diff --git "a/data.jsonl" "b/data.jsonl" new file mode 100644--- /dev/null +++ "b/data.jsonl" @@ -0,0 +1,250 @@ +{"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": "List all securities (security_id, ticker_symbol, security_name) that have a currency of 'EUR' and were last updated within the last 30 days, along with their exchange and sector information."}, {"role": "assistant", "content": "SELECT security_id, ticker_symbol, security_name, exchange, sector FROM financial_services.securities WHERE currency = 'EUR' AND last_updated >= 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 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)\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": "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 all medical records with the record_id, record_date, the patient's insurance policy_number, and the doctor's ID, for records linked to a currently active insurance policy."}, {"role": "assistant", "content": "SELECT mr.record_id, mr.record_date, pi.policy_number, mr.doctor_id\nFROM healthcare.medical_records mr\nINNER JOIN healthcare.patient_insurance pi ON mr.patient_id = pi.patient_id\nWHERE 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.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.json, created_at.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": "Provide a count of citizens registered per calendar year."}, {"role": "assistant", "content": "SELECT CAST(EXTRACT(YEAR FROM registration_date) AS INTEGER) AS registration_year, COUNT(*) AS citizen_count FROM government_services.citizens GROUP BY 1 ORDER BY 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 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": "List all ERC20 tokens where the price is greater than $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.address WHERE tpl.price > 10 AND tm.is_erc20 = 1;"}, {"role": "user", "content": "I think there's an error in your query - it should be 'tpl.price > 10' not 'tpl.price > 10'. Also, can you add the current price to the results?"}, {"role": "assistant", "content": "SELECT tm.name, tm.symbol, tm.contract_address, tpl.price FROM token_metas tm JOIN token_prices_latest tpl ON tm.contract_address = tpl.address WHERE tpl.price > 10 AND tm.is_erc20 = 1;"}, {"role": "user", "content": "Now sort these results by price in descending order and limit to the top 10."}, {"role": "assistant", "content": "SELECT tm.name, tm.symbol, tm.contract_address, tpl.price FROM token_metas tm JOIN token_prices_latest tpl ON tm.contract_address = tpl.address WHERE tpl.price > 10 AND tm.is_erc20 = 1 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 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, block_timestamp timestamp, transaction_index integer, transaction_hash varchar, log_index integer, contract_address varchar )\nCREATE TABLE erc20_balances ( block_number bigint, contract_address varchar, wallet_address varchar, amount varchar, pk varchar )\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 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_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 ( uuid varchar, blockchain varchar, address varchar, decimals bigint, symbol varchar, price real, timestamp timestamp )\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_balances ( block_number bigint, block_timestamp timestamp, tick varchar, wallet_address varchar, total_supply decimal, amount decimal )\nCREATE TABLE token_info ( 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 ( 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_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_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_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 ( block_number bigint, block_timestamp timestamp, tick varchar, wallet_address varchar, total_supply decimal, amount decimal )\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 full name and bar number of all lawyers who were hired before 2015."}, {"role": "assistant", "content": "SELECT first_name || ' ' || last_name AS lawyer_full_name, bar_number\nFROM legal_services.lawyers\nWHERE hire_date < '2015-01-01';"}], "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.clients ( client_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, company_name character varying(200), email character varying(128) UNIQUE NOT NULL, phone character varying(32), address text, date_registered timestamp NOT NULL, status character varying(32) NOT NULL, PRIMARY KEY (client_id) )\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.cases ( case_id character varying(64) NOT NULL, case_number character varying(100) UNIQUE, case_name text NOT NULL, client_id character varying(64) NOT NULL, lead_lawyer_id character varying(64) NOT NULL, case_type character varying(100) NOT NULL, status character varying(50) NOT NULL, date_opened timestamp NOT NULL, date_closed timestamp, description text, court_jurisdiction character varying(128), PRIMARY KEY (case_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": "What is the average ROI and average realized_ratio for each chain?"}, {"role": "assistant", "content": "SELECT chain,\n AVG(roi) AS avg_roi,\n AVG(realized_ratio) AS avg_realized_ratio\nFROM smart_money_token_performance\nGROUP BY chain;"}, {"role": "user", "content": "Now filter to only include chains where average ROI is above 0.5."}, {"role": "assistant", "content": "WITH stats AS (\n SELECT chain,\n AVG(roi) AS avg_roi,\n AVG(realized_ratio) AS avg_realized_ratio\n FROM smart_money_token_performance\n GROUP BY chain\n)\nSELECT chain, avg_roi, avg_realized_ratio\nFROM stats\nWHERE avg_roi > 0.5;"}], "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 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": "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": "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": "List properties and the average base rate of their room types."}, {"role": "assistant", "content": "SELECT T1.property_name , AVG(T2.base_rate) FROM hospitality_technology.properties AS T1 JOIN hospitality_technology.room_types AS T2 ON T1.property_id = T2.property_id GROUP BY T1.property_name"}, {"role": "user", "content": "Filter to only show properties where the average base rate is above 250."}, {"role": "assistant", "content": "SELECT T1.property_name , AVG(T2.base_rate) FROM hospitality_technology.properties AS T1 JOIN hospitality_technology.room_types AS T2 ON T1.property_id = T2.property_id GROUP BY T1.property_name HAVING AVG(T2.base_rate) > 250"}, {"role": "user", "content": "Also, only include properties in 'New York' or 'Florida' and order by average base rate descending."}, {"role": "assistant", "content": "SELECT T1.property_name , AVG(T2.base_rate) AS avg_base_rate FROM hospitality_technology.properties AS T1 JOIN hospitality_technology.room_types AS T2 ON T1.property_id = T2.property_id WHERE T1.state IN ('New York', 'Florida') GROUP BY T1.property_name HAVING AVG(T2.base_rate) > 250 ORDER BY avg_base_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 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)\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": "What is the average speed of train number T9876 during its last journey?"}, {"role": "assistant", "content": "I'm sorry, but I can't provide information on the average speed of train number T9876 during its last journey. The data in the trains table does not include details about travel speed or journey-specific performance metrics."}], "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": "Show me all distinct dosage forms used in prescriptions."}, {"role": "assistant", "content": "SELECT DISTINCT dosage FROM healthcare.prescriptions;"}], "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.prescriptions ( prescription_id text PRIMARY KEY, 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 int, prescription_date timestamp )\n"} +{"conversations": [{"role": "user", "content": "I need to find all tickets for a specific route 'RT456' along with the car details and route information."}, {"role": "assistant", "content": "SELECT t.ticket_id, t.seat_number, t.price, tc.car_number, tc.car_type, r.route_name, r.description\nFROM train_station_management.tickets t\nJOIN train_station_management.train_cars tc ON t.car_id = tc.car_id\nJOIN train_station_management.trains tr ON tc.train_id = tr.train_id\nJOIN train_station_management.routes r ON tr.route_id = r.route_id\nWHERE r.route_id = 'RT456';"}, {"role": "user", "content": "Can you filter this to show only tickets that have been checked in?"}, {"role": "assistant", "content": "SELECT t.ticket_id, t.seat_number, t.price, tc.car_number, tc.car_type, r.route_name, r.description\nFROM train_station_management.tickets t\nJOIN train_station_management.train_cars tc ON t.car_id = tc.car_id\nJOIN train_station_management.trains tr ON tc.train_id = tr.train_id\nJOIN train_station_management.routes r ON tr.route_id = r.route_id\nWHERE r.route_id = 'RT456' AND t.is_checked_in = true;"}, {"role": "user", "content": "Can you also add the ticket type to the results?"}, {"role": "assistant", "content": "SELECT t.ticket_id, t.seat_number, t.price, t.ticket_type, tc.car_number, tc.car_type, r.route_name, r.description\nFROM train_station_management.tickets t\nJOIN train_station_management.train_cars tc ON t.car_id = tc.car_id\nJOIN train_station_management.trains tr ON tc.train_id = tr.train_id\nJOIN train_station_management.routes r ON tr.route_id = r.route_id\nWHERE r.route_id = 'RT456' AND t.is_checked_in = true;"}], "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 train_station_management.train_cars (\n car_id character varying(64) NOT NULL, -- Unique identifier for the train car\n train_id character varying(64) NOT NULL, -- Foreign key referencing trains\n car_number character varying(10) NOT NULL, -- Identifier of the car within the train set\n car_type character varying(64) NOT NULL, -- e.g., Locomotive, Passenger, Sleeper, Dining, Baggage\n class character varying(32), -- e.g., First, Business, Economy (null for non-passenger cars)\n capacity integer, -- Passenger capacity of this specific car (null for non-passenger cars)\n features text, -- Comma-separated list of features (e.g., 'WiFi', 'Power Outlet', 'Accessible Restroom')\n PRIMARY KEY (car_id),\n FOREIGN KEY (train_id) REFERENCES train_station_management.trains(train_id)\n)\nCREATE TABLE train_station_management.routes (\n route_id character varying(64) NOT NULL, -- Unique identifier for the route\n route_name character varying(128) NOT NULL, -- Name of the route (e.g., 'Northeast Corridor')\n description text, -- Description of the route\n origin_station_id character varying(64) NOT NULL, -- Starting station\n destination_station_id character varying(64) NOT NULL, -- Final station\n is_active boolean NOT NULL DEFAULT true, -- Is the route currently operational?\n PRIMARY KEY (route_id),\n FOREIGN KEY (origin_station_id) REFERENCES train_station_management.stations(station_id),\n FOREIGN KEY (destination_station_id) REFERENCES train_station_management.stations(station_id)\n)\nCREATE TABLE train_station_management.tickets (\n ticket_id character varying(64) NOT NULL, -- Unique identifier for the ticket\n booking_id character varying(64) NOT NULL, -- Foreign key referencing the booking\n car_id character varying(64) NOT NULL, -- Foreign key referencing the train car\n seat_number character varying(10), -- Assigned seat number (e.g., '12A')\n ticket_type character varying(32) NOT NULL DEFAULT 'Adult', -- e.g., Adult, Child, Senior, Student\n price numeric(10, 2) NOT NULL, -- Price of this specific ticket\n is_checked_in boolean NOT NULL DEFAULT false, -- Has the passenger checked in with this ticket?\n qr_code_data text, -- Data for generating a QR code for the ticket\n PRIMARY KEY (ticket_id),\n FOREIGN KEY (booking_id) REFERENCES train_station_management.bookings(booking_id),\n FOREIGN KEY (car_id) REFERENCES train_station_management.train_cars(car_id)\n)\n"} +{"conversations": [{"role": "user", "content": "For each player, calculate the total quantity of items they have acquired. Return player_id and total_quantity."}, {"role": "assistant", "content": "SELECT player_id,\n SUM(quantity) AS total_quantity\nFROM gaming_technology.player_inventory\nGROUP BY player_id;"}, {"role": "user", "content": "Exclude players whose total_quantity is less than 50."}, {"role": "assistant", "content": "SELECT player_id,\n SUM(quantity) AS total_quantity\nFROM gaming_technology.player_inventory\nGROUP BY player_id\nHAVING SUM(quantity) >= 50;"}, {"role": "user", "content": "Also include the number of distinct items each player has acquired as distinct_item_count."}, {"role": "assistant", "content": "SELECT player_id,\n SUM(quantity) AS total_quantity,\n COUNT(DISTINCT item_id) AS distinct_item_count\nFROM gaming_technology.player_inventory\nGROUP BY player_id\nHAVING SUM(quantity) >= 50;"}, {"role": "user", "content": "Finally, order the results by total_quantity in descending order."}, {"role": "assistant", "content": "SELECT player_id,\n SUM(quantity) AS total_quantity,\n COUNT(DISTINCT item_id) AS distinct_item_count\nFROM gaming_technology.player_inventory\nGROUP BY player_id\nHAVING SUM(quantity) >= 50\nORDER BY total_quantity 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.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": "What is the average commission_rate for each agent status and only show statuses with an average commission_rate above 0.05?"}, {"role": "assistant", "content": "SELECT status,\n AVG(commission_rate) AS avg_commission_rate\nFROM insurance.agents\nGROUP BY status\nHAVING AVG(commission_rate) > 0.05;"}], "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, 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": "Show me the top 5 users who have interacted with DApps, along with the count of distinct DApps they interacted with and their wallet addresses."}, {"role": "assistant", "content": "SELECT w.user_id, COUNT(DISTINCT d.dapp_id) AS dapp_count, w.address FROM trading_platform.wallets w JOIN trading_platform.dapps d ON 1=1 GROUP BY w.user_id, w.address ORDER BY dapp_count DESC LIMIT 5;"}, {"role": "user", "content": "This query doesn't properly show DApp interactions. Please modify it to correctly join with a table that records user-DApp interactions."}, {"role": "assistant", "content": "I notice there's no interaction table in the provided schema. Without a table recording user-DApp interactions, I cannot generate this query accurately. Would you like to see users who have wallets and DApps separately instead?"}, {"role": "user", "content": "You're right. Instead, show me users who have wallets but have never interacted with any DApps, along with their wallet addresses."}, {"role": "assistant", "content": "SELECT w.user_id, w.address FROM trading_platform.wallets w WHERE NOT EXISTS (SELECT 1 FROM trading_platform.dapps d WHERE 1=1) GROUP BY w.user_id, w.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 trading_platform.wallets ( wallet_id.text, user_id.text, address.text, private_key.text, created_at.timestamp )\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.text, name.text, symbol.text, type.text )\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.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 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": "For all chains, which token held by centralized exchanges (CEX) has the highest ROI according to smart money token performance? Show token symbol, chain, exchange, total USD value held on CEX, and the smart money ROI."}, {"role": "assistant", "content": "SELECT c.token_symbol, c.chain, c.exchange, SUM(c.usd_value) AS total_usd_value, s.roi\nFROM cex_token_balance c\nJOIN smart_money_token_performance s ON c.token_symbol = s.token_symbol AND c.chain = s.chain\nGROUP BY c.token_symbol, c.chain, c.exchange, s.roi\nORDER BY s.roi DESC\nLIMIT 1;"}, {"role": "user", "content": "Instead of just the top one, show the top 3 tokens by ROI, and only include cases where the total USD value held on CEX is greater than $2,000,000."}, {"role": "assistant", "content": "SELECT c.token_symbol, c.chain, c.exchange, SUM(c.usd_value) AS total_usd_value, s.roi\nFROM cex_token_balance c\nJOIN smart_money_token_performance s ON c.token_symbol = s.token_symbol AND c.chain = s.chain\nGROUP BY c.token_symbol, c.chain, c.exchange, s.roi\nHAVING SUM(c.usd_value) > 2000000\nORDER BY s.roi DESC\nLIMIT 3;"}, {"role": "user", "content": "Add the last recorded price for each token, and sort by total_usd_value in descending order."}, {"role": "assistant", "content": "SELECT c.token_symbol, c.chain, c.exchange, SUM(c.usd_value) AS total_usd_value, s.roi, MAX(c.price) AS last_price\nFROM cex_token_balance c\nJOIN smart_money_token_performance s ON c.token_symbol = s.token_symbol AND c.chain = s.chain\nGROUP BY c.token_symbol, c.chain, c.exchange, s.roi\nHAVING SUM(c.usd_value) > 2000000\nORDER BY total_usd_value DESC\nLIMIT 3;"}, {"role": "user", "content": "I got duplicate tokens across exchanges. Can you show only the top exchange (with the greatest USD value) per token and chain combination?"}, {"role": "assistant", "content": "WITH cex_totals AS (\n SELECT c.token_symbol, c.chain, c.exchange, SUM(c.usd_value) AS total_usd_value, s.roi, MAX(c.price) AS last_price,\n ROW_NUMBER() OVER (PARTITION BY c.token_symbol, c.chain ORDER BY SUM(c.usd_value) DESC) as rn\n FROM cex_token_balance c\n JOIN smart_money_token_performance s ON c.token_symbol = s.token_symbol AND c.chain = s.chain\n GROUP BY c.token_symbol, c.chain, c.exchange, s.roi\n HAVING SUM(c.usd_value) > 2000000\n)\nSELECT token_symbol, chain, exchange, total_usd_value, roi, last_price\nFROM cex_totals\nWHERE rn = 1\nORDER BY total_usd_value 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 project_fundraising_record ( id character varying(32) NOT NULL, project_id character varying(32) NOT NULL, project_name character varying(128) NOT NULL, rounds_name character varying(32), investment_value numeric(38,14), investment_date character varying(128), introduction character varying(128), valuation numeric(38,14) )\nCREATE TABLE narrative_info ( narrative character varying(512) NOT NULL, top_3_coins text, price_change_percentage_1h double precision, price_change_percentage_24h double precision, price_change_percentage_7d double precision, market_cap double precision, volume_24h double precision, trend_rank bigint, token_num bigint )\nCREATE TABLE cex_token_balance ( snapshot_time character varying(32) NOT NULL, chain character varying(128) NOT NULL, address character varying(128) NOT NULL, exchange character varying(512) NOT NULL, token_address character varying(128) NOT NULL, token_symbol character varying(512), balance numeric(38,10), usd_value numeric(38,14), price double precision )\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) )\nCREATE TABLE smart_money_token_performance ( token_address character varying(100) NOT NULL, token_symbol character varying(100), pnl numeric(38,2), net_flow numeric(38,2), avg_cost numeric(38,16), price double precision, realized_ratio numeric(10,2), roi numeric(10,2), chain character varying(100) )\nCREATE TABLE smart_money_token_inflow ( token_address character varying(100) NOT NULL, token_symbol character varying(100), token_amount numeric(38,2), usd_value numeric(38,2), avg_price numeric(38,6), type int, address_amount integer, narrative character varying(100), chain character varying(100) )\n"} +{"conversations": [{"role": "user", "content": "Show me all asset types along with the count of distinct assets and the count of log actions for each type."}, {"role": "assistant", "content": "SELECT a.type, COUNT(DISTINCT a.asset_id) AS asset_count, COUNT(l.log_id) AS action_count FROM trading_platform.assets a LEFT JOIN trading_platform.logs l ON a.asset_id = l.details->>'asset_id' GROUP BY a.type ORDER BY action_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 trading_platform.assets ( asset_id text, name text, symbol text, type text )\nCREATE TABLE trading_platform.logs ( log_id text, user_id text, action text, details text, logged_at timestamp )\n"} +{"conversations": [{"role": "user", "content": "Which chain has the highest total USD inflow from buy transactions (type=1), and how many distinct tokens were involved in that inflow?"}, {"role": "assistant", "content": "SELECT chain, SUM(usd_value) AS total_inflow, COUNT(DISTINCT token_symbol) AS distinct_tokens\nFROM smart_money_token_inflow\nWHERE type = 1\nGROUP BY chain\nORDER BY total_inflow DESC\nLIMIT 1;"}, {"role": "user", "content": "I also want to see the average price at which those tokens were bought for that chain."}, {"role": "assistant", "content": "WITH inflow AS (\n SELECT chain, SUM(usd_value) AS total_inflow\n FROM smart_money_token_inflow\n WHERE type = 1\n GROUP BY chain\n), top_chain AS (\n SELECT chain FROM inflow ORDER BY total_inflow DESC LIMIT 1\n)\nSELECT i.chain, AVG(i.avg_price) AS avg_buy_price\nFROM smart_money_token_inflow i\nJOIN top_chain t ON i.chain = t.chain\nWHERE i.type = 1;"}, {"role": "user", "content": "Actually, filter to narratives where the total USD inflow is above 50000."}, {"role": "assistant", "content": "SELECT narrative, SUM(usd_value) AS total_inflow, COUNT(DISTINCT token_symbol) AS distinct_tokens\nFROM smart_money_token_inflow\nWHERE type = 1\nGROUP BY narrative\nHAVING SUM(usd_value) > 50000;"}, {"role": "user", "content": "Please order the results by average price descending and show the top 2 chains."}, {"role": "assistant", "content": "SELECT chain, SUM(usd_value) AS total_inflow, COUNT(DISTINCT token_symbol) AS distinct_tokens, AVG(avg_price) AS avg_buy_price\nFROM smart_money_token_inflow\nWHERE type = 1\nGROUP BY chain\nORDER BY avg_buy_price DESC\nLIMIT 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 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": "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": "Retrieve the policy_number, start_date, end_date, premium_amount, and corresponding product_name for policies with a coverage_limit greater than 500000."}, {"role": "assistant", "content": "SELECT p.policy_number, p.start_date, p.end_date, p.premium_amount, ip.product_name\nFROM insurance.policies p\nJOIN insurance.insurance_products ip ON p.product_id = ip.product_id\nWHERE p.coverage_limit > 500000;"}], "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.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 )\n"} +{"conversations": [{"role": "user", "content": "List all room types that have at least one service in the 'Spa' category, including the room type name, property name, and service name."}, {"role": "assistant", "content": "SELECT DISTINCT rt.type_name, p.property_name, s.service_name\nFROM hospitality_technology.room_types AS rt\nJOIN hospitality_technology.properties AS p ON rt.property_id = p.property_id\nJOIN hospitality_technology.services AS s ON rt.property_id = s.property_id\nWHERE s.category = 'Spa';"}, {"role": "user", "content": "Actually, only show room types with a base_rate above 200."}, {"role": "assistant", "content": "SELECT DISTINCT rt.type_name, p.property_name, s.service_name\nFROM hospitality_technology.room_types AS rt\nJOIN hospitality_technology.properties AS p ON rt.property_id = p.property_id\nJOIN hospitality_technology.services AS s ON rt.property_id = s.property_id\nWHERE s.category = 'Spa'\n AND rt.base_rate > 200;"}, {"role": "user", "content": "Also sort the results by base_rate descending and limit to 10."}, {"role": "assistant", "content": "SELECT DISTINCT rt.type_name, p.property_name, s.service_name\nFROM hospitality_technology.room_types AS rt\nJOIN hospitality_technology.properties AS p ON rt.property_id = p.property_id\nJOIN hospitality_technology.services AS s ON rt.property_id = s.property_id\nWHERE s.category = 'Spa'\n AND rt.base_rate > 200\nORDER BY rt.base_rate DESC\nLIMIT 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.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 ( 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 PRIMARY KEY, property_id text, type_name text, description text, base_rate numeric, max_occupancy int, bed_type text, area_sqft numeric, amenities text )\nCREATE TABLE hospitality_technology.reservations ( reservation_id text PRIMARY KEY, 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 int, num_children int, 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.services ( service_id.text, property_id.text, service_name.text, description.text, category.text, price.numeric, unit.text, is_available.boolean, department.text )\n"} +{"conversations": [{"role": "user", "content": "For each Avalanche token tick, calculate the total transfer volume and transaction count over the past 7 days using token_activities_avalanche. Include the token tick, total_volume, and tx_count."}, {"role": "assistant", "content": "SELECT\n tick,\n SUM(amt) AS total_volume,\n COUNT(*) AS tx_count\nFROM token_activities_avalanche\nWHERE block_timestamp >= CURRENT_DATE - INTERVAL '7 days'\nGROUP BY tick;"}, {"role": "user", "content": "Also include the creator address from token_info for each tick, and filter where total_volume > 1000 and creator starts with '0x1'."}, {"role": "assistant", "content": "SELECT\n a.tick,\n SUM(a.amt) AS total_volume,\n COUNT(*) AS tx_count,\n i.creator\nFROM token_activities_avalanche a\nJOIN token_info i\n ON a.tick = i.tick\nWHERE a.block_timestamp >= CURRENT_DATE - INTERVAL '7 days'\nGROUP BY a.tick, i.creator\nHAVING SUM(a.amt) > 1000\n AND i.creator LIKE '0x1%';"}, {"role": "user", "content": "Sort the results by total_volume descending and limit to the top 5 tokens."}, {"role": "assistant", "content": "SELECT\n a.tick,\n SUM(a.amt) AS total_volume,\n COUNT(*) AS tx_count,\n i.creator\nFROM token_activities_avalanche a\nJOIN token_info i\n ON a.tick = i.tick\nWHERE a.block_timestamp >= CURRENT_DATE - INTERVAL '7 days'\nGROUP BY a.tick, i.creator\nHAVING SUM(a.amt) > 1000\n AND i.creator LIKE '0x1%'\nORDER BY total_volume 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.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 (\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_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 (\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, -- The quantity held in the wallet\n pk integer NOT NULL -- Partition key for the table(floor(block_number / 7200))\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 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.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 (\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_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 )\n"} +{"conversations": [{"role": "user", "content": "List all reservations where the number of adults is greater than 2, showing reservation_id, guest_id, and the total_amount."}, {"role": "assistant", "content": "SELECT reservation_id, guest_id, total_amount\nFROM hospitality_technology.reservations\nWHERE num_adults > 2;"}, {"role": "user", "content": "Can you also include the room_type_id and the status for each reservation?"}, {"role": "assistant", "content": "SELECT reservation_id, guest_id, room_type_id, status, total_amount\nFROM hospitality_technology.reservations\nWHERE num_adults > 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 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.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": "For each customer, provide a summary of their account statuses, showing their full name, account status, and the count of accounts for each status."}, {"role": "assistant", "content": "SELECT c.first_name, c.last_name, a.status, COUNT(a.account_id) AS account_count FROM financial_services.accounts a JOIN financial_services.customers c ON a.customer_id = c.customer_id GROUP BY c.customer_id, c.first_name, c.last_name, a.status ORDER BY c.last_name, c.first_name, a.status;"}, {"role": "user", "content": "Refine this to only include customers who have accounts in at least two different statuses."}, {"role": "assistant", "content": "SELECT c.first_name, c.last_name, a.status, COUNT(a.account_id) AS account_count FROM financial_services.accounts a JOIN financial_services.customers c ON a.customer_id = c.customer_id GROUP BY c.customer_id, c.first_name, c.last_name, a.status HAVING c.customer_id IN ( SELECT customer_id FROM financial_services.accounts GROUP BY customer_id HAVING COUNT(DISTINCT status) >= 2 ) ORDER BY c.last_name, c.first_name, a.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 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)\n"} +{"conversations": [{"role": "user", "content": "Show the number of employees in each department."}, {"role": "assistant", "content": "SELECT department, COUNT(*) AS employee_count\nFROM financial_services.employees\ngroup BY department;"}, {"role": "user", "content": "Exclude departments that have less than 3 employees."}, {"role": "assistant", "content": "SELECT department, COUNT(*) AS employee_count\nFROM financial_services.employees\ngroup BY department\nHAVING COUNT(*) >= 3;"}, {"role": "user", "content": "Can you also show the average hire_date for employees in each department?"