_number bigint NOT NULL, -- deploy_block_number fields for the functionType in contract\n deploy_block_time bigint NOT NULL, -- deploy_block_time fields for the functionType in contract\n erc_type varchar NOT NULL, -- The type of token\n owner varchar NOT NULL, -- owner fields for the functionType in contract\n traits varchar NOT NULL, -- traits fields for the functionType in contract\n description varchar NOT NULL, -- description fields for the functionType in contract\n slug varchar NOT NULL, -- slug fields for the functionType in contract\n media_info varchar NOT NULL, -- media_info fields for the functionType in contract\n image_url varchar NOT NULL, -- image_url fields for the functionType in contract\n banner_image_url varchar NOT NULL, -- banner_image_url fields for the functionType in contract\n updated_at bigint NOT NULL, -- updated_at fields for the functionType in contract\n banner varchar NOT NULL, -- banner fields for the functionType in contract\n token_count bigint NOT NULL, -- token_count fields for the functionType in contract\n floor_price varchar NOT NULL, -- floor_price fields for the functionType in contract\n floor_price_symbol varchar NOT NULL, -- floor_price_symbol fields for the functionType in contract\n floor_price_contract varchar NOT NULL, -- floor_price_contract fields for the functionType in contract\n pk integer NOT NULL -- Partition key for the table(floor(deploy_block_time / 1000 / 86400 / 30))\n)\nCREATE TABLE token_prices ( uuid varchar, blockchain varchar, address varchar, decimals bigint, symbol varchar, price real, timestamp timestamp )\nCREATE TABLE token_prices_latest (\n blockchain varchar(36) NOT NULL, -- blockchain fields for the functionType in contract\n address varchar(42) NOT NULL, -- address fields for the functionType in contract\n decimals bigint NOT NULL, -- decimals fields for the functionType in contract\n symbol varchar(36) NOT NULL, -- symbol fields for the functionType in contract\n price real NOT NULL, -- price fields for the functionType in contract\n timestamp timestamp(6) NOT NULL -- timestamp fields for the functionType in contract\n)\nCREATE TABLE erc20_approval ( block_number bigint, block_timestamp timestamp, transaction_index integer, transaction_hash text, log_index integer, contract_address text, pk integer )\nCREATE TABLE token_balances ( block_number bigint, block_timestamp timestamp, tick text, wallet_address text, total_supply decimal, amount decimal )\nCREATE TABLE token_info (\n block_timestamp timestamp(3) NOT NULL, -- Timestamp of the block containing the inscription (matches block_timestamp in transactions table)\n block_number bigint NOT NULL, -- Block number containing the inscription (matches block_number in transactions table)\n tx_index integer NOT NULL, -- Index of the transaction containing the inscription (matches transaction_index in transactions table)\n tx_hash varchar(66) NOT NULL, -- Unique identifier of the transaction containing the inscription (matches hash in transactions table)\n tick varchar NOT NULL, -- Token tick\n max_supply decimal(38,0) NOT NULL, -- Max supply\n lim decimal(38,0) NOT NULL, -- Limit of each mint\n wlim decimal(38,0) NOT NULL, -- Limit of each address can maximum mint\n dec integer NOT NULL, -- Decimal for minimum divie\n creator varchar(42) NOT NULL -- Address originating the inscription (matches from_address in transactions table)\n)\nCREATE TABLE token_activities ( block_timestamp.timestamp, block_number.bigint, tx_index.integer, tx_hash.text, log_index.integer, type.text, tick.text, id.text, amt.decimal, from_address.text, to_address.text )\nCREATE TABLE mud_holesky_redstone ( address.text, table_id.text, key_bytes.text, key0.text, key1.text, static_data.text, encoded_lengths.text, dynamic_data.text, is_deleted.boolean, block_number.bigint, log_index.bigint )\nCREATE TABLE token_balances_bitcoin ( block_number bigint, block_timestamp timestamp, tick varchar, wallet_address varchar, total_supply varchar, amount varchar )\nCREATE TABLE token_info_bitcoin ( block_timestamp timestamp(3) NOT NULL, block_number bigint NOT NULL, tx_index integer NOT NULL, tx_hash varchar(66) NOT NULL, tick varchar(255) NOT NULL, max_supply decimal(38,0) NOT NULL, lim decimal(38,0) NOT NULL, wlim decimal(38,0) NOT NULL, dec integer NOT NULL, creator varchar(42) NOT NULL )\nCREATE TABLE token_activities_bitcoin ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash text, log_index integer, type text, tick text, id text, amt decimal, from_address text, to_address text )\nCREATE TABLE token_activities_avalanche ( block_timestamp timestamp(3) NOT NULL, block_number bigint NOT NULL, tx_index integer NOT NULL, tx_hash varchar(66) NOT NULL, log_index integer NOT NULL, type varchar(20) NOT NULL, tick varchar(255) NOT NULL, id varchar(255) NOT NULL, amt decimal(38,0) NOT NULL, from_address varchar(42) NOT NULL, to_address varchar(42) NOT NULL )\nCREATE TABLE token_balances_avalanche ( block_number bigint, block_timestamp timestamp, tick text, wallet_address text, total_supply decimal, amount decimal )\nCREATE TABLE token_info_avalanche ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash text, tick text, max_supply decimal, lim decimal, wlim decimal, dec integer, creator text, minted decimal, holders decimal, txs decimal, updated_timestamp timestamp, completed_timestamp timestamp, id text )\n"} {"conversations": [{"role": "user", "content": "List all wallets that were created during the hour of the day which saw the highest number of wallet creations. Show the wallet ID, user ID, address, and creation timestamp."}, {"role": "assistant", "content": "WITH HourlyCounts AS (\n SELECT EXTRACT(HOUR FROM created_at) AS hour, COUNT(*) AS wallet_count\n FROM web3.wallets\n GROUP BY 1\n),\nMaxHour AS (\n SELECT hour\n FROM HourlyCounts\n ORDER BY wallet_count DESC\n LIMIT 1\n)\nSELECT wallet_id, user_id, address, created_at\nFROM web3.wallets\nWHERE EXTRACT(HOUR FROM created_at) = (SELECT hour FROM MaxHour);"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE web3.wallets ( wallet_id text PRIMARY KEY, user_id text, address text, private_key text, created_at timestamp )\n"} {"conversations": [{"role": "user", "content": "Count the number of logs for each action type."}, {"role": "assistant", "content": "SELECT action,\n COUNT(*) AS count\nFROM trading_platform.logs\nGROUP BY action;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE trading_platform.logs ( log_id text PRIMARY KEY, user_id text, action text, details text, logged_at timestamp )\n"} {"conversations": [{"role": "user", "content": "What is the current operational status of the train car with car_id 'CAR123'?"}, {"role": "assistant", "content": "I'm sorry, but I can't provide information on the current operational status of the train car with car_id 'CAR123'. The data in the train_cars table does not include real-time status updates or operational conditions."}], "system": "You are an SQL statement expert and you can refuse the user's question if the question is not related to the table structure. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE train_station_management.train_cars ( car_id text PRIMARY KEY, train_id text, car_number text, car_type text, class text, capacity int, features text )\n"} {"conversations": [{"role": "user", "content": "Show me all active electric vehicles along with their make, model, and license plate, ordered by acquisition date with the newest first."}, {"role": "assistant", "content": "SELECT vehicle_id, make, model, license_plate, acquisition_date FROM transportation.vehicles WHERE status = 'active' AND fuel_type = 'electric' ORDER BY acquisition_date DESC;"}, {"role": "user", "content": "Now include the depot_id for these vehicles and filter to only show vehicles acquired in the last 2 years."}, {"role": "assistant", "content": "SELECT vehicle_id, make, model, license_plate, acquisition_date, depot_id FROM transportation.vehicles WHERE status = 'active' AND fuel_type = 'electric' AND acquisition_date >= CURRENT_DATE - INTERVAL '2 years' ORDER BY acquisition_date DESC;"}, {"role": "user", "content": "Can you also include the vehicle's capacity and order the results by capacity in descending order?"}, {"role": "assistant", "content": "SELECT vehicle_id, make, model, license_plate, acquisition_date, depot_id, capacity FROM transportation.vehicles WHERE status = 'active' AND fuel_type = 'electric' AND acquisition_date >= CURRENT_DATE - INTERVAL '2 years' ORDER BY capacity DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.vehicles ( vehicle_id character varying(64) NOT NULL, license_plate character varying(32) NOT NULL UNIQUE, vin character varying(17) UNIQUE, make character varying(64) NOT NULL, model character varying(64) NOT NULL, year integer NOT NULL, type character varying(32) NOT NULL, capacity integer, fuel_type character varying(32) NOT NULL, status character varying(32) NOT NULL, depot_id character varying(64), acquisition_date date, PRIMARY KEY (vehicle_id) )\n"} {"conversations": [{"role": "user", "content": "Show me the top 5 NFT collections with the highest floor price on Ethereum, along with their names and contract addresses, but only include collections with more than 5000 tokens."}, {"role": "assistant", "content": "SELECT nc.name, nc.contract_address, nc.floor_price FROM nft_collections nc WHERE nc.blockchain = 'Ethereum' AND nc.token_count > 5000 ORDER BY CAST(nc.floor_price AS decimal) DESC LIMIT 5;"}, {"role": "user", "content": "Can you join this with the nft_metadata table to include the average rarity score for these collections?"}, {"role": "assistant", "content": "SELECT nc.name, nc.contract_address, nc.floor_price, AVG(nm.rarity_score) as avg_rarity_score FROM nft_collections nc JOIN nft_metadata nm ON nc.contract_address = nm.contract_address WHERE nc.blockchain = 'Ethereum' AND nc.token_count > 5000 GROUP BY nc.name, nc.contract_address, nc.floor_price ORDER BY CAST(nc.floor_price AS decimal) DESC LIMIT 5;"}, {"role": "user", "content": "Now filter these results to only show collections with an average rarity score above 75."}, {"role": "assistant", "content": "SELECT nc.name, nc.contract_address, nc.floor_price, AVG(nm.rarity_score) as avg_rarity_score FROM nft_collections nc JOIN nft_metadata nm ON nc.contract_address = nm.contract_address WHERE nc.blockchain = 'Ethereum' AND nc.token_count > 5000 GROUP BY nc.name, nc.contract_address, nc.floor_price HAVING AVG(nm.rarity_score) > 75 ORDER BY CAST(nc.floor_price AS decimal) DESC LIMIT 5;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE token_metas ( block_timestamp timestamp(6) NOT NULL, block_number bigint NOT NULL, transaction_hash varchar NOT NULL, transaction_index bigint NOT NULL, from_address varchar NOT NULL, contract_address varchar NOT NULL, symbol varchar NOT NULL, total_supply varchar NOT NULL, name varchar NOT NULL, decimals bigint NOT NULL, is_erc20 integer NOT NULL, is_erc721 integer NOT NULL, is_erc1155 integer NOT NULL, is_proxy integer NOT NULL, extra_info varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE erc1155_approval_for_all ( block_number bigint NOT NULL, block_timestamp timestamp(3) NOT NULL, transaction_index integer NOT NULL, transaction_hash varchar(66) NOT NULL, log_index integer NOT NULL, contract_address varchar(42) NOT NULL )\nCREATE TABLE erc20_balances ( block_number bigint NOT NULL, contract_address varchar NOT NULL, wallet_address varchar NOT NULL, amount varchar NOT NULL, pk varchar NOT NULL )\nCREATE TABLE erc20_balances_historical ( block_number bigint NOT NULL, contract_address varchar NOT NULL, wallet_address varchar NOT NULL, amount varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE nft_holders ( block_number bigint NOT NULL, contract_address varchar NOT NULL, wallet_address varchar NOT NULL, token_id varchar NOT NULL, contract_type varchar NOT NULL, amount varchar NOT NULL, pk varchar NOT NULL )\nCREATE TABLE nft_holder_historical ( block_number bigint NOT NULL, contract_address varchar NOT NULL, wallet_address varchar NOT NULL, token_id varchar NOT NULL, contract_type varchar NOT NULL, amount varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE sui_coins ( object_id varchar NOT NULL, status varchar NOT NULL, coin_type varchar NOT NULL, balance varchar NOT NULL, owner varchar NOT NULL )\nCREATE TABLE sui_coins_metadata ( object_id varchar NOT NULL, coin_type varchar NOT NULL, status varchar NOT NULL, decimals bigint NOT NULL, description varchar NOT NULL, icon_url varchar NOT NULL, symbol varchar NOT NULL, name varchar NOT NULL )\nCREATE TABLE sui_nfts ( object_id varchar NOT NULL, status varchar NOT NULL, collection_type varchar NOT NULL, package_id varchar NOT NULL, previous_transaction varchar NOT NULL, display varchar NOT NULL, owner varchar NOT NULL, name varchar NOT NULL )\nCREATE TABLE nft_metadata ( blockchain varchar NOT NULL, contract_address varchar NOT NULL, token_id varchar NOT NULL, contract_name varchar NOT NULL, erc_type varchar NOT NULL, amount bigint NOT NULL, minter varchar NOT NULL, owner varchar NOT NULL, mint_block_number bigint NOT NULL, mint_time bigint NOT NULL, mint_transaction_hash varchar NOT NULL, mint_price varchar NOT NULL, token_uri varchar NOT NULL, metadata varchar NOT NULL, name varchar NOT NULL, image_uri varchar NOT NULL, traits varchar NOT NULL, updated_at bigint NOT NULL, status varchar NOT NULL, rarity_score real NOT NULL, rarity_rank integer NOT NULL, unique_attribute_count integer NOT NULL, pk integer NOT NULL )\nCREATE TABLE nft_collections ( blockchain varchar NOT NULL, contract_address varchar NOT NULL, name varchar NOT NULL, symbol varchar NOT NULL, deploy_block_number bigint NOT NULL, deploy_block_time bigint NOT NULL, erc_type varchar NOT NULL, owner varchar NOT NULL, traits varchar NOT NULL, description varchar NOT NULL, slug varchar NOT NULL, media_info varchar NOT NULL, image_url varchar NOT NULL, banner_image_url varchar NOT NULL, updated_at bigint NOT NULL, banner varchar NOT NULL, token_count bigint NOT NULL, floor_price varchar NOT NULL, floor_price_symbol varchar NOT NULL, floor_price_contract varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE token_prices ( uuid varchar(36) NOT NULL, blockchain varchar(36) NOT NULL, address varchar(42) NOT NULL, decimals bigint NOT NULL, symbol varchar(36) NOT NULL, price real NOT NULL, timestamp timestamp(6) NOT NULL )\nCREATE TABLE token_prices_latest ( blockchain varchar(36) NOT NULL, address varchar(42) NOT NULL, decimals bigint NOT NULL, symbol varchar(36) NOT NULL, price real NOT NULL, timestamp timestamp(6) NOT NULL )\nCREATE TABLE erc20_approval ( block_number bigint NOT NULL, block_timestamp timestamp(6) NOT NULL, transaction_index integer NOT NULL, transaction_hash varchar NOT NULL, log_index integer NOT NULL, contract_address varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE token_balances ( block_number bigint NOT NULL, block_timestamp timestamp(3) NOT NULL, tick varchar NOT NULL, wallet_address varchar(42) NOT NULL, total_supply decimal(38,0) NOT NULL, amount decimal(38,0) NOT NULL )\nCREATE TABLE token_info ( block_timestamp timestamp(3) NOT NULL, block_number bigint NOT NULL, tx_index integer NOT NULL, tx_hash varchar(66) NOT NULL, tick varchar NOT NULL, max_supply decimal(38,0) NOT NULL, lim decimal(38,0) NOT NULL, wlim decimal(38,0) NOT NULL, dec integer NOT NULL, creator varchar(42) NOT NULL )\nCREATE TABLE token_info_bitcoin ( block_timestamp timestamp(3) NOT NULL, block_number bigint NOT NULL, tx_index integer NOT NULL, tx_hash varchar(66) NOT NULL, tick varchar(255) NOT NULL, max_supply decimal(38,0) NOT NULL, lim decimal(38,0) NOT NULL, wlim decimal(38,0) NOT NULL, dec integer NOT NULL, creator varchar(42) NOT NULL )\nCREATE TABLE token_activities_bitcoin ( block_timestamp timestamp(3) NOT NULL, block_number bigint NOT NULL, tx_index integer NOT NULL, tx_hash varchar(66) NOT NULL, log_index integer NOT NULL, type varchar(20) NOT NULL, tick varchar(255) NOT NULL, id varchar(255) NOT NULL, amt decimal(38,0) NOT NULL, from_address varchar(62) NOT NULL, to_address varchar(62) NOT NULL )\nCREATE TABLE token_activities_avalanche ( block_timestamp timestamp(3) NOT NULL, block_number bigint NOT NULL, tx_index integer NOT NULL, tx_hash varchar(66) NOT NULL, log_index integer NOT NULL, type varchar(20) NOT NULL, tick varchar(255) NOT NULL, id varchar(255) NOT NULL, amt decimal(38,0) NOT NULL, from_address varchar(42) NOT NULL, to_address varchar(42) NOT NULL )\nCREATE TABLE token_balances_avalanche ( block_number bigint NOT NULL, block_timestamp timestamp(3) NOT NULL, tick varchar(20) NOT NULL, wallet_address varchar(42) NOT NULL, total_supply decimal(38,0) NOT NULL, amount decimal(38,0) NOT NULL )\nCREATE TABLE token_info_avalanche ( block_timestamp timestamp(3) NOT NULL, block_number bigint NOT NULL, tx_index integer NOT NULL, tx_hash varchar(66) NOT NULL, tick varchar(20) NOT NULL, max_supply decimal(38,0) NOT NULL, lim decimal(38,0) NOT NULL, wlim decimal(38,0) NOT NULL, dec integer NOT NULL, creator varchar(42) NOT NULL, minted decimal(38,0) NOT NULL, holders decimal(38,0) NOT NULL, txs decimal(38,0) NOT NULL, updated_timestamp timestamp(3) NOT NULL, completed_timestamp timestamp(3) NOT NULL, id varchar(255) NOT NULL )\n"} {"conversations": [{"role": "user", "content": "Find the average percentage share among all beneficiaries for each distinct relationship type."}, {"role": "assistant", "content": "SELECT relationship, AVG(percentage_share) FROM insurance.policy_beneficiaries GROUP BY relationship ORDER BY relationship;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.insurance_products ( product_id.text, product_name.text, product_type.text, description.text, base_premium.numeric, coverage_details.text, underwriting_rules.text, is_active.boolean, created_at.timestamp, updated_at.timestamp )\nCREATE TABLE insurance.policy_beneficiaries ( beneficiary_id text PRIMARY KEY, policy_id text, customer_id text, first_name text, last_name text, relationship text, percentage_share numeric, contact_info text, added_at timestamp )\n"} {"conversations": [{"role": "user", "content": "What is the average investment_value and total number of projects for each rounds_name in project_fundraising_record?"}, {"role": "assistant", "content": "SELECT rounds_name,\n AVG(investment_value) AS avg_investment,\n COUNT(DISTINCT project_id) AS project_count\nFROM project_fundraising_record\nGROUP BY rounds_name;"}, {"role": "user", "content": "Please show only rounds where project_count > 5, and order by avg_investment descending."}, {"role": "assistant", "content": "SELECT rounds_name,\n AVG(investment_value) AS avg_investment,\n COUNT(DISTINCT project_id) AS project_count\nFROM project_fundraising_record\nGROUP BY rounds_name\nHAVING COUNT(DISTINCT project_id) > 5\nORDER BY avg_investment DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE project_fundraising_record ( id text, project_id text, project_name text, rounds_name text, investment_value numeric, investment_date text, introduction text, valuation numeric )\nCREATE TABLE token_basic_info ( coin_id text, token_name text, token_symbol text, token_address text, chain text, price numeric, price_change_percentage_1h numeric, price_change_percentage_24h numeric, price_change_percentage_7d numeric, highest_price_24h numeric, lowest_price_24h numeric, market_cap numeric, market_cap_rank numeric, market_cap_change_percentage_24h text, total_volume text, narrative text, trend_rank numeric )\nCREATE TABLE narrative_info ( narrative text, top_3_coins text, price_change_percentage_1h numeric, price_change_percentage_24h numeric, price_change_percentage_7d numeric, market_cap numeric, volume_24h numeric, trend_rank numeric, token_num numeric )\nCREATE TABLE token_dexpool_info ( pair_address text, token_name text, token_symbol text, chain text, price numeric, price_change_percentage_1h numeric, price_change_percentage_6h numeric, price_change_percentage_24h numeric, makers_24h numeric, volume_24h numeric, liquidity numeric, market_cap numeric, trend_rank numeric )\nCREATE TABLE smart_money_token_performance ( token_address text, token_symbol text, pnl numeric, net_flow numeric, avg_cost numeric, price numeric, realized_ratio numeric, roi numeric, chain text )\n"} {"conversations": [{"role": "user", "content": "What is the current market cap and 7-day price change percentage for the top 3 narratives by trend rank?"}, {"role": "assistant", "content": "SELECT narrative, market_cap, price_change_percentage_7d FROM narrative_info ORDER BY trend_rank ASC LIMIT 3;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\n \"CREATE TABLE token_basic_info (\",\n \"coin_id character varying(100) NOT NULL, -- the id of the token\",\n \"token_name character varying(100) NOT NULL, -- the token's name\",\n \"token_symbol character varying(100) NOT NULL, -- the token's symbol\",\n \"token_address character varying(100) NOT NULL, -- the token's address\",\n \"chain text, -- the chain that the token resides\",\n \"price double precision, -- the current price of the token\",\n \"price_change_percentage_1h double precision, -- change in value divided by the absolute price value of the original token price in 1 hour\",\n \"price_change_percentage_24h double precision, -- change in value divided by the absolute price value of the original token price in 24 hours\",\n \"price_change_percentage_7d double precision, -- change in value divided by the absolute price value of the original token price in 7 days\",\n \"highest_price_24h double precision, -- the highest price of the token in 24 hours\",\n \"lowest_price_24h double precision, -- the lowest price of the token in 24 hours\",\n \"market_cap double precision, -- the market cap of the token\",\n \"market_cap_rank bigint, -- the rank of the token market cap in desc\",\n \"market_cap_change_percentage_24h text, -- the percentage of market cap changes in 24 hours\",\n \"total_volume text, -- the trade volum of the token both in decentralized exchange(DEX) and centralized exchange(CEX)\", \n \"narrative text, -- the category or narrative of the token\",\n \"trend_rank biging, -- the trending rank of the token, value 1 expresses the most popular token.\",\n \",PRIMARY KEY (coin_id, chain));\",\n\n \"CREATE TABLE narrative_info (\",\n \"narrative character varying(512) NOT NULL, -- the id of narrative\",\n \"top_3_coins text, -- the top 3 tokens in the narrative\",\n \"price_change_percentage_1h double precision, -- change in value divided by the absolute price value of the original token price in 1 hour in the narrative\",\n \"price_change_percentage_24h double precision, -- change in value divided by the absolute price value of the original token price in 24 hours in the narrative\",\n \"price_change_percentage_7d double precision, -- change in value divided by the absolute price value of the original token price in 7 days in the narrative\",\n \"market_cap double precision, -- the market cap of the narrative\",\n \"volume_24h double precision, -- the trade volume of the narrative\",\n \"trend_rank bigint, -- the trending rank of the narrative, value 1 expresses the most popular narrative\",\n \"token_num bigint, -- total token number in the narrative\",\n \",PRIMARY KEY (narrative));\"\n\n \"CREATE TABLE cex_token_balance (\",\n \"snapshot_time character varying(32) NOT NULL, -- the snapshot time of record, converted from original timestamp\",\n \"chain character varying(128) NOT NULL, -- the chain that the token resides\",\n \"address character varying(128) NOT NULL, -- the address that holds the assets, owned by a CEX\",\n \"exchange character varying(512) NOT NULL, -- a centralized exchange name\",\n \"token_address character varying(128) NOT NULL, -- token contract address\",\n \"token_symbol character varying(512), --token symbol\",\n \"balance numeric(38,10), -- token balance\",\n \"usd_value numeric(38,14), -- value of the token held in USD\",\n \"price double precision, --price of the token in USD\",\n \",PRIMARY KEY (snapshot_time, exchange, address, chain, token_address));\"\n\n \"CREATE TABLE smart_money_profit (\",\n \"address character varying(100) NOT NULL, -- the user's address\",\n \"rank INT, -- the rank of the address in trade performance, value 1 expresses the best address.