}, {"role": "assistant", "content": "SELECT department, COUNT(*) AS employee_count, AVG(hire_date) AS average_hire_date\nFROM financial_services.employees\ngroup BY department\nHAVING COUNT(*) >= 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 financial_services.accounts ( account_id text PRIMARY KEY, 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 ( transaction_id text PRIMARY KEY, 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.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 bigserial PRIMARY KEY, 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 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": "I want to see pairs of items from the same game that share the same rarity but are of different types. Show each pair's names and types."}, {"role": "assistant", "content": "SELECT a.game_id,\n a.item_name AS item1_name,\n a.item_type AS item1_type,\n b.item_name AS item2_name,\n b.item_type AS item2_type\nFROM gaming_technology.in_game_items a\nJOIN gaming_technology.in_game_items b\n ON a.game_id = b.game_id\n AND a.rarity = b.rarity\n AND a.item_type <> b.item_type\n AND a.item_id < b.item_id;"}, {"role": "user", "content": "Also include cost_currency and cost_amount for each item in the output."}, {"role": "assistant", "content": "SELECT a.game_id,\n a.item_name AS item1_name,\n a.item_type AS item1_type,\n a.cost_currency AS item1_currency,\n a.cost_amount AS item1_cost,\n b.item_name AS item2_name,\n b.item_type AS item2_type,\n b.cost_currency AS item2_currency,\n b.cost_amount AS item2_cost\nFROM gaming_technology.in_game_items a\nJOIN gaming_technology.in_game_items b\n ON a.game_id = b.game_id\n AND a.rarity = b.rarity\n AND a.item_type <> b.item_type\n AND a.item_id < b.item_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.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 )\n"} +{"conversations": [{"role": "user", "content": "Count the total number of cases that are currently marked as 'Open'."}, {"role": "assistant", "content": "SELECT COUNT(*) FROM cases WHERE status = 'Open'"}], "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.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 (\n appointment_id character varying(64) NOT NULL, -- unique identifier for the appointment\n client_id character varying(64) NOT NULL, -- FK to clients table\n lawyer_id character varying(64) NOT NULL, -- FK to lawyers table\n case_id character varying(64), -- FK to cases table (optional, if related to a specific case)\n start_time timestamp NOT NULL, -- scheduled start date and time\n end_time timestamp NOT NULL, -- scheduled end date and time\n location text, -- location of the meeting (address or virtual link)\n subject character varying(255), -- subject or purpose of the appointment\n notes text, -- additional notes for the appointment\n status character varying(50) NOT NULL, -- e.g., Scheduled, Completed, Canceled, Rescheduled\n created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP,\n PRIMARY KEY (appointment_id)\n)\n"} +{"conversations": [{"role": "user", "content": "List all medical records, showing the record ID, record date, and the full name of the doctor who created the record. Include the patient ID as well."}, {"role": "assistant", "content": "SELECT mr.record_id, mr.record_date, mr.patient_id, d.first_name, d.last_name FROM healthcare.medical_records mr JOIN doctors d ON mr.doctor_id = d.doctor_id;"}, {"role": "user", "content": "Refine this to only include records where the chief_complaint is not null or empty and the doctor's specialty is 'Cardiology'."}, {"role": "assistant", "content": "SELECT mr.record_id, mr.record_date, mr.patient_id, d.first_name, d.last_name FROM healthcare.medical_records mr JOIN doctors d ON mr.doctor_id = d.doctor_id WHERE (mr.chief_complaint IS NOT NULL AND mr.chief_complaint != '') AND d.specialty = 'Cardiology';"}, {"role": "user", "content": "Also, sort the results by record_date in descending order and limit the output to the top 10 records."}, {"role": "assistant", "content": "SELECT mr.record_id, mr.record_date, mr.patient_id, d.first_name, d.last_name FROM healthcare.medical_records mr JOIN doctors d ON mr.doctor_id = d.doctor_id WHERE (mr.chief_complaint IS NOT NULL AND mr.chief_complaint != '') AND d.specialty = 'Cardiology' ORDER BY mr.record_date 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 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)\n"} +{"conversations": [{"role": "user", "content": "List the ERC20 tokens (from token_metas) with exactly 6 decimals. Show their symbol, contract_address, and name."}, {"role": "assistant", "content": "SELECT symbol, contract_address, name FROM token_metas WHERE is_erc20 = 1 AND decimals = 6;"}, {"role": "user", "content": "Can you also include the total current supply for each token?"}, {"role": "assistant", "content": "SELECT symbol, contract_address, name, total_supply FROM token_metas WHERE is_erc20 = 1 AND decimals = 6;"}, {"role": "user", "content": "Now, join with token_prices_latest to also include the latest price for each token."}, {"role": "assistant", "content": "SELECT tm.symbol, tm.contract_address, tm.name, tm.total_supply, tpl.price AS latest_price\nFROM token_metas tm\nJOIN token_prices_latest tpl ON tm.contract_address = tpl.address AND tpl.blockchain = 'Ethereum'\nWHERE tm.is_erc20 = 1 AND tm.decimals = 6;"}, {"role": "user", "content": "Only include tokens where the latest price is between 0.5 and 2.0 USD, and limit the result to the top 5 tokens by price descending."}, {"role": "assistant", "content": "SELECT tm.symbol, tm.contract_address, tm.name, tm.total_supply, tpl.price AS latest_price\nFROM token_metas tm\nJOIN token_prices_latest tpl ON tm.contract_address = tpl.address AND tpl.blockchain = 'Ethereum'\nWHERE tm.is_erc20 = 1 AND tm.decimals = 6 AND tpl.price BETWEEN 0.5 AND 2.0\nORDER BY tpl.price 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.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 (\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 nft_holder_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(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, -- The quantity held in the wallet\n pk integer NOT NULL -- Partition key for the table(floor(block_number / 7200))\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 (\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 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.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": "For each chain, which centralized exchange holds the largest total USD value in their token balance as of the most recent snapshot?"}, {"role": "assistant", "content": "WITH latest_snapshot AS (\n SELECT MAX(snapshot_time) AS max_time FROM cex_token_balance\n)\nSELECT c.chain, c.exchange, SUM(c.usd_value) AS total_usd_value\nFROM cex_token_balance c\nJOIN latest_snapshot l ON c.snapshot_time = l.max_time\nGROUP BY c.chain, c.exchange\nQUALIFY ROW_NUMBER() OVER(PARTITION BY c.chain ORDER BY SUM(c.usd_value) DESC) = 1;"}, {"role": "user", "content": "Could you also include the number of distinct tokens each exchange holds in those chains?"}, {"role": "assistant", "content": "WITH latest_snapshot AS (\n SELECT MAX(snapshot_time) AS max_time FROM cex_token_balance\n),\nexchange_totals AS (\n SELECT c.chain, c.exchange, SUM(c.usd_value) AS total_usd_value, COUNT(DISTINCT c.token_symbol) AS token_count\n FROM cex_token_balance c\n JOIN latest_snapshot l ON c.snapshot_time = l.max_time\n GROUP BY c.chain, c.exchange\n),\nranked_exchanges AS (\n SELECT *, ROW_NUMBER() OVER(PARTITION BY chain ORDER BY total_usd_value DESC) AS rn\n FROM exchange_totals\n)\nSELECT chain, exchange, total_usd_value, token_count\nFROM ranked_exchanges\nWHERE rn = 1;"}, {"role": "user", "content": "I got an error with the QUALIFY clause. Can you rewrite the query using a derived table or CTE instead?"}, {"role": "assistant", "content": "WITH latest_snapshot AS (\n SELECT MAX(snapshot_time) AS max_time FROM cex_token_balance\n),\nexchange_totals AS (\n SELECT c.chain, c.exchange, SUM(c.usd_value) AS total_usd_value, COUNT(DISTINCT c.token_symbol) AS token_count\n FROM cex_token_balance c\n JOIN latest_snapshot l ON c.snapshot_time = l.max_time\n GROUP BY c.chain, c.exchange\n),\nmax_values AS (\n SELECT chain, MAX(total_usd_value) AS max_usd_value\n FROM exchange_totals\n GROUP BY chain\n)\nSELECT e.chain, e.exchange, e.total_usd_value, e.token_count\nFROM exchange_totals e\nJOIN max_values m ON e.chain = m.chain AND e.total_usd_value = m.max_usd_value;"}, {"role": "user", "content": "Now, only show exchanges where their usd_value is above $5,000,000."}, {"role": "assistant", "content": "WITH latest_snapshot AS (\n SELECT MAX(snapshot_time) AS max_time FROM cex_token_balance\n),\nexchange_totals AS (\n SELECT c.chain, c.exchange, SUM(c.usd_value) AS total_usd_value, COUNT(DISTINCT c.token_symbol) AS token_count\n FROM cex_token_balance c\n JOIN latest_snapshot l ON c.snapshot_time = l.max_time\n GROUP BY c.chain, c.exchange\n),\nmax_values AS (\n SELECT chain, MAX(total_usd_value) AS max_usd_value\n FROM exchange_totals\n GROUP BY chain\n)\nSELECT e.chain, e.exchange, e.total_usd_value, e.token_count\nFROM exchange_totals e\nJOIN max_values m ON e.chain = m.chain AND e.total_usd_value = m.max_usd_value\nWHERE e.total_usd_value > 5000000;"}], "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 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 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 )\n"} +{"conversations": [{"role": "user", "content": "How many diagnoses does each status have grouped by is_chronic flag?"}, {"role": "assistant", "content": "SELECT is_chronic, status, COUNT(*) AS count FROM healthcare.diagnoses GROUP BY is_chronic, 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 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 )\n"} +{"conversations": [{"role": "user", "content": "For each developer, can you find the next developer in the same country using a self join, returning developer_ids and names?"}, {"role": "assistant", "content": "SELECT d1.developer_id AS current_dev,\n d1.name AS current_name,\n d2.developer_id AS next_dev,\n d2.name AS next_name,\n d2.founded_year - d1.founded_year AS years_diff\nFROM developers d1\nJOIN developers d2\n ON d1.country = d2.country\n AND d2.founded_year > d1.founded_year;"}, {"role": "user", "content": "Exclude developers who don't have a next developer, and ensure we only pick the closest next by founded_year."}, {"role": "assistant", "content": "SELECT d1.developer_id AS current_dev,\n d1.name AS current_name,\n d2.developer_id AS next_dev,\n d2.name AS next_name,\n d2.founded_year - d1.founded_year AS years_diff\nFROM developers d1\nJOIN LATERAL (\n SELECT d2.developer_id, d2.name, d2.founded_year\n FROM developers d2\n WHERE d2.country = d1.country\n AND d2.founded_year > d1.founded_year\n ORDER BY d2.founded_year ASC\n LIMIT 1\n) d2 ON true;"}, {"role": "user", "content": "Finally, only include pairs where the difference in founded years is at most 5 years."}, {"role": "assistant", "content": "SELECT d1.developer_id AS current_dev,\n d1.name AS current_name,\n d2.developer_id AS next_dev,\n d2.name AS next_name,\n d2.founded_year - d1.founded_year AS years_diff\nFROM developers d1\nJOIN LATERAL (\n SELECT d2.developer_id, d2.name, d2.founded_year\n FROM developers d2\n WHERE d2.country = d1.country\n AND d2.founded_year > d1.founded_year\n ORDER BY d2.founded_year ASC\n LIMIT 1\n) d2 ON true\nWHERE (d2.founded_year - d1.founded_year) <= 5\nORDER BY d1.developer_id, years_diff 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 gaming_technology.developers ( developer_id uuid PRIMARY KEY, name text, country text, founded_year int, website text, created_at timestamptz )\n"} +{"conversations": [{"role": "user", "content": "List all events and any token transfers that occurred in the same transaction, showing event_id, event_name, transfer_id, and token_symbol."}, {"role": "assistant", "content": "SELECT\n e.event_id,\n e.event_name,\n tt.transfer_id,\n tk.token_symbol\nFROM web3.events e\nLEFT JOIN web3.token_transfers tt\n ON e.transaction_id = tt.transaction_id\nLEFT JOIN web3.tokens tk\n ON tt.token_id = tk.token_id\nORDER BY e.transaction_id, e.log_index;"}], "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.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.users ( user_id text, username text, email text, password_hash text, created_at timestamp )\n"} +{"conversations": [{"role": "user", "content": "Show me a list of all properties along with their average overall review rating."}, {"role": "assistant", "content": "SELECT p.property_id, p.property_name, AVG(r.rating_overall) AS avg_rating\nFROM hospitality_technology.properties p\nJOIN hospitality_technology.reviews r ON p.property_id = r.property_id\nGROUP BY p.property_id, 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.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": "I need to list the top 5 ERC20 tokens by total supply, including symbol, contract_address, and name."}, {"role": "assistant", "content": "SELECT tm.contract_address, tm.symbol, tm.name, CAST(tm.total_supply AS DECIMAL) AS total_supply\nFROM token_metas tm\nWHERE tm.is_erc20 = 1\nORDER BY CAST(tm.total_supply AS DECIMAL) DESC\nLIMIT 5;"}, {"role": "user", "content": "Also include the latest USD price for each token from token_prices using the most recent timestamp per token."}, {"role": "assistant", "content": "SELECT tm.contract_address, tm.symbol, tm.name, CAST(tm.total_supply AS DECIMAL) AS total_supply, tp.price\nFROM token_metas tm\nJOIN (\n SELECT address, price FROM token_prices tp1\n WHERE tp1.timestamp = (\n SELECT MAX(tp2.timestamp) FROM token_prices tp2 WHERE tp2.address = tp1.address\n )\n) tp ON tp.address = tm.contract_address\nWHERE tm.is_erc20 = 1\nORDER BY CAST(tm.total_supply AS DECIMAL) DESC\nLIMIT 5;"}, {"role": "user", "content": "Filter results to only include tokens where the price is greater than 2."}, {"role": "assistant", "content": "SELECT tm.contract_address, tm.symbol, tm.name, CAST(tm.total_supply AS DECIMAL) AS total_supply, tp.price\nFROM token_metas tm\nJOIN (\n SELECT address, price FROM token_prices tp1\n WHERE tp1.timestamp = (\n SELECT MAX(tp2.timestamp) FROM token_prices tp2 WHERE tp2.address = tp1.address\n )\n) tp ON tp.address = tm.contract_address\nWHERE tm.is_erc20 = 1\n AND tp.price > 2\nORDER BY CAST(tm.total_supply AS DECIMAL) DESC\nLIMIT 5;"}, {"role": "user", "content": "Order the results by price descending and limit to 5."}, {"role": "assistant", "content": "SELECT tm.contract_address, tm.symbol, tm.name, CAST(tm.total_supply AS DECIMAL) AS total_supply, tp.price\nFROM token_metas tm\nJOIN (\n SELECT address, price FROM token_prices tp1\n WHERE tp1.timestamp = (\n SELECT MAX(tp2.timestamp) FROM token_prices tp2 WHERE tp2.address = tp1.address\n )\n) tp ON tp.address = tm.contract_address\nWHERE tm.is_erc20 = 1\n AND tp.price > 2\nORDER BY tp.price 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.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 (\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 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 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 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_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 all NFT collections where the floor price is greater than 0.5 ETH, including their names and contract addresses."}, {"role": "assistant", "content": "SELECT name, contract_address FROM nft_collections WHERE CAST(floor_price AS decimal) > 0.5 AND floor_price_symbol = 'ETH';"}, {"role": "user", "content": "Can you also include the banner image URL and filter to only show ERC721 collections?"}, {"role": "assistant", "content": "SELECT name, contract_address, banner_image_url FROM nft_collections WHERE CAST(floor_price AS decimal) > 0.5 AND floor_price_symbol = 'ETH' AND erc_type = 'ERC721';"}, {"role": "user", "content": "Now sort these results by floor price in descending order and limit to the top 10."}, {"role": "assistant", "content": "SELECT name, contract_address, banner_image_url, floor_price FROM nft_collections WHERE CAST(floor_price AS decimal) > 0.5 AND floor_price_symbol = 'ETH' AND erc_type = 'ERC721' ORDER BY CAST(floor_price 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 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 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_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 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 ( 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 (\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 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_balances_bitcoin ( block_number bigint, block_timestamp timestamp, tick varchar, wallet_address varchar, total_supply varchar, amount varchar )\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 )\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 contract, can you list the token symbols and total supply of all tokens created by that contract, along with the contract's current status?"}, {"role": "assistant", "content": "SELECT c.contract_id, c.address AS contract_address, c.status, t.token_symbol, t.total_supply\nFROM web3.contracts c\nJOIN web3.tokens t ON c.address = t.contract_address\nORDER BY c.contract_id, t.token_symbol;"}], "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, address text, abi text, bytecode text, deployer_address text, deployed_at timestamp, network_id text, status text )\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 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 )\nCREATE TABLE web3.tokens ( token_id text, contract_address text, token_name text, token_symbol text, decimals integer, total_supply numeric )\nCREATE TABLE web3.token_transfers ( transfer_id text, token_id text, from_address text, to_address text, value numeric, transaction_id text, log_index integer )\nCREATE TABLE web3.users ( user_id text, username text, email text, password_hash text, created_at timestamp )\n"} +{"conversations": [{"role": "user", "content": "I want to identify pairs of bookings that share the same payment_transaction_id, showing both booking IDs and the payment_transaction_id."}, {"role": "assistant", "content": "SELECT b1.booking_id AS booking1, b2.booking_id AS booking2, b1.payment_transaction_id\nFROM transportation.bookings b1\nJOIN transportation.bookings b2\n ON b1.payment_transaction_id = b2.payment_transaction_id\n AND b1.booking_id < b2.booking_id;"}, {"role": "user", "content": "Now limit the results to only include pairs where both bookings have a status of 'Completed'."}, {"role": "assistant", "content": "SELECT b1.booking_id AS booking1, b2.booking_id AS booking2, b1.payment_transaction_id\nFROM transportation.bookings b1\nJOIN transportation.bookings b2\n ON b1.payment_transaction_id = b2.payment_transaction_id\n AND b1.booking_id < b2.booking_id\nWHERE b1.status = 'Completed'\n AND b2.status = 'Completed';"}], "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.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": "For each user with 'approved' KYC status, show their user ID and the total amount in their unspent UTXOs."}, {"role": "assistant", "content": "SELECT T1.user_id, SUM(T2.amount) FROM trading_platform.kyc_audit AS T1 JOIN trading_platform.utxos AS T2 ON T1.user_id = T2.user_id WHERE T1.status = 'approved' AND T2.spent = false GROUP BY T1.user_id;"}, {"role": "user", "content": "Only include users where the total unspent amount is greater than 100."}, {"role": "assistant", "content": "SELECT T1.user_id, SUM(T2.amount) FROM trading_platform.kyc_audit AS T1 JOIN trading_platform.utxos AS T2 ON T1.user_id = T2.user_id WHERE T1.status = 'approved' AND T2.spent = false GROUP BY T1.user_id HAVING SUM(T2.amount) > 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.utxos ( utxo_id text, transaction_id text, output_index integer, address text, amount numeric, spent boolean )\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.kyc_audit ( kyc_audit_id text, user_id text, status text, reviewed_at timestamp )\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 appointments along with the patient's full name and the doctor's full name."}, {"role": "assistant", "content": "SELECT\n a.appointment_id,\n a.appointment_time,\n p.first_name AS patient_first_name,\n p.last_name AS patient_last_name,\n d.first_name AS doctor_first_name,\n d.last_name AS doctor_last_name\nFROM healthcare.appointments AS a\nJOIN healthcare.patients AS p\n ON a.patient_id = p.patient_id\nJOIN healthcare.doctors AS d\n ON a.doctor_id = d.doctor_id;"}, {"role": "user", "content": "Only show appointments for patients born between 1980 and 2000."}, {"role": "assistant", "content": "SELECT\n a.appointment_id,\n a.appointment_time,\n p.first_name AS patient_first_name,\n p.last_name AS patient_last_name,\n d.first_name AS doctor_first_name,\n d.last_name AS doctor_last_name\nFROM healthcare.appointments AS a\nJOIN healthcare.patients AS p\n ON a.patient_id = p.patient_id\nJOIN healthcare.doctors AS d\n ON a.doctor_id = d.doctor_id\nWHERE\n p.date_of_birth BETWEEN '1980-01-01' AND '2000-12-31';"}, {"role": "user", "content": "Further filter results to only include appointments with status 'Scheduled' or 'Completed'."}, {"role": "assistant", "content": "SELECT\n a.appointment_id,\n a.appointment_time,\n p.first_name AS patient_first_name,\n p.last_name AS patient_last_name,\n d.first_name AS doctor_first_name,\n d.last_name AS doctor_last_name\nFROM healthcare.appointments AS a\nJOIN healthcare.patients AS p\n ON a.patient_id = p.patient_id\nJOIN healthcare.doctors AS d\n ON a.doctor_id = d.doctor_id\nWHERE\n p.date_of_birth BETWEEN '1980-01-01' AND '2000-12-31' AND a.status IN ('Scheduled', 'Completed');"}, {"role": "user", "content": "Order by patient last name ascending, then by appointment time descending, and limit to the first 50 results."}, {"role": "assistant", "content": "SELECT\n a.appointment_id,\n a.appointment_time,\n p.first_name AS patient_first_name,\n p.last_name AS patient_last_name,\n d.first_name AS doctor_first_name,\n d.last_name AS doctor_last_name\nFROM healthcare.appointments AS a\nJOIN healthcare.patients AS p\n ON a.patient_id = p.patient_id\nJOIN healthcare.doctors AS d\n ON a.doctor_id = d.doctor_id\nWHERE\n p.date_of_birth BETWEEN '1980-01-01' AND '2000-12-31' AND a.status IN ('Scheduled', 'Completed')\nORDER BY\n p.last_name ASC,\n a.appointment_time DESC\nLIMIT 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 (\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.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 PRIMARY KEY, medication_name text, generic_name text, manufacturer text, ndc_code text, description text )\nCREATE TABLE healthcare.prescriptions ( prescription_id character varying(64) NOT NULL, record_id character varying(64) NOT NULL, patient_id character varying(64) NOT NULL, doctor_id character varying(64) NOT NULL, medication_id character varying(64) NOT NULL, dosage character varying(100) NOT NULL, frequency character varying(100) NOT NULL, route character varying(50), start_date date NOT NULL, end_date date, quantity_dispensed numeric(10,2), refills_allowed integer NOT NULL DEFAULT 0, prescription_date timestamp with time zone NOT NULL DEFAULT current_timestamp, PRIMARY KEY (prescription_id) )\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)\n"} +{"conversations": [{"role": "user", "content": "List all depot locations in the United States with their city and state information."}, {"role": "assistant", "content": "SELECT name, city, state_province FROM transportation.locations WHERE type = 'depot' AND country = 'United States';"}, {"role": "user", "content": "Can you include the full address and order by state_province first, then by city?"}, {"role": "assistant", "content": "SELECT name, address_line1, city, state_province, postal_code FROM transportation.locations WHERE type = 'depot' AND country = 'United States' ORDER BY state_province, city;"}, {"role": "user", "content": "Now filter to only show depots in Texas or California and include their timezone."}, {"role": "assistant", "content": "SELECT name, address_line1, city, state_province, postal_code, timezone FROM transportation.locations WHERE type = 'depot' AND country = 'United States' AND state_province IN ('Texas', 'California') ORDER BY state_province, city;"}, {"role": "user", "content": "Actually, I need to see the latitude and longitude as well and limit to 5 results per state."}, {"role": "assistant", "content": "SELECT name, city, state_province, latitude, longitude FROM transportation.locations WHERE type = 'depot' AND country = 'United States' AND state_province IN ('Texas', 'California') ORDER BY state_province, city 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 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 )\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": "How many medications does each manufacturer have?"}, {"role": "assistant", "content": "SELECT manufacturer, COUNT(*) AS med_count\nFROM healthcare.medications\nGROUP BY manufacturer;"}, {"role": "user", "content": "Only include manufacturers with more than 10 medications."}, {"role": "assistant", "content": "SELECT manufacturer, COUNT(*) AS med_count\nFROM healthcare.medications\nGROUP BY manufacturer\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 healthcare.medications ( medication_id character varying(64) NOT NULL, medication_name character varying(255) NOT NULL, generic_name character varying(255), manufacturer character varying(100), ndc_code character varying(20) UNIQUE, description text, PRIMARY KEY (medication_id) )\n"} +{"conversations": [{"role": "user", "content": "I need to find pairs of players who share the same email domain. For each pair, return player1_id, player2_id, and the shared domain."}, {"role": "assistant", "content": "SELECT p1.player_id AS player1_id,\n p2.player_id AS player2_id,\n LOWER(SPLIT_PART(p1.email, '@', 2)) AS domain\nFROM gaming_technology.players p1\nJOIN gaming_technology.players p2\n ON LOWER(SPLIT_PART(p1.email, '@', 2)) = LOWER(SPLIT_PART(p2.email, '@', 2));"}, {"role": "user", "content": "Actually, I only want each combination once, so ensure player1_id is always less than player2_id."}, {"role": "assistant", "content": "SELECT p1.player_id AS player1_id,\n p2.player_id AS player2_id,\n LOWER(SPLIT_PART(p1.email, '@', 2)) AS domain\nFROM gaming_technology.players p1\nJOIN gaming_technology.players p2\n ON LOWER(SPLIT_PART(p1.email, '@', 2)) = LOWER(SPLIT_PART(p2.email, '@', 2))\nWHERE p1.player_id < p2.player_id;"}, {"role": "user", "content": "Also exclude any domain that appears only once among all players."}, {"role": "assistant", "content": "SELECT p1.player_id AS player1_id,\n p2.player_id AS player2_id,\n d.domain\nFROM (\n SELECT LOWER(SPLIT_PART(email, '@', 2)) AS domain\n FROM gaming_technology.players\n GROUP BY domain\n HAVING COUNT(*) > 1\n) d\nJOIN gaming_technology.players p1\n ON LOWER(SPLIT_PART(p1.email, '@', 2)) = d.domain\nJOIN gaming_technology.players p2\n ON LOWER(SPLIT_PART(p2.email, '@', 2)) = d.domain\nWHERE p1.player_id < p2.player_id;"}, {"role": "user", "content": "Finally, order the results by domain ascending and then by player1_id."}, {"role": "assistant", "content": "SELECT p1.player_id AS player1_id,\n p2.player_id AS player2_id,\n d.domain\nFROM (\n SELECT LOWER(SPLIT_PART(email, '@', 2)) AS domain\n FROM gaming_technology.players\n GROUP BY domain\n HAVING COUNT(*) > 1\n) d\nJOIN gaming_technology.players p1\n ON LOWER(SPLIT_PART(p1.email, '@', 2)) = d.domain\nJOIN gaming_technology.players p2\n ON LOWER(SPLIT_PART(p2.email, '@', 2)) = d.domain\nWHERE p1.player_id < p2.player_id\nORDER BY d.domain ASC, p1.player_id 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 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 )\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": "Which players have unlocked any achievement?"}, {"role": "assistant", "content": "SELECT DISTINCT player_id FROM player_achievements;"}, {"role": "user", "content": "Show me the player ID and the total number of points they've accumulated from all unlocked achievements."}, {"role": "assistant", "content": "SELECT pa.player_id, SUM(a.points) AS total_points FROM player_achievements pa JOIN achievements a ON pa.achievement_id = a.achievement_id GROUP BY pa.player_id;"}, {"role": "user", "content": "Can you filter this to only include players whose total points exceed 1000?"}, {"role": "assistant", "content": "SELECT pa.player_id, SUM(a.points) AS total_points FROM player_achievements pa JOIN achievements a ON pa.achievement_id = a.achievement_id GROUP BY pa.player_id HAVING SUM(a.points) > 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 gaming_technology.achievements ( achievement_id.uuid, game_id.uuid, name.text, description.text, icon_url.text, points.integer, hidden.boolean )\n"} +{"conversations": [{"role": "user", "content": "Show me all contracts deployed on the 'ethereum' network along with their deployer addresses and the count of events emitted by each contract, sorted by event count in descending order."