\",\n \"profit numeric(38,6), -- the profit user made in a month\",\n \"roi numeric(38,2), -- the roi of the user in a month\",\n \"realized_ratio numeric(38,2), -- the percentage of the user's realized profit\",\n \"most_profit_token character varying(100), -- the token symbol of the user's most profitable trade\",\n \"last_trade_time character varying(100), -- the last trade time of the user\",\n \"chain character varying(100), -- the chain that the address resides\",\n \"PRIMARY KEY (address, chain));\",\n\n \"CREATE TABLE smart_money_token_performance (\",\n \"token_address character varying(100) NOT NULL, -- the token's address\",\n \"token_symbol character varying(100), -- the tokens's symbol\",\n \"pnl numeric(38,2), -- the profit users made on this token\",\n \"net_flow numeric(38,2), -- the netflow of the token, means the money user spent minus the the money user sold of this token\",\n \"avg_cost numeric(38,16), -- the average cost price of user spent on this token\",\n \"price double precision, -- the current price of the token\",\n \"realized_ratio numeric(10,2), -- the ratio user sold of the token\",\n \"roi numeric(10,2), -- the roi users made of this token\",\n \"chain character varying(100), -- the chain that the token resides\",\n \"PRIMARY KEY (token_address, chain));\",\n\n \"CREATE TABLE smart_money_token_inflow (\",\n \"token_address character varying(100) NOT NULL, -- the token's address\",\n \"token_symbol character varying(100), -- the tokens's symbol\",\n \"token_amount numeric(38,2), -- the absolute value of the amount if user bought minus the amount user sold of this token\",\n \"usd_value numeric(38,2), -- the absolute usd value of the bought token minus sold token\",\n \"avg_price numeric(38,6), -- the average cost price of user spent on this token\",\n \"type int, -- the direction of the trade on this token. 1 means buying, 2 means selling\",\n \"address_amount integer, -- the amount of the user bought this token\",\n \"narrative character varying(100), -- the category or narrative of the token\",\n \"chain character varying(100), -- the chain that the token resides\",\n \",PRIMARY KEY (token_address, chain)\",\n\n"} {"conversations": [{"role": "user", "content": "List all users who have never followed anyone, showing their username, full name, email, and account creation date."}, {"role": "assistant", "content": "SELECT u.username,\n u.full_name,\n u.email,\n u.created_at\nFROM social_media.users AS u\nLEFT JOIN social_media.follows AS f\n ON u.user_id = f.follower_user_id\nWHERE f.follow_id IS NULL;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE social_media.users ( user_id text, username text, email text, password_hash text, full_name text, profile_picture_url text, bio text, location text, created_at timestamp, updated_at timestamp, is_verified boolean )\nCREATE TABLE social_media.posts ( post_id character varying(64) NOT NULL, user_id character varying(64) NOT NULL, content text, media_url text, media_type character varying(20), created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, updated_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, visibility character varying(20) NOT NULL DEFAULT 'public', location_lat numeric(9,6), location_lon numeric(9,6), PRIMARY KEY (post_id) )\nCREATE TABLE social_media.comments ( comment_id.text, post_id.text, user_id.text, parent_comment_id.text, content.text, created_at.timestamp, updated_at.timestamp )\nCREATE TABLE social_media.likes ( like_id text PRIMARY KEY, user_id text, post_id text, comment_id text, created_at timestamp )\nCREATE TABLE social_media.follows (\n follow_id character varying(64) NOT NULL, -- unique identifier for the follow relationship\n follower_user_id character varying(64) NOT NULL, -- identifier of the user who is following (FK to users.user_id)\n following_user_id character varying(64) NOT NULL, -- identifier of the user being followed (FK to users.user_id)\n created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of when the follow started\n PRIMARY KEY (follow_id),\n CONSTRAINT unique_follow UNIQUE (follower_user_id, following_user_id) -- prevent duplicate follows\n)\nCREATE TABLE social_media.hashtags ( hashtag_id character varying(64) NOT NULL, tag_name character varying(100) NOT NULL UNIQUE, created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, PRIMARY KEY (hashtag_id) )\nCREATE TABLE social_media.post_hashtags ( post_hashtag_id text PRIMARY KEY, post_id text, hashtag_id text )\nCREATE TABLE social_media.conversations ( conversation_id.text, created_at.timestamp, last_message_at.timestamp, is_group_chat.boolean, group_name.text )\nCREATE TABLE social_media.conversation_participants ( participant_id.text, conversation_id.text, user_id.text, joined_at.timestamp, last_read_at.timestamp )\nCREATE TABLE social_media.notifications ( notification_id.text, recipient_user_id.text, sender_user_id.text, notification_type.text, target_entity_id.text, target_entity_type.text, created_at.timestamp, read_at.timestamp )\nCREATE TABLE social_media.user_settings ( setting_id.text, user_id.text, theme.text, email_notifications_enabled.boolean, push_notifications_enabled.boolean, private_profile.boolean, updated_at.timestamp )\n"} {"conversations": [{"role": "user", "content": "For each citizen who has made at least one payment, show the citizen's full name, number of payments, and total amount paid, grouped by currency."}, {"role": "assistant", "content": "SELECT\n c.first_name || ' ' || c.last_name AS full_name,\n p.currency,\n COUNT(*) AS payment_count,\n SUM(p.amount) AS total_amount\nFROM government_services.citizens c\nJOIN government_services.payments p ON c.citizen_id = p.citizen_id\nGROUP BY full_name, p.currency;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.citizens ( citizen_id character varying(64) NOT NULL, national_id_number character varying(128) NOT NULL UNIQUE, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, date_of_birth date NOT NULL, gender character varying(20), primary_address text NOT NULL, contact_email character varying(128) UNIQUE, contact_phone character varying(32), registration_date timestamp NOT NULL, is_verified boolean DEFAULT false, PRIMARY KEY (citizen_id) )\nCREATE TABLE government_services.payments ( payment_id character varying(64) NOT NULL, application_id character varying(64), citizen_id character varying(64) NOT NULL, service_id character varying(64), amount numeric(12, 2) NOT NULL, currency character varying(3) NOT NULL DEFAULT 'USD', payment_method character varying(50), payment_provider_reference character varying(128), payment_timestamp timestamp NOT NULL, status character varying(30) NOT NULL, notes text, PRIMARY KEY (payment_id) )\nCREATE TABLE government_services.employees ( employee_id character varying(64) NOT NULL, agency_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, job_title character varying(150) NOT NULL, department character varying(100), work_email character varying(128) NOT NULL UNIQUE, work_phone character varying(32), hire_date date NOT NULL, termination_date date, access_level character varying(50), manager_employee_id character varying(64), PRIMARY KEY (employee_id) )\nCREATE TABLE government_services.service_locations ( location_id character varying(64) NOT NULL, agency_id character varying(64) NOT NULL, location_name character varying(200), address text NOT NULL, city character varying(100), state character varying(50), postal_code character varying(20), latitude numeric(9, 6), longitude numeric(9, 6), operating_hours text, contact_phone character varying(32), is_accessible boolean, PRIMARY KEY (location_id) )\nCREATE TABLE government_services.appointments ( appointment_id character varying(64) NOT NULL, citizen_id character varying(64) NOT NULL, employee_id character varying(64), location_id character varying(64), service_id character varying(64), scheduled_start_time timestamp NOT NULL, scheduled_end_time timestamp, purpose text NOT NULL, status character varying(30) NOT NULL, booking_method character varying(50), created_at timestamp NOT NULL, notes text, PRIMARY KEY (appointment_id) )\nCREATE TABLE government_services.notifications ( notification_id character varying(64) NOT NULL, citizen_id character varying(64) NOT NULL, application_id character varying(64), message_subject character varying(255), message_body text NOT NULL, channel character varying(30) NOT NULL, sent_at timestamp NOT NULL, status character varying(30) NOT NULL, related_entity_type character varying(50), related_entity_id character varying(64), PRIMARY KEY (notification_id) )\n"} {"conversations": [{"role": "user", "content": "I need the average capacity of vehicles for each fuel_type."}, {"role": "assistant", "content": "SELECT fuel_type,\n AVG(capacity) AS avg_capacity\nFROM transportation.vehicles\nGROUP BY fuel_type;"}, {"role": "user", "content": "Only include fuel types where the vehicle count is at least 10."}, {"role": "assistant", "content": "SELECT fuel_type,\n AVG(capacity) AS avg_capacity\nFROM transportation.vehicles\nGROUP BY fuel_type\nHAVING COUNT(*) >= 10;"}, {"role": "user", "content": "Also show the number of vehicles for each of these fuel types."}, {"role": "assistant", "content": "SELECT fuel_type,\n COUNT(*) AS vehicle_count,\n AVG(capacity) AS avg_capacity\nFROM transportation.vehicles\nGROUP BY fuel_type\nHAVING COUNT(*) >= 10;"}, {"role": "user", "content": "Please round avg_capacity to one decimal place."}, {"role": "assistant", "content": "SELECT fuel_type,\n COUNT(*) AS vehicle_count,\n ROUND(AVG(capacity)::numeric, 1) AS avg_capacity\nFROM transportation.vehicles\nGROUP BY fuel_type\nHAVING COUNT(*) >= 10;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.vehicles ( vehicle_id.text, license_plate.text, vin.text, make.text, model.text, year.integer, type.text, capacity.integer, fuel_type.text, status.text, depot_id.text, acquisition_date.date )\n"} {"conversations": [{"role": "user", "content": "Find all patients who have been prescribed medications with dosage greater than 50mg, along with their medication details and prescribing doctor's name."}, {"role": "assistant", "content": "SELECT p.patient_id, p.first_name, p.last_name, pr.dosage, pr.medication_id, pr.start_date, doc.first_name AS doctor_first_name, doc.last_name AS doctor_last_name FROM healthcare.patients p JOIN healthcare.prescriptions pr ON p.patient_id = pr.patient_id JOIN healthcare.doctors doc ON pr.doctor_id = doc.doctor_id WHERE CAST(SUBSTRING_INDEX(pr.dosage, 'mg', 1) AS UNSIGNED) > 50;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.patients ( patient_id.text, first_name.text, last_name.text, date_of_birth.date, gender.text, address.text, phone_number.text, email.text, emergency_contact_name.text, emergency_contact_phone.text, created_at.timestamp, updated_at.timestamp )\nCREATE TABLE healthcare.appointments ( appointment_id.text, patient_id.text, doctor_id.text, appointment_time.timestamp, duration_minutes.integer, reason.text, status.text, location_id.text, notes.text, created_at.timestamp )\nCREATE TABLE healthcare.diagnoses ( diagnosis_id.text, record_id.text, patient_id.text, doctor_id.text, diagnosis_code.text, code_type.text, description.text, diagnosis_date.date, status.text, is_chronic.boolean )\nCREATE TABLE healthcare.prescriptions ( prescription_id.text, record_id.text, patient_id.text, doctor_id.text, medication_id.text, dosage.text, frequency.text, route.text, start_date.date, end_date.date, quantity_dispensed.numeric, refills_allowed.integer, prescription_date.timestamp )\nCREATE TABLE healthcare.insurance_plans ( plan_id.text, plan_name.text, insurance_provider.text, plan_type.text, contact_phone.text, website.text )\n"} {"conversations": [{"role": "user", "content": "What are the maintenance costs for a specific aircraft model like the Airbus A320?"}, {"role": "assistant", "content": "I'm sorry, but I don't have access to data regarding maintenance costs for specific aircraft models such as the Airbus A320. The information in the database is limited to details like model name, manufacturer, passenger capacity, and technical specifications. For maintenance cost information, you may need to consult with the manufacturer or a maintenance service provider."}], "system": "You are an SQL statement expert and you can refuse the user's question if the question is not related to the table structure. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE manufacturing.aircraft_models ( model_id character varying(64) NOT NULL, model_name character varying(128) NOT NULL, manufacturer character varying(128) NOT NULL, passenger_capacity integer, max_range_km integer, engine_type character varying(100), wingspan_m numeric(6,2), status character varying(50) NOT NULL, first_flight_date date, PRIMARY KEY (model_id) )\n"} {"conversations": [{"role": "user", "content": "What is the current job satisfaction level or feedback from staff members working at a specific train station?"}, {"role": "assistant", "content": "I'm sorry, but I can't provide information on job satisfaction levels or feedback from staff members as this data is not included in the staff table."}], "system": "You are an SQL statement expert and you can refuse the user's question if the question is not related to the table structure. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE train_station_management.staff ( staff_id.text, first_name.text, last_name.text, role.text, primary_station_id.text, employee_number.text, hire_date.date, contact_email.text, contact_phone.text, is_active.boolean )\n"} {"conversations": [{"role": "user", "content": "List usernames and the length of their 'bio' field for users whose 'is_verified' status is true."}, {"role": "assistant", "content": "SELECT username, LENGTH(bio) AS bio_length FROM social_media.users WHERE is_verified IS TRUE;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE social_media.users ( user_id text PRIMARY KEY, username text, email text, password_hash text, full_name text, profile_picture_url text, bio text, location text, created_at timestamp, updated_at timestamp, is_verified bool )\n"} {"conversations": [{"role": "user", "content": "Count the number of registered citizens by gender."}, {"role": "assistant", "content": "SELECT\n gender,\n COUNT(*) AS citizen_count\nFROM government_services.citizens\nGROUP BY gender;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.citizens ( citizen_id character varying(64) NOT NULL, national_id_number character varying(128) NOT NULL UNIQUE, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, date_of_birth date NOT NULL, gender character varying(20), primary_address text NOT NULL, contact_email character varying(128) UNIQUE, contact_phone character varying(32), registration_date timestamp NOT NULL, is_verified boolean DEFAULT false, PRIMARY KEY (citizen_id) )\nCREATE TABLE government_services.payments ( payment_id character varying(64) NOT NULL, application_id character varying(64), citizen_id character varying(64) NOT NULL, service_id character varying(64), amount numeric(12, 2) NOT NULL, currency character varying(3) NOT NULL DEFAULT 'USD', payment_method character varying(50), payment_provider_reference character varying(128), payment_timestamp timestamp NOT NULL, status character varying(30) NOT NULL, notes text, PRIMARY KEY (payment_id) )\nCREATE TABLE government_services.employees ( employee_id character varying(64) NOT NULL, agency_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, job_title character varying(150) NOT NULL, department character varying(100), work_email character varying(128) NOT NULL UNIQUE, work_phone character varying(32), hire_date date NOT NULL, termination_date date, access_level character varying(50), manager_employee_id character varying(64), PRIMARY KEY (employee_id) )\nCREATE TABLE government_services.service_locations ( location_id character varying(64) NOT NULL, agency_id character varying(64) NOT NULL, location_name character varying(200), address text NOT NULL, city character varying(100), state character varying(50), postal_code character varying(20), latitude numeric(9, 6), longitude numeric(9, 6), operating_hours text, contact_phone character varying(32), is_accessible boolean, PRIMARY KEY (location_id) )\nCREATE TABLE government_services.appointments ( appointment_id character varying(64) NOT NULL, citizen_id character varying(64) NOT NULL, employee_id character varying(64), location_id character varying(64), service_id character varying(64), scheduled_start_time timestamp NOT NULL, scheduled_end_time timestamp, purpose text NOT NULL, status character varying(30) NOT NULL, booking_method character varying(50), created_at timestamp NOT NULL, notes text, PRIMARY KEY (appointment_id) )\nCREATE TABLE government_services.notifications ( notification_id character varying(64) NOT NULL, citizen_id character varying(64) NOT NULL, application_id character varying(64), message_subject character varying(255), message_body text NOT NULL, channel character varying(30) NOT NULL, sent_at timestamp NOT NULL, status character varying(30) NOT NULL, related_entity_type character varying(50), related_entity_id character varying(64), PRIMARY KEY (notification_id) )\n"} {"conversations": [{"role": "user", "content": "Count the number of staff members for each position."}, {"role": "assistant", "content": "SELECT\n position,\n COUNT(staff_id) AS staff_count\nFROM hospitality_technology.staff\nGROUP BY\n position;"}, {"role": "user", "content": "Only show positions that have more than 10 staff members and order the results by the count descending."}, {"role": "assistant", "content": "SELECT\n position,\n COUNT(staff_id) AS staff_count\nFROM hospitality_technology.staff\nGROUP BY\n position\nHAVING\n COUNT(staff_id) > 10\nORDER BY\n staff_count DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE hospitality_technology.properties (\n property_id character varying(64) NOT NULL, -- unique identifier for the property (hotel, resort, etc.)\n property_name character varying(255) NOT NULL, -- name of the property\n address_line1 character varying(255) NOT NULL, -- primary address line\n address_line2 character varying(255), -- secondary address line\n city character varying(100) NOT NULL, -- city\n state_province character varying(100), -- state or province\n postal_code character varying(20) NOT NULL, -- zip or postal code\n country_code character varying(3) NOT NULL, -- ISO country code (e.g., USA, CAN)\n phone_number character varying(30), -- main contact phone\n email_address character varying(255), -- main contact email\n property_type character varying(50) NOT NULL, -- e.g., Hotel, Resort, B&B, Motel\n star_rating numeric(2,1), -- star rating (e.g., 4.5)\n timezone character varying(64) NOT NULL, -- IANA timezone ID (e.g., America/New_York)\n manager_staff_id character varying(64), -- FK to staff table for the general manager\n created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, -- record creation time\n updated_at timestamp with time zone NOT NULL DEFAULT current_timestamp, -- record last update time\n PRIMARY KEY (property_id)\n)\nCREATE TABLE hospitality_technology.reservations ( reservation_id text, property_id text, guest_id text, room_id text, room_type_id text, check_in_date date, check_out_date date, actual_check_in_ts timestamp, actual_check_out_ts timestamp, num_adults integer, num_children integer, status text, booking_source text, rate_plan_id text, total_amount numeric, amount_paid numeric, special_requests text, created_at timestamp, updated_at timestamp )\nCREATE TABLE hospitality_technology.staff ( staff_id text PRIMARY KEY, property_id text, first_name text, last_name text, position text, work_email text, work_phone text, hire_date date, termination_date date, is_active boolean, access_level int, manager_id text, created_at timestamp )\nCREATE TABLE hospitality_technology.payments ( payment_id text, reservation_id text, guest_id text, bill_id text, amount numeric, currency_code text, payment_method text, card_type text, card_last_four text, transaction_ref text, payment_timestamp timestamp, status text, staff_id_processed text, notes text )\n"} {"conversations": [{"role": "user", "content": "Identify all instances where a vehicle's odometer_reading increased by more than 500 miles between two consecutive fuel log entries."}, {"role": "assistant", "content": "SELECT a.vehicle_id,\n a.fuel_log_id AS previous_log_id,\n b.fuel_log_id AS next_log_id,\n a.log_timestamp AS previous_time,\n b.log_timestamp AS next_time,\n b.odometer_reading - a.odometer_reading AS mile_increase\nFROM transportation.fuel_logs a\nJOIN transportation.fuel_logs b\n ON a.vehicle_id = b.vehicle_id\n AND b.log_timestamp = (\n SELECT MIN(log_timestamp)\n FROM transportation.fuel_logs\n WHERE vehicle_id = a.vehicle_id\n AND log_timestamp > a.log_timestamp\n )\nWHERE b.odometer_reading - a.odometer_reading > 500;"}, {"role": "user", "content": "Now restrict these increases to those where the time difference between entries is less than 7 days."}, {"role": "assistant", "content": "SELECT a.vehicle_id,\n a.fuel_log_id AS previous_log_id,\n b.fuel_log_id AS next_log_id,\n a.log_timestamp AS previous_time,\n b.log_timestamp AS next_time,\n b.odometer_reading - a.odometer_reading AS mile_increase,\n EXTRACT(epoch FROM (b.log_timestamp - a.log_timestamp))/3600 AS hours_diff\nFROM transportation.fuel_logs a\nJOIN transportation.fuel_logs b\n ON a.vehicle_id = b.vehicle_id\n AND b.log_timestamp = (\n SELECT MIN(log_timestamp)\n FROM transportation.fuel_logs\n WHERE vehicle_id = a.vehicle_id\n AND log_timestamp > a.log_timestamp\n )\nWHERE b.odometer_reading - a.odometer_reading > 500\n AND b.log_timestamp - a.log_timestamp < INTERVAL '7 days';"}, {"role": "user", "content": "Also include both the mile increase and the time difference in hours in the final output columns."}, {"role": "assistant", "content": "SELECT a.vehicle_id,\n a.fuel_log_id AS previous_log_id,\n b.fuel_log_id AS next_log_id,\n b.odometer_reading - a.odometer_reading AS mile_increase,\n EXTRACT(epoch FROM (b.log_timestamp - a.log_timestamp))/3600 AS hours_difference\nFROM transportation.fuel_logs a\nJOIN transportation.fuel_logs b\n ON a.vehicle_id = b.vehicle_id\n AND b.log_timestamp = (\n SELECT MIN(log_timestamp)\n FROM transportation.fuel_logs\n WHERE vehicle_id = a.vehicle_id\n AND log_timestamp > a.log_timestamp\n )\nWHERE b.odometer_reading - a.odometer_reading > 500\n AND b.log_timestamp - a.log_timestamp < INTERVAL '7 days';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.fuel_logs ( fuel_log_id.text, vehicle_id.text, trip_id.text, log_timestamp.timestamp, fuel_type.text, quantity.numeric, unit.text, cost_per_unit.numeric, total_cost.numeric, odometer_reading.integer, location_id.text )\n"} {"conversations": [{"role": "user", "content": "Show me all wallet addresses and their private keys for users who have more than 3 wallets."}, {"role": "assistant", "content": "SELECT w.address_id, w.private_key FROM blockchain.wallets w WHERE w.user_id IN (SELECT user_id FROM blockchain.wallets GROUP BY user_id HAVING COUNT(*) > 3);"}, {"role": "user", "content": "Now, filter these results to only show wallets where the private_key starts with '0x1'."}, {"role": "assistant", "content": "SELECT w.address_id, w.private_key FROM blockchain.wallets w WHERE w.user_id IN (SELECT user_id FROM blockchain.wallets GROUP BY user_id HAVING COUNT(*) > 3) AND w.private_key LIKE '0x1%';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE blockchain.wallets (\n wallet_id character varying(64) NOT NULL, -- unique identifier for the wallet\n user_id character varying(64) NOT NULL, -- identifier of the user owning the wallet\n address_id character varying(128) NOT NULL, -- identifier of the address associated with the wallet\n private_key text NOT NULL, -- private key of the wallet\n PRIMARY KEY (wallet_id)\n)\n"} {"conversations": [{"role": "user", "content": "Show all medications that share a manufacturer with at least one other medication. Return the medication_id, medication_name, and manufacturer for each."}, {"role": "assistant", "content": "SELECT m.medication_id,\n m.medication_name,\n m.manufacturer\nFROM healthcare.medications m\nJOIN (\n SELECT manufacturer\n FROM healthcare.medications\n GROUP BY manufacturer\n HAVING COUNT(*) > 1\n) multi ON m.manufacturer = multi.manufacturer;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.medications ( medication_id text, medication_name text, generic_name text, manufacturer text, ndc_code text, description text )\n"} {"conversations": [{"role": "user", "content": "List all document IDs, file names, and uploaded timestamps for documents that were uploaded on a weekend."