}, {"role": "assistant", "content": "SELECT c.address, c.deployer_address, COUNT(e.event_id) AS event_count FROM web3.contracts c LEFT JOIN web3.events e ON c.contract_id = e.contract_id WHERE c.network_id = 'ethereum' GROUP BY c.address, c.deployer_address ORDER BY event_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 web3.contracts (\n contract_id character varying(64) NOT NULL, -- unique identifier for the contract\n address character varying(128) NOT NULL, -- address of the deployed contract\n abi text NOT NULL, -- application binary interface of the contract\n bytecode text NOT NULL, -- bytecode of the contract\n deployer_address character varying(128) NOT NULL, -- address of the deployer\n deployed_at timestamp NOT NULL, -- time when the contract was deployed\n network_id character varying(64) NOT NULL, -- identifier of the network where the contract is deployed\n status character varying(32) NOT NULL, -- status of the contract (e.g., active, deprecated)\n PRIMARY KEY (contract_id)\n)\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": "For each diagnosis, show the diagnosis code, description, and the full name of the doctor who made the diagnosis."}, {"role": "assistant", "content": "SELECT dgn.diagnosis_code, dgn.description, doc.first_name AS doctor_first_name, doc.last_name AS doctor_last_name\nFROM healthcare.diagnoses dgn\nJOIN healthcare.doctors doc ON dgn.doctor_id = doc.doctor_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.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.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 (\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": "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": "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": "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": "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": "Show me the average market cap and average 24-hour price change percentage for tokens on each chain."}, {"role": "assistant", "content": "SELECT chain, AVG(market_cap) AS average_market_cap, AVG(price_change_percentage_24h) AS average_price_change_24h FROM token_basic_info GROUP BY chain;"}, {"role": "user", "content": "Now, only show chains where the average market cap is greater than 1,000,000,000."}, {"role": "assistant", "content": "SELECT chain, AVG(market_cap) AS average_market_cap, AVG(price_change_percentage_24h) AS average_price_change_24h FROM token_basic_info GROUP BY chain HAVING AVG(market_cap) > 1000000000;"}, {"role": "user", "content": "Also, order the results by average market cap in descending order."}, {"role": "assistant", "content": "SELECT chain, AVG(market_cap) AS average_market_cap, AVG(price_change_percentage_24h) AS average_price_change_24h FROM token_basic_info GROUP BY chain HAVING AVG(market_cap) > 1000000000 ORDER BY average_market_cap DESC;"}, {"role": "user", "content": "Can you also include the total number of tokens for each of these chains?"}, {"role": "assistant", "content": "SELECT chain, COUNT(*) AS number_of_tokens, AVG(market_cap) AS average_market_cap, AVG(price_change_percentage_24h) AS average_price_change_24h FROM token_basic_info GROUP BY chain HAVING AVG(market_cap) > 1000000000 ORDER BY average_market_cap DESC;"}], "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_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": "Provide every combination of medication name and insurance plan name."}, {"role": "assistant", "content": "SELECT m.medication_name, p.plan_name\nFROM healthcare.medications AS m\nCROSS JOIN healthcare.insurance_plans AS p;"}], "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 character varying(64) NOT NULL, record_id character varying(64) NOT NULL, patient_id character varying(64) NOT NULL, doctor_id character varying(64) NOT NULL, diagnosis_code character varying(20) NOT NULL, code_type character varying(10) NOT NULL DEFAULT 'ICD-10', description text, diagnosis_date date NOT NULL, status character varying(32) NOT NULL, is_chronic boolean DEFAULT false, PRIMARY KEY (diagnosis_id) )\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 ( plan_id.text, plan_name.text, insurance_provider.text, plan_type.text, contact_phone.text, website.text )\n"} +{"conversations": [{"role": "user", "content": "List the top 3 tokens by net flow on the Binance chain, including their symbol and average cost."}, {"role": "assistant", "content": "SELECT token_symbol, net_flow, avg_cost FROM smart_money_token_performance WHERE chain = 'Binance' ORDER BY net_flow DESC LIMIT 3;"}, {"role": "user", "content": "Actually, I want to see tokens with a positive net flow and ROI above 20%."}, {"role": "assistant", "content": "SELECT token_symbol, net_flow, avg_cost FROM smart_money_token_performance WHERE chain = 'Binance' AND net_flow > 0 AND roi > 20 ORDER BY net_flow DESC LIMIT 3;"}, {"role": "user", "content": "Can you also include the current price and order by ROI instead?"}, {"role": "assistant", "content": "SELECT token_symbol, net_flow, avg_cost, price FROM smart_money_token_performance WHERE chain = 'Binance' AND net_flow > 0 AND roi > 20 ORDER BY roi DESC LIMIT 3;"}, {"role": "user", "content": "Now filter these results to only include tokens with a price above $1."}, {"role": "assistant", "content": "SELECT token_symbol, net_flow, avg_cost, price FROM smart_money_token_performance WHERE chain = 'Binance' AND net_flow > 0 AND roi > 20 AND price > 1 ORDER BY roi DESC 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\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) )\n"} +{"conversations": [{"role": "user", "content": "List all insurance products that have 'auto' in their product type and are currently active, showing their product name and base premium."}, {"role": "assistant", "content": "SELECT product_id, product_name, product_type, base_premium FROM insurance.insurance_products WHERE product_type LIKE '%auto%' AND is_active = true;"}, {"role": "user", "content": "Now order these results by base premium in descending order and include the coverage details."}, {"role": "assistant", "content": "SELECT product_id, product_name, product_type, base_premium, coverage_details FROM insurance.insurance_products WHERE product_type LIKE '%auto%' AND is_active = true ORDER 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.customers ( customer_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, ssn_hash character varying(128), address_line1 character varying(255) NOT NULL, address_line2 character varying(255), city character varying(100) NOT NULL, state character varying(50) NOT NULL, zip_code character varying(20) NOT NULL, country character varying(50) NOT NULL DEFAULT 'USA', phone_number character varying(30), email character varying(128) UNIQUE, created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, updated_at timestamp, status character varying(20) NOT NULL DEFAULT 'Active', PRIMARY KEY (customer_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 character varying(64) NOT NULL, product_name character varying(150) NOT NULL, product_type character varying(50) NOT NULL, description text, base_premium numeric(10, 2) NOT NULL, coverage_details text, underwriting_rules text, is_active boolean NOT NULL DEFAULT true, created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, updated_at timestamp, PRIMARY KEY (product_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.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": "How many unique wallets hold each NFT (by contract_address and token_id) currently?"}, {"role": "assistant", "content": "SELECT contract_address, token_id, COUNT(DISTINCT wallet_address) AS holder_count\nFROM nft_holders\nGROUP BY contract_address, token_id;"}, {"role": "user", "content": "Filter the results to only include NFTs with more than 10 holders."}, {"role": "assistant", "content": "SELECT contract_address, token_id, COUNT(DISTINCT wallet_address) AS holder_count\nFROM nft_holders\nGROUP BY contract_address, token_id\nHAVING COUNT(DISTINCT wallet_address) > 10;"}, {"role": "user", "content": "Order the results by holder_count descending and limit to the top 20."}, {"role": "assistant", "content": "SELECT contract_address, token_id, COUNT(DISTINCT wallet_address) AS holder_count\nFROM nft_holders\nGROUP BY contract_address, token_id\nHAVING COUNT(DISTINCT wallet_address) > 10\nORDER BY holder_count DESC\nLIMIT 20;"}, {"role": "user", "content": "Also show the total amount held across all wallets for each NFT."}, {"role": "assistant", "content": "SELECT contract_address,\n token_id,\n COUNT(DISTINCT wallet_address) AS holder_count,\n SUM(CAST(amount AS numeric)) AS total_amount\nFROM nft_holders\nGROUP BY contract_address, token_id\nHAVING COUNT(DISTINCT wallet_address) > 10\nORDER BY holder_count DESC\nLIMIT 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 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 (\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 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 (\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 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_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 (\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_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 (\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_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": "Display each product alongside the most recently updated product of the same type. Return original_id, original_updated_at, recent_id, recent_updated_at, and product_type."}, {"role": "assistant", "content": "SELECT p.product_id AS original_id, p.updated_at AS original_updated_at, r.product_id AS recent_id, r.updated_at AS recent_updated_at, p.product_type FROM insurance.insurance_products p JOIN (SELECT product_type, MAX(updated_at) AS max_updated FROM insurance.insurance_products GROUP BY product_type) m ON p.product_type = m.product_type JOIN insurance.insurance_products r ON r.product_type = p.product_type AND r.updated_at = m.max_updated;"}, {"role": "user", "content": "Actually, exclude entries where original or recent updated_at is null."}, {"role": "assistant", "content": "SELECT p.product_id AS original_id, p.updated_at AS original_updated_at, r.product_id AS recent_id, r.updated_at AS recent_updated_at, p.product_type FROM insurance.insurance_products p JOIN (SELECT product_type, MAX(updated_at) AS max_updated FROM insurance.insurance_products WHERE updated_at IS NOT NULL GROUP BY product_type) m ON p.product_type = m.product_type AND p.updated_at IS NOT NULL JOIN insurance.insurance_products r ON r.product_type = p.product_type AND r.updated_at = m.max_updated;"}, {"role": "user", "content": "Also, only include product types that have more than 2 products."}, {"role": "assistant", "content": "SELECT p.product_id AS original_id, p.updated_at AS original_updated_at, r.product_id AS recent_id, r.updated_at AS recent_updated_at, p.product_type FROM insurance.insurance_products p JOIN (SELECT product_type, MAX(updated_at) AS max_updated FROM insurance.insurance_products WHERE updated_at IS NOT NULL GROUP BY product_type) m ON p.product_type = m.product_type AND p.updated_at IS NOT NULL JOIN insurance.insurance_products r ON r.product_type = p.product_type AND r.updated_at = m.max_updated WHERE p.product_type IN (SELECT product_type FROM insurance.insurance_products GROUP BY product_type HAVING COUNT(*) > 2);"}, {"role": "user", "content": "Finally, sort the results by recent_updated_at descending."}, {"role": "assistant", "content": "SELECT p.product_id AS original_id, p.updated_at AS original_updated_at, r.product_id AS recent_id, r.updated_at AS recent_updated_at, p.product_type FROM insurance.insurance_products p JOIN (SELECT product_type, MAX(updated_at) AS max_updated FROM insurance.insurance_products WHERE updated_at IS NOT NULL GROUP BY product_type) m ON p.product_type = m.product_type AND p.updated_at IS NOT NULL JOIN insurance.insurance_products r ON r.product_type = p.product_type AND r.updated_at = m.max_updated WHERE p.product_type IN (SELECT product_type FROM insurance.insurance_products GROUP BY product_type HAVING COUNT(*) > 2) ORDER BY recent_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.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 )\n"} +{"conversations": [{"role": "user", "content": "Show me the token names and their contract addresses where the total supply is greater than 1 million, sorted by total supply in descending order."}, {"role": "assistant", "content": "SELECT token_name, contract_address FROM web3.tokens WHERE total_supply > 1000000 ORDER BY total_supply 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.tokens ( token_id text, contract_address text, token_name text, token_symbol text, decimals integer, total_supply numeric )\n"} +{"conversations": [{"role": "user", "content": "List all patients who have active primary insurance plans with expiration dates within the next 60 days, including their policy numbers and subscriber names."}, {"role": "assistant", "content": "SELECT pi.patient_id, pi.policy_number, pi.subscriber_name FROM healthcare.patient_insurance pi WHERE pi.is_primary = true AND pi.expiration_date BETWEEN CURRENT_DATE AND (CURRENT_DATE + INTERVAL '60 days');"}, {"role": "user", "content": "Can you also include the insurance plan details and sort by expiration date?"}, {"role": "assistant", "content": "SELECT pi.patient_id, pi.policy_number, pi.subscriber_name, pi.plan_id, pi.effective_date, pi.expiration_date FROM healthcare.patient_insurance pi WHERE pi.is_primary = true AND pi.expiration_date BETWEEN CURRENT_DATE AND (CURRENT_DATE + INTERVAL '60 days') ORDER BY pi.expiration_date ASC;"}, {"role": "user", "content": "Actually, I need to see only patients whose insurance plans have a group number specified."}, {"role": "assistant", "content": "SELECT pi.patient_id, pi.policy_number, pi.subscriber_name, pi.plan_id, pi.group_number, pi.effective_date, pi.expiration_date FROM healthcare.patient_insurance pi WHERE pi.is_primary = true AND pi.expiration_date BETWEEN CURRENT_DATE AND (CURRENT_DATE + INTERVAL '60 days') AND pi.group_number IS NOT NULL ORDER BY pi.expiration_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.doctors ( doctor_id text PRIMARY KEY, 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.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.prescriptions ( prescription_id character varying(64) NOT NULL, record_id character varying(64) NOT NULL, patient_id character varying(64) NOT NULL, doctor_id character varying(64) NOT NULL, medication_id character varying(64) NOT NULL, dosage character varying(100) NOT NULL, frequency character varying(100) NOT NULL, route character varying(50), start_date date NOT NULL, end_date date, quantity_dispensed numeric(10,2), refills_allowed integer NOT NULL DEFAULT 0, prescription_date timestamp with time zone NOT NULL DEFAULT current_timestamp, PRIMARY KEY (prescription_id) )\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 documents are there for each document_type? Show document_type and count ordered by the count in descending order."}, {"role": "assistant", "content": "SELECT document_type,\n COUNT(*) AS count\nFROM legal_services.documents\nGROUP BY document_type\nORDER BY 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 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 )\n"} +{"conversations": [{"role": "user", "content": "Can you show me each user's address and the date their wallet was created?"}, {"role": "assistant", "content": "SELECT user_id, address, created_at FROM trading_platform.wallets;"}, {"role": "user", "content": "Now, can you show only wallets created after '2024-01-01' and include the user_id and address?"}, {"role": "assistant", "content": "SELECT user_id, address, created_at FROM trading_platform.wallets WHERE 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 trading_platform.wallets ( wallet_id text, user_id text, address text, private_key text, created_at timestamp )\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": "Find all primary insurance plans that became effective in the last 30 days, showing the patient IDs, policy numbers, and subscriber names, ordered by effective date."}, {"role": "assistant", "content": "SELECT patient_id, policy_number, subscriber_name, effective_date FROM healthcare.patient_insurance WHERE is_primary = true AND effective_date >= (CURRENT_DATE - INTERVAL '30 days') ORDER BY effective_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.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": "List all pairs of contracts deployed on the same day by the same deployer. Show deployer_address, deployment date, and both contract IDs."}, {"role": "assistant", "content": "SELECT\n c1.deployer_address,\n DATE(c1.deployed_at) AS deployment_date,\n c1.contract_id AS contract_id_1,\n c2.contract_id AS contract_id_2\nFROM web3.contracts c1\nJOIN web3.contracts c2\n ON c1.deployer_address = c2.deployer_address\n AND DATE(c1.deployed_at) = DATE(c2.deployed_at)\n AND c1.contract_id < c2.contract_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.contracts (\n contract_id character varying(64) NOT NULL, -- unique identifier for the contract\n address character varying(128) NOT NULL, -- address of the deployed contract\n abi text NOT NULL, -- application binary interface of the contract\n bytecode text NOT NULL, -- bytecode of the contract\n deployer_address character varying(128) NOT NULL, -- address of the deployer\n deployed_at timestamp NOT NULL, -- time when the contract was deployed\n network_id character varying(64) NOT NULL, -- identifier of the network where the contract is deployed\n status character varying(32) NOT NULL, -- status of the contract (e.g., active, deprecated)\n PRIMARY KEY (contract_id)\n)\n"} +{"conversations": [{"role": "user", "content": "For all NFT collections on the Ethereum blockchain, show me the collection name and the current floor price. Sort by floor price descending."}, {"role": "assistant", "content": "SELECT name, floor_price FROM nft_collections WHERE blockchain = 'Ethereum' ORDER BY CAST(floor_price AS FLOAT) DESC;"}, {"role": "user", "content": "Include also the collection symbol and the number of tokens in each collection."}, {"role": "assistant", "content": "SELECT name, symbol, floor_price, token_count FROM nft_collections WHERE blockchain = 'Ethereum' ORDER BY CAST(floor_price AS FLOAT) DESC;"}, {"role": "user", "content": "Can you also show the owner of each collection in the result?"}, {"role": "assistant", "content": "SELECT name, symbol, floor_price, token_count, owner FROM nft_collections WHERE blockchain = 'Ethereum' ORDER BY CAST(floor_price AS FLOAT) DESC;"}, {"role": "user", "content": "Now only include collections whose floor price is greater than 1 ETH."}, {"role": "assistant", "content": "SELECT name, symbol, floor_price, token_count, owner FROM nft_collections WHERE blockchain = 'Ethereum' AND CAST(floor_price AS FLOAT) > 1 AND floor_price_symbol = 'ETH' ORDER BY CAST(floor_price AS FLOAT) 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 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 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 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_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_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": "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 the top 5 ERC20 tokens with the highest total supply, along with their names and contract addresses, but only include tokens with decimals equal to 18."}, {"role": "assistant", "content": "SELECT name, contract_address, total_supply FROM token_metas WHERE is_erc20 = 1 AND decimals = 18 ORDER BY CAST(total_supply AS decimal) DESC LIMIT 5;"}, {"role": "user", "content": "Can you join this with the token_prices table to include the current price of each token?"}, {"role": "assistant", "content": "SELECT tm.name, tm.contract_address, tm.total_supply, tp.price FROM token_metas tm JOIN token_prices tp ON tm.contract_address = tp.address WHERE tm.is_erc20 = 1 AND tm.decimals = 18 ORDER BY CAST(tm.total_supply AS decimal) DESC LIMIT 5;"}, {"role": "user", "content": "Now filter these results to only show tokens where the price is greater than $0.1."}, {"role": "assistant", "content": "SELECT tm.name, tm.contract_address, tm.total_supply, tp.price FROM token_metas tm JOIN token_prices tp ON tm.contract_address = tp.address WHERE tm.is_erc20 = 1 AND tm.decimals = 18 AND tp.price > 0.1 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_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": "What is the current address of the employee with ID 'EMP234'?"}, {"role": "assistant", "content": "I'm sorry, but I can't provide the current address of an employee as this information is not stored in the database 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.text, first_name.text, last_name.text, job_title.text, skill_certifications.text, hire_date.date, assigned_line_id.text, employment_status.text, supervisor_employee_id.text )\n"} +{"conversations": [{"role": "user", "content": "Show me the top 3 tokens by USD value inflow where smart money was buying (type = 1), along with their token symbol and narrative."}, {"role": "assistant", "content": "SELECT token_symbol, narrative, usd_value FROM smart_money_token_inflow WHERE type = 1 ORDER BY usd_value DESC LIMIT 3;"}, {"role": "user", "content": "Actually, I want to see tokens with a USD value over $100,000."}, {"role": "assistant", "content": "SELECT token_symbol, narrative, usd_value FROM smart_money_token_inflow WHERE type = 1 AND usd_value > 100000 ORDER BY usd_value DESC LIMIT 3;"}, {"role": "user", "content": "Can you filter these results to only include tokens from the Ethereum chain?"}, {"role": "assistant", "content": "SELECT token_symbol, narrative, usd_value FROM smart_money_token_inflow WHERE type = 1 AND usd_value > 100000 AND chain = 'Ethereum' ORDER BY usd_value DESC LIMIT 3;"}, {"role": "user", "content": "Now include the 24-hour trading volume for these tokens from the token_dexpool_info table."}, {"role": "assistant", "content": "SELECT smti.token_symbol, smti.narrative, smti.usd_value, tdi.volume_24h FROM smart_money_token_inflow smti LEFT JOIN token_dexpool_info tdi ON smti.token_symbol = tdi.token_symbol AND smti.chain = tdi.chain WHERE smti.type = 1 AND smti.usd_value > 100000 AND smti.chain = 'Ethereum' ORDER BY smti.usd_value DESC 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 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 token_dexpool_info (\",\n \"pair_address character varying(512) NOT NULL, -- the id of dexpool\",\n \"token_name character varying(100) NOT NULL, -- the name of the token in the dexpool\",\n \"token_symbol character varying(100) NOT NULL, -- the token's symbol\",\n \"chain text, -- the chain that the dexpool 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_6h double precision, -- change in value divided by the absolute price value of the original token price in 6 hours\",\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 \"makers_24h double precision, -- the makers of the dex pool in 24 hours\",\n \"volume_24h double precision, -- the trade volume of the dex pool in 24 hours\",\n \"liquidity double precision, -- the liquidity of the dex pool\",\n \"market_cap double precision, -- the market cap of the token\",\n \"trend_rank bigint, -- the rank of token in the dex pool of recent trending, value 1 expresses the most popular token.\",\n \",PRIMARY KEY (pair_address, chain);\"\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_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 ERC20 tokens where the price is between $1 and $10, including their names, symbols, and contract addresses."}, {"role": "assistant", "content": "SELECT name, symbol, address FROM token_prices_latest WHERE price BETWEEN 1 AND 10 AND blockchain = 'ethereum';"}, {"role": "user", "content": "I think there's an error in your query - it should be joining with sui_coins_metadata on coin_type not address. Also, can you add the current price to the results?"}, {"role": "assistant", "content": "SELECT scm.name, scm.symbol, scm.coin_type, tpl.price FROM sui_coins_metadata scm JOIN token_prices_latest tpl ON scm.coin_type = tpl.address WHERE tpl.price BETWEEN 1 AND 10;"}, {"role": "user", "content": "Now filter these results to only show tokens with decimals equal to 18 and sort by name alphabetically."}, {"role": "assistant", "content": "SELECT scm.name, scm.symbol, scm.coin_type, tpl.price FROM sui_coins_metadata scm JOIN token_prices_latest tpl ON scm.coin_type = tpl.address WHERE tpl.price BETWEEN 1 AND 10 AND scm.decimals = 18 ORDER BY scm.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 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 nft_holder_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(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, -- The quantity held in the wallet\n pk integer NOT NULL -- Partition key for the table(floor(block_number / 7200))\n)\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 (\n object_id varchar NOT NULL, -- object id of the nft\n status varchar NOT NULL, -- status of the package, exists or deleted\n collection_type varchar NOT NULL, -- collection type of the nft, eg. 0x...123::avatars::Avatar\n package_id varchar NOT NULL, -- which package the nft belongs to, eg. 0x...123::avatars belongs to 0x...123\n previous_transaction varchar NOT NULL, -- previous transaction of the nft\n display varchar NOT NULL, -- nft metadata json object\n owner varchar NOT NULL, -- nft owner\n name varchar NOT NULL -- nft name\n)\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 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, address varchar, decimals bigint, symbol varchar, price real, timestamp timestamp )\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_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(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": "Which citizens have made payments but have not uploaded any documents? Please show their first and last names and contact emails."}, {"role": "assistant", "content": "SELECT DISTINCT c.first_name, c.last_name, c.contact_email\nFROM government_services.citizens c\nJOIN government_services.payments p ON c.citizen_id = p.citizen_id\nWHERE c.citizen_id NOT IN (\n SELECT d.citizen_id FROM government_services.documents d\n);"}, {"role": "user", "content": "Actually, do not include any citizens whose payments have a status other than 'Succeeded'."}, {"role": "assistant", "content": "SELECT DISTINCT c.first_name, c.last_name, c.contact_email\nFROM government_services.citizens c\nJOIN government_services.payments p ON c.citizen_id = p.citizen_id\nWHERE p.status = 'Succeeded'\nAND c.citizen_id NOT IN (\n SELECT d.citizen_id FROM government_services.documents d\n);"}, {"role": "user", "content": "I got an error about duplicate emails. Can you remove duplicate citizens based only on their contact email?"}, {"role": "assistant", "content": "SELECT DISTINCT ON (c.contact_email) c.first_name, c.last_name, c.contact_email\nFROM government_services.citizens c\nJOIN government_services.payments p ON c.citizen_id = p.citizen_id\nWHERE p.status = 'Succeeded'\nAND c.citizen_id NOT IN (\n SELECT d.citizen_id FROM government_services.documents d\n);"}, {"role": "user", "content": "Now, sort the result by first name ascending."}, {"role": "assistant", "content": "SELECT DISTINCT ON (c.contact_email) c.first_name, c.last_name, c.contact_email\nFROM government_services.citizens c\nJOIN government_services.payments p ON c.citizen_id = p.citizen_id\nWHERE p.status = 'Succeeded'\nAND c.citizen_id NOT IN (\n SELECT d.citizen_id FROM government_services.documents d\n)\nORDER BY c.first_name ASC, c.contact_email;"}], "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.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 the count of applications assigned to employees, grouped by the job title of the assigned employee."}, {"role": "assistant", "content": "SELECT e.job_title, COUNT(a.application_id) AS application_count FROM government_services.applications AS a JOIN government_services.employees AS e ON a.assigned_employee_id = e.employee_id GROUP BY e.job_title"}, {"role": "user", "content": "Filter the count to include only applications with status 'Processing'."}, {"role": "assistant", "content": "SELECT e.job_title, COUNT(a.application_id) AS application_count FROM government_services.applications AS a JOIN government_services.employees AS e ON a.assigned_employee_id = e.employee_id WHERE a.status = 'Processing' GROUP BY e.job_title"}, {"role": "user", "content": "Only display job titles that have more than 10 applications with 'Processing' status assigned."}, {"role": "assistant", "content": "SELECT e.job_title, COUNT(a.application_id) AS application_count FROM government_services.applications AS a JOIN government_services.employees AS e ON a.assigned_employee_id = e.employee_id WHERE a.status = 'Processing' GROUP BY e.job_title HAVING COUNT(a.application_id) > 10"}, {"role": "user", "content": "Instead of 'Processing' status, show the count for applications with status 'Pending Info'."