}, {"role": "assistant", "content": "SELECT document_id, file_name, uploaded_at FROM insurance.claim_documents WHERE EXTRACT(DOW FROM uploaded_at) IN (0, 6);"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.claim_documents ( document_id text PRIMARY KEY, claim_id text, document_type text, file_name text, file_path text, file_size_bytes int, mime_type text, uploaded_by text, uploaded_at timestamp, description text )\n"} {"conversations": [{"role": "user", "content": "List the full name of each lawyer along with the location and status of their appointments."}, {"role": "assistant", "content": "SELECT T1.first_name, T1.last_name, T2.location, T2.status FROM legal_services.lawyers AS T1 JOIN legal_services.appointments AS T2 ON T1.lawyer_id = T2.lawyer_id"}, {"role": "user", "content": "Please only show appointments with a status of 'completed' or 'cancelled', and sort by lawyer's last name."}, {"role": "assistant", "content": "SELECT T1.first_name, T1.last_name, T2.location, T2.status FROM legal_services.lawyers AS T1 JOIN legal_services.appointments AS T2 ON T1.lawyer_id = T2.lawyer_id WHERE T2.status IN ('completed', 'cancelled') ORDER BY T1.last_name"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.lawyers ( lawyer_id text PRIMARY KEY, first_name text, last_name text, bar_number text UNIQUE, firm_id text, email text UNIQUE, phone text, specialization text, hire_date timestamp, is_partner bool )\nCREATE TABLE legal_services.time_entries (\n entry_id character varying(64) NOT NULL, -- unique identifier for the time entry\n case_id character varying(64) NOT NULL, -- FK to cases table\n lawyer_id character varying(64) NOT NULL, -- FK to lawyers table (who performed the work)\n date_worked date NOT NULL, -- date the work was performed\n hours_spent numeric(5, 2) NOT NULL CHECK (hours_spent > 0), -- duration of work in hours (e.g., 1.5 for 1h 30m)\n billing_rate numeric(10, 2) NOT NULL, -- hourly rate applied for this entry\n description text NOT NULL, -- detailed description of the work performed\n is_billable boolean DEFAULT true, -- whether this time entry is billable to the client\n is_billed boolean DEFAULT false, -- whether this entry has been included in an invoice\n invoice_id character varying(64), -- FK to invoices table (once billed)\n created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- when the entry was recorded\n PRIMARY KEY (entry_id)\n)\nCREATE TABLE legal_services.appointments ( appointment_id text PRIMARY KEY, client_id text, lawyer_id text, case_id text, start_time timestamp, end_time timestamp, location text, subject text, notes text, status text, created_at timestamp )\n"} {"conversations": [{"role": "user", "content": "I need to find all bookings for a specific schedule with schedule_id 'sched_1122' and include the passenger and ticket details."}, {"role": "assistant", "content": "SMEMBERS schedule:sched_1122:bookings\nHGETALL booking:book_*\nHGETALL passenger:pass_*\nSMEMBERS booking:book_*:tickets\nHGETALL ticket:tkt_*"}, {"role": "user", "content": "Can you filter the tickets to show only those that are not checked in?"}, {"role": "assistant", "content": "SMEMBERS schedule:sched_1122:bookings\nHGETALL booking:book_*\nHGETALL passenger:pass_*\nSMEMBERS booking:book_*:tickets\nHGET ticket:tkt_* is_checked_in\nIF is_checked_in == 0 THEN\nHGETALL ticket:tkt_*\nENDIF"}, {"role": "user", "content": "Can you also include the car details for each ticket?"}, {"role": "assistant", "content": "SMEMBERS schedule:sched_1122:bookings\nHGETALL booking:book_*\nHGETALL passenger:pass_*\nSMEMBERS booking:book_*:tickets\nHGET ticket:tkt_* is_checked_in\nIF is_checked_in == 0 THEN\nHGETALL ticket:tkt_*\nHGET ticket:tkt_* car_id\nHGETALL car:car_*\nENDIF"}], "system": "You are an expert in writing database language. You can write a corresponding database language query to answer the user's question based on the table structure described by the table creation statement. \n##Table Structure\n// Use Hashes for platform details. Key format: platform:\n// HSET platform:plat_123 platform_id \"plat_123\" station_id \"station_xyz\" platform_number \"1A\" track_number \"T1\" status \"Operational\" length_meters 250.50 accessible 1\n\n// To link platforms to stations (optional):\n// SADD station:station_xyz:platforms platform:plat_123 platform:plat_456\n// Use Hashes for train details. Key format: train:\n// HSET train:train_789 train_id \"train_789\" train_number \"Acela 2151\" model \"Siemens Velaro\" ... status \"Active\" ...\n\n// To find train by train_number (optional index):\n// SET train_number:\"Acela 2151\" train:train_789\n// Use Hashes for car details. Key format: car:\n// HSET car:car_abc car_id \"car_abc\" train_id \"train_789\" car_number \"C3\" car_type \"Passenger\" class \"Business\" capacity 60 features \"WiFi,Power Outlet\"\n\n// To link cars to trains (optional):\n// SADD train:train_789:cars car:car_abc car:car_def\n// Use Hashes for details. Key format: route_station:\n// HSET route_station:rs_ne_1 route_station_id \"rs_ne_1\" route_id \"route_ne_corr\" station_id \"station_bos\" sequence_order 1 ...\n\n// To find stops for a route, use a Sorted Set (score by sequence_order):\n// ZADD route:route_ne_corr:stops 1 route_station:rs_ne_1\n// ZADD route:route_ne_corr:stops 2 route_station:rs_ne_2\n// Use Hashes for schedule details. Key format: schedule:\n// HSET schedule:sched_1122 schedule_id \"sched_1122\" train_id \"train_789\" route_id \"route_ne_corr\" departure_datetime \"2024-05-10T08:00:00-04:00\" ... status \"Scheduled\"\n// Use Hashes for details. Key format: schedule_stop:\n// HSET schedule_stop:stop_sched1122_1 stop_id \"stop_sched1122_1\" schedule_id \"sched_1122\" station_id \"station_bos\" ...\n\n// To find stops for a schedule, use a Sorted Set (score by sequence_order):\n// ZADD schedule:sched_1122:stops 1 schedule_stop:stop_sched1122_1\n// ZADD schedule:sched_1122:stops 2 schedule_stop:stop_sched1122_2\n// Use Hashes for passenger details. Key format: passenger:\n// HSET passenger:pass_pqr passenger_id \"pass_pqr\" first_name \"Alice\" last_name \"Smith\" email \"alice.smith@example.com\" ...\n\n// To find passenger by email (optional index):\n// SET passenger_email:\"alice.smith@example.com\" passenger:pass_pqr\n// Use Hashes for booking details. Key format: booking:\n// HSET booking:book_zyx booking_id \"book_zyx\" passenger_id \"pass_pqr\" schedule_id \"sched_1122\" ... status \"Confirmed\" ...\n\n// To link bookings to passengers/schedules (optional):\n// SADD passenger:pass_pqr:bookings booking:book_zyx\n// SADD schedule:sched_1122:bookings booking:book_zyx\n// Use Hashes for ticket details. Key format: ticket:\n// HSET ticket:tkt_1a2b ticket_id \"tkt_1a2b\" booking_id \"book_zyx\" car_id \"car_abc\" seat_number \"12A\" ... is_checked_in 0 ...\n\n// To link tickets to bookings (optional):\n// SADD booking:book_zyx:tickets ticket:tkt_1a2b\n// Use Hashes for staff details. Key format: staff:\n// HSET staff:staff_mno staff_id \"staff_mno\" first_name \"Bob\" ... employee_number \"E12345\" ... is_active 1\n\n// To find staff by employee number (optional index):\n// SET staff_employee_number:\"E12345\" staff:staff_mno\n// Use Hashes for maintenance record details. Key format: maintenance_record:\n// HSET maintenance_record:maint_rec_001 record_id \"maint_rec_001\" asset_id \"train_789\" asset_type \"Train\" ... status \"Completed\"\n\n// To link records to assets (optional):\n// SADD train:train_789:maintenance maintenance_record:maint_rec_001\n// SADD platform:plat_123:maintenance maintenance_record:maint_rec_002\n"} {"conversations": [{"role": "user", "content": "List the appointment ID, start time, and the case number for all appointments that are linked to a case."}, {"role": "assistant", "content": "SELECT T1.appointment_id, T1.start_time, T2.case_number FROM legal_services.appointments AS T1 JOIN legal_services.cases AS T2 ON T1.case_id = T2.case_id"}, {"role": "user", "content": "Refine this to only show appointments with status 'completed' associated with cases with status 'Closed'."}, {"role": "assistant", "content": "SELECT T1.appointment_id, T1.start_time, T2.case_number FROM legal_services.appointments AS T1 JOIN legal_services.cases AS T2 ON T1.case_id = T2.case_id WHERE T1.status = 'completed' AND T2.status = 'Closed'"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.cases ( case_id text, case_number text, case_name text, client_id text, lead_lawyer_id text, case_type text, status text, date_opened timestamp, date_closed timestamp, description text, court_jurisdiction text )\nCREATE TABLE legal_services.appointments ( appointment_id text, client_id text, lawyer_id text, case_id text, start_time timestamp, end_time timestamp, location text, subject text, notes text, status text, created_at timestamp )\n"} {"conversations": [{"role": "user", "content": "Show me the top 5 ERC20 tokens with the highest total supply, along with their names and contract addresses, but only include tokens where the price is greater than $0.10."}, {"role": "assistant", "content": "SELECT tm.name, tm.contract_address, tm.total_supply FROM token_metas tm WHERE tm.is_erc20 = 1 ORDER BY CAST(tm.total_supply AS decimal) DESC LIMIT 5;"}, {"role": "user", "content": "I think there's a typo in your query - it should be 'total_supply' not 'total_supply'. Also, can you join this with the token_prices_latest table to include the current price of each token?"}, {"role": "assistant", "content": "SELECT tm.name, tm.contract_address, tm.total_supply, tpl.price FROM token_metas tm JOIN token_prices_latest tpl ON tm.contract_address = tpl.address WHERE tm.is_erc20 = 1 AND tpl.price > 0.10 ORDER BY CAST(tm.total_supply AS decimal) DESC LIMIT 5;"}, {"role": "user", "content": "The token_prices_latest table isn't in the schema. Can you modify the query to use the erc20_balances table instead to show the total balance held across all wallets for each token?"}, {"role": "assistant", "content": "SELECT tm.name, tm.contract_address, tm.total_supply, SUM(CAST(eb.amount AS decimal)) AS total_balance FROM token_metas tm JOIN erc20_balances eb ON tm.contract_address = eb.contract_address WHERE tm.is_erc20 = 1 GROUP BY tm.name, tm.contract_address, tm.total_supply ORDER BY CAST(tm.total_supply AS decimal) DESC LIMIT 5;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE token_metas (\n block_timestamp timestamp(6) NOT NULL, -- Timestamp of the block when token metadata was recorded\n block_number bigint NOT NULL, -- Block number uniquely identifying the block\n transaction_hash varchar NOT NULL, -- Hash value of the transaction\n transaction_index bigint NOT NULL, -- Index of the transaction within the block\n from_address varchar NOT NULL, -- Address from which the transaction originated\n contract_address varchar NOT NULL, -- Address of the token contract\n symbol varchar NOT NULL, -- Symbol of the token\n total_supply varchar NOT NULL, -- erc20 contract total supply\n name varchar NOT NULL, -- Name of the token\n decimals bigint NOT NULL, -- Number of decimal places for the token\n is_erc20 integer NOT NULL, -- Flag indicating if the token is an ERC-20 token (0 or 1)\n is_erc721 integer NOT NULL, -- Flag indicating if the token is an ERC-721 token (0 or 1)\n is_erc1155 integer NOT NULL, -- Flag indicating if the token is an ERC-1155 token (0 or 1)\n is_proxy integer NOT NULL, -- Flag indicating if the token is a proxy (0 or 1)\n extra_info varchar NOT NULL, -- Additional information about the token\n pk integer NOT NULL -- Partition key for the table(floor(block_number / 5760))\n)\nCREATE TABLE erc1155_approval_for_all (\n block_number bigint NOT NULL, -- Block number containing the transaction\n block_timestamp timestamp(3) NOT NULL, -- Timestamp of the block containing the transaction\n transaction_index integer NOT NULL, -- Index of the transaction within the block\n transaction_hash varchar(66) NOT NULL, -- Transaction hash\n log_index integer NOT NULL, -- Log index\n contract_address varchar(42) NOT NULL -- Event contract address\n)\nCREATE TABLE erc20_balances ( block_number bigint NOT NULL, contract_address varchar NOT NULL, wallet_address varchar NOT NULL, amount varchar NOT NULL, pk varchar NOT NULL )\nCREATE TABLE erc20_balances_historical ( block_number bigint NOT NULL, contract_address varchar NOT NULL, wallet_address varchar NOT NULL, amount varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE nft_holders (\n block_number bigint NOT NULL, -- Block number containing the transaction\n contract_address varchar NOT NULL, -- Event contract address\n wallet_address varchar NOT NULL, -- The wallet address for the contract(with bloom filter)\n token_id varchar NOT NULL, -- NFT token id\n contract_type varchar NOT NULL, -- NFT contract type\n amount varchar NOT NULL, -- Number of held NFTs\n pk varchar NOT NULL -- The last string partition of the contract.\n)\nCREATE TABLE sui_coins ( object_id varchar NOT NULL, status varchar NOT NULL, coin_type varchar NOT NULL, balance varchar NOT NULL, owner varchar NOT NULL )\nCREATE TABLE sui_nfts ( object_id text, status text, collection_type text, package_id text, previous_transaction text, display text, owner text, name text )\nCREATE TABLE nft_metadata ( blockchain text, contract_address text, token_id text, contract_name text, erc_type text, amount bigint, minter text, owner text, mint_block_number bigint, mint_time bigint, mint_transaction_hash text, mint_price text, token_uri text, metadata text, name text, image_uri text, traits text, updated_at bigint, status text, rarity_score real, rarity_rank integer, unique_attribute_count integer, pk integer )\nCREATE TABLE erc20_approval ( block_number bigint, block_timestamp timestamp, transaction_index integer, transaction_hash text, log_index integer, contract_address text, pk integer )\nCREATE TABLE token_info (\n block_timestamp timestamp(3) NOT NULL, -- Timestamp of the block containing the inscription (matches block_timestamp in transactions table)\n block_number bigint NOT NULL, -- Block number containing the inscription (matches block_number in transactions table)\n tx_index integer NOT NULL, -- Index of the transaction containing the inscription (matches transaction_index in transactions table)\n tx_hash varchar(66) NOT NULL, -- Unique identifier of the transaction containing the inscription (matches hash in transactions table)\n tick varchar NOT NULL, -- Token tick\n max_supply decimal(38,0) NOT NULL, -- Max supply\n lim decimal(38,0) NOT NULL, -- Limit of each mint\n wlim decimal(38,0) NOT NULL, -- Limit of each address can maximum mint\n dec integer NOT NULL, -- Decimal for minimum divie\n creator varchar(42) NOT NULL -- Address originating the inscription (matches from_address in transactions table)\n)\nCREATE TABLE token_activities (\n block_timestamp timestamp(3) NOT NULL, -- Timestamp of the block containing the inscription (matches block_timestamp in transactions table)\n block_number bigint NOT NULL, -- Block number containing the inscription (matches block_number in transactions table)\n tx_index integer NOT NULL, -- Index of the transaction containing the inscription (matches transaction_index in transactions table)\n tx_hash varchar(66) NOT NULL, -- Unique identifier of the transaction containing the inscription (matches hash in transactions table)\n log_index integer NOT NULL, -- Index of the log within the transaction\n type varchar NOT NULL, -- mint | transfer | burn\n tick varchar NOT NULL, -- Token tick\n id varchar(255) NOT NULL, -- Unique identifier of the inscription\n amt decimal(38,0) NOT NULL, -- Mint amount\n from_address varchar(42) NOT NULL, -- Address sending the inscription (matches from_address in transactions table)\n to_address varchar(42) NOT NULL -- Address receiving the inscription (match to_address in transactions table)\n)\nCREATE TABLE token_activities_bitcoin ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash text, log_index integer, type text, tick text, id text, amt decimal, from_address text, to_address text )\nCREATE TABLE token_activities_avalanche ( block_timestamp.timestamp, block_number.bigint, tx_index.integer, tx_hash.text, log_index.integer, type.text, tick.text, id.text, amt.decimal, from_address.text, to_address.text )\n"} {"conversations": [{"role": "user", "content": "Show me the number of players registered in each country, along with the number of different games available for each country."}, {"role": "assistant", "content": "SELECT p.country_code, COUNT(DISTINCT p.player_id) AS player_count, COUNT(DISTINCT g.game_id) AS game_count\nFROM gaming_technology.players p\nCROSS JOIN gaming_technology.games g\nGROUP BY p.country_code;"}, {"role": "user", "content": "This doesn't make sense; the game count should be the number of games, not all possible combinations. Can you fix it to just show the count of players per country?"}, {"role": "assistant", "content": "SELECT p.country_code, COUNT(*) AS player_count\nFROM gaming_technology.players p\nGROUP BY p.country_code;"}, {"role": "user", "content": "Now add in the total number of servers located in each country, based on the players' country code matching the server's region."}, {"role": "assistant", "content": "SELECT p.country_code, COUNT(*) AS player_count,\n (SELECT COUNT(*) FROM gaming_technology.servers s WHERE s.region = p.country_code) AS server_count\nFROM gaming_technology.players p\nGROUP BY p.country_code;"}, {"role": "user", "content": "Show only countries where there are at least 5 servers."}, {"role": "assistant", "content": "SELECT p.country_code, COUNT(*) AS player_count,\n (SELECT COUNT(*) FROM gaming_technology.servers s WHERE s.region = p.country_code) AS server_count\nFROM gaming_technology.players p\nGROUP BY p.country_code\nHAVING (SELECT COUNT(*) FROM gaming_technology.servers s WHERE s.region = p.country_code) >= 5;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE gaming_technology.players ( player_id.uuid, username.text, email.text, password_hash.text, registration_date.timestamptz, last_login.timestamptz, country_code.text, status.text, profile_data.jsonb )\nCREATE TABLE gaming_technology.games (\n game_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for the game\n title character varying(200) NOT NULL, -- official title of the game\n developer_id uuid NOT NULL, -- FK linking to the developers table\n publisher_id uuid, -- FK linking to a potential publishers table (optional)\n genre character varying(100), -- primary genre (e.g., RPG, FPS, Strategy)\n release_date date, -- official release date\n description text, -- short description or synopsis of the game\n platform character varying(50) NOT NULL, -- primary platform (e.g., PC, PlayStation 5, Xbox Series X, Mobile)\n engine character varying(100), -- game engine used (e.g., Unreal Engine 5, Unity)\n website character varying(255), -- official website URL\n PRIMARY KEY (game_id)\n -- FOREIGN KEY (developer_id) REFERENCES gaming_technology.developers(developer_id) -- Example FK constraint\n)\nCREATE TABLE gaming_technology.servers ( server_id uuid NOT NULL DEFAULT gen_random_uuid(), game_id uuid NOT NULL, server_name character varying(150), region character varying(50) NOT NULL, ip_address character varying(45), port integer, current_players integer NOT NULL DEFAULT 0, max_players integer NOT NULL, status character varying(30) NOT NULL DEFAULT 'offline', last_heartbeat timestamp with time zone, PRIMARY KEY (server_id) )\nCREATE TABLE gaming_technology.achievements ( achievement_id uuid, game_id uuid, name text, description text, icon_url text, points integer, hidden boolean )\nCREATE TABLE gaming_technology.in_game_items ( item_id uuid NOT NULL DEFAULT gen_random_uuid(), game_id uuid NOT NULL, item_name character varying(150) NOT NULL, item_type character varying(50) NOT NULL, description text, rarity character varying(30), cost_currency character varying(10), cost_amount numeric(12, 2), attributes jsonb, PRIMARY KEY (item_id) )\n"} {"conversations": [{"role": "user", "content": "Show me the top 5 NFT collections with the highest token count on Ethereum, along with their names, symbols, and floor prices."}, {"role": "assistant", "content": "SELECT n.name, n.symbol, n.floor_price, n.token_count FROM nft_collections n WHERE n.blockchain = 'ethereum' ORDER BY n.token_count DESC LIMIT 5;"}, {"role": "user", "content": "Now, join this with the nft_metadata table to include the average rarity score for each collection."}, {"role": "assistant", "content": "SELECT n.name, n.symbol, n.floor_price, n.token_count, AVG(m.rarity_score) as avg_rarity_score FROM nft_collections n JOIN nft_metadata m ON n.contract_address = m.contract_address WHERE n.blockchain = 'ethereum' GROUP BY n.name, n.symbol, n.floor_price, n.token_count ORDER BY n.token_count DESC LIMIT 5;"}, {"role": "user", "content": "Can you filter these results to only show collections with an average rarity score greater than 80?"}, {"role": "assistant", "content": "SELECT n.name, n.symbol, n.floor_price, n.token_count, AVG(m.rarity_score) as avg_rarity_score FROM nft_collections n JOIN nft_metadata m ON n.contract_address = m.contract_address WHERE n.blockchain = 'ethereum' GROUP BY n.name, n.symbol, n.floor_price, n.token_count HAVING AVG(m.rarity_score) > 80 ORDER BY n.token_count DESC LIMIT 5;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE token_metas ( block_timestamp timestamp, block_number bigint, transaction_hash text, transaction_index bigint, from_address text, contract_address text, symbol text, total_supply text, name text, decimals bigint, is_erc20 integer, is_erc721 integer, is_erc1155 integer, is_proxy integer, extra_info text, pk integer )\nCREATE TABLE erc1155_approval_for_all ( block_number bigint, block_timestamp timestamp, transaction_index integer, transaction_hash text, log_index integer, contract_address text )\nCREATE TABLE erc20_balances ( block_number bigint, contract_address text, wallet_address text, amount text, pk text )\nCREATE TABLE sui_coins ( object_id text, status text, coin_type text, balance text, owner text )\nCREATE TABLE sui_coins_metadata ( object_id text, coin_type text, status text, decimals bigint, description text, icon_url text, symbol text, name text )\nCREATE TABLE sui_nfts ( object_id text, status text, collection_type text, package_id text, previous_transaction text, display text, owner text, name text )\nCREATE TABLE nft_metadata ( blockchain text, contract_address text, token_id text, contract_name text, erc_type text, amount bigint, minter text, owner text, mint_block_number bigint, mint_time bigint, mint_transaction_hash text, mint_price text, token_uri text, metadata text, name text, image_uri text, traits text, updated_at bigint, status text, rarity_score real, rarity_rank integer, unique_attribute_count integer, pk integer )\nCREATE TABLE nft_collections ( blockchain text, contract_address text, name text, symbol text, deploy_block_number bigint, deploy_block_time bigint, erc_type text, owner text, traits text, description text, slug text, media_info text, image_url text, banner_image_url text, updated_at bigint, banner text, token_count bigint, floor_price text, floor_price_symbol text, floor_price_contract text, pk integer )\nCREATE TABLE token_prices ( uuid text, blockchain text, address text, decimals bigint, symbol text, price real, timestamp timestamp )\nCREATE TABLE token_prices_latest ( blockchain text, address text, decimals bigint, symbol text, price real, timestamp timestamp )\nCREATE TABLE token_balances ( block_number bigint, block_timestamp timestamp, tick text, wallet_address text, total_supply decimal, amount decimal )\nCREATE TABLE token_info ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash text, tick text, max_supply decimal, lim decimal, wlim decimal, dec integer, creator text )\nCREATE TABLE token_activities ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash text, log_index integer, type text, tick text, id text, amt decimal, from_address text, to_address text )\nCREATE TABLE mud_holesky_redstone ( address text, table_id text, key_bytes text, key0 text, key1 text, static_data text, encoded_lengths text, dynamic_data text, is_deleted boolean, block_number bigint, log_index bigint )\nCREATE TABLE token_balances_bitcoin ( block_number bigint, block_timestamp timestamp, tick text, wallet_address text, total_supply text, amount text )\nCREATE TABLE token_activities_avalanche ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash text, log_index integer, type text, tick text, id text, amt decimal, from_address text, to_address text )\nCREATE TABLE token_balances_avalanche ( block_number bigint, block_timestamp timestamp, tick text, wallet_address text, total_supply decimal, amount decimal )\nCREATE TABLE token_info_avalanche ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash text, tick text, max_supply decimal, lim decimal, wlim decimal, dec integer, creator text, minted decimal, holders decimal, txs decimal, updated_timestamp timestamp, completed_timestamp timestamp, id text )\n"} {"conversations": [{"role": "user", "content": "Find employees who are managers and list the number of employees they directly manage. Show the manager's full name and the count of their direct reports."}, {"role": "assistant", "content": "SELECT m.first_name || ' ' || m.last_name AS manager_full_name, COUNT(e.employee_id) AS number_of_direct_reports FROM government_services.employees AS e JOIN government_services.employees AS m ON e.manager_employee_id = m.employee_id GROUP BY m.employee_id, manager_full_name;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.employees (\n employee_id character varying(64) NOT NULL, -- unique identifier for the government employee\n agency_id character varying(64) NOT NULL, -- FK to agencies table\n first_name character varying(100) NOT NULL,\n last_name character varying(100) NOT NULL,\n job_title character varying(150) NOT NULL,\n department character varying(100),\n work_email character varying(128) NOT NULL UNIQUE,\n work_phone character varying(32),\n hire_date date NOT NULL,\n termination_date date, -- null if currently employed\n access_level character varying(50), -- Role or permission level\n manager_employee_id character varying(64), -- FK to self for reporting structure\n PRIMARY KEY (employee_id)\n)\n"} {"conversations": [{"role": "user", "content": "How many lawyers who are partners were hired in each year? Show the hire year and the count."}, {"role": "assistant", "content": "SELECT strftime('%Y', hire_date) AS hire_year , count(lawyer_id) FROM legal_services.lawyers WHERE is_partner = true GROUP BY hire_year"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.lawyers (\n lawyer_id character varying(64) NOT NULL, -- unique identifier for the lawyer\n first_name character varying(100) NOT NULL, -- lawyer's first name\n last_name character varying(100) NOT NULL, -- lawyer's last name\n bar_number character varying(64) UNIQUE NOT NULL, -- lawyer's bar association number\n firm_id character varying(64), -- FK to law_firms table\n email character varying(128) UNIQUE NOT NULL, -- lawyer's professional email\n phone character varying(32), -- lawyer's contact phone number\n specialization text, -- areas of legal expertise\n hire_date timestamp NOT NULL, -- date the lawyer was hired or joined\n is_partner boolean DEFAULT false, -- flag indicating if the lawyer is a partner\n PRIMARY KEY (lawyer_id)\n)\n"} {"conversations": [{"role": "user", "content": "Show me wallet addresses that hold more than 1000 of any ERC1155 token, along with the token ID and contract address."}, {"role": "assistant", "content": "SELECT wallet_address, token_id, contract_address FROM erc20_balances WHERE CAST(amount AS decimal) > 1000;"}, {"role": "user", "content": "I think there's an error in your query - it should be using the nft_metadata table for ERC1155 tokens. Also, can you include the token name from the nft_metadata table?"}, {"role": "assistant", "content": "SELECT nm.owner as wallet_address, nm.token_id, nm.contract_address, nm.name FROM nft_metadata nm WHERE nm.erc_type = 'ERC1155' AND CAST(nm.amount AS decimal) > 1000;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE erc1155_approval_for_all (\n block_number bigint NOT NULL, -- Block number containing the transaction\n block_timestamp timestamp(3) NOT NULL, -- Timestamp of the block containing the transaction\n transaction_index integer NOT NULL, -- Index of the transaction within the block\n transaction_hash varchar(66) NOT NULL, -- Transaction hash\n log_index integer NOT NULL, -- Log index\n contract_address varchar(42) NOT NULL -- Event contract address\n)\nCREATE TABLE erc20_balances ( block_number.bigint, contract_address.text, wallet_address.text, amount.text, pk.text )\nCREATE TABLE erc20_balances_historical ( block_number bigint NOT NULL, contract_address varchar NOT NULL, wallet_address varchar NOT NULL, amount varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE nft_metadata (\n blockchain varchar NOT NULL, -- blockchain fields for the functionType in contract\n contract_address varchar NOT NULL, -- Contract address(with bloom filter)\n token_id varchar NOT NULL, -- The number of the token\n contract_name varchar NOT NULL, -- contract_name fields for the functionType in contract\n erc_type varchar NOT NULL, -- The type of token\n amount bigint NOT NULL, -- amount fields for the functionType in contract\n minter varchar NOT NULL, -- minter fields for the functionType in contract\n owner varchar NOT NULL, -- owner fields for the functionType in contract\n mint_block_number bigint NOT NULL, -- mint_block_number fields for the functionType in contract\n mint_time bigint NOT NULL, -- mint_time fields for the functionType in contract\n mint_transaction_hash varchar NOT NULL, -- mint_transaction_hash fields for the functionType in contract\n mint_price varchar NOT NULL, -- mint_price fields for the functionType in contract\n token_uri varchar NOT NULL, -- token_uri fields for the functionType in contract\n metadata varchar NOT NULL, -- metadata fields for the functionType in contract\n name varchar NOT NULL, -- name fields for the functionType in contract\n image_uri varchar NOT NULL, -- image_uri fields for the functionType in contract\n traits varchar NOT NULL, -- traits fields for the functionType in contract\n updated_at bigint NOT NULL, -- updated_at fields for the functionType in contract\n status varchar NOT NULL, -- status fields for the functionType in contract\n rarity_score real NOT NULL, -- rarity_score fields for the functionType in contract\n rarity_rank integer NOT NULL, -- rarity_rank fields for the functionType in contract\n unique_attribute_count integer NOT NULL, -- unique_attribute_count fields for the functionType in contract\n pk integer NOT NULL -- Partition key for the table(floor(mint_time / 1000 / 86400 / 30))\n)\nCREATE TABLE nft_collections ( blockchain.text, contract_address.text, name.text, symbol.text, deploy_block_number.bigint, deploy_block_time.bigint, erc_type.text, owner.text, traits.text, description.text, slug.text, media_info.text, image_url.text, banner_image_url.text, updated_at.bigint, banner.text, token_count.bigint, floor_price.text, floor_price_symbol.text, floor_price_contract.text, pk.integer )\nCREATE TABLE token_prices ( uuid varchar(36) NOT NULL, blockchain varchar(36) NOT NULL, address varchar(42) NOT NULL, decimals bigint NOT NULL, symbol varchar(36) NOT NULL, price real NOT NULL, timestamp timestamp(6) NOT NULL )\nCREATE TABLE erc20_approval ( block_number bigint NOT NULL, block_timestamp timestamp(6) NOT NULL, transaction_index integer NOT NULL, transaction_hash varchar NOT NULL, log_index integer NOT NULL, contract_address varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE token_info ( block_timestamp timestamp(3) NOT NULL, block_number bigint NOT NULL, tx_index integer NOT NULL, tx_hash varchar(66) NOT NULL, tick varchar NOT NULL, max_supply decimal(38,0) NOT NULL, lim decimal(38,0) NOT NULL, wlim decimal(38,0) NOT NULL, dec integer NOT NULL, creator varchar(42) NOT NULL )\nCREATE TABLE mud_holesky_redstone (\n address varchar NOT NULL, -- address fields for the functionType in contract\n table_id varchar NOT NULL, -- table_id fields for the functionType in contract\n key_bytes varchar NOT NULL, -- key_bytes fields for the functionType in contract\n key0 varchar NOT NULL, -- key0 fields for the functionType in contract\n key1 varchar NOT NULL, -- key1 fields for the functionType in contract\n static_data varchar NOT NULL, -- static_data fields for the functionType in contract\n encoded_lengths varchar NOT NULL, -- encoded_lengths fields for the functionType in contract\n dynamic_data varchar NOT NULL, -- dynamic_data fields for the functionType in contract\n is_deleted boolean NOT NULL, -- is_deleted fields for the functionType in contract\n block_number bigint NOT NULL, -- Block number uniquely identifying the block\n log_index bigint NOT NULL -- Index of the log within the transaction\n)\nCREATE TABLE token_info_bitcoin ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash varchar, tick varchar, max_supply decimal, lim decimal, wlim decimal, dec integer, creator varchar )\nCREATE TABLE token_info_avalanche ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash text, tick text, max_supply decimal, lim decimal, wlim decimal, dec integer, creator text, minted decimal, holders decimal, txs decimal, updated_timestamp timestamp, completed_timestamp timestamp, id text )\n"} {"conversations": [{"role": "user", "content": "Show a list of all wallet addresses along with the user_id who owns them, sorted by the wallet creation time."}, {"role": "assistant", "content": "SELECT user_id, address FROM web3.wallets ORDER BY created_at;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE web3.wallets (\n wallet_id character varying(64) NOT NULL, -- unique identifier for the wallet\n user_id character varying(64) NOT NULL, -- identifier of the user owning the wallet\n address character varying(128) NOT NULL, -- address of the wallet\n private_key text NOT NULL, -- private key of the wallet\n created_at timestamp NOT NULL, -- time when the wallet was created\n PRIMARY KEY (wallet_id)\n)\n"} {"conversations": [{"role": "user", "content": "I want to see, for each guest, the total number of payments they have made and the timestamp of their latest payment."}, {"role": "assistant", "content": "SELECT p.guest_id,\n COUNT(p.payment_id) AS payment_count,\n t.last_ts\nFROM hospitality_technology.payments p\nJOIN (\n SELECT guest_id,\n MAX(payment_timestamp) AS last_ts\n FROM hospitality_technology.payments\n GROUP BY guest_id\n) t ON p.guest_id = t.guest_id\nGROUP BY p.guest_id, t.last_ts;"}, {"role": "user", "content": "Only include guests whose latest payment status was 'Succeeded' and who have made at least 5 successful payments."}, {"role": "assistant", "content": "SELECT p.guest_id,\n COUNT(p.payment_id) AS payment_count,\n t.last_ts\nFROM hospitality_technology.payments p\nJOIN (\n SELECT guest_id,\n MAX(payment_timestamp) AS last_ts,\n COUNT(*) AS cnt\n FROM hospitality_technology.payments\n WHERE status = 'Succeeded'\n GROUP BY guest_id\n HAVING COUNT(*) >= 5\n) t ON p.guest_id = t.guest_id\nGROUP BY p.guest_id, t.last_ts;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE hospitality_technology.payments ( payment_id character varying(64) NOT NULL, reservation_id character varying(64), guest_id character varying(64) NOT NULL, bill_id character varying(64), amount numeric(12,2) NOT NULL, currency_code character varying(3) NOT NULL, payment_method character varying(50) NOT NULL, card_type character varying(50), card_last_four character varying(4), transaction_ref character varying(128), payment_timestamp timestamp with time zone NOT NULL DEFAULT current_timestamp, status character varying(50) NOT NULL, staff_id_processed character varying(64), notes text, PRIMARY KEY (payment_id), FOREIGN KEY (reservation_id) REFERENCES hospitality_technology.reservations(reservation_id), FOREIGN KEY (guest_id) REFERENCES hospitality_technology.guests(guest_id), FOREIGN KEY (staff_id_processed) REFERENCES hospitality_technology.staff(staff_id) )\n"} {"conversations": [{"role": "user", "content": "Count the total number of chronic diagnoses for each code_type."}, {"role": "assistant", "content": "SELECT\n code_type,\n COUNT(*) AS chronic_diagnosis_count\nFROM healthcare.diagnoses\nWHERE is_chronic = TRUE\nGROUP BY code_type;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.diagnoses ( diagnosis_id.text, record_id.text, patient_id.text, doctor_id.text, diagnosis_code.text, code_type.text, description.text, diagnosis_date.date, status.text, is_chronic.boolean )\nCREATE TABLE healthcare.prescriptions ( prescription_id.text, record_id.text, patient_id.text, doctor_id.text, medication_id.text, dosage.text, frequency.text, route.text, start_date.date, end_date.date, quantity_dispensed.numeric, refills_allowed.integer, prescription_date.timestamp )\n"} {"conversations": [{"role": "user", "content": "List each guest’s full name and the total number of service orders they have placed, ordered by order count descending."}, {"role": "assistant", "content": "SELECT g.guest_id,\n g.first_name || ' ' || g.last_name AS full_name,\n COUNT(so.order_id) AS order_count\nFROM hospitality_technology.guests g\nLEFT JOIN hospitality_technology.service_orders so\n ON g.guest_id = so.guest_id\nGROUP BY g.guest_id, full_name\nORDER BY order_count DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE hospitality_technology.guests ( guest_id text PRIMARY KEY, first_name text, last_name text, email text, phone_number text, date_of_birth date, address_line1 text, city text, state_province text, postal_code text, country_code text, preferences text, loyalty_member_id text, communication_consent boolean, created_at timestamp, updated_at timestamp )\nCREATE TABLE hospitality_technology.reservations ( reservation_id text, property_id text, guest_id text, room_id text, room_type_id text, check_in_date date, check_out_date date, actual_check_in_ts timestamp, actual_check_out_ts timestamp, num_adults integer, num_children integer, status text, booking_source text, rate_plan_id text, total_amount numeric, amount_paid numeric, special_requests text, created_at timestamp, updated_at timestamp )\nCREATE TABLE hospitality_technology.service_orders ( order_id.text, reservation_id.text, guest_id.text, service_id.text, staff_id_ordered.text, staff_id_delivered.text, order_timestamp.timestamp, delivery_timestamp.timestamp, quantity.integer, unit_price.numeric, total_price.numeric, status.text, notes.text, bill_id.text )\nCREATE TABLE hospitality_technology.reviews ( review_id character varying(64) NOT NULL, property_id character varying(64) NOT NULL, reservation_id character varying(64) UNIQUE, guest_id character varying(64) NOT NULL, rating_overall integer, rating_cleanliness integer, rating_service integer, rating_location integer, rating_value integer, comment text, review_source character varying(100), review_date timestamp with time zone NOT NULL DEFAULT current_timestamp, is_public boolean DEFAULT true, staff_response text, response_staff_id character varying(64), response_date timestamp with time zone, PRIMARY KEY (review_id), FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id), FOREIGN KEY (reservation_id) REFERENCES hospitality_technology.reservations(reservation_id), FOREIGN KEY (guest_id) REFERENCES hospitality_technology.guests(guest_id), FOREIGN KEY (response_staff_id) REFERENCES hospitality_technology.staff(staff_id) )\n"} {"conversations": [{"role": "user", "content": "List the first name, last name, and hire date of all lawyers who are partners."}, {"role": "assistant", "content": "SELECT first_name , last_name , hire_date FROM legal_services.lawyers WHERE is_partner = TRUE"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.lawyers (\n lawyer_id character varying(64) NOT NULL, -- unique identifier for the lawyer\n first_name character varying(100) NOT NULL, -- lawyer's first name\n last_name character varying(100) NOT NULL, -- lawyer's last name\n bar_number character varying(64) UNIQUE NOT NULL, -- lawyer's bar association number\n firm_id character varying(64), -- FK to law_firms table\n email character varying(128) UNIQUE NOT NULL, -- lawyer's professional email\n phone character varying(32), -- lawyer's contact phone number\n specialization text, -- areas of legal expertise\n hire_date timestamp NOT NULL, -- date the lawyer was hired or joined\n is_partner boolean DEFAULT false, -- flag indicating if the lawyer is a partner\n PRIMARY KEY (lawyer_id)\n)\n"} {"conversations": [{"role": "user", "content": "List all posts where the content mentions 'meeting'."}, {"role": "assistant", "content": "SELECT post_id, user_id, content, created_at FROM social_media.posts WHERE content LIKE '%meeting%'"}, {"role": "user", "content": "Also, only include those posts that are public."}, {"role": "assistant", "content": "SELECT post_id, user_id, content, created_at FROM social_media.posts WHERE content LIKE '%meeting%' AND visibility = 'public'"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE social_media.posts ( post_id text PRIMARY KEY, user_id text, content text, media_url text, media_type text, created_at timestamp, updated_at timestamp, visibility text, location_lat numeric, location_lon numeric )\n"} {"conversations": [{"role": "user", "content": "Find all users who registered with a Yahoo email address, along with their registration dates."}, {"role": "assistant", "content": "SELECT user_id, username, email, password_hash FROM blockchain.users WHERE email LIKE '%@yahoo.com';"}, {"role": "user", "content": "This query doesn't show registration dates. Can you modify it to include the registration date?"}, {"role": "assistant", "content": "I notice the users table doesn't have a registration date column. Would you like me to show other available information from the users table?"}, {"role": "user", "content": "Then just show me the count of Yahoo email users instead."}, {"role": "assistant", "content": "SELECT COUNT(*) as yahoo_user_count FROM blockchain.users WHERE email LIKE '%@yahoo.com';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE blockchain.blocks ( block_id text, previous_block_id text, timestamp timestamp, nonce integer, merkle_root text, difficulty integer )\nCREATE TABLE blockchain.transactions (\n transaction_id character varying(64) NOT NULL, -- unique identifier for the transaction\n block_id character varying(64) NOT NULL, -- identifier of the block containing the transaction\n sender_address character varying(128) NOT NULL, -- address of the sender\n receiver_address character varying(128) NOT NULL, -- address of the receiver\n amount numeric(38,14) NOT NULL, -- amount transferred\n timestamp timestamp NOT NULL, -- time when the transaction was created\n signature text NOT NULL, -- digital signature of the transaction\n PRIMARY KEY (transaction_id)\n)\nCREATE TABLE blockchain.addresses ( address_id text PRIMARY KEY, public_key text, balance numeric )\nCREATE TABLE blockchain.users ( user_id character varying(64) NOT NULL, username character varying(128) NOT NULL, email character varying(128) NOT NULL, password_hash text NOT NULL, PRIMARY KEY (user_id) )\n"} {"conversations": [{"role": "user", "content": "Show me all SUI coins with a balance greater than 1000, including their symbol and name."}, {"role": "assistant", "content": "SELECT sc.object_id, sc.coin_type, sc.balance, scm.symbol, scm.name FROM sui_coins sc JOIN sui_coins_metadata scm ON sc.coin_type = scm.coin_type WHERE CAST(sc.balance AS DECIMAL) > 1000;"}, {"role": "user", "content": "Also, include the owner address for each coin in the result."}, {"role": "assistant", "content": "SELECT sc.object_id, sc.coin_type, sc.balance, sc.owner, scm.symbol, scm.name FROM sui_coins sc JOIN sui_coins_metadata scm ON sc.coin_type = scm.coin_type WHERE CAST(sc.balance AS DECIMAL) > 1000;"}, {"role": "user", "content": "Only show coins which are currently 'active', and add the coin description."}, {"role": "assistant", "content": "SELECT sc.object_id, sc.coin_type, sc.balance, sc.owner, scm.symbol, scm.name, scm.description FROM sui_coins sc JOIN sui_coins_metadata scm ON sc.coin_type = scm.coin_type WHERE CAST(sc.balance AS DECIMAL) > 1000 AND sc.status = 'active' AND scm.status = 'active';"}, {"role": "user", "content": "Actually, limit the result to just 10 coins and sort them by balance descending."}, {"role": "assistant", "content": "SELECT sc.object_id, sc.coin_type, sc.balance, sc.owner, scm.symbol, scm.name, scm.description FROM sui_coins sc JOIN sui_coins_metadata scm ON sc.coin_type = scm.coin_type WHERE CAST(sc.balance AS DECIMAL) > 1000 AND sc.status = 'active' AND scm.status = 'active' ORDER BY CAST(sc.balance AS DECIMAL) DESC LIMIT 10;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE erc20_balances ( block_number bigint, contract_address varchar, wallet_address varchar, amount varchar, pk varchar )\nCREATE TABLE erc20_balances_historical ( block_number bigint, contract_address varchar, wallet_address varchar, amount varchar, pk integer )\nCREATE TABLE nft_holder_historical ( block_number bigint, contract_address varchar, wallet_address varchar, token_id varchar, contract_type varchar, amount varchar, pk integer )\nCREATE TABLE sui_coins ( object_id varchar, status varchar, coin_type varchar, balance varchar, owner varchar )\nCREATE TABLE sui_coins_metadata ( object_id varchar, coin_type varchar, status varchar, decimals bigint, description varchar, icon_url varchar, symbol varchar, name varchar )\nCREATE TABLE nft_metadata ( blockchain varchar, contract_address varchar, token_id varchar, contract_name varchar, erc_type varchar, amount bigint, minter varchar, owner varchar, mint_block_number bigint, mint_time bigint, mint_transaction_hash varchar, mint_price varchar, token_uri varchar, metadata varchar, name varchar, image_uri varchar, traits varchar, updated_at bigint, status varchar, rarity_score real, rarity_rank integer, unique_attribute_count integer, pk integer )\nCREATE TABLE nft_collections ( blockchain varchar, contract_address varchar, name varchar, symbol varchar, deploy_block_number bigint, deploy_block_time bigint, erc_type varchar, owner varchar, traits varchar, description varchar, slug varchar, media_info varchar, image_url varchar, banner_image_url varchar, updated_at bigint, banner varchar, token_count bigint, floor_price varchar, floor_price_symbol varchar, floor_price_contract varchar, pk integer )\nCREATE TABLE token_prices_latest ( blockchain varchar, address varchar, decimals bigint, symbol varchar, price real, timestamp timestamp )\nCREATE TABLE erc20_approval ( block_number bigint, block_timestamp timestamp, transaction_index integer, transaction_hash varchar, log_index integer, contract_address varchar, pk integer )\nCREATE TABLE token_activities ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash varchar, log_index integer, type varchar, tick varchar, id varchar, amt decimal, from_address varchar, to_address varchar )\nCREATE TABLE mud_holesky_redstone ( address varchar, table_id varchar, key_bytes varchar, key0 varchar, key1 varchar, static_data varchar, encoded_lengths varchar, dynamic_data varchar, is_deleted boolean, block_number bigint, log_index bigint )\nCREATE TABLE token_info_bitcoin ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash varchar, tick varchar, max_supply decimal, lim decimal, wlim decimal, dec integer, creator varchar )\nCREATE TABLE token_info_avalanche ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash varchar, tick varchar, max_supply decimal, lim decimal, wlim decimal, dec integer, creator varchar, minted decimal, holders decimal, txs decimal, updated_timestamp timestamp, completed_timestamp timestamp, id varchar )\n"} {"conversations": [{"role": "user", "content": "Show me all users who have wallets but have never placed any orders, along with their wallet creation dates."