}, {"role": "assistant", "content": "SELECT e.job_title, COUNT(a.application_id) AS application_count FROM government_services.applications AS a JOIN government_services.employees AS e ON a.assigned_employee_id = e.employee_id WHERE a.status = 'Pending Info' GROUP BY e.job_title HAVING COUNT(a.application_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 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.applications (\n application_id character varying(64) NOT NULL, -- unique identifier for the application\n citizen_id character varying(64) NOT NULL, -- FK to citizens table\n service_id character varying(64) NOT NULL, -- FK to services table\n submitted_at timestamp NOT NULL, -- time the application was submitted\n status character varying(50) NOT NULL, -- e.g., Submitted, Processing, Approved, Rejected, Pending Info\n last_updated_at timestamp NOT NULL, -- time the status or details last changed\n assigned_employee_id character varying(64), -- FK to employees table (optional)\n decision_date date, -- date when a final decision was made\n notes text, -- internal notes or citizen-provided comments\n reference_number character varying(100) UNIQUE, -- publicly visible reference number\n PRIMARY KEY (application_id)\n)\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.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) )\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": "Show me all wallet addresses that belong to user_id 'U1001', along with their private keys."}, {"role": "assistant", "content": "SELECT address_id, private_key FROM blockchain.wallets WHERE user_id = 'U1001';"}, {"role": "user", "content": "Now join this with another table to show the count of transactions for each of these wallet addresses."}, {"role": "assistant", "content": "Note: The schema only includes the wallets table. Without a transactions table in the schema, this query cannot be executed. Please provide the transactions table structure if you need this analysis."}], "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": "What is the average trade price for each asset for trades executed between '2024-05-01' and '2024-05-31'?"}, {"role": "assistant", "content": "SELECT\n asset_id,\n AVG(price) AS avg_price\nFROM trading_platform.trades\nWHERE traded_at >= '2024-05-01' AND traded_at < '2024-06-01'\nGROUP BY 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.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)\n"} +{"conversations": [{"role": "user", "content": "For each game, show the game_id, title, the number of servers currently online, and the total current_players on those servers."}, {"role": "assistant", "content": "SELECT g.game_id, g.title, COUNT(s.server_id) AS online_servers, SUM(s.current_players) AS total_online_players\nFROM gaming_technology.games g\nJOIN gaming_technology.servers s ON g.game_id = s.game_id\nWHERE s.status = 'online'\nGROUP BY g.game_id, g.title;"}, {"role": "user", "content": "Only include games released after January 1st, 2022."}, {"role": "assistant", "content": "SELECT g.game_id, g.title, COUNT(s.server_id) AS online_servers, SUM(s.current_players) AS total_online_players\nFROM gaming_technology.games g\nJOIN gaming_technology.servers s ON g.game_id = s.game_id\nWHERE s.status = 'online'\n AND g.release_date > '2022-01-01'\nGROUP BY g.game_id, g.title;"}], "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.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": "Give me the total number of reservations and the sum of total_amount by month for the year 2023."}, {"role": "assistant", "content": "SELECT DATE_TRUNC('month', check_in_date) AS month,\n COUNT(*) AS reservation_count,\n SUM(total_amount) AS total_revenue\nFROM hospitality_technology.reservations\nWHERE EXTRACT(YEAR FROM check_in_date) = 2023\nGROUP BY DATE_TRUNC('month', check_in_date)\nORDER BY month;"}, {"role": "user", "content": "Actually, I only want reservations with status 'CheckedOut' or 'Completed'."}, {"role": "assistant", "content": "SELECT DATE_TRUNC('month', check_in_date) AS month,\n COUNT(*) AS reservation_count,\n SUM(total_amount) AS total_revenue\nFROM hospitality_technology.reservations\nWHERE EXTRACT(YEAR FROM check_in_date) = 2023\n AND status IN ('CheckedOut', 'Completed')\nGROUP BY DATE_TRUNC('month', check_in_date)\nORDER BY 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 hospitality_technology.reservations ( reservation_id text PRIMARY KEY, 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 int, num_children int, status text, booking_source text, rate_plan_id text, total_amount numeric, amount_paid numeric, special_requests text, created_at timestamp, updated_at timestamp )\n"} +{"conversations": [{"role": "user", "content": "For each guest, calculate their total spending on delivered service orders and the total number of those orders."}, {"role": "assistant", "content": "SELECT g.guest_id,\n g.first_name || ' ' || g.last_name AS full_name,\n SUM(so.total_price) AS total_spent,\n COUNT(*) AS total_orders\nFROM hospitality_technology.guests g\nJOIN hospitality_technology.service_orders so\n ON g.guest_id = so.guest_id\nWHERE so.status = 'delivered'\nGROUP BY g.guest_id, full_name;"}, {"role": "user", "content": "I need the breakdown by month for the current year. Show guest ID, month, total spent, and total orders."}, {"role": "assistant", "content": "SELECT so.guest_id,\n DATE_TRUNC('month', so.delivery_timestamp) AS month,\n SUM(so.total_price) AS total_spent,\n COUNT(*) AS total_orders\nFROM hospitality_technology.service_orders so\nWHERE so.status = 'delivered'\n AND so.delivery_timestamp >= '2024-01-01'\n AND so.delivery_timestamp < '2025-01-01'\nGROUP BY so.guest_id, month\nORDER BY month;"}, {"role": "user", "content": "Also include the guest’s email and only show months where total spent is greater than 500."}, {"role": "assistant", "content": "SELECT sub.guest_id,\n g.email,\n sub.month,\n sub.total_spent,\n sub.total_orders\nFROM (\n SELECT so.guest_id,\n DATE_TRUNC('month', so.delivery_timestamp) AS month,\n SUM(so.total_price) AS total_spent,\n COUNT(*) AS total_orders\n FROM hospitality_technology.service_orders so\n WHERE so.status = 'delivered'\n AND so.delivery_timestamp >= '2024-01-01'\n AND so.delivery_timestamp < '2025-01-01'\n GROUP BY so.guest_id, month\n) sub\nJOIN hospitality_technology.guests g\n ON sub.guest_id = g.guest_id\nWHERE sub.total_spent > 500\nORDER BY sub.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 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": "Show me the top 3 narratives by trend rank, along with their top 3 tokens and 7-day price change percentage."}, {"role": "assistant", "content": "SELECT ni.narrative, ni.top_3_coins, ni.price_change_percentage_7d FROM narrative_info ni ORDER BY ni.trend_rank ASC LIMIT 3;"}, {"role": "user", "content": "Can you also include the 24-hour trading volume for these narratives?"}, {"role": "assistant", "content": "SELECT ni.narrative, ni.top_3_coins, ni.price_change_percentage_7d, ni.volume_24h FROM narrative_info ni ORDER BY ni.trend_rank ASC LIMIT 3;"}, {"role": "user", "content": "Actually, I only want narratives with a 7-day price change percentage above 10%."}, {"role": "assistant", "content": "SELECT ni.narrative, ni.top_3_coins, ni.price_change_percentage_7d, ni.volume_24h FROM narrative_info ni WHERE ni.price_change_percentage_7d > 10 ORDER BY ni.trend_rank ASC LIMIT 3;"}, {"role": "user", "content": "Now order the results by 24-hour trading volume in descending order."}, {"role": "assistant", "content": "SELECT ni.narrative, ni.top_3_coins, ni.price_change_percentage_7d, ni.volume_24h FROM narrative_info ni WHERE ni.price_change_percentage_7d > 10 ORDER BY ni.volume_24h DESC 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 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": "Show all room types that offer 'WiFi' in their amenities."}, {"role": "assistant", "content": "SELECT room_type_id, property_id, type_name, amenities FROM hospitality_technology.room_types WHERE amenities LIKE '%WiFi%';"}, {"role": "user", "content": "Only include those with a base rate below 100 and return the results sorted by base_rate ascending."}, {"role": "assistant", "content": "SELECT room_type_id, property_id, type_name, amenities, base_rate FROM hospitality_technology.room_types WHERE amenities LIKE '%WiFi%' AND base_rate < 100 ORDER BY base_rate 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.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": "List all wallets holding the NFT with contract_address '0xabc123' and token_id '100' and the amount held."}, {"role": "assistant", "content": "SELECT wallet_address, amount\nFROM nft_holders\nWHERE contract_address = '0xabc123'\n AND token_id = '100';"}, {"role": "user", "content": "Also include the NFT name from nft_metadata by joining on contract_address and token_id."}, {"role": "assistant", "content": "SELECT nh.wallet_address,\n nh.amount,\n nm.name\nFROM nft_holders nh\nJOIN nft_metadata nm ON nh.contract_address = nm.contract_address\n AND nh.token_id = nm.token_id\nWHERE nh.contract_address = '0xabc123'\n AND nh.token_id = '100';"}, {"role": "user", "content": "Finally, add the collection name from nft_collections where blockchain is 'Ethereum'."}, {"role": "assistant", "content": "SELECT nh.wallet_address,\n nh.amount,\n nm.name,\n nc.name AS collection_name\nFROM nft_holders nh\nJOIN nft_metadata nm ON nh.contract_address = nm.contract_address\n AND nh.token_id = nm.token_id\nJOIN nft_collections nc ON nh.contract_address = nc.contract_address\n AND nc.blockchain = 'Ethereum'\nWHERE nh.contract_address = '0xabc123'\n AND nh.token_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 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 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_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 )\n"} +{"conversations": [{"role": "user", "content": "Show me all transactions (transaction_id, amount, transaction_type) where the transaction_type is 'Transfer' and the status is 'Completed', along with the account_id and related_account_id."}, {"role": "assistant", "content": "SELECT transaction_id, amount, transaction_type, account_id, related_account_id FROM financial_services.transactions WHERE transaction_type = 'Transfer' AND status = 'Completed';"}, {"role": "user", "content": "Now modify the query to include only transfers with amounts greater than $1,000 and sort them by transaction_date in descending order."}, {"role": "assistant", "content": "SELECT transaction_id, amount, transaction_type, account_id, related_account_id FROM financial_services.transactions WHERE transaction_type = 'Transfer' AND status = 'Completed' AND amount > 1000 ORDER BY transaction_date 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.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.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 )\n"} +{"conversations": [{"role": "user", "content": "What is the average number of appointments assigned per employee for each job title?"}, {"role": "assistant", "content": "SELECT e.job_title, CAST(COUNT(a.appointment_id) AS REAL) / COUNT(DISTINCT e.employee_id) AS average_appointments_per_employee FROM government_services.employees e LEFT JOIN government_services.appointments a ON e.employee_id = a.employee_id GROUP BY e.job_title;"}], "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": "Count the number of policies issued in each calendar year, and show the year and the count."}, {"role": "assistant", "content": "SELECT EXTRACT(YEAR FROM issued_at), COUNT(*) FROM insurance.policies WHERE issued_at IS NOT NULL GROUP BY 1 ORDER BY 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 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 ( 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.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.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": "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 ORDER BY p.star_rating DESC;"}, {"role": "user", "content": "Now, filter the results to only include room types with a max occupancy of at least 4 people and a base rate below $300."}, {"role": "assistant", "content": "SELECT p.property_name, p.star_rating, rt.type_name, rt.base_rate, rt.max_occupancy 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 AND rt.base_rate < 300 ORDER BY p.star_rating 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": "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": "Find all wallets created by users in the last 7 days along with any tokens that have a total supply greater than 10 million, showing the wallet address and token details."}, {"role": "assistant", "content": "SELECT w.address AS wallet_address, t.token_name, t.token_symbol, t.total_supply, t.contract_address FROM web3.wallets w JOIN web3.tokens t ON t.total_supply > 10000000 WHERE w.created_at >= CURRENT_DATE - 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 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) )\nCREATE TABLE web3.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) )\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": "Calculate the total PNL and total Net Flow for all tokens recorded on the 'Arbitrum' chain."}, {"role": "assistant", "content": "SELECT SUM(pnl) as total_pnl, SUM(net_flow) as total_net_flow FROM smart_money_token_performance WHERE chain = 'Arbitrum';"}, {"role": "user", "content": "Can you calculate the total PNL and total Net Flow for *all* chains? Show the chain, total PNL, and total Net Flow, ordered by total PNL in descending order."}, {"role": "assistant", "content": "SELECT chain, SUM(pnl) as total_pnl, SUM(net_flow) as total_net_flow FROM smart_money_token_performance GROUP BY chain ORDER BY total_pnl 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 smart_money_token_performance ( token_address character varying(100) NOT NULL, token_symbol character varying(100), pnl numeric(38,2), net_flow numeric(38,2), avg_cost numeric(38,16), price double precision, realized_ratio numeric(10,2), roi numeric(10,2), chain character varying(100) )\n"} +{"conversations": [{"role": "user", "content": "How many likes were given to comments in June 2024?"}, {"role": "assistant", "content": "SELECT COUNT(*) AS comment_likes_count\nFROM social_media.likes\nWHERE comment_id IS NOT NULL \n AND DATE_TRUNC('month', 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 character varying(64) NOT NULL, post_id character varying(64) NOT NULL, user_id character varying(64) NOT NULL, parent_comment_id character varying(64), content text NOT NULL, created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, updated_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, PRIMARY KEY (comment_id) )\nCREATE TABLE social_media.likes ( like_id character varying(64) NOT NULL, user_id character varying(64) NOT NULL, post_id character varying(64), comment_id character varying(64), created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, PRIMARY KEY (like_id), CONSTRAINT unique_user_like UNIQUE (user_id, post_id, comment_id), CONSTRAINT check_like_target CHECK (post_id IS NOT NULL OR comment_id IS NOT NULL) )\nCREATE TABLE social_media.post_hashtags ( post_hashtag_id character varying(64) NOT NULL, post_id character varying(64) NOT NULL, hashtag_id character varying(64) NOT NULL, PRIMARY KEY (post_hashtag_id), CONSTRAINT unique_post_hashtag UNIQUE (post_id, hashtag_id) )\nCREATE TABLE social_media.conversations ( conversation_id character varying(64) NOT NULL, created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, last_message_at timestamp, is_group_chat boolean NOT NULL DEFAULT false, group_name character varying(100), PRIMARY KEY (conversation_id) )\nCREATE TABLE social_media.notifications ( notification_id character varying(64) NOT NULL, recipient_user_id character varying(64) NOT NULL, sender_user_id character varying(64), notification_type character varying(30) NOT NULL, target_entity_id character varying(64), target_entity_type character varying(20), created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, read_at timestamp, PRIMARY KEY (notification_id) )\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": "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": "What are the top 5 tokens by 7-day price change percentage? Show token_symbol, token_name, narrative, and chain, ordered by price_change_percentage_7d descending."}, {"role": "assistant", "content": "```sql\nSELECT\n token_symbol,\n token_name,\n narrative,\n chain\nFROM token_basic_info\nORDER BY price_change_percentage_7d DESC\nLIMIT 5;\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 project_fundraising_record ( id character varying(32) NOT NULL, project_id character varying(32) NOT NULL, project_name character varying(128) NOT NULL, rounds_name character varying(32), investment_value numeric(38,14), investment_date character varying(128), introduction character varying(128), valuation numeric(38,14) )\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 )\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\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 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": "Find the full names and emails of citizens who have received notifications with the status 'Sent' related to a document. Also show the document_id for each notification."}, {"role": "assistant", "content": "SELECT c.first_name || ' ' || c.last_name AS full_name, c.contact_email, n.related_entity_id AS document_id \nFROM government_services.notifications n\nJOIN government_services.citizens c ON n.citizen_id = c.citizen_id\nWHERE n.status = 'Sent' AND n.related_entity_type = 'Document';"}], "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.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.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.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.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": "For each group chat, list its ID, name, creation time, and the creation time of the next group chat created after it, ordered by creation time."}, {"role": "assistant", "content": "SELECT conversation_id, group_name, created_at, LEAD(created_at) OVER (ORDER BY created_at) AS next_group_chat_created_at FROM social_media.conversations WHERE is_group_chat = true ORDER BY created_at;"}, {"role": "user", "content": "Only show pairs where the next group chat was created within 48 hours of the current one, and also include the time difference in hours."}, {"role": "assistant", "content": "WITH RankedGroupChats AS ( SELECT conversation_id, group_name, created_at, LEAD(created_at) OVER (ORDER BY created_at) AS next_group_chat_created_at FROM social_media.conversations WHERE is_group_chat = true ) SELECT conversation_id, group_name, created_at, next_group_chat_created_at, EXTRACT(EPOCH FROM (next_group_chat_created_at - created_at)) / 3600 AS time_difference_hours FROM RankedGroupChats WHERE next_group_chat_created_at IS NOT NULL AND EXTRACT(EPOCH FROM (next_group_chat_created_at - created_at)) <= 48 * 3600 ORDER BY created_at;"}, {"role": "user", "content": "Further refine: Only include group chats whose names contain 'Discuss'."}, {"role": "assistant", "content": "WITH RankedGroupChats AS ( SELECT conversation_id, group_name, created_at, LEAD(created_at) OVER (ORDER BY created_at) AS next_group_chat_created_at FROM social_media.conversations WHERE is_group_chat = true ) SELECT conversation_id, group_name, created_at, next_group_chat_created_at, EXTRACT(EPOCH FROM (next_group_chat_created_at - created_at)) / 3600 AS time_difference_hours FROM RankedGroupChats WHERE next_group_chat_created_at IS NOT NULL AND EXTRACT(EPOCH FROM (next_group_chat_created_at - created_at)) <= 48 * 3600 AND group_name LIKE '%Discuss%' 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 social_media.conversations ( conversation_id character varying(64) NOT NULL, created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, last_message_at timestamp, is_group_chat boolean NOT NULL DEFAULT false, group_name character varying(100), PRIMARY KEY (conversation_id) )\n"} +{"conversations": [{"role": "user", "content": "Compute the total invoiced amount and average payment delay (in days) by status for invoices issued between 2024-01-01 and 2024-06-30."}, {"role": "assistant", "content": "SELECT status,\n SUM(total_amount) AS total_invoiced,\n AVG(EXTRACT(day FROM (payment_date::date - issue_date))) AS avg_payment_delay_days\n FROM legal_services.invoices\n WHERE issue_date BETWEEN '2024-01-01' AND '2024-06-30'\n GROUP BY status;"}, {"role": "user", "content": "Also show the count of invoices per status."}, {"role": "assistant", "content": "SELECT status,\n SUM(total_amount) AS total_invoiced,\n AVG(EXTRACT(day FROM (payment_date::date - issue_date))) AS avg_payment_delay_days,\n COUNT(*) AS invoice_count\n FROM legal_services.invoices\n WHERE issue_date BETWEEN '2024-01-01' AND '2024-06-30'\n GROUP BY status;"}, {"role": "user", "content": "Exclude statuses where total_invoiced is less than 10000."}, {"role": "assistant", "content": "SELECT status,\n SUM(total_amount) AS total_invoiced,\n AVG(EXTRACT(day FROM (payment_date::date - issue_date))) AS avg_payment_delay_days,\n COUNT(*) AS invoice_count\n FROM legal_services.invoices\n WHERE issue_date BETWEEN '2024-01-01' AND '2024-06-30'\n GROUP BY status\nHAVING SUM(total_amount) >= 10000;"}, {"role": "user", "content": "Finally, order the results by avg_payment_delay_days ascending."}, {"role": "assistant", "content": "SELECT status,\n SUM(total_amount) AS total_invoiced,\n AVG(EXTRACT(day FROM (payment_date::date - issue_date))) AS avg_payment_delay_days,\n COUNT(*) AS invoice_count\n FROM legal_services.invoices\n WHERE issue_date BETWEEN '2024-01-01' AND '2024-06-30'\n GROUP BY status\nHAVING SUM(total_amount) >= 10000\n ORDER BY avg_payment_delay_days 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 legal_services.invoices ( invoice_id text PRIMARY KEY, invoice_number text UNIQUE, 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": "List users who have received notifications triggered by another user (non-system notifications). Show the recipient username, notification type, and the sender username."}, {"role": "assistant", "content": "SELECT T1.username AS recipient_username, T2.notification_type, T3.username AS sender_username FROM social_media.users AS T1 JOIN social_media.notifications AS T2 ON T1.user_id = T2.recipient_user_id JOIN social_media.users AS T3 ON T2.sender_user_id = T3.user_id;"}, {"role": "user", "content": "Refine the list from Turn 1 to only include notifications of type 'follow' or 'mention'."}, {"role": "assistant", "content": "SELECT T1.username AS recipient_username, T2.notification_type, T3.username AS sender_username FROM social_media.users AS T1 JOIN social_media.notifications AS T2 ON T1.user_id = T2.recipient_user_id JOIN social_media.users AS T3 ON T2.sender_user_id = T3.user_id WHERE T2.notification_type IN ('follow', 'mention');"}, {"role": "user", "content": "Further filter to only include notifications created in 2024 and order the results by notification creation time descending."}, {"role": "assistant", "content": "SELECT T1.username AS recipient_username, T2.notification_type, T3.username AS sender_username FROM social_media.users AS T1 JOIN social_media.notifications AS T2 ON T1.user_id = T2.recipient_user_id JOIN social_media.users AS T3 ON T2.sender_user_id = T3.user_id WHERE T2.notification_type IN ('follow', 'mention') AND EXTRACT(YEAR FROM T2.created_at) = 2024 ORDER BY T2.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 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": "Which doctors have issued prescriptions with a route of 'Oral'? Please show doctor_id and the number of such prescriptions they have written."}, {"role": "assistant", "content": "SELECT doctor_id, COUNT(*) AS oral_prescription_count\nFROM healthcare.prescriptions\nWHERE route = 'Oral'\nGROUP BY doctor_id;"}, {"role": "user", "content": "Now, only include doctors who have written more than 10 oral prescriptions and sort the list by oral_prescription_count descending."}, {"role": "assistant", "content": "SELECT doctor_id, COUNT(*) AS oral_prescription_count\nFROM healthcare.prescriptions\nWHERE route = 'Oral'\nGROUP BY doctor_id\nHAVING COUNT(*) > 10\nORDER BY oral_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.prescriptions (\n prescription_id character varying(64) NOT NULL, -- unique identifier for the prescription\n record_id character varying(64) NOT NULL, -- FK linking to the medical record where it was prescribed\n patient_id character varying(64) NOT NULL, -- FK to patients table\n doctor_id character varying(64) NOT NULL, -- FK to prescribing doctor\n medication_id character varying(64) NOT NULL, -- FK to medications table\n dosage character varying(100) NOT NULL, -- e.g., '100mg', '1 tablet'\n frequency character varying(100) NOT NULL, -- e.g., 'Once daily', 'Twice a day with meals'\n route character varying(50), -- e.g., 'Oral', 'Topical', 'Intravenous'\n start_date date NOT NULL, -- date prescription begins\n end_date date, -- date prescription ends (if applicable)\n quantity_dispensed numeric(10,2), -- amount dispensed (e.g., number of tablets)\n refills_allowed integer NOT NULL DEFAULT 0, -- number of allowed refills\n prescription_date timestamp with time zone NOT NULL DEFAULT current_timestamp,\n PRIMARY KEY (prescription_id)\n)\n"} +{"conversations": [{"role": "user", "content": "For each trip, show the trip_id, vehicle's license plate, total fuel quantity, and number of fueling events."}, {"role": "assistant", "content": "SELECT t.trip_id, v.license_plate, SUM(f.quantity) AS total_fuel, COUNT(f.fuel_log_id) AS fueling_events FROM transportation.trips t JOIN transportation.fuel_logs f ON t.trip_id = f.trip_id JOIN transportation.vehicles v ON t.vehicle_id = v.vehicle_id GROUP BY t.trip_id, v.license_plate;"}], "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.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 (\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.maintenance_logs (\n log_id character varying(64) NOT NULL, -- unique identifier for the maintenance record\n vehicle_id character varying(64) NOT NULL, -- identifier of the vehicle serviced\n service_date date NOT NULL, -- date the service was performed\n odometer_reading integer, -- vehicle mileage at time of service\n service_type character varying(128) NOT NULL, -- type of service (e.g., Oil Change, Tire Rotation, Engine Repair)\n description text NOT NULL, -- detailed description of work done\n cost numeric(10, 2), -- cost of the service\n mechanic_name character varying(128), -- name or ID of the mechanic/shop\n next_service_due_date date, -- recommended date for next service\n PRIMARY KEY (log_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)\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 (\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 the trip ID, route number, vehicle ID, and the total fuel cost associated with each trip."}, {"role": "assistant", "content": "SELECT t.trip_id, r.route_number, t.vehicle_id, SUM(fl.total_cost) AS total_fuel_cost FROM transportation.trips t JOIN transportation.routes r ON t.route_id = r.route_id JOIN transportation.fuel_logs fl ON t.trip_id = fl.trip_id GROUP BY t.trip_id, r.route_number, t.vehicle_id;"}, {"role": "user", "content": "Only include trips where the total fuel cost is greater than 1000."}, {"role": "assistant", "content": "SELECT t.trip_id, r.route_number, t.vehicle_id, SUM(fl.total_cost) AS total_fuel_cost FROM transportation.trips t JOIN transportation.routes r ON t.route_id = r.route_id JOIN transportation.fuel_logs fl ON t.trip_id = fl.trip_id GROUP BY t.trip_id, r.route_number, t.vehicle_id HAVING SUM(fl.total_cost) > 1000;"}, {"role": "user", "content": "Also, order the results by total fuel cost in descending order."}, {"role": "assistant", "content": "SELECT t.trip_id, r.route_number, t.vehicle_id, SUM(fl.total_cost) AS total_fuel_cost FROM transportation.trips t JOIN transportation.routes r ON t.route_id = r.route_id JOIN transportation.fuel_logs fl ON t.trip_id = fl.trip_id GROUP BY t.trip_id, r.route_number, t.vehicle_id HAVING SUM(fl.total_cost) > 1000 ORDER BY total_fuel_cost 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.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, 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.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 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 ( 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 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": "Find pairs of customers who share the same last name and live in the same city. List the two customer IDs as customer1_id, customer2_id, their first names as first_name1, first_name2, and city."}, {"role": "assistant", "content": "SELECT c1.customer_id AS customer1_id,\n c2.customer_id AS customer2_id,\n c1.first_name AS first_name1,\n c2.first_name AS first_name2,\n c1.city\nFROM insurance.customers c1\nJOIN insurance.customers c2\n ON c1.last_name = c2.last_name\n AND c1.city = c2.city\n AND c1.customer_id < c2.customer_id;"}, {"role": "user", "content": "Only include customers who are currently active."}, {"role": "assistant", "content": "SELECT c1.customer_id AS customer1_id,\n c2.customer_id AS customer2_id,\n c1.first_name AS first_name1,\n c2.first_name AS first_name2,\n c1.city\nFROM insurance.customers c1\nJOIN insurance.customers c2\n ON c1.last_name = c2.last_name\n AND c1.city = c2.city\n AND c1.customer_id < c2.customer_id\nWHERE c1.status = 'active'\n AND c2.status = 'active';"}, {"role": "user", "content": "Also include their email addresses and sort the results by city ascending and then by first_name1."}, {"role": "assistant", "content": "SELECT c1.customer_id AS customer1_id,\n c2.customer_id AS customer2_id,\n c1.first_name AS first_name1,\n c2.first_name AS first_name2,\n c1.city,\n c1.email AS email1,\n c2.email AS email2\nFROM insurance.customers c1\nJOIN insurance.customers c2\n ON c1.last_name = c2.last_name\n AND c1.city = c2.city\n AND c1.customer_id < c2.customer_id\nWHERE c1.status = 'active'\n AND c2.status = 'active'\nORDER BY c1.city ASC, c1.first_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 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": "Can you provide a breakdown of total and average account balance by account_type and currency for each account status?"}, {"role": "assistant", "content": "SELECT account_type, currency, status, COUNT(*) AS total_accounts, SUM(balance) AS total_balance, AVG(balance) AS average_balance\nFROM financial_services.accounts\nGROUP BY account_type, currency, status;"}, {"role": "user", "content": "Could you include the minimum and maximum interest rate for each group as well?"}, {"role": "assistant", "content": "SELECT account_type, currency, status, COUNT(*) AS total_accounts, SUM(balance) AS total_balance, AVG(balance) AS average_balance, MIN(interest_rate) AS min_interest_rate, MAX(interest_rate) AS max_interest_rate\nFROM financial_services.accounts\nGROUP BY account_type, currency, status;"}, {"role": "user", "content": "Only show groups where the total_accounts is greater than 20."}, {"role": "assistant", "content": "SELECT account_type, currency, status, COUNT(*) AS total_accounts, SUM(balance) AS total_balance, AVG(balance) AS average_balance, MIN(interest_rate) AS min_interest_rate, MAX(interest_rate) AS max_interest_rate\nFROM financial_services.accounts\nGROUP BY account_type, currency, status\nHAVING COUNT(*) > 20;"}, {"role": "user", "content": "Please sort the results by average_balance in descending order."}, {"role": "assistant", "content": "SELECT account_type, currency, status, COUNT(*) AS total_accounts, SUM(balance) AS total_balance, AVG(balance) AS average_balance, MIN(interest_rate) AS min_interest_rate, MAX(interest_rate) AS max_interest_rate\nFROM financial_services.accounts\nGROUP BY account_type, currency, status\nHAVING COUNT(*) > 20\nORDER BY average_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.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)\n"} +{"conversations": [{"role": "user", "content": "What is the schedule of trains arriving at station with ID 'ST789' tomorrow?"}, {"role": "assistant", "content": "I'm sorry, but I can't provide the train schedule for station ID 'ST789' as this information is not available in the current database. The table only contains details about station attributes such as name, location, and number of platforms. For train schedules, please refer to the relevant train service provider or timetable database."}], "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": "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": "List the medical record ID and record date for all medical records that are linked to an appointment whose duration was longer than the average duration of all appointments."}, {"role": "assistant", "content": "SELECT T1.record_id, T1.record_date FROM healthcare.medical_records AS T1 JOIN healthcare.appointments AS T2 ON T1.appointment_id = T2.appointment_id WHERE T2.duration_minutes > (SELECT AVG(duration_minutes) FROM healthcare.appointments);"}], "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.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 ( 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 character varying(64) NOT NULL, record_id character varying(64) NOT NULL, patient_id character varying(64) NOT NULL, doctor_id character varying(64) NOT NULL, diagnosis_code character varying(20) NOT NULL, code_type character varying(10) NOT NULL DEFAULT 'ICD-10', description text, diagnosis_date date NOT NULL, status character varying(32) NOT NULL, is_chronic boolean DEFAULT false, PRIMARY KEY (diagnosis_id) )\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.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": "Get each user's ID, the count of wallets they own, and the total amount of their unspent UTXOs across all wallets."}, {"role": "assistant", "content": "SELECT w.user_id,\n COUNT(DISTINCT w.wallet_id) AS wallet_count,\n COALESCE(SUM(u.amount), 0) AS total_unspent\nFROM trading_platform.wallets w\nLEFT JOIN trading_platform.utxos u\n ON w.address = u.address\n AND u.spent = false\nGROUP BY w.user_id;"}, {"role": "user", "content": "Only include users who have more than one wallet."}, {"role": "assistant", "content": "SELECT w.user_id,\n COUNT(DISTINCT w.wallet_id) AS wallet_count,\n COALESCE(SUM(u.amount), 0) AS total_unspent\nFROM trading_platform.wallets w\nLEFT JOIN trading_platform.utxos u\n ON w.address = u.address\n AND u.spent = false\nGROUP BY w.user_id\nHAVING COUNT(DISTINCT w.wallet_id) > 1;"}, {"role": "user", "content": "Also include the date of the earliest wallet created by each user."}, {"role": "assistant", "content": "SELECT w.user_id,\n COUNT(DISTINCT w.wallet_id) AS wallet_count,\n COALESCE(SUM(u.amount), 0) AS total_unspent,\n MIN(w.created_at) AS first_wallet_date\nFROM trading_platform.wallets w\nLEFT JOIN trading_platform.utxos u\n ON w.address = u.address\n AND u.spent = false\nGROUP BY w.user_id\nHAVING COUNT(DISTINCT w.wallet_id) > 1;"}, {"role": "user", "content": "Sort the results by total_unspent descending and limit to the top 10."}, {"role": "assistant", "content": "SELECT w.user_id,\n COUNT(DISTINCT w.wallet_id) AS wallet_count,\n COALESCE(SUM(u.amount), 0) AS total_unspent,\n MIN(w.created_at) AS first_wallet_date\nFROM trading_platform.wallets w\nLEFT JOIN trading_platform.utxos u\n ON w.address = u.address\n AND u.spent = false\nGROUP BY w.user_id\nHAVING COUNT(DISTINCT w.wallet_id) > 1\nORDER BY total_unspent DESC\nLIMIT 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 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.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.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.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.notifications (\n notification_id character varying(64) NOT NULL, -- unique identifier for the notification\n user_id character varying(64) NOT NULL, -- identifier of the user receiving the notification\n message text NOT NULL, -- message of the notification\n sent_at timestamp NOT NULL, -- time when the notification was sent\n read_at timestamp, -- time when the notification was read\n PRIMARY KEY (notification_id)\n)\n"} +{"conversations": [{"role": "user", "content": "Show prescriptions with their corresponding chief complaint from the medical record. Return prescription_id, record_id, and chief_complaint."}, {"role": "assistant", "content": "SELECT p.prescription_id, p.record_id, mr.chief_complaint\nFROM healthcare.prescriptions p\nLEFT JOIN healthcare.medical_records mr ON p.record_id = mr.record_id;"}, {"role": "user", "content": "Only include prescriptions where chief_complaint contains 'fever' and the route is 'Oral'."}, {"role": "assistant", "content": "SELECT p.prescription_id, p.record_id, mr.chief_complaint\nFROM healthcare.prescriptions p\nLEFT JOIN healthcare.medical_records mr ON p.record_id = mr.record_id\nWHERE mr.chief_complaint ILIKE '%fever%'\n AND p.route = 'Oral';"}, {"role": "user", "content": "Also include the medication_name by joining the medications table and sort the results by prescription_date ascending."}, {"role": "assistant", "content": "SELECT p.prescription_id,\n p.record_id,\n mr.chief_complaint,\n m.medication_name\nFROM healthcare.prescriptions p\nLEFT JOIN healthcare.medical_records mr ON p.record_id = mr.record_id\nLEFT JOIN healthcare.medications m ON p.medication_id = m.medication_id\nWHERE mr.chief_complaint ILIKE '%fever%'\n AND p.route = 'Oral'\nORDER BY p.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.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.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.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": "Could you list each game_id along with the count of hidden achievements and the count of visible achievements?"}, {"role": "assistant", "content": "SELECT game_id,\n SUM(CASE WHEN hidden THEN 1 ELSE 0 END) AS hidden_count,\n SUM(CASE WHEN NOT hidden THEN 1 ELSE 0 END) AS visible_count\nFROM gaming_technology.achievements\nGROUP BY game_id;"}, {"role": "user", "content": "Actually, please provide pairs of one hidden and one visible achievement name for each game where both types exist."}, {"role": "assistant", "content": "SELECT h.game_id,\n h.name AS hidden_name,\n v.name AS visible_name\nFROM gaming_technology.achievements h\nJOIN gaming_technology.achievements v\n ON h.game_id = v.game_id\n AND h.hidden = TRUE\n AND v.hidden = FALSE\nWHERE EXISTS (\n SELECT 1 FROM gaming_technology.achievements x\n WHERE x.game_id = h.game_id\n AND x.hidden = FALSE\n)\nAND EXISTS (\n SELECT 1 FROM gaming_technology.achievements y\n WHERE y.game_id = h.game_id\n AND y.hidden = TRUE\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 gaming_technology.achievements ( achievement_id.uuid, game_id.uuid, name.text, description.text, icon_url.text, points.integer, hidden.boolean )\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": "List the content and sent time for messages sent by user 'U101'."}, {"role": "assistant", "content": "SELECT content, sent_at FROM social_media.messages WHERE sender_user_id = 'U101';"}, {"role": "user", "content": "Could you also include the group name for those messages and only show messages sent in group chats?"}, {"role": "assistant", "content": "SELECT m.content, m.sent_at, c.name AS group_name FROM social_media.messages m JOIN social_media.conversations c ON m.conversation_id = c.conversation_id WHERE m.sender_user_id = 'U101' AND c.type = 'group';"}, {"role": "user", "content": "Now filter to include only messages sent in June 2024 and order them by sent time descending."}, {"role": "assistant", "content": "SELECT m.content, m.sent_at, c.name AS group_name FROM social_media.messages m JOIN social_media.conversations c ON m.conversation_id = c.conversation_id WHERE m.sender_user_id = 'U101' AND c.type = 'group' AND m.sent_at >= '2024-06-01' AND m.sent_at < '2024-07-01' ORDER BY m.sent_at DESC;"}, {"role": "user", "content": "Also limit the results to the top 15."}, {"role": "assistant", "content": "SELECT m.content, m.sent_at, c.name AS group_name FROM social_media.messages m JOIN social_media.conversations c ON m.conversation_id = c.conversation_id WHERE m.sender_user_id = 'U101' AND c.type = 'group' AND m.sent_at >= '2024-06-01' AND m.sent_at < '2024-07-01' ORDER BY m.sent_at DESC LIMIT 15;"}], "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.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)\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": "Find the contract address and name for all NFT collections listed on the 'Ethereum' blockchain."}, {"role": "assistant", "content": "SELECT contract_address, name FROM nft_collections WHERE blockchain = 'Ethereum'"}, {"role": "user", "content": "For these collections, can you show the count of unique wallet addresses holding NFTs in each collection by joining with nft_holders?"}, {"role": "assistant", "content": "SELECT T1.contract_address, T1.name, COUNT(DISTINCT T2.wallet_address) AS unique_holder_count FROM nft_collections AS T1 JOIN nft_holders AS T2 ON T1.contract_address = T2.contract_address WHERE T1.blockchain = 'Ethereum' GROUP BY T1.contract_address, T1.name"}, {"role": "user", "content": "Please filter the results to only include collections that have more than 100 unique holders."}, {"role": "assistant", "content": "SELECT T1.contract_address, T1.name, COUNT(DISTINCT T2.wallet_address) AS unique_holder_count FROM nft_collections AS T1 JOIN nft_holders AS T2 ON T1.contract_address = T2.contract_address WHERE T1.blockchain = 'Ethereum' GROUP BY T1.contract_address, T1.name HAVING COUNT(DISTINCT T2.wallet_address) > 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(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 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 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 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 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": "List all trades with their order_id, trade_type, and commission for trades with commission higher than 100."}, {"role": "assistant", "content": "SELECT trade_id, order_id, trade_type, commission FROM financial_services.trades WHERE commission > 100;"}, {"role": "user", "content": "Include the security_name and ticker_symbol for each trade as well."}, {"role": "assistant", "content": "SELECT t.trade_id, t.order_id, t.trade_type, t.commission, s.security_name, s.ticker_symbol FROM financial_services.trades t INNER JOIN financial_services.securities s ON t.security_id = s.security_id WHERE t.commission > 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 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 )\nCREATE TABLE financial_services.accounts ( account_id text PRIMARY KEY, 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 character varying(64) NOT NULL, account_id character varying(64) NOT NULL, security_id character varying(64) NOT NULL, order_id character varying(64), trade_type character varying(10) NOT NULL, quantity numeric(19, 8) NOT NULL, price_per_unit numeric(19, 8) NOT NULL, total_amount numeric(19, 4) NOT NULL, commission numeric(10, 4), trade_timestamp timestamp NOT NULL, settlement_date date, status character varying(32) NOT NULL, execution_venue character varying(100), PRIMARY KEY (trade_id), FOREIGN KEY (account_id) REFERENCES financial_services.accounts(account_id), FOREIGN KEY (security_id) REFERENCES financial_services.securities(security_id) )\nCREATE TABLE financial_services.market_data ( data_point_id bigserial NOT NULL, security_id character varying(64) NOT NULL, data_timestamp timestamp NOT NULL, open_price numeric(19, 8), high_price numeric(19, 8), low_price numeric(19, 8), close_price numeric(19, 8) NOT NULL, adjusted_close_price numeric(19, 8), volume bigint, source character varying(50), PRIMARY KEY (data_point_id), UNIQUE (security_id, data_timestamp), FOREIGN KEY (security_id) REFERENCES financial_services.securities(security_id) )\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": "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": "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": "For each user with at least two wallets, calculate the average time difference in hours between consecutive wallet creations. Return user_id and avg_diff_hours."}, {"role": "assistant", "content": "SELECT user_id, AVG(EXTRACT(EPOCH FROM (created_at - prev_created)) / 3600) AS avg_diff_hours FROM (SELECT user_id, created_at, LAG(created_at) OVER (PARTITION BY user_id ORDER BY created_at) AS prev_created FROM web3.wallets) t WHERE prev_created IS NOT NULL GROUP BY user_id;"}, {"role": "user", "content": "Actually, restrict the results to users whose avg_diff_hours is less than 24 hours and sort by avg_diff_hours ascending."}, {"role": "assistant", "content": "WITH diffs AS (SELECT user_id, EXTRACT(EPOCH FROM (created_at - prev_created)) / 3600 AS diff_hours FROM (SELECT user_id, created_at, LAG(created_at) OVER (PARTITION BY user_id ORDER BY created_at) AS prev_created FROM web3.wallets) sub WHERE prev_created IS NOT NULL) SELECT user_id, AVG(diff_hours) AS avg_diff_hours FROM diffs GROUP BY user_id HAVING AVG(diff_hours) < 24 ORDER BY avg_diff_hours;"}], "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 (\n contract_id character varying(64) NOT NULL, -- unique identifier for the contract\n address character varying(128) NOT NULL, -- address of the deployed contract\n abi text NOT NULL, -- application binary interface of the contract\n bytecode text NOT NULL, -- bytecode of the contract\n deployer_address character varying(128) NOT NULL, -- address of the deployer\n deployed_at timestamp NOT NULL, -- time when the contract was deployed\n network_id character varying(64) NOT NULL, -- identifier of the network where the contract is deployed\n status character varying(32) NOT NULL, -- status of the contract (e.g., active, deprecated)\n PRIMARY KEY (contract_id)\n)\nCREATE TABLE web3.transactions (\n transaction_id character varying(64) NOT NULL, -- unique identifier for the transaction\n from_address character varying(128) NOT NULL, -- address of the sender\n to_address character varying(128), -- address of the receiver (can be null for contract deployment)\n value numeric(38,14) NOT NULL, -- value transferred\n gas_used integer NOT NULL, -- amount of gas used by the transaction\n gas_price numeric(38,14) NOT NULL, -- price of gas at the time of the transaction\n block_number integer NOT NULL, -- block number containing the transaction\n timestamp timestamp NOT NULL, -- time when the transaction was mined\n input_data text, -- input data of the transaction (can be null)\n status character varying(32) NOT NULL, -- status of the transaction (e.g., success, failed)\n nonce integer NOT NULL, -- nonce of the sender at the time of the transaction\n PRIMARY KEY (transaction_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)\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 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": "What is the total sum of all amounts for all UTXOs in the system, regardless of whether they are spent or unspent?"}, {"role": "assistant", "content": "SELECT SUM(amount) FROM trading_platform.utxos"}], "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 PRIMARY KEY, username text, email text, password_hash text, created_at timestamp )\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 ( 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 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.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.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 ( dapp_id.text, name.text, description.text, url.text )\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 ( kyc_audit_id.text, user_id.text, status.text, reviewed_at.timestamp )\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)\nCREATE TABLE trading_platform.notifications ( notification_id.text, user_id.text, message.text, sent_at.timestamp, read_at.timestamp )\n"} +{"conversations": [{"role": "user", "content": "List the name and symbol for all assets that do not have a corresponding entry with the key 'website' in the metadata table."}, {"role": "assistant", "content": "SELECT T1.name , T1.symbol FROM trading_platform.assets AS T1 LEFT JOIN trading_platform.metadata AS T2 ON T1.asset_id = T2.asset_id AND T2.key = 'website' WHERE T2.metadata_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 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 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 (\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 ( asset_id text PRIMARY KEY, name text, symbol text, type text )\nCREATE TABLE trading_platform.utxos ( utxo_id.text, transaction_id.text, output_index.integer, address.text, amount.numeric, spent.boolean )\nCREATE TABLE trading_platform.dapps ( dapp_id.text, name.text, description.text, url.text )\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)\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": "Find, for each token, how many unique recipient addresses it has. Show token_symbol, contract_address, and recipient_count, ordered by recipient_count descending."}, {"role": "assistant", "content": "SELECT t.token_symbol,\n t.contract_address,\n COUNT(DISTINCT tt.to_address) AS recipient_count\nFROM web3.tokens t\nJOIN web3.token_transfers tt\n ON t.token_id = tt.token_id\nGROUP BY t.token_symbol, t.contract_address\nORDER BY recipient_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 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 (\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)\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": "List all time entries for lawyers specializing in 'Criminal Law'. Show the entry ID, the date worked, hours spent, and the first and last name of the lawyer who performed the work."}, {"role": "assistant", "content": "SELECT te.entry_id, te.date_worked, te.hours_spent, l.first_name, l.last_name FROM legal_services.time_entries te JOIN legal_services.lawyers l ON te.lawyer_id = l.lawyer_id WHERE l.specialization = 'Criminal Law';"}], "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)\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.invoices (\n invoice_id character varying(64) NOT NULL, -- unique identifier for the invoice\n invoice_number character varying(100) UNIQUE NOT NULL, -- user-facing invoice number\n client_id character varying(64) NOT NULL, -- FK to clients table\n case_id character varying(64), -- FK to cases table (optional, could be general retainer)\n issue_date date NOT NULL, -- date the invoice was generated\n due_date date NOT NULL, -- date the payment is due\n total_amount numeric(12, 2) NOT NULL, -- total amount due on the invoice\n amount_paid numeric(12, 2) DEFAULT 0.00, -- amount already paid\n status character varying(50) NOT NULL, -- e.g., Draft, Sent, Paid, Partially Paid, Overdue, Void\n payment_date timestamp, -- date the invoice was fully paid (nullable)\n notes text, -- additional notes or terms on the invoice\n created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP,\n PRIMARY KEY (invoice_id)\n)\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": "Which games have achievements where the points value is exactly 0? List the game title and the achievement name."}, {"role": "assistant", "content": "SELECT g.title AS game_title, a.name AS achievement_name\nFROM gaming_technology.achievements a\nJOIN gaming_technology.games g ON a.game_id = g.game_id\nWHERE a.points = 0;"}, {"role": "user", "content": "Show also the achievement's description and whether it is hidden."}, {"role": "assistant", "content": "SELECT g.title AS game_title, a.name AS achievement_name, a.description, a.hidden\nFROM gaming_technology.achievements a\nJOIN gaming_technology.games g ON a.game_id = g.game_id\nWHERE a.points = 0;"}, {"role": "user", "content": "Only show achievements released in games before 2020."}, {"role": "assistant", "content": "SELECT g.title AS game_title, a.name AS achievement_name, a.description, a.hidden\nFROM gaming_technology.achievements a\nJOIN gaming_technology.games g ON a.game_id = g.game_id\nWHERE a.points = 0 AND g.release_date < '2020-01-01';"}, {"role": "user", "content": "Sort the results by game_title ascending, then achievement_name ascending."}, {"role": "assistant", "content": "SELECT g.title AS game_title, a.name AS achievement_name, a.description, a.hidden\nFROM gaming_technology.achievements a\nJOIN gaming_technology.games g ON a.game_id = g.game_id\nWHERE a.points = 0 AND g.release_date < '2020-01-01'\nORDER BY g.title ASC, a.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 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": "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": "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": "How many claims were reported in the last 90 days?"}, {"role": "assistant", "content": "SELECT COUNT(*) FROM claims WHERE reported_date >= 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 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 character varying(64) NOT NULL, product_name character varying(150) NOT NULL, product_type character varying(50) NOT NULL, description text, base_premium numeric(10, 2) NOT NULL, coverage_details text, underwriting_rules text, is_active boolean NOT NULL DEFAULT true, created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, updated_at timestamp, PRIMARY KEY (product_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 )\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": "Show me each patient's full name along with the name of every doctor they've had an appointment with."}, {"role": "assistant", "content": "SELECT p.first_name || ' ' || p.last_name AS patient_full_name, d.first_name || ' ' || d.last_name AS doctor_full_name\nFROM healthcare.appointments a\nJOIN healthcare.patients p ON a.patient_id = p.patient_id\nJOIN healthcare.doctors d ON a.doctor_id = d.doctor_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.patients ( patient_id text PRIMARY KEY, 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 ( doctor_id text PRIMARY KEY, 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.appointments ( appointment_id text PRIMARY KEY, patient_id text, doctor_id text, appointment_time timestamp, duration_minutes int, reason text, status text, location_id text, notes text, created_at timestamp )\nCREATE TABLE healthcare.medications ( medication_id text PRIMARY KEY, medication_name text, generic_name text, manufacturer text, ndc_code text, description text )\nCREATE TABLE healthcare.prescriptions ( prescription_id text PRIMARY KEY, 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 int, prescription_date timestamp )\nCREATE TABLE healthcare.patient_insurance ( patient_insurance_id text PRIMARY KEY, 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 all comments that are replies, including the comment_id, parent_comment_id, and post_id."}, {"role": "assistant", "content": "SELECT comment_id, parent_comment_id, post_id FROM social_media.comments WHERE parent_comment_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 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.follows ( follow_id text PRIMARY KEY, follower_user_id text, following_user_id text, created_at timestamp )\n"} +{"conversations": [{"role": "user", "content": "List all guests who have never left a review, including their full name and email."}, {"role": "assistant", "content": "SELECT g.guest_id, g.first_name, g.last_name, g.email \nFROM hospitality_technology.guests g \nLEFT JOIN hospitality_technology.reviews r ON g.guest_id = r.guest_id \nWHERE r.review_id IS NULL;"}, {"role": "user", "content": "Can you also include their phone number?"}, {"role": "assistant", "content": "SELECT g.guest_id, g.first_name, g.last_name, g.email, g.phone_number \nFROM hospitality_technology.guests g \nLEFT JOIN hospitality_technology.reviews r ON g.guest_id = r.guest_id \nWHERE r.review_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 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 ( room_id text PRIMARY KEY, property_id text, room_number text, room_type_id text, floor int, status text, is_smoking boolean, features text, current_condition text, last_cleaned_at timestamp )\nCREATE TABLE hospitality_technology.room_types ( room_type_id text PRIMARY KEY, property_id text, type_name text, description text, base_rate numeric, max_occupancy int, 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 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 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 text PRIMARY KEY, reservation_id text, guest_id text, service_id text, staff_id_ordered text, staff_id_delivered text, order_timestamp timestamp, delivery_timestamp timestamp, quantity int, unit_price numeric, total_price numeric, status text, notes text, bill_id text )\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 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": "List the names and types of all in-game items that have a rarity of 'Epic'."}, {"role": "assistant", "content": "SELECT item_name, item_type FROM gaming_technology.in_game_items WHERE rarity = 'Epic';"}, {"role": "user", "content": "Further restrict the list to only include items of item_type 'Weapon'."}, {"role": "assistant", "content": "SELECT item_name, item_type FROM gaming_technology.in_game_items WHERE rarity = 'Epic' AND item_type = 'Weapon';"}, {"role": "user", "content": "Order these results by their cost_amount in descending order."}, {"role": "assistant", "content": "SELECT item_name, item_type FROM gaming_technology.in_game_items WHERE rarity = 'Epic' AND item_type = 'Weapon' ORDER BY cost_amount DESC;"}, {"role": "user", "content": "Please also include the cost_currency and cost_amount in the output."}, {"role": "assistant", "content": "SELECT item_name, item_type, cost_currency, cost_amount FROM gaming_technology.in_game_items WHERE rarity = 'Epic' AND item_type = 'Weapon' ORDER BY cost_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 gaming_technology.players ( player_id uuid, username text, email text, password_hash text, registration_date timestamp with time zone, last_login timestamp with time zone, country_code text, status text, profile_data jsonb )\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.game_sessions ( session_id uuid, player_id uuid, game_id uuid, server_id uuid, start_time timestamp with time zone, end_time timestamp with time zone, duration_seconds integer, score integer, session_data jsonb )\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, 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": "For each wallet, find the next wallet created by the same user. Return the user_id, the earlier wallet_id, the later wallet_id, and the time difference in minutes between their creation times."