}, {"role": "assistant", "content": "SELECT u.user_id, u.username, w.wallet_id, w.created_at FROM trading_platform.users u JOIN trading_platform.wallets w ON u.user_id = w.user_id LEFT JOIN trading_platform.orders o ON u.user_id = o.user_id WHERE o.order_id IS NULL ORDER BY w.created_at DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE trading_platform.users (\n user_id character varying(64) NOT NULL, -- unique identifier for the user\n username character varying(128) NOT NULL, -- username of the user\n email character varying(128) NOT NULL, -- email address of the user\n password_hash text NOT NULL, -- hashed password of the user\n created_at timestamp NOT NULL, -- time when the user account was created\n PRIMARY KEY (user_id)\n)\nCREATE TABLE trading_platform.wallets (\n wallet_id character varying(64) NOT NULL, -- unique identifier for the wallet\n user_id character varying(64) NOT NULL, -- identifier of the user owning the wallet\n address character varying(128) NOT NULL, -- address of the wallet\n private_key text NOT NULL, -- private key of the wallet\n created_at timestamp NOT NULL, -- time when the wallet was created\n PRIMARY KEY (wallet_id)\n)\nCREATE TABLE trading_platform.orders (\n order_id character varying(64) NOT NULL, -- unique identifier for the order\n user_id character varying(64) NOT NULL, -- identifier of the user placing the order\n wallet_id character varying(64) NOT NULL, -- identifier of the wallet used for the order\n asset_id character varying(64) NOT NULL, -- identifier of the asset being traded\n order_type character varying(32) NOT NULL, -- type of the order (e.g., buy, sell)\n quantity numeric(38,14) NOT NULL, -- quantity of the asset in the order\n price numeric(38,14) NOT NULL, -- price per unit of the asset\n status character varying(32) NOT NULL, -- status of the order (e.g., open, filled, canceled)\n created_at timestamp NOT NULL, -- time when the order was created\n PRIMARY KEY (order_id)\n)\nCREATE TABLE trading_platform.trades (\n trade_id character varying(64) NOT NULL, -- unique identifier for the trade\n order_id character varying(64) NOT NULL, -- identifier of the order that led to the trade\n buyer_id character varying(64) NOT NULL, -- identifier of the buyer\n seller_id character varying(64) NOT NULL, -- identifier of the seller\n asset_id character varying(64) NOT NULL, -- identifier of the asset being traded\n quantity numeric(38,14) NOT NULL, -- quantity of the asset in the trade\n price numeric(38,14) NOT NULL, -- price per unit of the asset\n traded_at timestamp NOT NULL, -- time when the trade was executed\n PRIMARY KEY (trade_id)\n)\nCREATE TABLE trading_platform.assets (\n asset_id character varying(64) NOT NULL, -- unique identifier for the asset\n name character varying(128) NOT NULL, -- name of the asset\n symbol character varying(32) NOT NULL, -- symbol of the asset\n type character varying(32) NOT NULL, -- type of the asset (e.g., cryptocurrency, stock)\n PRIMARY KEY (asset_id)\n)\nCREATE TABLE trading_platform.dapps (\n dapp_id character varying(64) NOT NULL, -- unique identifier for the DApp\n name character varying(128) NOT NULL, -- name of the DApp\n description text NOT NULL, -- description of the DApp\n url character varying(256) NOT NULL, -- URL of the DApp\n PRIMARY KEY (dapp_id)\n)\nCREATE TABLE trading_platform.peers (\n peer_id character varying(64) NOT NULL, -- unique identifier for the peer\n ip_address character varying(15) NOT NULL, -- IP address of the peer\n port integer NOT NULL, -- port number of the peer\n last_seen timestamp NOT NULL, -- last time the peer was active\n PRIMARY KEY (peer_id)\n)\nCREATE TABLE trading_platform.metadata (\n metadata_id character varying(64) NOT NULL, -- unique identifier for the metadata\n asset_id character varying(64) NOT NULL, -- identifier of the asset the metadata is associated with\n key character varying(128) NOT NULL, -- key of the metadata\n value text NOT NULL, -- value of the metadata\n PRIMARY KEY (metadata_id)\n)\nCREATE TABLE trading_platform.kyc_audit (\n kyc_audit_id character varying(64) NOT NULL, -- unique identifier for the KYC audit\n user_id character varying(64) NOT NULL, -- identifier of the user being audited\n status character varying(32) NOT NULL, -- status of the KYC audit (e.g., pending, approved, rejected)\n reviewed_at timestamp NOT NULL, -- time when the KYC audit was reviewed\n PRIMARY KEY (kyc_audit_id)\n)\nCREATE TABLE trading_platform.logs (\n log_id character varying(64) NOT NULL, -- unique identifier for the log entry\n user_id character varying(64), -- identifier of the user associated with the log entry\n action character varying(128) NOT NULL, -- action performed\n details text NOT NULL, -- details of the action\n logged_at timestamp NOT NULL, -- time when the log entry was created\n PRIMARY KEY (log_id)\n)\n"} {"conversations": [{"role": "user", "content": "What is the total USD value held across all wallets for the ERC20 token with symbol 'DAI'?"}, {"role": "assistant", "content": "SELECT SUM((eb.amount::numeric / POWER(10, tm.decimals)) * tpl.price) AS total_usd\nFROM erc20_balances eb\nJOIN token_metas tm ON eb.contract_address = tm.contract_address AND tm.symbol = 'DAI'\nJOIN token_prices_latest tpl ON tm.contract_address = tpl.address AND tpl.blockchain = 'Ethereum';"}, {"role": "user", "content": "Could you break it down to show the top 5 wallets by USD value for this token?"}, {"role": "assistant", "content": "SELECT eb.wallet_address,\n SUM((eb.amount::numeric / POWER(10, tm.decimals)) * tpl.price) AS usd_value\nFROM erc20_balances eb\nJOIN token_metas tm ON eb.contract_address = tm.contract_address AND tm.symbol = 'DAI'\nJOIN token_prices_latest tpl ON tm.contract_address = tpl.address AND tpl.blockchain = 'Ethereum'\nGROUP BY eb.wallet_address\nORDER BY usd_value DESC\nLIMIT 5;"}, {"role": "user", "content": "I received a type error because amount is stored as text. Can you cast the fields to numeric explicitly in the query?"}, {"role": "assistant", "content": "SELECT eb.wallet_address,\n SUM((CAST(eb.amount AS numeric) / POWER(10, tm.decimals)) * CAST(tpl.price AS numeric)) AS usd_value\nFROM erc20_balances eb\nJOIN token_metas tm ON eb.contract_address = tm.contract_address AND tm.symbol = 'DAI'\nJOIN token_prices_latest tpl ON tm.contract_address = tpl.address AND tpl.blockchain = 'Ethereum'\nGROUP BY eb.wallet_address\nORDER BY usd_value DESC\nLIMIT 5;"}, {"role": "user", "content": "Also include the latest price timestamp alongside the USD value for each wallet."}, {"role": "assistant", "content": "SELECT eb.wallet_address,\n SUM((CAST(eb.amount AS numeric) / POWER(10, tm.decimals)) * tpl.price) AS usd_value,\n MAX(tpl.timestamp) AS price_timestamp\nFROM erc20_balances eb\nJOIN token_metas tm ON eb.contract_address = tm.contract_address AND tm.symbol = 'DAI'\nJOIN token_prices_latest tpl ON tm.contract_address = tpl.address AND tpl.blockchain = 'Ethereum'\nGROUP BY eb.wallet_address\nORDER BY usd_value DESC\nLIMIT 5;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE token_metas ( block_timestamp timestamp, block_number bigint, transaction_hash varchar, transaction_index bigint, from_address varchar, contract_address varchar, symbol varchar, total_supply varchar, name varchar, decimals bigint, is_erc20 integer, is_erc721 integer, is_erc1155 integer, is_proxy integer, extra_info varchar, pk integer )\nCREATE TABLE erc1155_approval_for_all ( block_number bigint NOT NULL, block_timestamp timestamp(3) NOT NULL, transaction_index integer NOT NULL, transaction_hash varchar(66) NOT NULL, log_index integer NOT NULL, contract_address varchar(42) NOT NULL )\nCREATE TABLE erc20_balances ( block_number.bigint, contract_address.text, wallet_address.text, amount.text, pk.text )\nCREATE TABLE erc20_balances_historical (\n block_number bigint NOT NULL, -- Block number containing the transaction\n contract_address varchar NOT NULL, -- Event contract address\n wallet_address varchar NOT NULL, -- The wallet address for the contract\n amount varchar NOT NULL, -- Wallet's on-chain balance at the corresponding block height\n pk integer NOT NULL -- Partition key for the table(floor(block_number / 7200))\n)\nCREATE TABLE nft_holder_historical ( block_number.bigint, contract_address.text, wallet_address.text, token_id.text, contract_type.text, amount.text, pk.integer )\nCREATE TABLE sui_coins_metadata ( object_id varchar, coin_type varchar, status varchar, decimals bigint, description varchar, icon_url varchar, symbol varchar, name varchar )\nCREATE TABLE nft_metadata ( blockchain text, contract_address text, token_id text, contract_name text, erc_type text, amount bigint, minter text, owner text, mint_block_number bigint, mint_time bigint, mint_transaction_hash text, mint_price text, token_uri text, metadata text, name text, image_uri text, traits text, updated_at bigint, status text, rarity_score real, rarity_rank integer, unique_attribute_count integer, pk integer )\nCREATE TABLE nft_collections (\n blockchain varchar NOT NULL, -- blockchain fields for the functionType in contract\n contract_address varchar NOT NULL, -- Contract address(with bloom filter)\n name varchar NOT NULL, -- name fields for the functionType in contract\n symbol varchar NOT NULL, -- symbol fields for the functionType in contract\n deploy_block_number bigint NOT NULL, -- deploy_block_number fields for the functionType in contract\n deploy_block_time bigint NOT NULL, -- deploy_block_time fields for the functionType in contract\n erc_type varchar NOT NULL, -- The type of token\n owner varchar NOT NULL, -- owner fields for the functionType in contract\n traits varchar NOT NULL, -- traits fields for the functionType in contract\n description varchar NOT NULL, -- description fields for the functionType in contract\n slug varchar NOT NULL, -- slug fields for the functionType in contract\n media_info varchar NOT NULL, -- media_info fields for the functionType in contract\n image_url varchar NOT NULL, -- image_url fields for the functionType in contract\n banner_image_url varchar NOT NULL, -- banner_image_url fields for the functionType in contract\n updated_at bigint NOT NULL, -- updated_at fields for the functionType in contract\n banner varchar NOT NULL, -- banner fields for the functionType in contract\n token_count bigint NOT NULL, -- token_count fields for the functionType in contract\n floor_price varchar NOT NULL, -- floor_price fields for the functionType in contract\n floor_price_symbol varchar NOT NULL, -- floor_price_symbol fields for the functionType in contract\n floor_price_contract varchar NOT NULL, -- floor_price_contract fields for the functionType in contract\n pk integer NOT NULL -- Partition key for the table(floor(deploy_block_time / 1000 / 86400 / 30))\n)\nCREATE TABLE token_prices ( uuid varchar, blockchain varchar, address varchar, decimals bigint, symbol varchar, price real, timestamp timestamp )\nCREATE TABLE token_prices_latest (\n blockchain varchar(36) NOT NULL, -- blockchain fields for the functionType in contract\n address varchar(42) NOT NULL, -- address fields for the functionType in contract\n decimals bigint NOT NULL, -- decimals fields for the functionType in contract\n symbol varchar(36) NOT NULL, -- symbol fields for the functionType in contract\n price real NOT NULL, -- price fields for the functionType in contract\n timestamp timestamp(6) NOT NULL -- timestamp fields for the functionType in contract\n)\nCREATE TABLE erc20_approval ( block_number bigint, block_timestamp timestamp, transaction_index integer, transaction_hash text, log_index integer, contract_address text, pk integer )\nCREATE TABLE token_info (\n block_timestamp timestamp(3) NOT NULL, -- Timestamp of the block containing the inscription (matches block_timestamp in transactions table)\n block_number bigint NOT NULL, -- Block number containing the inscription (matches block_number in transactions table)\n tx_index integer NOT NULL, -- Index of the transaction containing the inscription (matches transaction_index in transactions table)\n tx_hash varchar(66) NOT NULL, -- Unique identifier of the transaction containing the inscription (matches hash in transactions table)\n tick varchar NOT NULL, -- Token tick\n max_supply decimal(38,0) NOT NULL, -- Max supply\n lim decimal(38,0) NOT NULL, -- Limit of each mint\n wlim decimal(38,0) NOT NULL, -- Limit of each address can maximum mint\n dec integer NOT NULL, -- Decimal for minimum divie\n creator varchar(42) NOT NULL -- Address originating the inscription (matches from_address in transactions table)\n)\nCREATE TABLE token_info_bitcoin ( block_timestamp timestamp(3) NOT NULL, block_number bigint NOT NULL, tx_index integer NOT NULL, tx_hash varchar(66) NOT NULL, tick varchar(255) NOT NULL, max_supply decimal(38,0) NOT NULL, lim decimal(38,0) NOT NULL, wlim decimal(38,0) NOT NULL, dec integer NOT NULL, creator varchar(42) NOT NULL )\nCREATE TABLE token_activities_avalanche ( block_timestamp timestamp(3) NOT NULL, block_number bigint NOT NULL, tx_index integer NOT NULL, tx_hash varchar(66) NOT NULL, log_index integer NOT NULL, type varchar(20) NOT NULL, tick varchar(255) NOT NULL, id varchar(255) NOT NULL, amt decimal(38,0) NOT NULL, from_address varchar(42) NOT NULL, to_address varchar(42) NOT NULL )\nCREATE TABLE token_info_avalanche ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash text, tick text, max_supply decimal, lim decimal, wlim decimal, dec integer, creator text, minted decimal, holders decimal, txs decimal, updated_timestamp timestamp, completed_timestamp timestamp, id text )\n"} {"conversations": [{"role": "user", "content": "List all active policies, showing the policy number, the customer's full name, and the agent's full name who sold the policy."}, {"role": "assistant", "content": "SELECT T1.policy_number, T2.first_name, T2.last_name, T3.first_name, T3.last_name FROM policies AS T1 JOIN customers AS T2 ON T1.customer_id = T2.customer_id JOIN agents AS T3 ON T1.agent_id = T3.agent_id WHERE T1.status = 'active'"}, {"role": "user", "content": "Can you also add the product name and the policy's premium amount to the results?"}, {"role": "assistant", "content": "SELECT T1.policy_number, T2.first_name AS customer_first_name, T2.last_name AS customer_last_name, T3.first_name AS agent_first_name, T3.last_name AS agent_last_name, T4.product_name, T1.premium_amount FROM policies AS T1 JOIN customers AS T2 ON T1.customer_id = T2.customer_id JOIN agents AS T3 ON T1.agent_id = T3.agent_id JOIN insurance_products AS T4 ON T1.product_id = T4.product_id WHERE T1.status = 'active'"}, {"role": "user", "content": "Actually, filter those results to only include policies with a premium amount greater than 5000 and only sold by agents whose license state is 'CA'."}, {"role": "assistant", "content": "SELECT T1.policy_number, T2.first_name AS customer_first_name, T2.last_name AS customer_last_name, T3.first_name AS agent_first_name, T3.last_name AS agent_last_name, T4.product_name, T1.premium_amount FROM policies AS T1 JOIN customers AS T2 ON T1.customer_id = T2.customer_id JOIN agents AS T3 ON T1.agent_id = T3.agent_id JOIN insurance_products AS T4 ON T1.product_id = T4.product_id WHERE T1.status = 'active' AND T1.premium_amount > 5000 AND T3.license_state = 'CA'"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.customers ( customer_id text PRIMARY KEY, first_name text, last_name text, date_of_birth date, ssn_hash text, address_line1 text, address_line2 text, city text, state text, zip_code text, country text, phone_number text, email text, created_at timestamp, updated_at timestamp, status text )\nCREATE TABLE insurance.policies ( policy_id character varying(64) NOT NULL, customer_id character varying(64) NOT NULL, product_id character varying(64) NOT NULL, agent_id character varying(64), policy_number character varying(100) NOT NULL UNIQUE, start_date date NOT NULL, end_date date NOT NULL, premium_amount numeric(12, 2) NOT NULL, coverage_limit numeric(15, 2) NOT NULL, deductible numeric(10, 2) NOT NULL, status character varying(30) NOT NULL, issued_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, cancellation_date date, cancellation_reason text, PRIMARY KEY (policy_id) )\nCREATE TABLE insurance.claims ( claim_id character varying(64) NOT NULL, policy_id character varying(64) NOT NULL, customer_id character varying(64) NOT NULL, incident_date timestamp NOT NULL, reported_date timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, description text NOT NULL, estimated_loss numeric(15, 2), status character varying(30) NOT NULL, settlement_amount numeric(15, 2), settlement_date date, claim_handler_id character varying(64), police_report_number character varying(100), PRIMARY KEY (claim_id) )\nCREATE TABLE insurance.agents ( agent_id text PRIMARY KEY, first_name text, last_name text, agency_name text, license_number text, license_state text, contact_email text, contact_phone text, hire_date date, termination_date date, status text, commission_rate numeric, manager_id text )\nCREATE TABLE insurance.premium_payments ( payment_id text PRIMARY KEY, policy_id text, customer_id text, payment_date timestamp, amount_paid numeric, payment_method text, transaction_reference text, due_date date, payment_period_start date, payment_period_end date, status text )\n"} {"conversations": [{"role": "user", "content": "How many posts have a media file attached?"}, {"role": "assistant", "content": "SELECT count(*) FROM social_media.posts WHERE media_url IS NOT NULL;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE social_media.users ( user_id text PRIMARY KEY, username text, email text, password_hash text, full_name text, profile_picture_url text, bio text, location text, created_at timestamp, updated_at timestamp, is_verified bool )\nCREATE TABLE social_media.posts ( post_id text PRIMARY KEY, user_id text, content text, media_url text, media_type text, created_at timestamp, updated_at timestamp, visibility text, location_lat numeric, location_lon numeric )\nCREATE TABLE social_media.comments ( comment_id text PRIMARY KEY, post_id text, user_id text, parent_comment_id text, content text, created_at timestamp, updated_at timestamp )\nCREATE TABLE social_media.likes ( like_id text PRIMARY KEY, user_id text, post_id text, comment_id text, created_at timestamp )\nCREATE TABLE social_media.hashtags ( hashtag_id text PRIMARY KEY, tag_name text, created_at timestamp )\nCREATE TABLE social_media.post_hashtags ( post_hashtag_id text PRIMARY KEY, post_id text, hashtag_id text )\nCREATE TABLE social_media.messages ( message_id text PRIMARY KEY, conversation_id text, sender_user_id text, content text, media_url text, media_type text, sent_at timestamp, read_at timestamp )\nCREATE TABLE social_media.conversations ( conversation_id text PRIMARY KEY, created_at timestamp, last_message_at timestamp, is_group_chat bool, group_name text )\nCREATE TABLE social_media.conversation_participants ( participant_id text PRIMARY KEY, conversation_id text, user_id text, joined_at timestamp, last_read_at timestamp )\nCREATE TABLE social_media.notifications ( notification_id text PRIMARY KEY, recipient_user_id text, sender_user_id text, notification_type text, target_entity_id text, target_entity_type text, created_at timestamp, read_at timestamp )\nCREATE TABLE social_media.user_settings ( setting_id text PRIMARY KEY, user_id text, theme text, email_notifications_enabled bool, push_notifications_enabled bool, private_profile bool, updated_at timestamp )\n"} {"conversations": [{"role": "user", "content": "Get the number of agents grouped by status. Return status and agent_count."}, {"role": "assistant", "content": "SELECT status,\n COUNT(*) AS agent_count\n FROM insurance.agents\n GROUP BY status;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.agents ( agent_id text PRIMARY KEY, first_name text, last_name text, agency_name text, license_number text, license_state text, contact_email text, contact_phone text, hire_date date, termination_date date, status text, commission_rate numeric, manager_id text )\n"} {"conversations": [{"role": "user", "content": "Count the number of posts that have a media URL but no textual content."}, {"role": "assistant", "content": "SELECT COUNT(*) FROM social_media.posts AS T1 WHERE T1.media_url IS NOT NULL AND (T1.content IS NULL OR T1.content = '');"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE social_media.users (\n user_id character varying(64) NOT NULL, -- unique identifier for the user\n username character varying(50) NOT NULL UNIQUE, -- user's unique handle\n email character varying(128) NOT NULL UNIQUE, -- user's email address\n password_hash text NOT NULL, -- hashed password\n full_name character varying(100), -- user's full name\n profile_picture_url text, -- URL to the profile picture\n bio text, -- short user biography\n location character varying(100), -- user's location\n created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of account creation\n updated_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of last profile update\n is_verified boolean NOT NULL DEFAULT false, -- verification status\n PRIMARY KEY (user_id)\n)\nCREATE TABLE social_media.posts (\n post_id character varying(64) NOT NULL, -- unique identifier for the post\n user_id character varying(64) NOT NULL, -- identifier of the user who created the post (FK to users.user_id)\n content text, -- textual content of the post\n media_url text, -- URL to attached media (image/video)\n media_type character varying(20), -- type of media ('image', 'video', null)\n created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of post creation\n updated_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of last post edit\n visibility character varying(20) NOT NULL DEFAULT 'public', -- visibility ('public', 'friends', 'private')\n location_lat numeric(9,6), -- latitude of post location\n location_lon numeric(9,6), -- longitude of post location\n PRIMARY KEY (post_id)\n)\nCREATE TABLE social_media.comments (\n comment_id character varying(64) NOT NULL, -- unique identifier for the comment\n post_id character varying(64) NOT NULL, -- identifier of the post being commented on (FK to posts.post_id)\n user_id character varying(64) NOT NULL, -- identifier of the user who made the comment (FK to users.user_id)\n parent_comment_id character varying(64), -- identifier of the parent comment if it's a reply (FK to comments.comment_id)\n content text NOT NULL, -- textual content of the comment\n created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of comment creation\n updated_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of last comment edit\n PRIMARY KEY (comment_id)\n)\nCREATE TABLE social_media.likes (\n like_id character varying(64) NOT NULL, -- unique identifier for the like\n user_id character varying(64) NOT NULL, -- identifier of the user who liked (FK to users.user_id)\n post_id character varying(64), -- identifier of the post being liked (FK to posts.post_id, nullable)\n comment_id character varying(64), -- identifier of the comment being liked (FK to comments.comment_id, nullable)\n created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of when the like occurred\n PRIMARY KEY (like_id),\n CONSTRAINT unique_user_like UNIQUE (user_id, post_id, comment_id), -- prevent duplicate likes\n CONSTRAINT check_like_target CHECK (post_id IS NOT NULL OR comment_id IS NOT NULL) -- ensure it likes something\n)\nCREATE TABLE social_media.follows (\n follow_id character varying(64) NOT NULL, -- unique identifier for the follow relationship\n follower_user_id character varying(64) NOT NULL, -- identifier of the user who is following (FK to users.user_id)\n following_user_id character varying(64) NOT NULL, -- identifier of the user being followed (FK to users.user_id)\n created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of when the follow started\n PRIMARY KEY (follow_id),\n CONSTRAINT unique_follow UNIQUE (follower_user_id, following_user_id) -- prevent duplicate follows\n)\nCREATE TABLE social_media.hashtags (\n hashtag_id character varying(64) NOT NULL, -- unique identifier for the hashtag\n tag_name character varying(100) NOT NULL UNIQUE, -- the actual hashtag text (without '#')\n created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp when the hashtag was first used\n PRIMARY KEY (hashtag_id)\n)\nCREATE TABLE social_media.messages (\n message_id character varying(64) NOT NULL, -- unique identifier for the message\n conversation_id character varying(64) NOT NULL, -- identifier for the conversation thread (FK to conversations.conversation_id)\n sender_user_id character varying(64) NOT NULL, -- identifier of the sender (FK to users.user_id)\n content text, -- textual content of the message\n media_url text, -- URL to attached media (image/video)\n media_type character varying(20), -- type of media ('image', 'video', null)\n sent_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp when message was sent\n read_at timestamp, -- timestamp when message was read by recipient(s)\n PRIMARY KEY (message_id)\n)\nCREATE TABLE social_media.conversations (\n conversation_id character varying(64) NOT NULL, -- unique identifier for the conversation\n created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp when conversation was initiated\n last_message_at timestamp, -- timestamp of the last message in the conversation\n is_group_chat boolean NOT NULL DEFAULT false, -- indicates if it's a group chat or direct message\n group_name character varying(100), -- name of the group chat (if applicable)\n PRIMARY KEY (conversation_id)\n)\nCREATE TABLE social_media.conversation_participants (\n participant_id character varying(64) NOT NULL, -- unique identifier for the participant entry\n conversation_id character varying(64) NOT NULL, -- identifier of the conversation (FK to conversations.conversation_id)\n user_id character varying(64) NOT NULL, -- identifier of the user in the conversation (FK to users.user_id)\n joined_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp when user joined the conversation\n last_read_at timestamp, -- timestamp indicating up to when the user has read messages\n PRIMARY KEY (participant_id),\n CONSTRAINT unique_user_conversation UNIQUE (conversation_id, user_id) -- prevent user being added multiple times\n)\nCREATE TABLE social_media.notifications (\n notification_id character varying(64) NOT NULL, -- unique identifier for the notification\n recipient_user_id character varying(64) NOT NULL, -- user receiving the notification (FK to users.user_id)\n sender_user_id character varying(64), -- user triggering the notification (FK to users.user_id, can be null for system notifications)\n notification_type character varying(30) NOT NULL, -- type of notification ('like', 'comment', 'follow', 'mention', 'message')\n target_entity_id character varying(64), -- ID of the related entity (post_id, comment_id, user_id, conversation_id)\n target_entity_type character varying(20), -- type of the related entity ('post', 'comment', 'user', 'conversation')\n created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp notification was created\n read_at timestamp, -- timestamp notification was marked as read\n PRIMARY KEY (notification_id)\n)\nCREATE TABLE social_media.user_settings (\n setting_id character varying(64) NOT NULL, -- unique identifier for the setting entry\n user_id character varying(64) NOT NULL UNIQUE, -- user the settings belong to (FK to users.user_id)\n theme character varying(20) DEFAULT 'light', -- UI theme ('light', 'dark')\n email_notifications_enabled boolean DEFAULT true, -- enable/disable email notifications\n push_notifications_enabled boolean DEFAULT true, -- enable/disable push notifications\n private_profile boolean DEFAULT false, -- is the user profile private\n updated_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of last setting change\n PRIMARY KEY (setting_id)\n)\n"} {"conversations": [{"role": "user", "content": "Show me all ERC20 token transfers where the amount is over 5000, including the sender and receiver addresses."}, {"role": "assistant", "content": "SELECT from_address, to_address, amt, tick, tx_hash FROM token_activities WHERE type = 'transfer' AND CAST(amt AS DECIMAL) > 5000;"}, {"role": "user", "content": "Add the token symbol and decimals for each transfer by joining to the latest token price table."}, {"role": "assistant", "content": "SELECT ta.from_address, ta.to_address, ta.amt, ta.tick, ta.tx_hash, tpl.symbol, tpl.decimals FROM token_activities ta JOIN token_prices_latest tpl ON ta.tick = tpl.symbol WHERE ta.type = 'transfer' AND CAST(ta.amt AS DECIMAL) > 5000;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE erc20_balances ( block_number bigint, contract_address varchar, wallet_address varchar, amount varchar, pk varchar )\nCREATE TABLE erc20_balances_historical ( block_number bigint, contract_address varchar, wallet_address varchar, amount varchar, pk integer )\nCREATE TABLE nft_holder_historical ( block_number bigint, contract_address varchar, wallet_address varchar, token_id varchar, contract_type varchar, amount varchar, pk integer )\nCREATE TABLE sui_coins ( object_id varchar, status varchar, coin_type varchar, balance varchar, owner varchar )\nCREATE TABLE sui_coins_metadata ( object_id varchar, coin_type varchar, status varchar, decimals bigint, description varchar, icon_url varchar, symbol varchar, name varchar )\nCREATE TABLE nft_metadata ( blockchain varchar, contract_address varchar, token_id varchar, contract_name varchar, erc_type varchar, amount bigint, minter varchar, owner varchar, mint_block_number bigint, mint_time bigint, mint_transaction_hash varchar, mint_price varchar, token_uri varchar, metadata varchar, name varchar, image_uri varchar, traits varchar, updated_at bigint, status varchar, rarity_score real, rarity_rank integer, unique_attribute_count integer, pk integer )\nCREATE TABLE nft_collections ( blockchain varchar, contract_address varchar, name varchar, symbol varchar, deploy_block_number bigint, deploy_block_time bigint, erc_type varchar, owner varchar, traits varchar, description varchar, slug varchar, media_info varchar, image_url varchar, banner_image_url varchar, updated_at bigint, banner varchar, token_count bigint, floor_price varchar, floor_price_symbol varchar, floor_price_contract varchar, pk integer )\nCREATE TABLE token_prices_latest ( blockchain varchar, address varchar, decimals bigint, symbol varchar, price real, timestamp timestamp )\nCREATE TABLE erc20_approval ( block_number bigint, block_timestamp timestamp, transaction_index integer, transaction_hash varchar, log_index integer, contract_address varchar, pk integer )\nCREATE TABLE token_activities ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash varchar, log_index integer, type varchar, tick varchar, id varchar, amt decimal, from_address varchar, to_address varchar )\nCREATE TABLE mud_holesky_redstone ( address varchar, table_id varchar, key_bytes varchar, key0 varchar, key1 varchar, static_data varchar, encoded_lengths varchar, dynamic_data varchar, is_deleted boolean, block_number bigint, log_index bigint )\nCREATE TABLE token_info_bitcoin ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash varchar, tick varchar, max_supply decimal, lim decimal, wlim decimal, dec integer, creator varchar )\nCREATE TABLE token_info_avalanche ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash varchar, tick varchar, max_supply decimal, lim decimal, wlim decimal, dec integer, creator varchar, minted decimal, holders decimal, txs decimal, updated_timestamp timestamp, completed_timestamp timestamp, id varchar )\n"} {"conversations": [{"role": "user", "content": "For each claim, show the corresponding product_type of the insurance product for the related policy."}, {"role": "assistant", "content": "SELECT cl.claim_id, ip.product_type\nFROM insurance.claims cl\nJOIN insurance.policies p ON cl.policy_id = p.policy_id\nJOIN insurance.insurance_products ip ON p.product_id = ip.product_id;"}, {"role": "user", "content": "Sorry, there is no policies table, I got an error. Can you try joining claims to insurance_products another way?"}, {"role": "assistant", "content": "-- Unable to join directly since there is no 'policies' table connecting claims to insurance_products. If policy_id equals product_id, you may try:\nSELECT claim_id, policy_id, product_type\nFROM insurance.claims\nJOIN insurance.insurance_products ON claims.policy_id = insurance_products.product_id;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.customers ( customer_id.text, first_name.text, last_name.text, date_of_birth.date, ssn_hash.text, address_line1.text, address_line2.text, city.text, state.text, zip_code.text, country.text, phone_number.text, email.text, created_at.timestamp, updated_at.timestamp, status.text )\nCREATE TABLE insurance.claims ( claim_id.text, policy_id.text, customer_id.text, incident_date.timestamp, reported_date.timestamp, description.text, estimated_loss.numeric, status.text, settlement_amount.numeric, settlement_date.date, claim_handler_id.text, police_report_number.text )\nCREATE TABLE insurance.insurance_products ( product_id.text, product_name.text, product_type.text, description.text, base_premium.numeric, coverage_details.text, underwriting_rules.text, is_active.boolean, created_at.timestamp, updated_at.timestamp )\nCREATE TABLE insurance.claim_documents ( document_id.text, claim_id.text, document_type.text, file_name.text, file_path.text, file_size_bytes.integer, mime_type.text, uploaded_by.text, uploaded_at.timestamp, description.text )\n"} {"conversations": [{"role": "user", "content": "Could you list each game title along with its developer's name and the total number of servers hosting it?"}, {"role": "assistant", "content": "SELECT g.title, d.name AS developer_name, COUNT(s.server_id) AS server_count\nFROM gaming_technology.games g\nLEFT JOIN gaming_technology.developers d ON g.developer_id = d.developer_id\nLEFT JOIN gaming_technology.servers s ON g.game_id = s.game_id\nGROUP BY g.title, d.name;"}, {"role": "user", "content": "Actually, please include only servers with status = 'online' and exclude games with zero online servers."}, {"role": "assistant", "content": "SELECT g.title, d.name AS developer_name, COUNT(s.server_id) AS server_count\nFROM gaming_technology.games g\nJOIN gaming_technology.developers d ON g.developer_id = d.developer_id\nJOIN gaming_technology.servers s ON g.game_id = s.game_id\nWHERE s.status = 'online'\nGROUP BY g.title, d.name;"}, {"role": "user", "content": "I want to see only developers based in 'USA'."}, {"role": "assistant", "content": "SELECT g.title, d.name AS developer_name, COUNT(s.server_id) AS server_count\nFROM gaming_technology.games g\nJOIN gaming_technology.developers d ON g.developer_id = d.developer_id\nJOIN gaming_technology.servers s ON g.game_id = s.game_id AND s.status = 'online'\nWHERE d.country = 'USA'\nGROUP BY g.title, d.name;"}, {"role": "user", "content": "Finally, sort the results by server_count in descending order."}, {"role": "assistant", "content": "SELECT g.title, d.name AS developer_name, COUNT(s.server_id) AS server_count\nFROM gaming_technology.games g\nJOIN gaming_technology.developers d ON g.developer_id = d.developer_id\nJOIN gaming_technology.servers s ON g.game_id = s.game_id AND s.status = 'online'\nWHERE d.country = 'USA'\nGROUP BY g.title, d.name\nORDER BY server_count DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE gaming_technology.games ( game_id uuid, title text, developer_id uuid, publisher_id uuid, genre text, release_date date, description text, platform text, engine text, website text )\nCREATE TABLE gaming_technology.developers ( developer_id uuid, name text, country text, founded_year integer, website text, created_at timestamp with time zone )\nCREATE TABLE gaming_technology.servers ( server_id uuid, game_id uuid, server_name text, region text, ip_address text, port integer, current_players integer, max_players integer, status text, last_heartbeat timestamp with time zone )\nCREATE TABLE gaming_technology.achievements ( achievement_id uuid, game_id uuid, name text, description text, icon_url text, points integer, hidden boolean )\nCREATE TABLE gaming_technology.player_achievements ( player_achievement_id uuid, player_id uuid, achievement_id uuid, unlocked_at timestamp with time zone )\nCREATE TABLE gaming_technology.in_game_items ( item_id uuid, game_id uuid, item_name text, item_type text, description text, rarity text, cost_currency text, cost_amount numeric, attributes jsonb )\nCREATE TABLE gaming_technology.player_inventory ( inventory_id uuid, player_id uuid, item_id uuid, quantity integer, acquired_at timestamp with time zone, instance_data jsonb )\n"} {"conversations": [{"role": "user", "content": "How many documents of each type exist in the system? Show the document type and the count."}, {"role": "assistant", "content": "SELECT document_type, COUNT(*) AS document_count\nFROM legal_services.documents\ngroup BY document_type;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.clients ( client_id text, first_name text, last_name text, company_name text, email text, phone text, address text, date_registered timestamp, status text )\nCREATE TABLE legal_services.law_firms ( firm_id text, firm_name text, address text, phone text, website text, founded_date date, managing_partner_id text )\nCREATE TABLE legal_services.cases ( case_id text, case_number text, case_name text, client_id text, lead_lawyer_id text, case_type text, status text, date_opened timestamp, date_closed timestamp, description text, court_jurisdiction text )\nCREATE TABLE legal_services.documents ( document_id text, case_id text, document_name text, document_type text, storage_path text, uploaded_by_lawyer_id text, upload_timestamp timestamp, version integer, description text )\nCREATE TABLE legal_services.time_entries ( entry_id text, case_id text, lawyer_id text, date_worked date, hours_spent numeric, billing_rate numeric, description text, is_billable boolean, is_billed boolean, invoice_id text, created_at timestamp )\n"} {"conversations": [{"role": "user", "content": "For projects that have completed more than one fundraising round, calculate the average investment value across all their recorded rounds. Display the project name and this average value."}, {"role": "assistant", "content": "SELECT project_name, AVG(investment_value) AS average_investment FROM project_fundraising_record GROUP BY project_name HAVING COUNT(*) > 1;"}, {"role": "user", "content": "Can you modify this to only show projects where the average investment value is greater than 10 million USD and order the results by average investment value descending?"}, {"role": "assistant", "content": "SELECT project_name, AVG(investment_value) AS average_investment FROM project_fundraising_record GROUP BY project_name HAVING COUNT(*) > 1 AND AVG(investment_value) > 10000000 ORDER BY average_investment DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE project_fundraising_record ( id character varying(32) NOT NULL, -- fundraising record id project_id character varying(32) NOT NULL, -- the invested project's id project_name character varying(128) NOT NULL, -- name of the invested project rounds_name character varying(32), -- name of the fundraising round investment_value numeric(38,14), -- amount of the fundraising in USD investment_date character varying(128), -- the date of the investment happened introduction character varying(128), -- the introduction of the invested project valuation numeric(38,14), -- the valuation of the project in USD when invested )\n"} {"conversations": [{"role": "user", "content": "For each vehicle, list its vehicle_id, license_plate, and any older vehicle of the same type (showing older_vehicle_id and older year)."}, {"role": "assistant", "content": "SELECT cur.vehicle_id,\n cur.license_plate,\n old.vehicle_id AS older_vehicle_id,\n old.year AS older_vehicle_year\nFROM transportation.vehicles cur\nJOIN transportation.vehicles old\n ON cur.type = old.type\n AND old.year < cur.year\nORDER BY cur.vehicle_id, old.year DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.vehicles (\n vehicle_id character varying(64) NOT NULL, -- unique identifier for the vehicle\n license_plate character varying(32) NOT NULL UNIQUE, -- vehicle license plate\n vin character varying(17) UNIQUE, -- vehicle identification number\n make character varying(64) NOT NULL, -- manufacturer of the vehicle\n model character varying(64) NOT NULL, -- model of the vehicle\n year integer NOT NULL, -- manufacturing year\n type character varying(32) NOT NULL, -- type of vehicle (e.g., Bus, Train, Truck, Car, Van)\n capacity integer, -- passenger or cargo capacity\n fuel_type character varying(32) NOT NULL, -- e.g., Diesel, Gasoline, Electric, Hydrogen\n status character varying(32) NOT NULL, -- e.g., Active, Maintenance, Decommissioned\n depot_id character varying(64), -- identifier of the home depot/base\n acquisition_date date, -- date the vehicle was acquired\n PRIMARY KEY (vehicle_id)\n)\n"} {"conversations": [{"role": "user", "content": "What is the fuel consumption rate of train number T1234?"}, {"role": "assistant", "content": "I'm sorry, but I don't have information on the fuel consumption rate of train number T1234. The data available in the system only includes details such as train ID, model, manufacturer, year manufactured, capacity, status, and maintenance dates."}], "system": "You are an SQL statement expert and you can refuse the user's question if the question is not related to the table structure. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE train_station_management.trains ( train_id character varying(64) NOT NULL, train_number character varying(32) NOT NULL, model character varying(128), manufacturer character varying(128), year_manufactured integer, capacity integer NOT NULL, status character varying(32) NOT NULL DEFAULT 'Active', last_maintenance_date date, next_maintenance_date date, PRIMARY KEY (train_id), UNIQUE (train_number) )\n"} {"conversations": [{"role": "user", "content": "How many hashtags have been created in March 2024?"}, {"role": "assistant", "content": "```sql\nSELECT COUNT(*) AS march_2024_hashtag_count\nFROM social_media.hashtags\nWHERE created_at >= '2024-03-01'\n AND created_at < '2024-04-01';\n```"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE social_media.users ( user_id text PRIMARY KEY, username text, email text, password_hash text, full_name text, profile_picture_url text, bio text, location text, created_at timestamp, updated_at timestamp, is_verified bool )\nCREATE TABLE social_media.hashtags ( hashtag_id text PRIMARY KEY, tag_name text, created_at timestamp )\nCREATE TABLE social_media.conversation_participants ( participant_id text PRIMARY KEY, conversation_id text, user_id text, joined_at timestamp, last_read_at timestamp )\nCREATE TABLE social_media.notifications ( notification_id text PRIMARY KEY, recipient_user_id text, sender_user_id text, notification_type text, target_entity_id text, target_entity_type text, created_at timestamp, read_at timestamp )\n"} {"conversations": [{"role": "user", "content": "Show each player's username and the number of distinct games they have played sessions on."}, {"role": "assistant", "content": "SELECT\n p.username,\n COUNT(DISTINCT gs.game_id) AS games_played\nFROM gaming_technology.players p\nJOIN gaming_technology.game_sessions gs\n ON p.player_id = gs.player_id\nGROUP BY p.username;"}, {"role": "user", "content": "Now include each player's total number of achievements unlocked."}, {"role": "assistant", "content": "SELECT\n p.username,\n COUNT(DISTINCT gs.game_id) AS games_played,\n COUNT(pa.achievement_id) AS achievements_unlocked\nFROM gaming_technology.players p\nJOIN gaming_technology.game_sessions gs\n ON p.player_id = gs.player_id\nLEFT JOIN gaming_technology.player_achievements pa\n ON p.player_id = pa.player_id\nGROUP BY p.username;"}, {"role": "user", "content": "Exclude players who have played fewer than 3 games or have not unlocked any achievements."}, {"role": "assistant", "content": "SELECT\n p.username,\n COUNT(DISTINCT gs.game_id) AS games_played,\n COUNT(pa.achievement_id) AS achievements_unlocked\nFROM gaming_technology.players p\nJOIN gaming_technology.game_sessions gs\n ON p.player_id = gs.player_id\nLEFT JOIN gaming_technology.player_achievements pa\n ON p.player_id = pa.player_id\nGROUP BY p.username\nHAVING COUNT(DISTINCT gs.game_id) >= 3\n AND COUNT(pa.achievement_id) > 0;"}, {"role": "user", "content": "Also include the first session start_time as first_play and the first achievement unlocked date as first_achievement."}, {"role": "assistant", "content": "SELECT\n p.username,\n COUNT(DISTINCT gs.game_id) AS games_played,\n COUNT(pa.achievement_id) AS achievements_unlocked,\n MIN(gs.start_time) AS first_play,\n MIN(pa.unlocked_at) AS first_achievement\nFROM gaming_technology.players p\nJOIN gaming_technology.game_sessions gs\n ON p.player_id = gs.player_id\nLEFT JOIN gaming_technology.player_achievements pa\n ON p.player_id = pa.player_id\nGROUP BY p.username\nHAVING COUNT(DISTINCT gs.game_id) >= 3\n AND COUNT(pa.achievement_id) > 0;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE gaming_technology.players ( player_id uuid NOT NULL DEFAULT gen_random_uuid(), username character varying(100) NOT NULL UNIQUE, email character varying(255) NOT NULL UNIQUE, password_hash text NOT NULL, registration_date timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP, last_login timestamp with time zone, country_code character(2), status character varying(20) NOT NULL DEFAULT 'active', profile_data jsonb, PRIMARY KEY (player_id) )\nCREATE TABLE gaming_technology.games ( game_id uuid PRIMARY KEY, title text, developer_id uuid, publisher_id uuid, genre text, release_date date, description text, platform text, engine text, website text )\nCREATE TABLE gaming_technology.game_sessions ( session_id uuid NOT NULL DEFAULT gen_random_uuid(), player_id uuid NOT NULL, game_id uuid NOT NULL, server_id uuid, start_time timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP, end_time timestamp with time zone, duration_seconds integer, score integer, session_data jsonb, PRIMARY KEY (session_id) )\nCREATE TABLE gaming_technology.servers ( server_id uuid PRIMARY KEY, game_id uuid, server_name text, region text, ip_address text, port int, current_players int, max_players int, status text, last_heartbeat timestamptz )\nCREATE TABLE gaming_technology.achievements ( achievement_id.uuid, game_id.uuid, name.text, description.text, icon_url.text, points.integer, hidden.boolean )\nCREATE TABLE gaming_technology.player_achievements ( player_achievement_id uuid PRIMARY KEY, player_id uuid, achievement_id uuid, unlocked_at timestamptz )\nCREATE TABLE gaming_technology.player_inventory ( inventory_id uuid PRIMARY KEY, player_id uuid, item_id uuid, quantity int, acquired_at timestamptz, instance_data jsonb )\n"} {"conversations": [{"role": "user", "content": "For the 'DeFi' narrative, what is the average ROI and the total net inflow (usd_value where type=1) from smart money token inflow?"}, {"role": "assistant", "content": "SELECT AVG(sm.roi) AS avg_roi, SUM(smt.usd_value) AS total_net_inflow\nFROM smart_money_token_inflow smt\nJOIN smart_money_profit sm ON smt.chain = sm.chain\nWHERE smt.narrative = 'DeFi' AND smt.type = 1;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE token_basic_info ( coin_id text, token_name text, token_symbol text, token_address text, chain text, price numeric, price_change_percentage_1h numeric, price_change_percentage_24h numeric, price_change_percentage_7d numeric, highest_price_24h numeric, lowest_price_24h numeric, market_cap numeric, market_cap_rank numeric, market_cap_change_percentage_24h text, total_volume text, narrative text, trend_rank numeric )\nCREATE TABLE narrative_info ( narrative text, top_3_coins text, price_change_percentage_1h numeric, price_change_percentage_24h numeric, price_change_percentage_7d numeric, market_cap numeric, volume_24h numeric, trend_rank numeric, token_num numeric )\nCREATE TABLE cex_token_balance ( snapshot_time text, chain text, address text, exchange text, token_address text, token_symbol text, balance numeric, usd_value numeric, price numeric )\nCREATE TABLE smart_money_profit ( address text, rank numeric, profit numeric, roi numeric, realized_ratio numeric, most_profit_token text, last_trade_time text, chain text )\nCREATE TABLE smart_money_token_inflow ( token_address text, token_symbol text, token_amount numeric, usd_value numeric, avg_price numeric, type numeric, address_amount numeric, narrative text, chain text )\n"} {"conversations": [{"role": "user", "content": "List all rooms that have a 'Jacuzzi' feature, including the room_number, property_id, type_name, and base_rate."}, {"role": "assistant", "content": "SELECT r.room_number,\n r.property_id,\n rt.type_name,\n rt.base_rate\nFROM hospitality_technology.rooms AS r\nJOIN hospitality_technology.room_types AS rt\n ON r.room_type_id = rt.room_type_id\n AND r.property_id = rt.property_id\nWHERE r.features ILIKE '%Jacuzzi%';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE hospitality_technology.rooms ( room_id.text, property_id.text, room_number.text, room_type_id.text, floor.integer, status.text, is_smoking.boolean, features.text, current_condition.text, last_cleaned_at.timestamp )\nCREATE TABLE hospitality_technology.room_types ( room_type_id.text, property_id.text, type_name.text, description.text, base_rate.numeric, max_occupancy.integer, bed_type.text, area_sqft.numeric, amenities.text )\nCREATE TABLE hospitality_technology.guests ( guest_id.text, first_name.text, last_name.text, email.text, phone_number.text, date_of_birth.date, address_line1.text, city.text, state_province.text, postal_code.text, country_code.text, preferences.text, loyalty_member_id.text, communication_consent.boolean, created_at.timestamp, updated_at.timestamp )\nCREATE TABLE hospitality_technology.staff ( staff_id.text, property_id.text, first_name.text, last_name.text, position.text, work_email.text, work_phone.text, hire_date.date, termination_date.date, is_active.boolean, access_level.integer, manager_id.text, created_at.timestamp )\nCREATE TABLE hospitality_technology.service_orders ( order_id.text, reservation_id.text, guest_id.text, service_id.text, staff_id_ordered.text, staff_id_delivered.text, order_timestamp.timestamp, delivery_timestamp.timestamp, quantity.integer, unit_price.numeric, total_price.numeric, status.text, notes.text, bill_id.text )\nCREATE TABLE hospitality_technology.payments ( payment_id.text, reservation_id.text, guest_id.text, bill_id.text, amount.numeric, currency_code.text, payment_method.text, card_type.text, card_last_four.text, transaction_ref.text, payment_timestamp.timestamp, status.text, staff_id_processed.text, notes.text )\nCREATE TABLE hospitality_technology.reviews ( review_id.text, property_id.text, reservation_id.text, guest_id.text, rating_overall.integer, rating_cleanliness.integer, rating_service.integer, rating_location.integer, rating_value.integer, comment.text, review_source.text, review_date.timestamp, is_public.boolean, staff_response.text, response_staff_id.text, response_date.timestamp )\n"} {"conversations": [{"role": "user", "content": "For each patient, show the total number of diagnoses they have received, along with their patient ID and the ID of their latest diagnosis. Join with the diagnoses table."