}, {"role": "assistant", "content": "SELECT user_id,\n wallet_id AS first_wallet_id,\n next_wallet_id,\n EXTRACT(EPOCH FROM (next_created_at - created_at)) / 60 AS minutes_diff\nFROM (\n SELECT wallet_id,\n user_id,\n created_at,\n LEAD(wallet_id) OVER (PARTITION BY user_id ORDER BY created_at) AS next_wallet_id,\n LEAD(created_at) OVER (PARTITION BY user_id ORDER BY created_at) AS next_created_at\n FROM web3.wallets\n) sub\nWHERE next_wallet_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 web3.wallets ( wallet_id text, user_id text, address text, private_key text, created_at timestamp )\n"} +{"conversations": [{"role": "user", "content": "For each reservation, list the guest ID, property name, and the total amount booked. Only include reservations where the total amount is greater than 300."}, {"role": "assistant", "content": "SELECT r.reservation_id, r.guest_id, p.property_name, r.total_amount\nFROM hospitality_technology.reservations r\nJOIN hospitality_technology.properties p ON r.property_id = p.property_id\nWHERE r.total_amount > 300;"}], "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.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.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.service_orders ( order_id text PRIMARY KEY, reservation_id text, guest_id text, service_id text, staff_id_ordered text, staff_id_delivered text, order_timestamp timestamp, delivery_timestamp timestamp, quantity int, unit_price numeric, total_price numeric, status text, notes text, bill_id text )\n"} +{"conversations": [{"role": "user", "content": "Show me all active policies for customers who live in California, along with their total premium payments made so far."}, {"role": "assistant", "content": "SELECT p.policy_id, p.policy_number, c.first_name, c.last_name, p.premium_amount, SUM(pp.amount_paid) AS total_payments_made FROM insurance.policies p JOIN insurance.customers c ON p.customer_id = c.customer_id LEFT JOIN insurance.premium_payments pp ON p.policy_id = pp.policy_id WHERE p.status = 'Active' AND c.state = 'California' GROUP BY p.policy_id, p.policy_number, c.first_name, c.last_name, p.premium_amount;"}, {"role": "user", "content": "I also want to see how many claims each of these policies has had."}, {"role": "assistant", "content": "SELECT p.policy_id, p.policy_number, c.first_name, c.last_name, p.premium_amount, SUM(pp.amount_paid) AS total_payments_made, COUNT(cl.claim_id) AS claim_count FROM insurance.policies p JOIN insurance.customers c ON p.customer_id = c.customer_id LEFT JOIN insurance.premium_payments pp ON p.policy_id = pp.policy_id LEFT JOIN insurance.claims cl ON p.policy_id = cl.policy_id WHERE p.status = 'Active' AND c.state = 'California' GROUP BY p.policy_id, p.policy_number, c.first_name, c.last_name, p.premium_amount;"}, {"role": "user", "content": "Actually, I only want to see policies that have at least one claim."}, {"role": "assistant", "content": "SELECT p.policy_id, p.policy_number, c.first_name, c.last_name, p.premium_amount, SUM(pp.amount_paid) AS total_payments_made, COUNT(cl.claim_id) AS claim_count FROM insurance.policies p JOIN insurance.customers c ON p.customer_id = c.customer_id LEFT JOIN insurance.premium_payments pp ON p.policy_id = pp.policy_id JOIN insurance.claims cl ON p.policy_id = cl.policy_id WHERE p.status = 'Active' AND c.state = 'California' GROUP BY p.policy_id, p.policy_number, c.first_name, c.last_name, p.premium_amount HAVING COUNT(cl.claim_id) > 0;"}, {"role": "user", "content": "Now show me the average settlement amount for these policies' claims."}, {"role": "assistant", "content": "SELECT p.policy_id, p.policy_number, c.first_name, c.last_name, p.premium_amount, SUM(pp.amount_paid) AS total_payments_made, COUNT(cl.claim_id) AS claim_count, AVG(cl.settlement_amount) AS avg_settlement FROM insurance.policies p JOIN insurance.customers c ON p.customer_id = c.customer_id LEFT JOIN insurance.premium_payments pp ON p.policy_id = pp.policy_id JOIN insurance.claims cl ON p.policy_id = cl.policy_id WHERE p.status = 'Active' AND c.state = 'California' GROUP BY p.policy_id, p.policy_number, c.first_name, c.last_name, p.premium_amount HAVING COUNT(cl.claim_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 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 (\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.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.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 (\n document_id character varying(64) NOT NULL, -- unique identifier for the document\n claim_id character varying(64) NOT NULL, -- identifier of the claim this document relates to (FK to claims)\n document_type character varying(50) NOT NULL, -- e.g., Police Report, Photo, Invoice, Medical Bill\n file_name character varying(255) NOT NULL, -- original name of the uploaded file\n file_path character varying(512) NOT NULL, -- storage path (e.g., S3 URL, network path)\n file_size_bytes integer, -- size of the file in bytes\n mime_type character varying(100), -- MIME type of the file (e.g., 'image/jpeg', 'application/pdf')\n uploaded_by character varying(64), -- identifier of the user/system who uploaded (FK to users/customers)\n uploaded_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- time of upload\n description text, -- optional description of the document\n PRIMARY KEY (document_id)\n)\n"} +{"conversations": [{"role": "user", "content": "How many players are registered for each country? Return the country_code and the player count."}, {"role": "assistant", "content": "SELECT country_code, COUNT(*) AS player_count FROM gaming_technology.players GROUP BY country_code;"}, {"role": "user", "content": "I only want to see countries where there are at least 3 players. Please also order the result by player_count descending."}, {"role": "assistant", "content": "SELECT country_code, COUNT(*) AS player_count FROM gaming_technology.players GROUP BY country_code HAVING COUNT(*) >= 3 ORDER BY player_count DESC;"}, {"role": "user", "content": "Remove countries where the country_code is NULL."}, {"role": "assistant", "content": "SELECT country_code, COUNT(*) AS player_count FROM gaming_technology.players WHERE country_code IS NOT NULL GROUP BY country_code HAVING COUNT(*) >= 3 ORDER BY player_count DESC;"}, {"role": "user", "content": "Please also include the earliest registration_date for each country."}, {"role": "assistant", "content": "SELECT country_code, COUNT(*) AS player_count, MIN(registration_date) AS earliest_registration FROM gaming_technology.players WHERE country_code IS NOT NULL GROUP BY country_code HAVING COUNT(*) >= 3 ORDER BY player_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 ( 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) )\n"} +{"conversations": [{"role": "user", "content": "Find the most recent verified document for each application, showing application_id, document_id, and verification_timestamp."}, {"role": "assistant", "content": "SELECT d.document_id, d.application_id, d.verification_timestamp\nFROM government_services.documents d\nJOIN (\n SELECT application_id, MAX(verification_timestamp) AS latest_ts\n FROM government_services.documents\n WHERE verification_status = 'Verified'\n GROUP BY application_id\n) m ON d.application_id = m.application_id\n AND d.verification_timestamp = m.latest_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 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 the total number of likes made on posts versus comments. Show two columns: like_type (either 'post' or 'comment') and like_count."}, {"role": "assistant", "content": "SELECT CASE WHEN post_id IS NOT NULL THEN 'post' ELSE 'comment' END AS like_type, COUNT(*) AS like_count\nFROM social_media.likes\nWHERE post_id IS NOT NULL OR comment_id IS NOT NULL\nGROUP BY like_type;"}, {"role": "user", "content": "Actually, I want to see this broken down per user as well. Include user_id in the results."}, {"role": "assistant", "content": "SELECT user_id, CASE WHEN post_id IS NOT NULL THEN 'post' ELSE 'comment' END AS like_type, COUNT(*) AS like_count\nFROM social_media.likes\nWHERE post_id IS NOT NULL OR comment_id IS NOT NULL\nGROUP BY user_id, like_type;"}, {"role": "user", "content": "Only include users who have liked at least 2 comments."}, {"role": "assistant", "content": "SELECT user_id, 'comment' AS like_type, COUNT(*) AS like_count\nFROM social_media.likes\nWHERE comment_id IS NOT NULL\nGROUP BY user_id\nHAVING COUNT(*) >= 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 social_media.likes ( like_id text PRIMARY KEY, user_id text, post_id text, comment_id text, created_at timestamp )\n"} +{"conversations": [{"role": "user", "content": "How many wallets were created in the year 2023?"}, {"role": "assistant", "content": "SELECT COUNT(*) FROM web3.wallets WHERE created_at >= '2023-01-01 00:00:00' AND created_at < '2024-01-01 00:00:00';"}, {"role": "user", "content": "Okay, instead of the count, show me the wallet ID and creation date for wallets created in January 2023."}, {"role": "assistant", "content": "SELECT wallet_id, created_at FROM web3.wallets WHERE created_at >= '2023-01-01 00:00:00' AND created_at < '2023-02-01 00:00:00';"}, {"role": "user", "content": "Actually, only show me the ones belonging to user ID 'user_example123'."}, {"role": "assistant", "content": "SELECT wallet_id, created_at FROM web3.wallets WHERE created_at >= '2023-01-01 00:00:00' AND created_at < '2023-02-01 00:00:00' AND user_id = 'user_example123';"}, {"role": "user", "content": "Can you sort these by creation date in ascending order and only show the first 5?"}, {"role": "assistant", "content": "SELECT wallet_id, created_at FROM web3.wallets WHERE created_at >= '2023-01-01 00:00:00' AND created_at < '2023-02-01 00:00:00' AND user_id = 'user_example123' ORDER BY created_at ASC LIMIT 5;"}], "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 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": "Show me all in-progress trips with their vehicle IDs and the difference between scheduled and actual departure time in minutes."}, {"role": "assistant", "content": "SELECT trip_id, vehicle_id, EXTRACT(EPOCH FROM (actual_departure - scheduled_departure))/60 AS departure_delay_minutes FROM transportation.trips WHERE status = 'in-progress';"}, {"role": "user", "content": "Can you include the driver ID and filter to only show trips that have been delayed by more than 15 minutes?"}, {"role": "assistant", "content": "SELECT trip_id, vehicle_id, driver_id, EXTRACT(EPOCH FROM (actual_departure - scheduled_departure))/60 AS departure_delay_minutes FROM transportation.trips WHERE status = 'in-progress' AND EXTRACT(EPOCH FROM (actual_departure - scheduled_departure))/60 > 15;"}, {"role": "user", "content": "Now order these results by the delay time in descending order and include the passenger count."}, {"role": "assistant", "content": "SELECT trip_id, vehicle_id, driver_id, EXTRACT(EPOCH FROM (actual_departure - scheduled_departure))/60 AS departure_delay_minutes, passenger_count FROM transportation.trips WHERE status = 'in-progress' AND EXTRACT(EPOCH FROM (actual_departure - scheduled_departure))/60 > 15 ORDER BY departure_delay_minutes 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 ( 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 )\n"} +{"conversations": [{"role": "user", "content": "List all group chat conversations and the number of messages in each group chat."}, {"role": "assistant", "content": "SELECT c.conversation_id,\n c.group_name,\n COUNT(m.message_id) AS message_count\nFROM social_media.conversations c\nJOIN social_media.messages m\n ON c.conversation_id = m.conversation_id\nWHERE c.is_group_chat = true\nGROUP BY c.conversation_id, c.group_name;"}, {"role": "user", "content": "Actually, only include group chats with more than 10 messages and order by message_count descending."}, {"role": "assistant", "content": "SELECT c.conversation_id,\n c.group_name,\n COUNT(m.message_id) AS message_count\nFROM social_media.conversations c\nJOIN social_media.messages m\n ON c.conversation_id = m.conversation_id\nWHERE c.is_group_chat = true\nGROUP BY c.conversation_id, c.group_name\nHAVING COUNT(m.message_id) > 10\nORDER BY message_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 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.follows ( follow_id.text, follower_user_id.text, following_user_id.text, created_at.timestamp )\nCREATE TABLE social_media.messages ( message_id character varying(64) NOT NULL, conversation_id character varying(64) NOT NULL, sender_user_id character varying(64) NOT NULL, content text, media_url text, media_type character varying(20), sent_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, read_at timestamp, PRIMARY KEY (message_id) )\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.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": "Retrieve the contract_id, creator_address, and deployment timestamp for all contracts where the contract code contains the word 'token'."}, {"role": "assistant", "content": "SELECT contract_id, creator_address, timestamp\nFROM blockchain.smart_contracts\nWHERE code ILIKE '%token%';"}], "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 (\n contract_id character varying(64) NOT NULL, -- unique identifier for the smart contract\n creator_address character varying(128) NOT NULL, -- address of the creator of the contract\n code text NOT NULL, -- code of the smart contract\n timestamp timestamp NOT NULL, -- time when the contract was deployed\n PRIMARY KEY (contract_id)\n)\n"} +{"conversations": [{"role": "user", "content": "How many appointments were created in the last 24 hours?"}, {"role": "assistant", "content": "SELECT COUNT(*) FROM healthcare.appointments WHERE created_at >= NOW() - INTERVAL '24 hours';"}], "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 character varying(64) NOT NULL, patient_id character varying(64) NOT NULL, doctor_id character varying(64) NOT NULL, appointment_time timestamp with time zone NOT NULL, duration_minutes integer NOT NULL, reason text, status character varying(32) NOT NULL, location_id character varying(64), notes text, created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, PRIMARY KEY (appointment_id) )\n"} +{"conversations": [{"role": "user", "content": "Show me the total number of trades and total volume for each buyer-seller pair where the same two users traded multiple assets."}, {"role": "assistant", "content": "SELECT buyer_id, seller_id, COUNT(DISTINCT asset_id) AS asset_count, COUNT(*) AS trade_count, SUM(quantity * price) AS total_volume FROM trading_platform.trades GROUP BY buyer_id, seller_id HAVING COUNT(DISTINCT asset_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 trading_platform.trades ( trade_id text, order_id text, buyer_id text, seller_id text, asset_id text, quantity numeric, price numeric, traded_at timestamp )\n"} +{"conversations": [{"role": "user", "content": "Find reviews that contain the word 'dirty' in the comment section, showing the review ID, comment, and rating."}, {"role": "assistant", "content": "SELECT review_id, comment, rating_overall FROM hospitality_technology.reviews WHERE LOWER(comment) LIKE '%dirty%';"}, {"role": "user", "content": "Also, only include reviews that are marked as public and have a rating_cleanliness of 2 or less."}, {"role": "assistant", "content": "SELECT review_id, comment, rating_overall FROM hospitality_technology.reviews WHERE LOWER(comment) LIKE '%dirty%' AND is_public = TRUE AND rating_cleanliness <= 2;"}, {"role": "user", "content": "Filter this list further to exclude reviews submitted before January 1st, 2023 and sort by review date ascending."}, {"role": "assistant", "content": "SELECT review_id, comment, rating_overall FROM hospitality_technology.reviews WHERE LOWER(comment) LIKE '%dirty%' AND is_public = TRUE AND rating_cleanliness <= 2 AND review_date >= '2023-01-01' ORDER BY review_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 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 me all invoice numbers and due dates where the amount paid is exactly zero."}, {"role": "assistant", "content": "SELECT invoice_number, due_date FROM legal_services.invoices WHERE amount_paid = 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 legal_services.invoices ( invoice_id text PRIMARY KEY, invoice_number text UNIQUE, 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": "Provide a summary of transactions by status, showing the count and the total amount for each status."}, {"role": "assistant", "content": "SELECT status, COUNT(*) AS transaction_count, SUM(amount) AS total_amount FROM financial_services.transactions GROUP BY status;"}, {"role": "user", "content": "Only include statuses where the total transaction count exceeds 5."}, {"role": "assistant", "content": "SELECT status, COUNT(*) AS transaction_count, SUM(amount) AS total_amount FROM financial_services.transactions GROUP BY status HAVING COUNT(*) > 5;"}, {"role": "user", "content": "Sort the results by transaction count descending."}, {"role": "assistant", "content": "SELECT status, COUNT(*) AS transaction_count, SUM(amount) AS total_amount FROM financial_services.transactions GROUP BY status HAVING COUNT(*) > 5 ORDER BY transaction_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.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 )\nCREATE TABLE financial_services.accounts ( account_id character varying(64) NOT NULL, customer_id character varying(64) NOT NULL, account_number character varying(128) NOT NULL UNIQUE, account_type character varying(50) NOT NULL, balance numeric(19, 4) NOT NULL DEFAULT 0.00, currency character varying(3) NOT NULL, opened_date date NOT NULL, status character varying(32) NOT NULL, interest_rate numeric(5, 4), last_updated_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, PRIMARY KEY (account_id), FOREIGN KEY (customer_id) REFERENCES financial_services.customers(customer_id) )\nCREATE TABLE financial_services.transactions ( transaction_id character varying(64) NOT NULL, account_id character varying(64) NOT NULL, related_account_id character varying(64), transaction_type character varying(50) NOT NULL, amount numeric(19, 4) NOT NULL, currency character varying(3) NOT NULL, transaction_date timestamp NOT NULL, effective_date date NOT NULL, description text, status character varying(32) NOT NULL, reference_number character varying(128), PRIMARY KEY (transaction_id), FOREIGN KEY (account_id) REFERENCES financial_services.accounts(account_id), FOREIGN KEY (related_account_id) REFERENCES financial_services.accounts(account_id) )\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 (\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 ( 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(100) NOT NULL, department character varying(100), branch_id character varying(64), email character varying(128) NOT NULL UNIQUE, phone_extension character varying(20), hire_date date NOT NULL, termination_date date, manager_id character varying(64), status character varying(32) NOT NULL, PRIMARY KEY (employee_id), FOREIGN KEY (branch_id) REFERENCES financial_services.branches(branch_id), FOREIGN KEY (manager_id) REFERENCES financial_services.employees(employee_id) )\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 me the top 5 users by the total trade volume (quantity * price) as buyers, along with their email addresses and the number of distinct assets they traded."}, {"role": "assistant", "content": "SELECT u.user_id, u.email, COUNT(DISTINCT t.asset_id) AS distinct_assets_traded, SUM(t.quantity * t.price) AS total_trade_volume FROM trading_platform.users u JOIN trading_platform.trades t ON u.user_id = t.buyer_id GROUP BY u.user_id, u.email ORDER BY total_trade_volume DESC LIMIT 5;"}, {"role": "user", "content": "Now filter these results to only include trades that happened in the last 30 days."}, {"role": "assistant", "content": "SELECT u.user_id, u.email, COUNT(DISTINCT t.asset_id) AS distinct_assets_traded, SUM(t.quantity * t.price) AS total_trade_volume FROM trading_platform.users u JOIN trading_platform.trades t ON u.user_id = t.buyer_id WHERE t.traded_at >= NOW() - INTERVAL '30 days' GROUP BY u.user_id, u.email ORDER BY total_trade_volume DESC LIMIT 5;"}, {"role": "user", "content": "Actually, I want to see the average trade size (quantity) for each of these users as well."}, {"role": "assistant", "content": "SELECT u.user_id, u.email, COUNT(DISTINCT t.asset_id) AS distinct_assets_traded, SUM(t.quantity * t.price) AS total_trade_volume, AVG(t.quantity) AS avg_trade_size FROM trading_platform.users u JOIN trading_platform.trades t ON u.user_id = t.buyer_id WHERE t.traded_at >= NOW() - INTERVAL '30 days' GROUP BY u.user_id, u.email ORDER BY total_trade_volume 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 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.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 (\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 ( 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 text, ip_address text, port integer, last_seen timestamp )\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 ( kyc_audit_id text, user_id text, status text, reviewed_at timestamp )\nCREATE TABLE trading_platform.logs ( log_id character varying(64) NOT NULL, user_id character varying(64), action character varying(128) NOT NULL, details text NOT NULL, logged_at timestamp NOT NULL, PRIMARY KEY (log_id) )\nCREATE TABLE trading_platform.notifications ( notification_id.text, user_id.text, message.text, sent_at.timestamp, read_at.timestamp )\n"} +{"conversations": [{"role": "user", "content": "For each employee who has verified more than one document, list their employee ID, the first document they verified, and the next document they verified, along with both verification timestamps."}, {"role": "assistant", "content": "SELECT\n d1.verified_by_employee_id AS employee_id,\n d1.document_id AS first_verified_document,\n d1.verification_timestamp AS first_verification_time,\n d2.document_id AS next_verified_document,\n d2.verification_timestamp AS next_verification_time\nFROM government_services.documents d1\nJOIN government_services.documents d2\n ON d1.verified_by_employee_id = d2.verified_by_employee_id\n AND d2.verification_timestamp > d1.verification_timestamp\nWHERE d1.verification_status = 'Verified'\n AND d2.verification_status = 'Verified';"}], "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": "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": "List all developers along with the total number of achievements available in games that they have developed."}, {"role": "assistant", "content": "SELECT d.name, COUNT(a.achievement_id) AS total_achievements\nFROM gaming_technology.developers d\nJOIN gaming_technology.games g ON d.developer_id = g.developer_id\nJOIN gaming_technology.achievements a ON g.game_id = a.game_id\nGROUP BY d.developer_id, d.name;"}, {"role": "user", "content": "Actually, I want to see only those developers that have more than 20 total achievements in their games."}, {"role": "assistant", "content": "SELECT d.name, COUNT(a.achievement_id) AS total_achievements\nFROM gaming_technology.developers d\nJOIN gaming_technology.games g ON d.developer_id = g.developer_id\nJOIN gaming_technology.achievements a ON g.game_id = a.game_id\nGROUP BY d.developer_id, d.name\nHAVING COUNT(a.achievement_id) > 20;"}, {"role": "user", "content": "Can you also add the country of each developer in the result and sort by the total_achievements in descending order?"}, {"role": "assistant", "content": "SELECT d.name, d.country, COUNT(a.achievement_id) AS total_achievements\nFROM gaming_technology.developers d\nJOIN gaming_technology.games g ON d.developer_id = g.developer_id\nJOIN gaming_technology.achievements a ON g.game_id = a.game_id\nGROUP BY d.developer_id, d.name, d.country\nHAVING COUNT(a.achievement_id) > 20\nORDER BY total_achievements DESC;"}, {"role": "user", "content": "My database does not have the table gaming_technology.games, can you revise the SQL using only the four provided tables?"}, {"role": "assistant", "content": "-- There is no direct way to relate developers to achievements using only the four given tables because there are no games or mapping from developers to games. Therefore, this query cannot be performed with only the provided tables."}], "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.developers ( developer_id.uuid, name.text, country.text, founded_year.integer, website.text, created_at.timestamptz )\nCREATE TABLE gaming_technology.game_sessions ( session_id.uuid, player_id.uuid, game_id.uuid, server_id.uuid, start_time.timestamptz, end_time.timestamptz, duration_seconds.integer, score.integer, session_data.jsonb )\nCREATE TABLE gaming_technology.achievements ( achievement_id.uuid, game_id.uuid, name.text, description.text, icon_url.text, points.integer, hidden.boolean )\n"} +{"conversations": [{"role": "user", "content": "List the IDs and names of all service locations that have no phone number specified."}, {"role": "assistant", "content": "SELECT location_id, location_name \nFROM government_services.service_locations \nWHERE contact_phone IS NULL OR contact_phone = '';"}], "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.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.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.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.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 ERC20 tokens where the total supply is between '1000000000' and '5000000000'. Show the symbol and name."}, {"role": "assistant", "content": "SELECT symbol, name FROM token_metas WHERE is_erc20 = 1 AND total_supply >= '1000000000' AND total_supply <= '5000000000'"}, {"role": "user", "content": "Also include the decimals and contract address."}, {"role": "assistant", "content": "SELECT symbol, name, decimals, contract_address FROM token_metas WHERE is_erc20 = 1 AND total_supply >= '1000000000' AND total_supply <= '5000000000'"}, {"role": "user", "content": "Filter these tokens to only include those where is_proxy is 0."}, {"role": "assistant", "content": "SELECT symbol, name, decimals, contract_address FROM token_metas WHERE is_erc20 = 1 AND total_supply >= '1000000000' AND total_supply <= '5000000000' AND is_proxy = 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 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 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 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 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_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 each trip's trip_id, scheduled_departure, actual_departure, the first and last name of the assigned driver, and the fare total collected from all bookings with that trip_id."}, {"role": "assistant", "content": "SELECT t.trip_id, t.scheduled_departure, t.actual_departure, d.first_name, d.last_name,\n COALESCE(SUM(b.fare), 0) AS total_fare\nFROM transportation.trips t\nJOIN transportation.drivers d ON t.driver_id = d.driver_id\nLEFT JOIN transportation.bookings b ON t.trip_id = b.trip_id\nGROUP BY t.trip_id, t.scheduled_departure, t.actual_departure, d.first_name, d.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 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.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 )\n"} +{"conversations": [{"role": "user", "content": "I want to find all claim IDs that have both an 'Accident Report' and a 'Police Report' document."}, {"role": "assistant", "content": "SELECT DISTINCT a.claim_id\nFROM insurance.claim_documents a\nJOIN insurance.claim_documents b\n ON a.claim_id = b.claim_id\nWHERE a.document_type = 'Accident Report'\n AND b.document_type = 'Police Report';"}, {"role": "user", "content": "Now, only include those pairs if both documents were uploaded after '2024-06-01'."}, {"role": "assistant", "content": "SELECT DISTINCT a.claim_id\nFROM insurance.claim_documents a\nJOIN insurance.claim_documents b\n ON a.claim_id = b.claim_id\nWHERE a.document_type = 'Accident Report'\n AND b.document_type = 'Police Report'\n AND a.uploaded_at > '2024-06-01'\n AND b.uploaded_at > '2024-06-01';"}, {"role": "user", "content": "Additionally, ensure that both files are larger than 500 KB."}, {"role": "assistant", "content": "SELECT DISTINCT a.claim_id\nFROM insurance.claim_documents a\nJOIN insurance.claim_documents b\n ON a.claim_id = b.claim_id\nWHERE a.document_type = 'Accident Report'\n AND b.document_type = 'Police Report'\n AND a.uploaded_at > '2024-06-01'\n AND b.uploaded_at > '2024-06-01'\n AND a.file_size_bytes > 512000\n AND b.file_size_bytes > 512000;"}, {"role": "user", "content": "Finally, show me the file_name and uploaded_by for both document types in the results."