}, {"role": "assistant", "content": "SELECT patient_id, COUNT(diagnosis_id) AS diagnosis_count, MAX(diagnosis_id) AS latest_diagnosis_id\nFROM healthcare.diagnoses\nGROUP BY patient_id;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.appointments ( appointment_id text, patient_id text, doctor_id text, appointment_time timestamp, duration_minutes integer, reason text, status text, location_id text, notes text, created_at timestamp )\nCREATE TABLE healthcare.medical_records ( record_id text, patient_id text, appointment_id text, doctor_id text, record_date timestamp, chief_complaint text, present_illness_history text, past_medical_history text, physical_examination_notes text, assessment text, treatment_plan text, vitals text, created_at timestamp )\nCREATE TABLE healthcare.diagnoses ( diagnosis_id text, record_id text, patient_id text, doctor_id text, diagnosis_code text, code_type text, description text, diagnosis_date date, status text, is_chronic boolean )\nCREATE TABLE healthcare.medications ( medication_id text, medication_name text, generic_name text, manufacturer text, ndc_code text, description text )\nCREATE TABLE healthcare.prescriptions ( prescription_id text, record_id text, patient_id text, doctor_id text, medication_id text, dosage text, frequency text, route text, start_date date, end_date date, quantity_dispensed numeric, refills_allowed integer, prescription_date timestamp )\nCREATE TABLE healthcare.insurance_plans ( plan_id text, plan_name text, insurance_provider text, plan_type text, contact_phone text, website text )\nCREATE TABLE healthcare.patient_insurance ( patient_insurance_id text, patient_id text, plan_id text, policy_number text, group_number text, subscriber_name text, effective_date date, expiration_date date, is_primary boolean )\n"} {"conversations": [{"role": "user", "content": "How many games are available in each genre? List genre and game_count."}, {"role": "assistant", "content": "SELECT genre, COUNT(*) AS game_count\nFROM gaming_technology.games\nGROUP BY genre;"}, {"role": "user", "content": "Now only include genres with at least 5 games."}, {"role": "assistant", "content": "SELECT genre, COUNT(*) AS game_count\nFROM gaming_technology.games\nGROUP BY genre\nHAVING COUNT(*) >= 5;"}, {"role": "user", "content": "Also show the earliest release_date for each of these genres."}, {"role": "assistant", "content": "SELECT genre, COUNT(*) AS game_count, MIN(release_date) AS earliest_release\nFROM gaming_technology.games\nGROUP BY genre\nHAVING COUNT(*) >= 5;"}, {"role": "user", "content": "Sort by game_count descending and limit to top 3."}, {"role": "assistant", "content": "SELECT genre, COUNT(*) AS game_count, MIN(release_date) AS earliest_release\nFROM gaming_technology.games\nGROUP BY genre\nHAVING COUNT(*) >= 5\nORDER BY game_count DESC\nLIMIT 3;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE gaming_technology.games ( game_id uuid PRIMARY KEY, title text, developer_id uuid, publisher_id uuid, genre text, release_date date, description text, platform text, engine text, website text )\n"} {"conversations": [{"role": "user", "content": "Show me all reservations with their guest IDs and room IDs where the total amount is greater than $500 and the status is 'Confirmed', ordered by check-in date."}, {"role": "assistant", "content": "SELECT reservation_id, guest_id, room_id, check_in_date, total_amount FROM hospitality_technology.reservations WHERE total_amount > 500 AND status = 'Confirmed' ORDER BY check_in_date;"}, {"role": "user", "content": "Now, join this with the service_orders table to include the total price of all services ordered for each reservation."}, {"role": "assistant", "content": "SELECT r.reservation_id, r.guest_id, r.room_id, r.check_in_date, r.total_amount, SUM(so.total_price) AS total_service_price FROM hospitality_technology.reservations r LEFT JOIN hospitality_technology.service_orders so ON r.reservation_id = so.reservation_id WHERE r.total_amount > 500 AND r.status = 'Confirmed' GROUP BY r.reservation_id, r.guest_id, r.room_id, r.check_in_date, r.total_amount ORDER BY r.check_in_date;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE hospitality_technology.reservations ( reservation_id.text, property_id.text, guest_id.text, room_id.text, room_type_id.text, check_in_date.date, check_out_date.date, actual_check_in_ts.timestamp, actual_check_out_ts.timestamp, num_adults.integer, num_children.integer, status.text, booking_source.text, rate_plan_id.text, total_amount.numeric, amount_paid.numeric, special_requests.text, created_at.timestamp, updated_at.timestamp )\nCREATE TABLE hospitality_technology.service_orders ( order_id character varying(64) NOT NULL, reservation_id character varying(64), guest_id character varying(64) NOT NULL, service_id character varying(64) NOT NULL, staff_id_ordered character varying(64), staff_id_delivered character varying(64), order_timestamp timestamp with time zone NOT NULL DEFAULT current_timestamp, delivery_timestamp timestamp with time zone, quantity integer NOT NULL DEFAULT 1, unit_price numeric(10, 2) NOT NULL, total_price numeric(12, 2) NOT NULL, status character varying(50) NOT NULL, notes text, bill_id character varying(64), PRIMARY KEY (order_id), FOREIGN KEY (reservation_id) REFERENCES hospitality_technology.reservations(reservation_id), FOREIGN KEY (guest_id) REFERENCES hospitality_technology.guests(guest_id), FOREIGN KEY (service_id) REFERENCES hospitality_technology.services(service_id), FOREIGN KEY (staff_id_ordered) REFERENCES hospitality_technology.staff(staff_id), FOREIGN KEY (staff_id_delivered) REFERENCES hospitality_technology.staff(staff_id) )\nCREATE TABLE hospitality_technology.reviews ( review_id character varying(64) NOT NULL, property_id character varying(64) NOT NULL, reservation_id character varying(64) UNIQUE, guest_id character varying(64) NOT NULL, rating_overall integer, rating_cleanliness integer, rating_service integer, rating_location integer, rating_value integer, comment text, review_source character varying(100), review_date timestamp with time zone NOT NULL DEFAULT current_timestamp, is_public boolean DEFAULT true, staff_response text, response_staff_id character varying(64), response_date timestamp with time zone, PRIMARY KEY (review_id), FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id), FOREIGN KEY (reservation_id) REFERENCES hospitality_technology.reservations(reservation_id), FOREIGN KEY (guest_id) REFERENCES hospitality_technology.guests(guest_id), FOREIGN KEY (response_staff_id) REFERENCES hospitality_technology.staff(staff_id) )\n"} {"conversations": [{"role": "user", "content": "特定の職種の従業員情報を取得したいです。従業員ID、名前、職種、雇用日を表示してください。"}, {"role": "assistant", "content": "db.employees.find(\n { job_title: '' },\n { employee_id: 1, first_name: 1, last_name: 1, job_title: 1, hire_date: 1, _id: 0 }\n).sort({ hire_date: -1 })"}, {"role": "user", "content": "雇用日が2020年1月1日以降の従業員だけに絞り込むことはできますか？"}, {"role": "assistant", "content": "db.employees.find(\n { \n job_title: '',\n hire_date: { $gte: ISODate('2020-01-01') }\n },\n { employee_id: 1, first_name: 1, last_name: 1, job_title: 1, hire_date: 1, _id: 0 }\n).sort({ hire_date: -1 })"}, {"role": "user", "content": "雇用ステータスが「Active」の従業員だけをさらに条件に加えられますか？"}, {"role": "assistant", "content": "db.employees.find(\n { \n job_title: '',\n hire_date: { $gte: ISODate('2020-01-01') },\n employment_status: 'Active'\n },\n { employee_id: 1, first_name: 1, last_name: 1, job_title: 1, hire_date: 1, _id: 0 }\n).sort({ hire_date: -1 })"}, {"role": "user", "content": "スキル認定情報も結果に含めてください。"}, {"role": "assistant", "content": "db.employees.find(\n { \n job_title: '',\n hire_date: { $gte: ISODate('2020-01-01') },\n employment_status: 'Active'\n },\n { employee_id: 1, first_name: 1, last_name: 1, job_title: 1, hire_date: 1, skill_certifications: 1, _id: 0 }\n).sort({ hire_date: -1 })"}], "system": "You are an expert in writing database language. You can write a corresponding database language query to answer the user's question based on the table structure described by the table creation statement. \n##Table Structure\nCollection 'assembly_steps'. Document structure: { _id: , step_id: String, line_id: String (reference), step_number: NumberInt, step_name: String, description: String, standard_duration_hours: Decimal128, required_skill_level: String, workstation: String }. Required: step_id, line_id, step_number, step_name. Index on line_id, step_number.\nCollection 'employees'. Document structure: { _id: , employee_id: String, first_name: String, last_name: String, job_title: String, skill_certifications: [String], hire_date: ISODate, assigned_line_id: String (reference, optional), employment_status: String, supervisor_employee_id: String (reference, optional) }. Required: employee_id, first_name, last_name, job_title, hire_date, employment_status.\n"} {"conversations": [{"role": "user", "content": "List the first name, last name, license number, and status for all drivers whose license expires in the next 6 months."}, {"role": "assistant", "content": "SELECT\n first_name,\n last_name,\n license_number,\n status\nFROM transportation.drivers\nWHERE\n license_expiry_date BETWEEN CURRENT_DATE AND CURRENT_DATE + INTERVAL '6 month'\nORDER BY\n license_expiry_date;"}, {"role": "user", "content": "Now, count how many drivers from that list have an 'Active' status."}, {"role": "assistant", "content": "SELECT\n COUNT(*)\nFROM transportation.drivers\nWHERE\n license_expiry_date BETWEEN CURRENT_DATE AND CURRENT_DATE + INTERVAL '6 month' AND status = 'Active';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.drivers ( driver_id text PRIMARY KEY, employee_id text, first_name text, last_name text, license_number text, license_expiry_date date, contact_number text, email text, hire_date date, status text )\n"} {"conversations": [{"role": "user", "content": "How many trips are there for each driver?"}, {"role": "assistant", "content": "SELECT driver_id, COUNT(*) AS trip_count FROM transportation.trips GROUP BY driver_id;"}, {"role": "user", "content": "Can you also show the total number of completed trips for each driver?"}, {"role": "assistant", "content": "SELECT driver_id, COUNT(*) AS completed_trip_count FROM transportation.trips WHERE status = 'Completed' GROUP BY driver_id;"}, {"role": "user", "content": "Now, include both the total trips and completed trips for each driver in the same result."}, {"role": "assistant", "content": "SELECT driver_id, COUNT(*) AS total_trips, SUM(CASE WHEN status = 'Completed' THEN 1 ELSE 0 END) AS completed_trips FROM transportation.trips GROUP BY driver_id;"}, {"role": "user", "content": "Sort the output by the number of completed trips in descending order."}, {"role": "assistant", "content": "SELECT driver_id, COUNT(*) AS total_trips, SUM(CASE WHEN status = 'Completed' THEN 1 ELSE 0 END) AS completed_trips FROM transportation.trips GROUP BY driver_id ORDER BY completed_trips DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.trips (\n trip_id character varying(64) NOT NULL, -- unique identifier for a specific trip instance\n route_id character varying(64), -- identifier of the route being followed (can be null for ad-hoc trips)\n vehicle_id character varying(64) NOT NULL, -- identifier of the vehicle used\n driver_id character varying(64) NOT NULL, -- identifier of the driver operating\n scheduled_departure timestamp with time zone NOT NULL, -- planned departure time\n actual_departure timestamp with time zone, -- actual departure time\n scheduled_arrival timestamp with time zone NOT NULL, -- planned arrival time\n actual_arrival timestamp with time zone, -- actual arrival time\n origin_location_id character varying(64) NOT NULL, -- actual starting location (could differ from route origin)\n destination_location_id character varying(64) NOT NULL, -- actual ending location (could differ from route destination)\n status character varying(32) NOT NULL, -- e.g., Scheduled, In Progress, Completed, Delayed, Cancelled\n passenger_count integer, -- number of passengers (if applicable)\n cargo_manifest_id character varying(64), -- link to cargo details (if applicable)\n PRIMARY KEY (trip_id)\n)\n"} {"conversations": [{"role": "user", "content": "What is the detailed repair history for train number T5678?"}, {"role": "assistant", "content": "I'm sorry, but I can't provide the detailed repair history for train number T5678 as this information is not available in the current database table. The table only includes basic information such as train ID, model, manufacturer, capacity, status, and maintenance dates. For repair history, you may need to consult a different database or department."}], "system": "You are an SQL statement expert and you can refuse the user's question if the question is not related to the table structure. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE train_station_management.trains ( train_id text, train_number text, model text, manufacturer text, year_manufactured integer, capacity integer, status text, last_maintenance_date date, next_maintenance_date date )\n"} {"conversations": [{"role": "user", "content": "Find all pairs of transactions that occurred in the same block and were sent to the same address. Show both transaction IDs, the shared recipient address, and the block number."}, {"role": "assistant", "content": "SELECT t1.transaction_id AS tx1,\n t2.transaction_id AS tx2,\n t1.to_address,\n t1.block_number\nFROM transactions t1\nJOIN transactions t2\n ON t1.to_address = t2.to_address\n AND t1.block_number = t2.block_number\n AND t1.transaction_id < t2.transaction_id;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE web3.transactions ( transaction_id text, from_address text, to_address text, value numeric, gas_used integer, gas_price numeric, block_number integer, timestamp timestamp, input_data text, status text, nonce integer )\n"} {"conversations": [{"role": "user", "content": "What is the total USD value held by all centralized exchanges (CEX) for the token with the symbol 'BTC'?"}, {"role": "assistant", "content": "SELECT SUM(usd_value) AS total_btc_cex_value FROM cex_token_balance WHERE token_symbol = 'BTC';"}, {"role": "user", "content": "Can you break down the total USD value for 'BTC' held by CEXes by chain?"}, {"role": "assistant", "content": "SELECT chain, SUM(usd_value) AS total_btc_cex_value FROM cex_token_balance WHERE token_symbol = 'BTC' GROUP BY chain ORDER BY total_btc_cex_value DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE project_fundraising_record ( id character varying(32) NOT NULL, -- fundraising record id project_id character varying(32) NOT NULL, -- the invested project's id project_name character varying(128) NOT NULL, -- name of the invested project rounds_name character varying(32), -- name of the fundraising round investment_value numeric(38,14), -- amount of the fundraising in USD investment_date character varying(128), -- the date of the investment happened introduction character varying(128), -- the introduction of the invested project valuation numeric(38,14), -- the valuation of the project in USD when invested )\nCREATE TABLE token_basic_info ( coin_id character varying(100) NOT NULL, -- the id of the token token_name character varying(100) NOT NULL, -- the token's name token_symbol character varying(100) NOT NULL, -- the token's symbol token_address character varying(100) NOT NULL, -- the token's address chain text, -- the chain that the token resides price double precision, -- the current price of the token price_change_percentage_1h double precision, -- change in value divided by the absolute price value of the original token price in 1 hour price_change_percentage_24h double precision, -- change in value divided by the absolute price value of the original token price in 24 hours price_change_percentage_7d double precision, -- change in value divided by the absolute price value of the original token price in 7 days highest_price_24h double precision, -- the highest price of the token in 24 hours lowest_price_24h double precision, -- the lowest price of the token in 24 hours market_cap double precision, -- the market cap of the token market_cap_rank bigint, -- the rank of the token market cap in desc market_cap_change_percentage_24h text, -- the percentage of market cap changes in 24 hours total_volume text, -- the trade volum of the token both in decentralized exchange(DEX) and centralized exchange(CEX) narrative text, -- the category or narrative of the token trend_rank biging, -- the trending rank of the token, value 1 expresses the most popular token. ,PRIMARY KEY (coin_id, chain) )\nCREATE TABLE token_dexpool_info ( pair_address.text, token_name.text, token_symbol.text, chain.text, price.numeric, price_change_percentage_1h.numeric, price_change_percentage_6h.numeric, price_change_percentage_24h.numeric, makers_24h.numeric, volume_24h.numeric, liquidity.numeric, market_cap.numeric, trend_rank.numeric )\nCREATE TABLE cex_token_balance ( snapshot_time character varying(32) NOT NULL, -- the snapshot time of record, converted from original timestamp chain character varying(128) NOT NULL, -- the chain that the token resides address character varying(128) NOT NULL, -- the address that holds the assets, owned by a CEX exchange character varying(512) NOT NULL, -- a centralized exchange name token_address character varying(128) NOT NULL, -- token contract address token_symbol character varying(512), --token symbol balance numeric(38,10), -- token balance usd_value numeric(38,14), -- value of the token held in USD price double precision, --price of the token in USD ,PRIMARY KEY (snapshot_time, exchange, address, chain, token_address) )\nCREATE TABLE smart_money_profit ( address text, rank numeric, profit numeric, roi numeric, realized_ratio numeric, most_profit_token text, last_trade_time text, chain text )\nCREATE TABLE smart_money_token_performance ( token_address.text, token_symbol.text, pnl.numeric, net_flow.numeric, avg_cost.numeric, price.numeric, realized_ratio.numeric, roi.numeric, chain.text )\nCREATE TABLE smart_money_token_inflow ( token_address.text, token_symbol.text, token_amount.numeric, usd_value.numeric, avg_price.numeric, type.numeric, address_amount.numeric, narrative.text, chain.text )\n"} {"conversations": [{"role": "user", "content": "List the top 5 largest PDF documents in claim_documents, showing document_id, claim_id, file_name, and file_size_bytes."}, {"role": "assistant", "content": "SELECT document_id,\n claim_id,\n file_name,\n file_size_bytes\nFROM insurance.claim_documents\nWHERE document_type = 'pdf'\nORDER BY file_size_bytes DESC\nLIMIT 5;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.claims ( claim_id.text, policy_id.text, customer_id.text, incident_date.timestamp, reported_date.timestamp, description.text, estimated_loss.numeric, status.text, settlement_amount.numeric, settlement_date.date, claim_handler_id.text, police_report_number.text )\nCREATE TABLE insurance.premium_payments ( payment_id character varying(64) NOT NULL, policy_id character varying(64) NOT NULL, customer_id character varying(64) NOT NULL, payment_date timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, amount_paid numeric(12, 2) NOT NULL, payment_method character varying(50), transaction_reference character varying(128) UNIQUE, due_date date, payment_period_start date, payment_period_end date, status character varying(30) NOT NULL DEFAULT 'Completed', PRIMARY KEY (payment_id) )\nCREATE TABLE insurance.claim_documents ( document_id text PRIMARY KEY, claim_id text, document_type text, file_name text, file_path text, file_size_bytes int, mime_type text, uploaded_by text, uploaded_at timestamp, description text )\n"} {"conversations": [{"role": "user", "content": "Show me all intercity routes with their origin and destination locations, including the city and country for each location."}, {"role": "assistant", "content": "SELECT r.route_id, r.route_number, r.type, orig.name AS origin_name, orig.city AS origin_city, orig.country AS origin_country, dest.name AS destination_name, dest.city AS destination_city, dest.country AS destination_country FROM transportation.routes r JOIN transportation.locations orig ON r.origin_location_id = orig.location_id JOIN transportation.locations dest ON r.destination_location_id = dest.location_id WHERE r.type = 'Intercity Train';"}, {"role": "user", "content": "Now filter these results to only show routes where both origin and destination are in the same country, and include the distance in kilometers."}, {"role": "assistant", "content": "SELECT r.route_id, r.route_number, r.distance_km, orig.city AS origin_city, dest.city AS destination_city, orig.country FROM transportation.routes r JOIN transportation.locations orig ON r.origin_location_id = orig.location_id JOIN transportation.locations dest ON r.destination_location_id = dest.location_id WHERE r.type = 'Intercity Train' AND orig.country = dest.country;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.routes (\n route_id character varying(64) NOT NULL, -- unique identifier for the route\n route_number character varying(32) NOT NULL UNIQUE, -- public-facing route number/name\n description text, -- description of the route\n origin_location_id character varying(64) NOT NULL, -- identifier of the starting location\n destination_location_id character varying(64) NOT NULL, -- identifier of the ending location\n distance_km numeric(10, 2), -- estimated distance in kilometers\n estimated_duration_minutes integer, -- estimated travel time in minutes\n type character varying(32) NOT NULL, -- e.g., City Bus, Intercity Train, Cargo Delivery\n PRIMARY KEY (route_id)\n)\nCREATE TABLE transportation.trips ( trip_id.text, route_id.text, vehicle_id.text, driver_id.text, scheduled_departure.timestamp, actual_departure.timestamp, scheduled_arrival.timestamp, actual_arrival.timestamp, origin_location_id.text, destination_location_id.text, status.text, passenger_count.integer, cargo_manifest_id.text )\nCREATE TABLE transportation.locations ( location_id.text, name.text, type.text, address_line1.text, city.text, state_province.text, postal_code.text, country.text, latitude.numeric, longitude.numeric, timezone.text )\nCREATE TABLE transportation.maintenance_logs ( log_id.text, vehicle_id.text, service_date.date, odometer_reading.integer, service_type.text, description.text, cost.numeric, mechanic_name.text, next_service_due_date.date )\nCREATE TABLE transportation.passengers ( passenger_id character varying(64) NOT NULL, first_name character varying(128) NOT NULL, last_name character varying(128) NOT NULL, email character varying(128) UNIQUE, phone_number character varying(32) UNIQUE, date_of_birth date, loyalty_program_id character varying(64), created_at timestamp with time zone NOT NULL, PRIMARY KEY (passenger_id) )\nCREATE TABLE transportation.bookings ( booking_id text PRIMARY KEY, passenger_id text, trip_id text, seat_number text, booking_time timestamp, status text, fare numeric, payment_transaction_id text, special_requests text )\n"} {"conversations": [{"role": "user", "content": "List the full names and dates of birth for all patients who do not have a phone number on record."