}, {"role": "assistant", "content": "SELECT\n a.claim_id,\n a.file_name AS accident_file_name,\n a.uploaded_by AS accident_uploaded_by,\n b.file_name AS police_file_name,\n b.uploaded_by AS police_uploaded_by\nFROM insurance.claim_documents a\nJOIN insurance.claim_documents b\n ON a.claim_id = b.claim_id\nWHERE a.document_type = 'Accident Report'\n AND b.document_type = 'Police Report'\n AND a.uploaded_at > '2024-06-01'\n AND b.uploaded_at > '2024-06-01'\n AND a.file_size_bytes > 512000\n AND b.file_size_bytes > 512000;"}], "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": "For each policy, find the latest payment date. Show the policy_id and the maximum payment_date."}, {"role": "assistant", "content": "SELECT policy_id, MAX(payment_date) AS latest_payment_date FROM insurance.premium_payments GROUP BY policy_id;"}, {"role": "user", "content": "Restrict the results to only show policies where the latest payment date was before '2024-01-01'."}, {"role": "assistant", "content": "SELECT policy_id, MAX(payment_date) AS latest_payment_date FROM insurance.premium_payments GROUP BY policy_id HAVING MAX(payment_date) < '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 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 rooms are there on each floor?"}, {"role": "assistant", "content": "SELECT floor, COUNT(*) FROM hospitality_technology.rooms GROUP BY floor"}, {"role": "user", "content": "Only show floors with more than 10 rooms."}, {"role": "assistant", "content": "SELECT floor, COUNT(*) FROM hospitality_technology.rooms GROUP BY floor HAVING 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 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)\n"} +{"conversations": [{"role": "user", "content": "List the content and comment ID for all comments made by users with private profiles."}, {"role": "assistant", "content": "SELECT c.comment_id, c.content FROM social_media.comments AS c JOIN social_media.user_settings AS us ON c.user_id = us.user_id WHERE us.private_profile = TRUE;"}, {"role": "user", "content": "Only show comments created in the year 2024."}, {"role": "assistant", "content": "SELECT c.comment_id, c.content FROM social_media.comments AS c JOIN social_media.user_settings AS us ON c.user_id = us.user_id WHERE us.private_profile = TRUE AND c.created_at >= '2024-01-01' AND c.created_at < '2025-01-01';"}], "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.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.conversation_participants ( participant_id text, conversation_id text, user_id text, joined_at timestamp, last_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": "Show the document type, verification status, and the full name of the citizen who uploaded each document."}, {"role": "assistant", "content": "SELECT d.document_type, d.verification_status, CONCAT(c.first_name, ' ', c.last_name) AS citizen_full_name FROM government_services.documents d JOIN government_services.citizens c ON d.citizen_id = c.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 (\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)\n"} +{"conversations": [{"role": "user", "content": "Show me all appointments along with any diagnoses recorded for the same patient on the same day. Include appointment_id, patient_id, appointment_time, and diagnosis_description."}, {"role": "assistant", "content": "SELECT T1.appointment_id, T1.patient_id, T1.appointment_time, T2.description FROM healthcare.appointments AS T1 JOIN healthcare.diagnoses AS T2 ON T1.patient_id = T2.patient_id AND DATE(T1.appointment_time) = T2.diagnosis_date;"}, {"role": "user", "content": "Refine this to only include diagnoses that are marked as 'chronic'."}, {"role": "assistant", "content": "SELECT T1.appointment_id, T1.patient_id, T1.appointment_time, T2.description FROM healthcare.appointments AS T1 JOIN healthcare.diagnoses AS T2 ON T1.patient_id = T2.patient_id AND DATE(T1.appointment_time) = T2.diagnosis_date WHERE T2.is_chronic = true;"}, {"role": "user", "content": "Additionally, filter to only include appointments where the status is 'Completed'."}, {"role": "assistant", "content": "SELECT T1.appointment_id, T1.patient_id, T1.appointment_time, T2.description FROM healthcare.appointments AS T1 JOIN healthcare.diagnoses AS T2 ON T1.patient_id = T2.patient_id AND DATE(T1.appointment_time) = T2.diagnosis_date WHERE T2.is_chronic = true AND T1.status = 'Completed';"}], "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 character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, specialty character varying(100) NOT NULL, license_number character varying(50) UNIQUE NOT NULL, phone_number character varying(20), email character varying(128) UNIQUE, hospital_affiliation_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 (doctor_id) )\nCREATE TABLE healthcare.appointments ( appointment_id character varying(64) NOT NULL, patient_id character varying(64) NOT NULL, doctor_id character varying(64) NOT NULL, appointment_time timestamp with time zone NOT NULL, duration_minutes integer NOT NULL, reason text, status character varying(32) NOT NULL, location_id character varying(64), notes text, created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, PRIMARY KEY (appointment_id) )\nCREATE TABLE healthcare.diagnoses ( diagnosis_id character varying(64) NOT NULL, record_id character varying(64) NOT NULL, patient_id character varying(64) NOT NULL, doctor_id character varying(64) NOT NULL, diagnosis_code character varying(20) NOT NULL, code_type character varying(10) NOT NULL DEFAULT 'ICD-10', description text, diagnosis_date date NOT NULL, status character varying(32) NOT NULL, is_chronic boolean DEFAULT false, PRIMARY KEY (diagnosis_id) )\nCREATE TABLE healthcare.medications ( medication_id character varying(64) NOT NULL, medication_name character varying(255) NOT NULL, generic_name character varying(255), manufacturer character varying(100), ndc_code character varying(20) UNIQUE, description text, PRIMARY KEY (medication_id) )\n"} +{"conversations": [{"role": "user", "content": "Retrieve all documents uploaded in 2024, showing document_id, uploaded_by, and uploaded_at."}, {"role": "assistant", "content": "SELECT document_id,\n uploaded_by,\n uploaded_at\nFROM insurance.claim_documents\nWHERE uploaded_at >= '2024-01-01'\n AND uploaded_at < '2025-01-01';"}, {"role": "user", "content": "Actually, please only include documents larger than 1MB."}, {"role": "assistant", "content": "SELECT document_id,\n uploaded_by,\n uploaded_at,\n file_size_bytes\nFROM insurance.claim_documents\nWHERE uploaded_at >= '2024-01-01'\n AND uploaded_at < '2025-01-01'\n AND file_size_bytes > 1048576;"}, {"role": "user", "content": "And sort them by file_size_bytes descending."}, {"role": "assistant", "content": "SELECT document_id,\n uploaded_by,\n uploaded_at,\n file_size_bytes\nFROM insurance.claim_documents\nWHERE uploaded_at >= '2024-01-01'\n AND uploaded_at < '2025-01-01'\n AND file_size_bytes > 1048576\nORDER BY file_size_bytes DESC;"}, {"role": "user", "content": "Limit the results to the first 5 entries."}, {"role": "assistant", "content": "SELECT document_id,\n uploaded_by,\n uploaded_at,\n file_size_bytes\nFROM insurance.claim_documents\nWHERE uploaded_at >= '2024-01-01'\n AND uploaded_at < '2025-01-01'\n AND file_size_bytes > 1048576\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.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": "Can you show me all achievement unlock records where the same player unlocked two different achievements within the same day? Please show player_id, achievement_id_1, achievement_id_2, and the unlock dates for each."}, {"role": "assistant", "content": "SELECT pa1.player_id, pa1.achievement_id as achievement_id_1, pa2.achievement_id as achievement_id_2, pa1.unlocked_at as unlock_date_1, pa2.unlocked_at as unlock_date_2\nFROM gaming_technology.player_achievements pa1\nJOIN gaming_technology.player_achievements pa2\n ON pa1.player_id = pa2.player_id\n AND pa1.achievement_id <> pa2.achievement_id\n AND DATE(pa1.unlocked_at) = DATE(pa2.unlocked_at)\n AND pa1.unlocked_at < pa2.unlocked_at;"}, {"role": "user", "content": "Add a condition to only include records where both achievements were unlocked on or after January 1st, 2024."}, {"role": "assistant", "content": "SELECT pa1.player_id, pa1.achievement_id as achievement_id_1, pa2.achievement_id as achievement_id_2, pa1.unlocked_at as unlock_date_1, pa2.unlocked_at as unlock_date_2\nFROM gaming_technology.player_achievements pa1\nJOIN gaming_technology.player_achievements pa2\n ON pa1.player_id = pa2.player_id\n AND pa1.achievement_id <> pa2.achievement_id\n AND DATE(pa1.unlocked_at) = DATE(pa2.unlocked_at)\n AND pa1.unlocked_at < pa2.unlocked_at\nWHERE pa1.unlocked_at >= '2024-01-01' AND pa2.unlocked_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 gaming_technology.player_achievements ( player_achievement_id uuid, player_id uuid, achievement_id uuid, unlocked_at timestamp with time zone )\n"} +{"conversations": [{"role": "user", "content": "Show each contract's address along with the total number of events it has emitted and the total number of transactions sent to it."}, {"role": "assistant", "content": "SELECT\n c.address,\n COUNT(e.event_id) AS event_count,\n COUNT(t.transaction_id) AS tx_count\nFROM web3.contracts c\nLEFT JOIN web3.events e\n ON c.contract_id = e.contract_id\nLEFT JOIN web3.transactions t\n ON c.address = t.to_address\nGROUP BY c.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.contracts (\n contract_id character varying(64) NOT NULL, -- unique identifier for the contract\n address character varying(128) NOT NULL, -- address of the deployed contract\n abi text NOT NULL, -- application binary interface of the contract\n bytecode text NOT NULL, -- bytecode of the contract\n deployer_address character varying(128) NOT NULL, -- address of the deployer\n deployed_at timestamp NOT NULL, -- time when the contract was deployed\n network_id character varying(64) NOT NULL, -- identifier of the network where the contract is deployed\n status character varying(32) NOT NULL, -- status of the contract (e.g., active, deprecated)\n PRIMARY KEY (contract_id)\n)\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.transactions (\n transaction_id character varying(64) NOT NULL, -- unique identifier for the transaction\n from_address character varying(128) NOT NULL, -- address of the sender\n to_address character varying(128), -- address of the receiver (can be null for contract deployment)\n value numeric(38,14) NOT NULL, -- value transferred\n gas_used integer NOT NULL, -- amount of gas used by the transaction\n gas_price numeric(38,14) NOT NULL, -- price of gas at the time of the transaction\n block_number integer NOT NULL, -- block number containing the transaction\n timestamp timestamp NOT NULL, -- time when the transaction was mined\n input_data text, -- input data of the transaction (can be null)\n status character varying(32) NOT NULL, -- status of the transaction (e.g., success, failed)\n nonce integer NOT NULL, -- nonce of the sender at the time of the transaction\n PRIMARY KEY (transaction_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.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)\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 addresses with a balance greater than 1000, ordered by balance in descending order."}, {"role": "assistant", "content": "SELECT address_id, public_key, balance FROM blockchain.addresses WHERE balance > 1000 ORDER BY balance DESC;"}, {"role": "user", "content": "Now, join this with another query to show the difference between each address's balance and the average balance of all addresses."}, {"role": "assistant", "content": "SELECT a.address_id, a.public_key, a.balance, (a.balance - (SELECT AVG(balance) FROM blockchain.addresses)) AS balance_difference FROM blockchain.addresses a WHERE a.balance > 1000 ORDER BY a.balance DESC;"}, {"role": "user", "content": "Can you modify this to show the percentage difference instead of absolute difference?"}, {"role": "assistant", "content": "SELECT a.address_id, a.public_key, a.balance, ((a.balance - (SELECT AVG(balance) FROM blockchain.addresses)) / (SELECT AVG(balance) FROM blockchain.addresses)) * 100 AS percentage_difference FROM blockchain.addresses a WHERE a.balance > 1000 ORDER BY a.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 blockchain.addresses ( address_id text PRIMARY KEY, public_key text, balance numeric )\n"} +{"conversations": [{"role": "user", "content": "能否帮我查询特定列车行程(schedule_id 为 'sched_001')的详细信息，包括列车出发和到达时间，以及该行程所属路线的ID和相关乘客信息？"}, {"role": "assistant", "content": "SELECT s.schedule_id, s.train_id, s.route_id, s.departure_datetime, s.arrival_datetime, s.status, p.passenger_id, p.first_name, p.last_name, p.email\nFROM schedules s\nLEFT JOIN passengers p ON s.schedule_id = (SELECT schedule_id FROM bookings WHERE passenger_id = p.passenger_id)\nWHERE s.schedule_id = 'sched_001';"}, {"role": "user", "content": "能否将结果限制在状态为‘Scheduled’的行程上，并且只显示乘客的姓名和电子邮件？"}, {"role": "assistant", "content": "SELECT s.schedule_id, s.train_id, s.route_id, s.departure_datetime, s.arrival_datetime, s.status, p.passenger_id, p.first_name, p.last_name, p.email\nFROM schedules s\nLEFT JOIN passengers p ON s.schedule_id = (SELECT schedule_id FROM bookings WHERE passenger_id = p.passenger_id)\nWHERE s.schedule_id = 'sched_001' AND s.status = 'Scheduled';"}, {"role": "user", "content": "能否再加入行程的备注信息，并按出发时间降序排列？"}, {"role": "assistant", "content": "SELECT s.schedule_id, s.train_id, s.route_id, s.departure_datetime, s.arrival_datetime, s.status, s.notes, p.passenger_id, p.first_name, p.last_name, p.email\nFROM schedules s\nLEFT JOIN passengers p ON s.schedule_id = (SELECT schedule_id FROM bookings WHERE passenger_id = p.passenger_id)\nWHERE s.schedule_id = 'sched_001' AND s.status = 'Scheduled'\nORDER BY s.departure_datetime DESC;"}, {"role": "user", "content": "如果没有关联的乘客信息，能否只显示行程信息？"}, {"role": "assistant", "content": "SELECT s.schedule_id, s.train_id, s.route_id, s.departure_datetime, s.arrival_datetime, s.status, s.notes, p.passenger_id, p.first_name, p.last_name, p.email\nFROM schedules s\nLEFT JOIN passengers p ON s.schedule_id = (SELECT schedule_id FROM bookings WHERE passenger_id = p.passenger_id)\nWHERE s.schedule_id = 'sched_001' AND s.status = 'Scheduled'\nORDER BY s.departure_datetime DESC;"}], "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// PUT /schedules\n{\n \"mappings\": {\n \"properties\": {\n \"schedule_id\": { \"type\": \"keyword\" },\n \"train_id\": { \"type\": \"keyword\" }, // References trains index\n \"route_id\": { \"type\": \"keyword\" }, // References routes index\n \"departure_datetime\": { \"type\": \"date\" }, // ISO 8601 format recommended\n \"arrival_datetime\": { \"type\": \"date\" },\n \"status\": { \"type\": \"keyword\" },\n \"notes\": { \"type\": \"text\" }\n }\n }\n}\n// PUT /passengers\n{\n \"mappings\": {\n \"properties\": {\n \"passenger_id\": { \"type\": \"keyword\" },\n \"first_name\": { \n \"type\": \"text\", \n \"fields\": { \"keyword\": { \"type\": \"keyword\", \"ignore_above\": 100 } }\n },\n \"last_name\": { \n \"type\": \"text\", \n \"fields\": { \"keyword\": { \"type\": \"keyword\", \"ignore_above\": 100 } }\n },\n \"email\": { \"type\": \"keyword\" }, // Often used for exact matches\n \"phone_number\": { \"type\": \"keyword\" },\n \"date_of_birth\": { \"type\": \"date\", \"format\": \"yyyy-MM-dd\" },\n \"loyalty_program_id\": { \"type\": \"keyword\" },\n \"created_at\": { \"type\": \"date\" }\n }\n }\n}\n"} +{"conversations": [{"role": "user", "content": "Show policy numbers and product names for all policies that started in 2023."}, {"role": "assistant", "content": "SELECT p.policy_number, ip.product_name FROM insurance.policies AS p JOIN insurance.insurance_products AS ip ON p.product_id = ip.product_id WHERE date_part('year', p.start_date) = 2023"}, {"role": "user", "content": "Add the policy status and the product type to the list."}, {"role": "assistant", "content": "SELECT p.policy_number, ip.product_name, p.status, ip.product_type FROM insurance.policies AS p JOIN insurance.insurance_products AS ip ON p.product_id = ip.product_id WHERE date_part('year', p.start_date) = 2023"}, {"role": "user", "content": "Filter these policies to only include those where the product is currently active and the policy status is 'active'."}, {"role": "assistant", "content": "SELECT p.policy_number, ip.product_name, p.status, ip.product_type FROM insurance.policies AS p JOIN insurance.insurance_products AS ip ON p.product_id = ip.product_id WHERE date_part('year', p.start_date) = 2023 AND p.status = 'active' AND ip.is_active = 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 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.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": "Show the name, symbol, and type of each asset, along with the total number of orders placed for each asset."}, {"role": "assistant", "content": "SELECT a.name, a.symbol, a.type, COUNT(o.order_id) AS order_count\nFROM trading_platform.assets a\nLEFT JOIN trading_platform.orders o ON a.asset_id = o.asset_id\nGROUP BY a.asset_id, a.name, a.symbol, a.type;"}, {"role": "user", "content": "Only include assets that have at least 10 orders, and order the result by order_count descending."}, {"role": "assistant", "content": "SELECT a.name, a.symbol, a.type, COUNT(o.order_id) AS order_count\nFROM trading_platform.assets a\nLEFT JOIN trading_platform.orders o ON a.asset_id = o.asset_id\nGROUP BY a.asset_id, a.name, a.symbol, a.type\nHAVING COUNT(o.order_id) >= 10\nORDER BY order_count DESC;"}, {"role": "user", "content": "Instead of all orders, only consider orders with status 'open'."}, {"role": "assistant", "content": "SELECT a.name, a.symbol, a.type, COUNT(o.order_id) AS open_order_count\nFROM trading_platform.assets a\nLEFT JOIN trading_platform.orders o ON a.asset_id = o.asset_id AND o.status = 'open'\nGROUP BY a.asset_id, a.name, a.symbol, a.type\nHAVING COUNT(o.order_id) >= 10\nORDER BY open_order_count DESC;"}, {"role": "user", "content": "The SQL doesn't work because some assets have no open orders, but I want to include those assets with a count of 0. Please update the query accordingly."}, {"role": "assistant", "content": "SELECT a.name, a.symbol, a.type, COUNT(o.order_id) AS open_order_count\nFROM trading_platform.assets a\nLEFT JOIN trading_platform.orders o ON a.asset_id = o.asset_id AND o.status = 'open'\nGROUP BY a.asset_id, a.name, a.symbol, a.type\nHAVING COUNT(o.order_id) >= 10 OR COUNT(o.order_id) = 0\nORDER BY open_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 trading_platform.wallets ( wallet_id.text, user_id.text, address.text, private_key.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.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 ( asset_id text, name text, symbol text, type text )\nCREATE TABLE trading_platform.dapps ( dapp_id text PRIMARY KEY, name text, description text, url text )\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.notifications ( notification_id.text, user_id.text, message.text, sent_at.timestamp, read_at.timestamp )\n"} +{"conversations": [{"role": "user", "content": "List all passengers who have never made a booking, showing their passenger_id, first_name, last_name, and email."}, {"role": "assistant", "content": "SELECT\n p.passenger_id,\n p.first_name,\n p.last_name,\n p.email\nFROM transportation.passengers p\nLEFT JOIN transportation.bookings b ON p.passenger_id = b.passenger_id\nWHERE b.booking_id IS NULL;"}, {"role": "user", "content": "Actually, please include their phone_number as well."}, {"role": "assistant", "content": "SELECT\n p.passenger_id,\n p.first_name,\n p.last_name,\n p.email,\n p.phone_number\nFROM transportation.passengers p\nLEFT JOIN transportation.bookings b ON p.passenger_id = b.passenger_id\nWHERE b.booking_id IS NULL;"}, {"role": "user", "content": "Also, limit to passengers created after '2022-01-01'."}, {"role": "assistant", "content": "SELECT\n p.passenger_id,\n p.first_name,\n p.last_name,\n p.email,\n p.phone_number\nFROM transportation.passengers p\nLEFT JOIN transportation.bookings b ON p.passenger_id = b.passenger_id\nWHERE b.booking_id IS NULL\n AND p.created_at > '2022-01-01';"}, {"role": "user", "content": "Finally, sort the results by last_name in ascending order."}, {"role": "assistant", "content": "SELECT\n p.passenger_id,\n p.first_name,\n p.last_name,\n p.email,\n p.phone_number\nFROM transportation.passengers p\nLEFT JOIN transportation.bookings b ON p.passenger_id = b.passenger_id\nWHERE b.booking_id IS NULL\n AND p.created_at > '2022-01-01'\nORDER BY p.last_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 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": "Show me all smart contracts created by addresses that have created more than 3 contracts, along with the count of contracts each creator has made."}, {"role": "assistant", "content": "SELECT creator_address, COUNT(*) AS contract_count FROM blockchain.smart_contracts GROUP BY creator_address HAVING COUNT(*) > 3;"}, {"role": "user", "content": "Now filter these results to only show contracts created in the last 6 months."}, {"role": "assistant", "content": "SELECT sc.creator_address, COUNT(*) AS contract_count FROM blockchain.smart_contracts sc WHERE sc.timestamp >= NOW() - INTERVAL '6 months' GROUP BY sc.creator_address HAVING COUNT(*) > 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.smart_contracts ( contract_id text PRIMARY KEY, creator_address text, code text, timestamp timestamp )\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 each case ID with its latest uploaded document. I want to see the case ID, document name, version, and upload timestamp for the most recently uploaded document in each case."}, {"role": "assistant", "content": "SELECT d.case_id, d.document_name, d.version, d.upload_timestamp\nFROM legal_services.documents d\nINNER JOIN (\n SELECT case_id, MAX(upload_timestamp) AS max_upload_timestamp\n FROM legal_services.documents\n GROUP BY case_id\n) latest ON d.case_id = latest.case_id AND d.upload_timestamp = latest.max_upload_timestamp;"}, {"role": "user", "content": "I actually also need to see the document type for these latest documents."}, {"role": "assistant", "content": "SELECT d.case_id, d.document_name, d.version, d.upload_timestamp, d.document_type\nFROM legal_services.documents d\nINNER JOIN (\n SELECT case_id, MAX(upload_timestamp) AS max_upload_timestamp\n FROM legal_services.documents\n GROUP BY case_id\n) latest ON d.case_id = latest.case_id AND d.upload_timestamp = latest.max_upload_timestamp;"}, {"role": "user", "content": "Now, only show cases where the latest uploaded document is a 'Contract'."}, {"role": "assistant", "content": "SELECT d.case_id, d.document_name, d.version, d.upload_timestamp, d.document_type\nFROM legal_services.documents d\nINNER JOIN (\n SELECT case_id, MAX(upload_timestamp) AS max_upload_timestamp\n FROM legal_services.documents\n GROUP BY case_id\n) latest ON d.case_id = latest.case_id AND d.upload_timestamp = latest.max_upload_timestamp\nWHERE d.document_type = 'Contract';"}], "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 )\n"} +{"conversations": [{"role": "user", "content": "What is the average profit for smart money addresses on the 'Arbitrum' chain?"}, {"role": "assistant", "content": "SELECT AVG(profit) FROM smart_money_profit WHERE chain = 'Arbitrum'"}, {"role": "user", "content": "And how many smart money addresses on the 'Polygon' chain have a profit greater than $1000?"}, {"role": "assistant", "content": "SELECT COUNT(address) FROM smart_money_profit WHERE chain = 'Polygon' AND profit > 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 smart_money_profit ( address text, rank numeric, profit numeric, roi numeric, realized_ratio numeric, most_profit_token text, last_trade_time text, chain text )\n"} +{"conversations": [{"role": "user", "content": "Generate a report listing each manager with the number of agents they manage. Include manager_id, manager's full name, and report_count."}, {"role": "assistant", "content": "SELECT m.agent_id AS manager_id,\n m.first_name || ' ' || m.last_name AS manager_name,\n COUNT(a.agent_id) AS report_count\nFROM insurance.agents m\nLEFT JOIN insurance.agents a\n ON m.agent_id = a.manager_id\nGROUP BY m.agent_id, m.first_name, m.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 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 )\n"} +{"conversations": [{"role": "user", "content": "Show me all room types with a base rate over $200 and max occupancy of at least 4, along with their property IDs and amenities."}, {"role": "assistant", "content": "SELECT room_type_id, property_id, type_name, base_rate, max_occupancy, amenities FROM hospitality_technology.room_types WHERE base_rate > 200 AND max_occupancy >= 4;"}, {"role": "user", "content": "Now, join this with the guests table to show only room types from properties where the guest's country code is 'USA'."}, {"role": "assistant", "content": "SELECT rt.room_type_id, rt.property_id, rt.type_name, rt.base_rate, rt.max_occupancy, rt.amenities FROM hospitality_technology.room_types rt JOIN hospitality_technology.guests g ON rt.property_id = g.property_id WHERE rt.base_rate > 200 AND rt.max_occupancy >= 4 AND g.country_code = 'USA';"}], "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.room_types ( room_type_id text PRIMARY KEY, property_id text, type_name text, description text, base_rate numeric, max_occupancy int, 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 )\n"} +{"conversations": [{"role": "user", "content": "Which policies have a premium amount greater than the base premium of their respective insurance product? Please show the policy_number, premium_amount, product_name, and base_premium."}, {"role": "assistant", "content": "SELECT p.policy_number, p.premium_amount, ip.product_name, ip.base_premium\nFROM insurance.policies p\nINNER JOIN insurance.insurance_products ip ON p.product_id = ip.product_id\nWHERE p.premium_amount > ip.base_premium;"}, {"role": "user", "content": "Now, only include policies where the coverage_limit is above 500,000."}, {"role": "assistant", "content": "SELECT p.policy_number, p.premium_amount, ip.product_name, ip.base_premium\nFROM insurance.policies p\nINNER JOIN insurance.insurance_products ip ON p.product_id = ip.product_id\nWHERE p.premium_amount > ip.base_premium\n AND p.coverage_limit > 500000;"}, {"role": "user", "content": "Actually, I also want to see only active policies."}, {"role": "assistant", "content": "SELECT p.policy_number, p.premium_amount, ip.product_name, ip.base_premium\nFROM insurance.policies p\nINNER JOIN insurance.insurance_products ip ON p.product_id = ip.product_id\nWHERE p.premium_amount > ip.base_premium\n AND p.coverage_limit > 500000\n AND p.status = 'Active';"}, {"role": "user", "content": "Could you sort the results by premium_amount in descending order?"}, {"role": "assistant", "content": "SELECT p.policy_number, p.premium_amount, ip.product_name, ip.base_premium\nFROM insurance.policies p\nINNER JOIN insurance.insurance_products ip ON p.product_id = ip.product_id\nWHERE p.premium_amount > ip.base_premium\n AND p.coverage_limit > 500000\n AND p.status = 'Active'\nORDER BY p.premium_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 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.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 )\n"} +{"conversations": [{"role": "user", "content": "Show policy numbers, start dates, and the type of the insurance product for policies with a deductible greater than 500."}, {"role": "assistant", "content": "SELECT T1.policy_number, T1.start_date, T2.product_type FROM insurance.policies AS T1 JOIN insurance.insurance_products AS T2 ON T1.product_id = T2.product_id WHERE T1.deductible > 500;"}, {"role": "user", "content": "Could you also include the product name and only show results for policies that are currently 'active'?"}, {"role": "assistant", "content": "SELECT T1.policy_number, T1.start_date, T2.product_type, T2.product_name FROM insurance.policies AS T1 JOIN insurance.insurance_products AS T2 ON T1.product_id = T2.product_id WHERE T1.deductible > 500 AND T1.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.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.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 )\n"} +{"conversations": [{"role": "user", "content": "List the usernames and emails of all users who registered on '2023-03-15'."}, {"role": "assistant", "content": "SELECT username, email FROM web3.users WHERE DATE(created_at) = '2023-03-15';"}, {"role": "user", "content": "Instead of the list, can you just give me the total number of users who registered on '2023-03-15'?"}, {"role": "assistant", "content": "SELECT COUNT(*) FROM web3.users WHERE DATE(created_at) = '2023-03-15';"}], "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.users ( user_id text, username text, email text, password_hash text, created_at timestamp )\n"} +{"conversations": [{"role": "user", "content": "Find pairs of reservations at the same property where the second check-in is within 7 days after the first check-out. Return first_reservation, second_reservation, and gap_days."}, {"role": "assistant", "content": "SELECT r1.reservation_id AS first_reservation,\n r2.reservation_id AS second_reservation,\n CAST(r2.check_in_date - r1.check_out_date AS INTEGER) AS gap_days\nFROM hospitality_technology.reservations r1\nJOIN hospitality_technology.reservations r2\n ON r1.property_id = r2.property_id\n AND r2.check_in_date > r1.check_out_date\n AND r2.check_in_date <= r1.check_out_date + INTERVAL '7 days';"}, {"role": "user", "content": "Now restrict to pairs where the first reservation status = 'CheckedOut' and the second reservation status = 'Confirmed'."