}, {"role": "assistant", "content": "SELECT first_name, last_name, date_of_birth FROM healthcare.patients WHERE phone_number IS NULL OR TRIM(phone_number) = '';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.patients ( patient_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, date_of_birth date NOT NULL, gender character varying(10), address text, phone_number character varying(20), email character varying(128) UNIQUE, emergency_contact_name character varying(200), emergency_contact_phone character varying(20), created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, updated_at timestamp with time zone NOT NULL DEFAULT current_timestamp, PRIMARY KEY (patient_id) )\nCREATE TABLE healthcare.appointments ( appointment_id.text, patient_id.text, doctor_id.text, appointment_time.timestamp, duration_minutes.integer, reason.text, status.text, location_id.text, notes.text, created_at.timestamp )\nCREATE TABLE healthcare.diagnoses (\n diagnosis_id character varying(64) NOT NULL, -- unique identifier for the diagnosis entry\n record_id character varying(64) NOT NULL, -- FK linking to the specific medical record entry\n patient_id character varying(64) NOT NULL, -- FK to patients table\n doctor_id character varying(64) NOT NULL, -- FK to doctors table (diagnosing doctor)\n diagnosis_code character varying(20) NOT NULL, -- standard code (e.g., ICD-10)\n code_type character varying(10) NOT NULL DEFAULT 'ICD-10', -- type of code used\n description text, -- textual description of the diagnosis\n diagnosis_date date NOT NULL, -- date the diagnosis was made\n status character varying(32) NOT NULL, -- e.g., Active, Resolved, Ruled Out\n is_chronic boolean DEFAULT false, -- flag for chronic conditions\n PRIMARY KEY (diagnosis_id)\n)\nCREATE TABLE healthcare.prescriptions ( prescription_id text, record_id text, patient_id text, doctor_id text, medication_id text, dosage text, frequency text, route text, start_date date, end_date date, quantity_dispensed numeric, refills_allowed integer, prescription_date timestamp )\nCREATE TABLE healthcare.insurance_plans ( plan_id text, plan_name text, insurance_provider text, plan_type text, contact_phone text, website text )\nCREATE TABLE healthcare.patient_insurance ( patient_insurance_id.text, patient_id.text, plan_id.text, policy_number.text, group_number.text, subscriber_name.text, effective_date.date, expiration_date.date, is_primary.boolean )\n"} {"conversations": [{"role": "user", "content": "What is the average daily trading volume for each security_id in the market_data table from the last 30 days?"}, {"role": "assistant", "content": "SELECT security_id, AVG(volume) as avg_daily_volume FROM financial_services.market_data WHERE data_timestamp >= CURRENT_DATE - INTERVAL '30 days' GROUP BY security_id;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE financial_services.accounts ( account_id text, customer_id text, account_number text, account_type text, balance numeric, currency text, opened_date date, status text, interest_rate numeric, last_updated_at timestamp )\nCREATE TABLE financial_services.securities ( security_id.text, ticker_symbol.text, isin_code.text, cusip_code.text, security_name.text, security_type.text, exchange.text, currency.text, issuer_name.text, sector.text, last_updated.timestamp )\nCREATE TABLE financial_services.trades ( trade_id text, account_id text, security_id text, order_id text, trade_type text, quantity numeric, price_per_unit numeric, total_amount numeric, commission numeric, trade_timestamp timestamp, settlement_date date, status text, execution_venue text )\nCREATE TABLE financial_services.market_data ( data_point_id.bigint, security_id.text, data_timestamp.timestamp, open_price.numeric, high_price.numeric, low_price.numeric, close_price.numeric, adjusted_close_price.numeric, volume.bigint, source.text )\nCREATE TABLE financial_services.employees ( employee_id text, first_name text, last_name text, job_title text, department text, branch_id text, email text, phone_extension text, hire_date date, termination_date date, manager_id text, status text )\n"} {"conversations": [{"role": "user", "content": "List all reviews with their property IDs and overall ratings where the rating is 4 or higher."}, {"role": "assistant", "content": "SELECT review_id, property_id, rating_overall FROM hospitality_technology.reviews WHERE rating_overall >= 4;"}, {"role": "user", "content": "Now, include only reviews that have a staff response."}, {"role": "assistant", "content": "SELECT review_id, property_id, rating_overall FROM hospitality_technology.reviews WHERE rating_overall >= 4 AND staff_response IS NOT NULL;"}, {"role": "user", "content": "The query is missing the review date. Can you include that as well?"}, {"role": "assistant", "content": "SELECT review_id, property_id, rating_overall, review_date FROM hospitality_technology.reviews WHERE rating_overall >= 4 AND staff_response IS NOT NULL;"}, {"role": "user", "content": "Actually, I need to see the reviews ordered by rating in descending order, and only show the top 10."}, {"role": "assistant", "content": "SELECT review_id, property_id, rating_overall, review_date FROM hospitality_technology.reviews WHERE rating_overall >= 4 AND staff_response IS NOT NULL ORDER BY rating_overall DESC LIMIT 10;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE hospitality_technology.reservations ( reservation_id.text, property_id.text, guest_id.text, room_id.text, room_type_id.text, check_in_date.date, check_out_date.date, actual_check_in_ts.timestamp, actual_check_out_ts.timestamp, num_adults.integer, num_children.integer, status.text, booking_source.text, rate_plan_id.text, total_amount.numeric, amount_paid.numeric, special_requests.text, created_at.timestamp, updated_at.timestamp )\nCREATE TABLE hospitality_technology.service_orders ( order_id character varying(64) NOT NULL, reservation_id character varying(64), guest_id character varying(64) NOT NULL, service_id character varying(64) NOT NULL, staff_id_ordered character varying(64), staff_id_delivered character varying(64), order_timestamp timestamp with time zone NOT NULL DEFAULT current_timestamp, delivery_timestamp timestamp with time zone, quantity integer NOT NULL DEFAULT 1, unit_price numeric(10, 2) NOT NULL, total_price numeric(12, 2) NOT NULL, status character varying(50) NOT NULL, notes text, bill_id character varying(64), PRIMARY KEY (order_id), FOREIGN KEY (reservation_id) REFERENCES hospitality_technology.reservations(reservation_id), FOREIGN KEY (guest_id) REFERENCES hospitality_technology.guests(guest_id), FOREIGN KEY (service_id) REFERENCES hospitality_technology.services(service_id), FOREIGN KEY (staff_id_ordered) REFERENCES hospitality_technology.staff(staff_id), FOREIGN KEY (staff_id_delivered) REFERENCES hospitality_technology.staff(staff_id) )\nCREATE TABLE hospitality_technology.reviews ( review_id character varying(64) NOT NULL, property_id character varying(64) NOT NULL, reservation_id character varying(64) UNIQUE, guest_id character varying(64) NOT NULL, rating_overall integer, rating_cleanliness integer, rating_service integer, rating_location integer, rating_value integer, comment text, review_source character varying(100), review_date timestamp with time zone NOT NULL DEFAULT current_timestamp, is_public boolean DEFAULT true, staff_response text, response_staff_id character varying(64), response_date timestamp with time zone, PRIMARY KEY (review_id), FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id), FOREIGN KEY (reservation_id) REFERENCES hospitality_technology.reservations(reservation_id), FOREIGN KEY (guest_id) REFERENCES hospitality_technology.guests(guest_id), FOREIGN KEY (response_staff_id) REFERENCES hospitality_technology.staff(staff_id) )\n"} {"conversations": [{"role": "user", "content": "Show all active customers who live in the same zip_code."}, {"role": "assistant", "content": "SELECT a.customer_id AS cust1,\n b.customer_id AS cust2,\n a.zip_code\nFROM financial_services.customers a\nJOIN financial_services.customers b\n ON a.zip_code = b.zip_code\n AND a.customer_id < b.customer_id\nWHERE a.status = 'Active'\n AND b.status = 'Active';"}, {"role": "user", "content": "Please ensure we don't list duplicate pairs and order by zip_code and cust1."}, {"role": "assistant", "content": "SELECT a.customer_id AS cust1,\n b.customer_id AS cust2,\n a.zip_code\nFROM financial_services.customers a\nJOIN financial_services.customers b\n ON a.zip_code = b.zip_code\n AND a.customer_id < b.customer_id\nWHERE a.status = 'Active'\n AND b.status = 'Active'\nORDER BY a.zip_code, a.customer_id;"}, {"role": "user", "content": "Include the city and state in the result as well."}, {"role": "assistant", "content": "SELECT a.customer_id AS cust1,\n b.customer_id AS cust2,\n a.zip_code,\n a.city,\n a.state\nFROM financial_services.customers a\nJOIN financial_services.customers b\n ON a.zip_code = b.zip_code\n AND a.customer_id < b.customer_id\nWHERE a.status = 'Active'\n AND b.status = 'Active'\nORDER BY a.zip_code, a.customer_id;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE financial_services.customers ( customer_id text PRIMARY KEY, first_name text, last_name text, date_of_birth date, ssn_hash text, address text, city text, state text, zip_code text, country text, email text, phone_number text, created_at timestamp, status text, risk_profile text )\n"} {"conversations": [{"role": "user", "content": "Show the total number of policies in each status."}, {"role": "assistant", "content": "SELECT status, COUNT(*) FROM insurance.policies GROUP BY status"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.customers ( customer_id.text, first_name.text, last_name.text, date_of_birth.date, ssn_hash.text, address_line1.text, address_line2.text, city.text, state.text, zip_code.text, country.text, phone_number.text, email.text, created_at.timestamp, updated_at.timestamp, status.text )\nCREATE TABLE insurance.policies (\n policy_id character varying(64) NOT NULL, -- unique identifier for the policy\n customer_id character varying(64) NOT NULL, -- identifier for the policyholder (FK to customers)\n product_id character varying(64) NOT NULL, -- identifier for the insurance product (FK to insurance_products)\n agent_id character varying(64), -- identifier for the agent who sold the policy (FK to agents)\n policy_number character varying(100) NOT NULL UNIQUE, -- customer-facing policy number\n start_date date NOT NULL, -- date the policy coverage begins\n end_date date NOT NULL, -- date the policy coverage ends\n premium_amount numeric(12, 2) NOT NULL, -- total premium for the policy term\n coverage_limit numeric(15, 2) NOT NULL, -- maximum amount covered\n deductible numeric(10, 2) NOT NULL, -- amount customer pays before coverage kicks in\n status character varying(30) NOT NULL, -- e.g., Active, Expired, Cancelled, Pending\n issued_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- when the policy was issued\n cancellation_date date,\n cancellation_reason text,\n PRIMARY KEY (policy_id)\n)\nCREATE TABLE insurance.insurance_products ( product_id.text, product_name.text, product_type.text, description.text, base_premium.numeric, coverage_details.text, underwriting_rules.text, is_active.boolean, created_at.timestamp, updated_at.timestamp )\nCREATE TABLE insurance.agents ( agent_id.text, first_name.text, last_name.text, agency_name.text, license_number.text, license_state.text, contact_email.text, contact_phone.text, hire_date.date, termination_date.date, status.text, commission_rate.numeric, manager_id.text )\nCREATE TABLE insurance.claim_documents ( document_id.text, claim_id.text, document_type.text, file_name.text, file_path.text, file_size_bytes.integer, mime_type.text, uploaded_by.text, uploaded_at.timestamp, description.text )\n"} {"conversations": [{"role": "user", "content": "How many notifications have been sent for comments in total?"}, {"role": "assistant", "content": "SELECT COUNT(*)\nFROM social_media.notifications\nWHERE target_entity_type = 'comment';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE social_media.users ( user_id.text, username.text, email.text, password_hash.text, full_name.text, profile_picture_url.text, bio.text, location.text, created_at.timestamp, updated_at.timestamp, is_verified.boolean )\nCREATE TABLE social_media.likes ( like_id.text, user_id.text, post_id.text, comment_id.text, created_at.timestamp )\nCREATE TABLE social_media.follows ( follow_id.text, follower_user_id.text, following_user_id.text, created_at.timestamp )\nCREATE TABLE social_media.hashtags ( hashtag_id.text, tag_name.text, created_at.timestamp )\nCREATE TABLE social_media.notifications ( notification_id.text, recipient_user_id.text, sender_user_id.text, notification_type.text, target_entity_id.text, target_entity_type.text, created_at.timestamp, read_at.timestamp )\n"} {"conversations": [{"role": "user", "content": "List the usernames of players who own at least one item from the game with title 'Game Title X'."}, {"role": "assistant", "content": "SELECT DISTINCT T1.username FROM players AS T1 INNER JOIN player_inventory AS T2 ON T1.player_id = T2.player_id INNER JOIN items AS T3 ON T2.item_id = T3.item_id INNER JOIN games AS T4 ON T3.game_id = T4.game_id WHERE T4.title = 'Game Title X';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE gaming_technology.player_inventory ( inventory_id uuid NOT NULL DEFAULT gen_random_uuid(), player_id uuid NOT NULL, item_id uuid NOT NULL, quantity integer NOT NULL DEFAULT 1, acquired_at timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP, instance_data jsonb, PRIMARY KEY (inventory_id) )\n"} {"conversations": [{"role": "user", "content": "Show me all customers who have missing contact information (either phone number or email is null), along with their state and city."}, {"role": "assistant", "content": "SELECT first_name, last_name, state, city FROM insurance.customers WHERE phone_number IS NULL OR email IS NULL;"}, {"role": "user", "content": "Now filter these to only show customers from Florida or New York who were created in the last year."}, {"role": "assistant", "content": "SELECT first_name, last_name, state, city FROM insurance.customers WHERE (phone_number IS NULL OR email IS NULL) AND state IN ('Florida', 'New York') AND created_at >= CURRENT_DATE - INTERVAL '1 year';"}, {"role": "user", "content": "I also want to see when these customers were last updated (updated_at field)."}, {"role": "assistant", "content": "SELECT first_name, last_name, state, city, updated_at FROM insurance.customers WHERE (phone_number IS NULL OR email IS NULL) AND state IN ('Florida', 'New York') AND created_at >= CURRENT_DATE - INTERVAL '1 year';"}, {"role": "user", "content": "Finally, order the results by state first, then by the most recently updated customers first."}, {"role": "assistant", "content": "SELECT first_name, last_name, state, city, updated_at FROM insurance.customers WHERE (phone_number IS NULL OR email IS NULL) AND state IN ('Florida', 'New York') AND created_at >= CURRENT_DATE - INTERVAL '1 year' ORDER BY state, updated_at DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.customers (\n customer_id character varying(64) NOT NULL, -- unique identifier for the customer\n first_name character varying(100) NOT NULL, -- customer's first name\n last_name character varying(100) NOT NULL, -- customer's last name\n date_of_birth date NOT NULL, -- customer's date of birth\n ssn_hash character varying(128), -- Hashed social security number (or national ID)\n address_line1 character varying(255) NOT NULL,\n address_line2 character varying(255),\n city character varying(100) NOT NULL,\n state character varying(50) NOT NULL,\n zip_code character varying(20) NOT NULL,\n country character varying(50) NOT NULL DEFAULT 'USA',\n phone_number character varying(30),\n email character varying(128) UNIQUE, -- unique email address\n created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- when the customer record was created\n updated_at timestamp, -- when the customer record was last updated\n status character varying(20) NOT NULL DEFAULT 'Active', -- e.g., Active, Inactive, Prospect\n PRIMARY KEY (customer_id)\n)\n"} {"conversations": [{"role": "user", "content": "Show me the top 5 narratives by market cap, along with their 24-hour trading volume and 7-day price change percentage."}, {"role": "assistant", "content": "SELECT narrative.text, volume_24h.numeric, price_change_percentage_7d.numeric FROM narrative_info ORDER BY market_cap.numeric DESC LIMIT 5;"}, {"role": "user", "content": "Can you also include the top 3 coins for each of these narratives?"}, {"role": "assistant", "content": "SELECT narrative.text, volume_24h.numeric, price_change_percentage_7d.numeric, top_3_coins.text FROM narrative_info ORDER BY market_cap.numeric DESC LIMIT 5;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE narrative_info ( narrative.text, top_3_coins.text, price_change_percentage_1h.numeric, price_change_percentage_24h.numeric, price_change_percentage_7d.numeric, market_cap.numeric, volume_24h.numeric, trend_rank.numeric, token_num.numeric )\n"} {"conversations": [{"role": "user", "content": "What is the total revenue generated by ticket sales at the station with ID 'ST101' for the past month?"}, {"role": "assistant", "content": "I'm sorry, but I can't provide information on the revenue generated by ticket sales as this data is not available in the current database table. The table only contains details about station information such as name, location, and platform count. If you have another question or need assistance with something else related to the station data, I'm happy to help."}], "system": "You are an SQL statement expert and you can refuse the user's question if the question is not related to the table structure. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE train_station_management.stations ( station_id.text, station_name.text, city.text, state_province.text, country_code.text, address.text, timezone.text, number_of_platforms.integer, created_at.timestamp, last_updated_at.timestamp )\n"} {"conversations": [{"role": "user", "content": "For each property, show the most expensive room type by base_rate, including the property name, room type name, and the highest base_rate."}, {"role": "assistant", "content": "SELECT p.property_name,\n rt.type_name,\n MAX(rt.base_rate) AS max_base_rate\nFROM hospitality_technology.room_types rt\nJOIN hospitality_technology.properties p\n ON rt.property_id = p.property_id\nGROUP BY p.property_name;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE hospitality_technology.properties ( property_id text PRIMARY KEY, property_name text, address_line1 text, address_line2 text, city text, state_province text, postal_code text, country_code text, phone_number text, email_address text, property_type text, star_rating numeric, timezone text, manager_staff_id text, created_at timestamp, updated_at timestamp )\nCREATE TABLE hospitality_technology.rooms (\n room_id character varying(64) NOT NULL, -- unique identifier for the room\n property_id character varying(64) NOT NULL, -- FK to properties table\n room_number character varying(10) NOT NULL, -- room number identifier (e.g., '101', 'Suite 2B')\n room_type_id character varying(64) NOT NULL, -- FK to room_types table\n floor integer, -- floor number the room is on\n status character varying(50) NOT NULL, -- e.g., Available, Occupied, Cleaning, OutOfOrder, Maintenance\n is_smoking boolean NOT NULL DEFAULT false, -- smoking allowed flag\n features text, -- description of features (e.g., Balcony, Sea View, Jacuzzi)\n current_condition text, -- notes on room condition\n last_cleaned_at timestamp with time zone, -- timestamp of last cleaning\n PRIMARY KEY (room_id),\n FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id),\n FOREIGN KEY (room_type_id) REFERENCES hospitality_technology.room_types(room_type_id)\n)\nCREATE TABLE hospitality_technology.room_types ( room_type_id text, property_id text, type_name text, description text, base_rate numeric, max_occupancy integer, bed_type text, area_sqft numeric, amenities text )\nCREATE TABLE hospitality_technology.guests ( guest_id text PRIMARY KEY, first_name text, last_name text, email text, phone_number text, date_of_birth date, address_line1 text, city text, state_province text, postal_code text, country_code text, preferences text, loyalty_member_id text, communication_consent boolean, created_at timestamp, updated_at timestamp )\nCREATE TABLE hospitality_technology.staff ( staff_id text, property_id text, first_name text, last_name text, position text, work_email text, work_phone text, hire_date date, termination_date date, is_active boolean, access_level integer, manager_id text, created_at timestamp )\nCREATE TABLE hospitality_technology.services (\n service_id character varying(64) NOT NULL, -- unique identifier for a chargeable service\n property_id character varying(64) NOT NULL, -- FK to properties table\n service_name character varying(150) NOT NULL, -- e.g., Room Service - Burger, Spa - Massage 60min, Laundry - Shirt\n description text,\n category character varying(100), -- e.g., Food & Beverage, Wellness, Business Center, Activities\n price numeric(10, 2) NOT NULL, -- price per unit/instance\n unit character varying(30), -- e.g., Per Item, Per Hour, Per Day\n is_available boolean NOT NULL DEFAULT true, -- is the service currently offered?\n department character varying(100), -- department responsible (e.g., F&B, Spa, Housekeeping)\n PRIMARY KEY (service_id),\n FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id)\n)\nCREATE TABLE hospitality_technology.service_orders ( order_id.text, reservation_id.text, guest_id.text, service_id.text, staff_id_ordered.text, staff_id_delivered.text, order_timestamp.timestamp, delivery_timestamp.timestamp, quantity.integer, unit_price.numeric, total_price.numeric, status.text, notes.text, bill_id.text )\nCREATE TABLE hospitality_technology.payments (\n payment_id character varying(64) NOT NULL, -- unique identifier for the payment transaction\n reservation_id character varying(64), -- FK to reservations (if payment is for a stay)\n guest_id character varying(64) NOT NULL, -- FK to guests (who paid)\n bill_id character varying(64), -- FK to bills/invoices this payment applies to\n amount numeric(12,2) NOT NULL, -- amount of the payment\n currency_code character varying(3) NOT NULL, -- ISO currency code (e.g., USD, EUR)\n payment_method character varying(50) NOT NULL, -- e.g., CreditCard, Cash, BankTransfer, Points, Voucher\n card_type character varying(50), -- e.g., Visa, MasterCard, Amex (if CC)\n card_last_four character varying(4), -- last 4 digits of CC (if CC)\n transaction_ref character varying(128), -- reference ID from payment gateway or processor\n payment_timestamp timestamp with time zone NOT NULL DEFAULT current_timestamp, -- when the payment occurred\n status character varying(50) NOT NULL, -- e.g., Pending, Succeeded, Failed, Refunded, Disputed\n staff_id_processed character varying(64), -- FK to staff (who processed the payment)\n notes text, -- notes about the payment\n PRIMARY KEY (payment_id),\n FOREIGN KEY (reservation_id) REFERENCES hospitality_technology.reservations(reservation_id),\n FOREIGN KEY (guest_id) REFERENCES hospitality_technology.guests(guest_id),\n FOREIGN KEY (staff_id_processed) REFERENCES hospitality_technology.staff(staff_id)\n)\nCREATE TABLE hospitality_technology.reviews ( review_id character varying(64) NOT NULL, property_id character varying(64) NOT NULL, reservation_id character varying(64) UNIQUE, guest_id character varying(64) NOT NULL, rating_overall integer, rating_cleanliness integer, rating_service integer, rating_location integer, rating_value integer, comment text, review_source character varying(100), review_date timestamp with time zone NOT NULL DEFAULT current_timestamp, is_public boolean DEFAULT true, staff_response text, response_staff_id character varying(64), response_date timestamp with time zone, PRIMARY KEY (review_id), FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id), FOREIGN KEY (reservation_id) REFERENCES hospitality_technology.reservations(reservation_id), FOREIGN KEY (guest_id) REFERENCES hospitality_technology.guests(guest_id), FOREIGN KEY (response_staff_id) REFERENCES hospitality_technology.staff(staff_id) )\n"} {"conversations": [{"role": "user", "content": "Find all pairs of distinct routes that share the same origin location ID. List the route IDs and route numbers for both routes in each pair, along with the shared origin location ID."}, {"role": "assistant", "content": "SELECT r1.route_id AS route1_id, r1.route_number AS route1_number, r2.route_id AS route2_id, r2.route_number AS route2_number, r1.origin_location_id FROM transportation.routes AS r1 JOIN transportation.routes AS r2 ON r1.origin_location_id = r2.origin_location_id WHERE r1.route_id < r2.route_id;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.routes ( route_id.text, route_number.text, description.text, origin_location_id.text, destination_location_id.text, distance_km.numeric, estimated_duration_minutes.integer, type.text )\n"}