}, {"role": "assistant", "content": "SELECT r1.reservation_id AS first_reservation,\n r2.reservation_id AS second_reservation,\n CAST(r2.check_in_date - r1.check_out_date AS INTEGER) AS gap_days\nFROM hospitality_technology.reservations r1\nJOIN hospitality_technology.reservations r2\n ON r1.property_id = r2.property_id\n AND r2.check_in_date > r1.check_out_date\n AND r2.check_in_date <= r1.check_out_date + INTERVAL '7 days'\nWHERE r1.status = 'CheckedOut'\n AND r2.status = 'Confirmed';"}, {"role": "user", "content": "Lastly, order by gap_days ascending and limit to 5 results."}, {"role": "assistant", "content": "SELECT r1.reservation_id AS first_reservation,\n r2.reservation_id AS second_reservation,\n CAST(r2.check_in_date - r1.check_out_date AS INTEGER) AS gap_days\nFROM hospitality_technology.reservations r1\nJOIN hospitality_technology.reservations r2\n ON r1.property_id = r2.property_id\n AND r2.check_in_date > r1.check_out_date\n AND r2.check_in_date <= r1.check_out_date + INTERVAL '7 days'\nWHERE r1.status = 'CheckedOut'\n AND r2.status = 'Confirmed'\nORDER BY gap_days 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 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 )\n"} +{"conversations": [{"role": "user", "content": "List all users and the count of wallets they own."}, {"role": "assistant", "content": "SELECT u.username, COUNT(w.wallet_id) AS wallet_count FROM blockchain.users u JOIN blockchain.wallets w ON u.user_id = w.user_id GROUP BY u.user_id, u.username;"}, {"role": "user", "content": "Filter the previous list to only include users who own more than 2 wallets."}, {"role": "assistant", "content": "SELECT u.username, COUNT(w.wallet_id) AS wallet_count FROM blockchain.users u JOIN blockchain.wallets w ON u.user_id = w.user_id GROUP BY u.user_id, u.username HAVING COUNT(w.wallet_id) > 2;"}, {"role": "user", "content": "Now, for those users, also include the total sum of balances across all addresses associated with their wallets."}, {"role": "assistant", "content": "SELECT u.username, COUNT(DISTINCT w.wallet_id) AS wallet_count, SUM(a.balance) AS total_balance FROM blockchain.users u JOIN blockchain.wallets w ON u.user_id = w.user_id JOIN blockchain.addresses a ON w.address_id = a.address_id GROUP BY u.user_id, u.username HAVING COUNT(DISTINCT w.wallet_id) > 2;"}], "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 blockchain.addresses ( address_id character varying(128) NOT NULL, public_key text NOT NULL, balance numeric(38,14) NOT NULL, PRIMARY KEY (address_id) )\nCREATE TABLE blockchain.nodes ( node_id character varying(64) NOT NULL, ip_address character varying(15) NOT NULL, port integer NOT NULL, last_seen timestamp NOT NULL, PRIMARY KEY (node_id) )\nCREATE TABLE blockchain.wallets ( wallet_id character varying(64) NOT NULL, user_id character varying(64) NOT NULL, address_id character varying(128) NOT NULL, private_key text NOT NULL, PRIMARY KEY (wallet_id) )\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": "For each player, show their player_id and the number of unique games they have played sessions on."}, {"role": "assistant", "content": "SELECT player_id, COUNT(DISTINCT game_id) AS unique_games\nFROM gaming_technology.game_sessions\nGROUP BY player_id;"}, {"role": "user", "content": "Also show the total number of sessions they have played."}, {"role": "assistant", "content": "SELECT player_id, COUNT(DISTINCT game_id) AS unique_games, COUNT(*) AS total_sessions\nFROM gaming_technology.game_sessions\nGROUP BY player_id;"}, {"role": "user", "content": "Only include players who have played on more than 2 unique games."}, {"role": "assistant", "content": "SELECT player_id, COUNT(DISTINCT game_id) AS unique_games, COUNT(*) AS total_sessions\nFROM gaming_technology.game_sessions\nGROUP BY player_id\nHAVING COUNT(DISTINCT game_id) > 2;"}, {"role": "user", "content": "For each result, include the player's username as well."}, {"role": "assistant", "content": "SELECT p.player_id, p.username, COUNT(DISTINCT gs.game_id) AS unique_games, COUNT(*) AS total_sessions\nFROM gaming_technology.players p\nJOIN gaming_technology.game_sessions gs ON p.player_id = gs.player_id\nGROUP BY p.player_id, p.username\nHAVING COUNT(DISTINCT gs.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 ( 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.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 ( 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.player_achievements ( player_achievement_id.uuid, player_id.uuid, achievement_id.uuid, unlocked_at.timestamptz )\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 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": "Show me all premium payments made in Q1 2023, along with their payment methods and amounts, sorted by payment date."}, {"role": "assistant", "content": "SELECT payment_method, amount_paid, payment_date FROM insurance.premium_payments WHERE payment_date BETWEEN '2023-01-01' AND '2023-03-31' ORDER BY payment_date;"}, {"role": "user", "content": "Now break this down by payment method to show the total amount collected per payment method in that quarter."}, {"role": "assistant", "content": "SELECT payment_method, SUM(amount_paid) AS total_amount FROM insurance.premium_payments WHERE payment_date BETWEEN '2023-01-01' AND '2023-03-31' GROUP BY payment_method ORDER BY total_amount DESC;"}, {"role": "user", "content": "I also want to see the average payment amount for each payment method in Q1 2023."}, {"role": "assistant", "content": "SELECT payment_method, AVG(amount_paid) AS average_payment FROM insurance.premium_payments WHERE payment_date BETWEEN '2023-01-01' AND '2023-03-31' GROUP BY payment_method ORDER BY average_payment DESC;"}, {"role": "user", "content": "Finally, show me only payment methods where the average payment was greater than $300."}, {"role": "assistant", "content": "SELECT payment_method, AVG(amount_paid) AS average_payment FROM insurance.premium_payments WHERE payment_date BETWEEN '2023-01-01' AND '2023-03-31' GROUP BY payment_method HAVING AVG(amount_paid) > 300 ORDER BY average_payment 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.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) )\n"} +{"conversations": [{"role": "user", "content": "Display the name and type of each location, as well as the earliest and latest maintenance service_date for vehicles assigned to that location (assuming vehicle_id matches location_id)."}, {"role": "assistant", "content": "SELECT l.name, l.type,\n MIN(m.service_date) AS earliest_service,\n MAX(m.service_date) AS latest_service\nFROM transportation.locations l\nLEFT JOIN transportation.maintenance_logs m ON l.location_id = m.vehicle_id\nGROUP BY l.location_id, l.name, l.type;"}, {"role": "user", "content": "I got an error because some locations do not have any maintenance logs. Please only show locations that have at least one associated maintenance log."}, {"role": "assistant", "content": "SELECT l.name, l.type,\n MIN(m.service_date) AS earliest_service,\n MAX(m.service_date) AS latest_service\nFROM transportation.locations l\nJOIN transportation.maintenance_logs m ON l.location_id = m.vehicle_id\nGROUP BY l.location_id, l.name, l.type;"}, {"role": "user", "content": "Now, include the total cost of all maintenance performed for each location."}, {"role": "assistant", "content": "SELECT l.name, l.type,\n MIN(m.service_date) AS earliest_service,\n MAX(m.service_date) AS latest_service,\n SUM(m.cost) AS total_maintenance_cost\nFROM transportation.locations l\nJOIN transportation.maintenance_logs m ON l.location_id = m.vehicle_id\nGROUP BY l.location_id, l.name, l.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 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.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": "For each chain, find the narrative category that has the highest total market_cap and display the chain, narrative, and that total market_cap."}, {"role": "assistant", "content": "SELECT chain,\n narrative,\n total_cap\nFROM (\n SELECT chain,\n narrative,\n SUM(market_cap) AS total_cap,\n RANK() OVER (PARTITION BY chain ORDER BY SUM(market_cap) DESC) AS rnk\n FROM token_basic_info\n GROUP BY chain, narrative\n) t\nWHERE rnk = 1;"}, {"role": "user", "content": "I received an error about window functions. Can you rewrite the query without using window functions?"}, {"role": "assistant", "content": "WITH agg AS (\n SELECT chain,\n narrative,\n SUM(market_cap) AS total_cap\n FROM token_basic_info\n GROUP BY chain, narrative\n),\nmax_cap AS (\n SELECT chain,\n MAX(total_cap) AS max_cap\n FROM agg\n GROUP BY chain\n)\nSELECT a.chain,\n a.narrative,\n a.total_cap\nFROM agg a\nJOIN max_cap m\n ON a.chain = m.chain\n AND a.total_cap = m.max_cap;"}], "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 )\n"} +{"conversations": [{"role": "user", "content": "Which patients have insurance policies that are effective between May 1st, 2023 and October 1st, 2023? Show their patient_id, policy_number, and effective_date, and also include the related plan_id."}, {"role": "assistant", "content": "SELECT patient_id, policy_number, effective_date, plan_id FROM healthcare.patient_insurance WHERE effective_date >= '2023-05-01' AND effective_date <= '2023-10-01';"}, {"role": "user", "content": "I only want to see policies that are still primary. Could you adjust the query to add that condition?"}, {"role": "assistant", "content": "SELECT patient_id, policy_number, effective_date, plan_id FROM healthcare.patient_insurance WHERE effective_date >= '2023-05-01' AND effective_date <= '2023-10-01' AND is_primary = true;"}, {"role": "user", "content": "Actually, please also show only entries where the subscriber_name starts with the letter 'A'."}, {"role": "assistant", "content": "SELECT patient_id, policy_number, effective_date, plan_id FROM healthcare.patient_insurance WHERE effective_date >= '2023-05-01' AND effective_date <= '2023-10-01' AND is_primary = true AND subscriber_name LIKE 'A%';"}], "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.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": "List all fuel logs where the fuel type is diesel and the quantity is more than 50 liters, including the vehicle ID and total cost."}, {"role": "assistant", "content": "SELECT fuel_log_id, vehicle_id, trip_id, log_timestamp, quantity, total_cost FROM transportation.fuel_logs WHERE fuel_type = 'diesel' AND quantity > 50 AND unit = 'liters';"}, {"role": "user", "content": "Can you also include the trip ID and order the results by the most expensive fuel logs first?"}, {"role": "assistant", "content": "SELECT fuel_log_id, vehicle_id, trip_id, log_timestamp, quantity, total_cost FROM transportation.fuel_logs WHERE fuel_type = 'diesel' AND quantity > 50 AND unit = 'liters' ORDER BY total_cost DESC;"}, {"role": "user", "content": "Now filter these results to only show logs from the last 30 days."}, {"role": "assistant", "content": "SELECT fuel_log_id, vehicle_id, trip_id, log_timestamp, quantity, total_cost FROM transportation.fuel_logs WHERE fuel_type = 'diesel' AND quantity > 50 AND unit = 'liters' AND log_timestamp >= CURRENT_DATE - INTERVAL '30 days' ORDER BY total_cost DESC;"}, {"role": "user", "content": "There seems to be a typo in your SQL - it should be 'INTERVAL' not 'INTERVAL'. Also, can you include the location name where the fueling occurred?"}, {"role": "assistant", "content": "SELECT fl.fuel_log_id, fl.vehicle_id, fl.trip_id, fl.log_timestamp, fl.quantity, fl.total_cost, l.name AS location_name FROM transportation.fuel_logs fl LEFT JOIN transportation.locations l ON fl.location_id = l.location_id WHERE fl.fuel_type = 'diesel' AND fl.quantity > 50 AND fl.unit = 'liters' AND fl.log_timestamp >= CURRENT_DATE - INTERVAL '30 days' ORDER BY fl.total_cost 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 )\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.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.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 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": "List the transaction IDs and gas used for transactions where gas used is greater than 500000."}, {"role": "assistant", "content": "SELECT transaction_id, gas_used FROM web3.transactions WHERE gas_used > 500000;"}, {"role": "user", "content": "Order the results by gas used in descending order."}, {"role": "assistant", "content": "SELECT transaction_id, gas_used FROM web3.transactions WHERE gas_used > 500000 ORDER BY gas_used 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.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.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.users ( user_id text, username text, email text, password_hash text, created_at timestamp )\n"} +{"conversations": [{"role": "user", "content": "Find all contracts where the deployer address is the same as the contract address, indicating self-deployed contracts."}, {"role": "assistant", "content": "SELECT address, deployer_address FROM web3.contracts WHERE address = deployer_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.contracts ( contract_id text, address text, abi text, bytecode text, deployer_address text, deployed_at timestamp, network_id text, status text )\n"} +{"conversations": [{"role": "user", "content": "For each trip, show the trip ID, scheduled departure, and the last name of the driver."}, {"role": "assistant", "content": "SELECT t.trip_id, t.scheduled_departure, d.last_name\nFROM transportation.trips t\nJOIN transportation.drivers d ON t.driver_id = d.driver_id;"}, {"role": "user", "content": "I see some trip IDs are repeated. Only show distinct pairs of trip ID and driver last name."}, {"role": "assistant", "content": "SELECT DISTINCT t.trip_id, d.last_name\nFROM transportation.trips t\nJOIN transportation.drivers d ON t.driver_id = d.driver_id;"}, {"role": "user", "content": "Also, for these trips, include the name of the destination location."}, {"role": "assistant", "content": "SELECT DISTINCT t.trip_id, d.last_name, l.name AS destination_location_name\nFROM transportation.trips t\nJOIN transportation.drivers d ON t.driver_id = d.driver_id\nJOIN transportation.locations l ON t.destination_location_id = l.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 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.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 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.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 ( 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 pairs of tokens where the absolute difference in their decimals is exactly 2, showing both token_ids and their decimals."}, {"role": "assistant", "content": "SELECT t1.token_id AS token_id1,\n t1.decimals AS decimals1,\n t2.token_id AS token_id2,\n t2.decimals AS decimals2\nFROM web3.tokens t1\nJOIN web3.tokens t2\n ON ABS(t1.decimals - t2.decimals) = 2\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 ( token_id text PRIMARY KEY, contract_address text, token_name text, token_symbol text, decimals int, total_supply numeric )\n"} +{"conversations": [{"role": "user", "content": "Show me all intercity routes that have an estimated duration of more than 2 hours, along with their origin and destination locations."}, {"role": "assistant", "content": "SELECT r.route_id, r.route_number, r.estimated_duration_minutes, lo.name AS origin_location, ld.name AS destination_location FROM transportation.routes r JOIN transportation.locations lo ON r.origin_location_id = lo.location_id JOIN transportation.locations ld ON r.destination_location_id = ld.location_id WHERE r.type = 'Intercity Train' AND r.estimated_duration_minutes > 120 ORDER BY r.estimated_duration_minutes DESC;"}, {"role": "user", "content": "Can you include the distance in kilometers and filter to only show routes longer than 100 km?"}, {"role": "assistant", "content": "SELECT r.route_id, r.route_number, r.distance_km, r.estimated_duration_minutes, lo.name AS origin_location, ld.name AS destination_location FROM transportation.routes r JOIN transportation.locations lo ON r.origin_location_id = lo.location_id JOIN transportation.locations ld ON r.destination_location_id = ld.location_id WHERE r.type = 'Intercity Train' AND r.estimated_duration_minutes > 120 AND r.distance_km > 100 ORDER BY r.distance_km DESC;"}, {"role": "user", "content": "Now show me the average passenger count for trips on these routes in the last month."}, {"role": "assistant", "content": "SELECT r.route_id, r.route_number, AVG(t.passenger_count) AS average_passengers FROM transportation.routes r JOIN transportation.trips t ON r.route_id = t.route_id WHERE r.type = 'Intercity Train' AND r.estimated_duration_minutes > 120 AND r.distance_km > 100 AND t.actual_departure >= (CURRENT_DATE - INTERVAL '1 month') GROUP BY r.route_id, r.route_number ORDER BY average_passengers 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 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 (\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 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 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 (\n log_id character varying(64) NOT NULL, -- unique identifier for the maintenance record\n vehicle_id character varying(64) NOT NULL, -- identifier of the vehicle serviced\n service_date date NOT NULL, -- date the service was performed\n odometer_reading integer, -- vehicle mileage at time of service\n service_type character varying(128) NOT NULL, -- type of service (e.g., Oil Change, Tire Rotation, Engine Repair)\n description text NOT NULL, -- detailed description of work done\n cost numeric(10, 2), -- cost of the service\n mechanic_name character varying(128), -- name or ID of the mechanic/shop\n next_service_due_date date, -- recommended date for next service\n PRIMARY KEY (log_id)\n)\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 (\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 wallet addresses that have unspent UTXOs with amounts greater than 100, along with the total unspent amount for each address."}, {"role": "assistant", "content": "SELECT w.address, SUM(u.amount) AS total_unspent FROM trading_platform.wallets w JOIN trading_platform.utxos u ON w.address = u.address WHERE u.spent = false AND u.amount > 100 GROUP BY w.address;"}, {"role": "user", "content": "Now modify the query to only include wallets created in the last year."}, {"role": "assistant", "content": "SELECT w.address, SUM(u.amount) AS total_unspent FROM trading_platform.wallets w JOIN trading_platform.utxos u ON w.address = u.address WHERE u.spent = false AND u.amount > 100 AND w.created_at >= NOW() - INTERVAL '1 year' GROUP BY w.address;"}, {"role": "user", "content": "I notice the query has a typo in 'INTERVAL'. Also, can you include the user's email address in the results?"}, {"role": "assistant", "content": "SELECT w.address, u.email, SUM(ut.amount) AS total_unspent FROM trading_platform.wallets w JOIN trading_platform.users u ON w.user_id = u.user_id JOIN trading_platform.utxos ut ON w.address = ut.address WHERE ut.spent = false AND ut.amount > 100 AND w.created_at >= NOW() - INTERVAL '1 year' GROUP BY w.address, u.email;"}], "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 PRIMARY KEY, username text, email text, password_hash text, created_at timestamp )\nCREATE TABLE trading_platform.wallets ( wallet_id text PRIMARY KEY, user_id text, address text, private_key text, created_at timestamp )\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.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": "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": "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": "Find all prescriptions for patients who have at least one appointment scheduled in the future. Show the prescription ID, patient ID, medication name, and the earliest future appointment time for that patient."}, {"role": "assistant", "content": "SELECT pr.prescription_id, pr.patient_id, m.medication_name, ( SELECT MIN(ap.appointment_time) FROM healthcare.appointments AS ap WHERE ap.patient_id = p.patient_id AND ap.appointment_time > CURRENT_TIMESTAMP ) AS earliest_future_appointment_time FROM healthcare.prescriptions AS pr JOIN healthcare.patients AS p ON pr.patient_id = p.patient_id JOIN healthcare.medications AS m ON pr.medication_id = m.medication_id WHERE p.patient_id IN ( SELECT patient_id FROM healthcare.appointments WHERE appointment_time > CURRENT_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 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.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.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.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 all active customers from California who were born before 1980, along with their contact information."}, {"role": "assistant", "content": "SELECT first_name, last_name, phone_number, email, address_line1, address_line2, city, state, zip_code FROM insurance.customers WHERE state = 'California' AND date_of_birth < '1980-01-01' AND status = 'Active';"}, {"role": "user", "content": "Now filter these results to only show customers who have provided both a phone number and an email address."}, {"role": "assistant", "content": "SELECT first_name, last_name, phone_number, email, address_line1, address_line2, city, state, zip_code FROM insurance.customers WHERE state = 'California' AND date_of_birth < '1980-01-01' AND status = 'Active' AND phone_number IS NOT NULL AND email IS NOT NULL;"}, {"role": "user", "content": "I also want to see how long these customers have been in our system (difference between current date and created_at in years)."}, {"role": "assistant", "content": "SELECT first_name, last_name, phone_number, email, address_line1, address_line2, city, state, zip_code, EXTRACT(YEAR FROM AGE(CURRENT_DATE, created_at)) AS years_in_system FROM insurance.customers WHERE state = 'California' AND date_of_birth < '1980-01-01' AND status = 'Active' AND phone_number IS NOT NULL AND email IS NOT NULL;"}, {"role": "user", "content": "Finally, order the results by the longest tenure in our system first, then by last name alphabetically."}, {"role": "assistant", "content": "SELECT first_name, last_name, phone_number, email, address_line1, address_line2, city, state, zip_code, EXTRACT(YEAR FROM AGE(CURRENT_DATE, created_at)) AS years_in_system FROM insurance.customers WHERE state = 'California' AND date_of_birth < '1980-01-01' AND status = 'Active' AND phone_number IS NOT NULL AND email IS NOT NULL ORDER BY years_in_system DESC, last_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 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": "List all medical record IDs and the record date for records created by doctors specializing in 'Gastroenterology'."}, {"role": "assistant", "content": "SELECT mr.record_id, mr.record_date FROM healthcare.medical_records mr JOIN healthcare.doctors d ON mr.doctor_id = d.doctor_id WHERE d.specialty = 'Gastroenterology';"}, {"role": "user", "content": "Could you also include the patient's first and last name for these records?"}, {"role": "assistant", "content": "SELECT mr.record_id, mr.record_date, p.first_name, p.last_name FROM healthcare.medical_records mr JOIN healthcare.doctors d ON mr.doctor_id = d.doctor_id JOIN healthcare.patients p ON mr.patient_id = p.patient_id WHERE d.specialty = 'Gastroenterology';"}, {"role": "user", "content": "Now, only show records for male patients."}, {"role": "assistant", "content": "SELECT mr.record_id, mr.record_date, p.first_name, p.last_name FROM healthcare.medical_records mr JOIN healthcare.doctors d ON mr.doctor_id = d.doctor_id JOIN healthcare.patients p ON mr.patient_id = p.patient_id WHERE d.specialty = 'Gastroenterology' AND p.gender = 'Male';"}, {"role": "user", "content": "Additionally, restrict the results to medical records that have at least one associated diagnosis with status 'Resolved'."}, {"role": "assistant", "content": "SELECT DISTINCT mr.record_id, mr.record_date, p.first_name, p.last_name FROM healthcare.medical_records mr JOIN healthcare.doctors d ON mr.doctor_id = d.doctor_id JOIN healthcare.patients p ON mr.patient_id = p.patient_id JOIN healthcare.diagnoses diag ON mr.record_id = diag.record_id WHERE d.specialty = 'Gastroenterology' AND p.gender = 'Male' AND diag.status = 'Resolved';"}], "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 ( 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.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.prescriptions ( prescription_id character varying(64) NOT NULL, record_id character varying(64) NOT NULL, patient_id character varying(64) NOT NULL, doctor_id character varying(64) NOT NULL, medication_id character varying(64) NOT NULL, dosage character varying(100) NOT NULL, frequency character varying(100) NOT NULL, route character varying(50), start_date date NOT NULL, end_date date, quantity_dispensed numeric(10,2), refills_allowed integer NOT NULL DEFAULT 0, prescription_date timestamp with time zone NOT NULL DEFAULT current_timestamp, PRIMARY KEY (prescription_id) )\nCREATE TABLE healthcare.insurance_plans ( plan_id character varying(64) NOT NULL, plan_name character varying(200) NOT NULL, insurance_provider character varying(100) NOT NULL, plan_type character varying(50), contact_phone character varying(20), website character varying(255), PRIMARY KEY (plan_id) )\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": "How many unique tokens are recorded for each chain in the latest snapshot in cex_token_balance?"}, {"role": "assistant", "content": "WITH latest_snapshot AS (\n SELECT MAX(snapshot_time) AS max_time FROM cex_token_balance\n)\nSELECT \n chain, \n COUNT(DISTINCT token_symbol) AS unique_token_count\nFROM cex_token_balance c\nJOIN latest_snapshot l ON c.snapshot_time = l.max_time\nGROUP BY chain\nORDER BY unique_token_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 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 )\n"} +{"conversations": [{"role": "user", "content": "Show me all pairs of cases led by the same lawyer, including both case names and the lead lawyer ID."}, {"role": "assistant", "content": "SELECT c1.lead_lawyer_id,\n c1.case_name AS case_name_1,\n c2.case_name AS case_name_2\nFROM legal_services.cases c1\nJOIN legal_services.cases c2\n ON c1.lead_lawyer_id = c2.lead_lawyer_id\n AND c1.case_id < c2.case_id;"}, {"role": "user", "content": "Actually, only include pairs where the case types are also the same."}, {"role": "assistant", "content": "SELECT c1.lead_lawyer_id,\n c1.case_name AS case_name_1,\n c2.case_name AS case_name_2\nFROM legal_services.cases c1\nJOIN legal_services.cases c2\n ON c1.lead_lawyer_id = c2.lead_lawyer_id\n AND c1.case_type = c2.case_type\n AND c1.case_id < c2.case_id;"}, {"role": "user", "content": "Also, show me the earliest opening date between the two cases for each pair."}, {"role": "assistant", "content": "SELECT c1.lead_lawyer_id,\n c1.case_name AS case_name_1,\n c2.case_name AS case_name_2,\n LEAST(c1.date_opened, c2.date_opened) AS earliest_open_date\nFROM legal_services.cases c1\nJOIN legal_services.cases c2\n ON c1.lead_lawyer_id = c2.lead_lawyer_id\n AND c1.case_type = c2.case_type\n AND c1.case_id < c2.case_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.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 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 $0.1."}, {"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 > 0.1 ORDER BY CAST(tm.total_supply AS decimal) DESC LIMIT 5;"}, {"role": "user", "content": "I think there's an error in your query - it should be 'tpl.symbol' not 'tm.symbol'. Also, can you add the decimals to the results?"}, {"role": "assistant", "content": "SELECT tm.name, tm.contract_address, tm.decimals, tm.total_supply, tpl.symbol, 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 > 0.1 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.contract_address, tm.decimals, tm.total_supply, tpl.symbol, 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 > 0.1 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, 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 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_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 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_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 token_prices ( uuid varchar, blockchain varchar, address varchar, decimals bigint, symbol varchar, price real, timestamp timestamp )\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_balances ( block_number bigint, block_timestamp timestamp, tick varchar, wallet_address varchar, total_supply decimal, amount decimal )\nCREATE TABLE token_info ( 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 ( 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_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 ( block_number bigint, block_timestamp timestamp, tick varchar, wallet_address varchar, total_supply decimal, amount decimal )\n"} +{"conversations": [{"role": "user", "content": "Show the name, description, and URL for all DApps."}, {"role": "assistant", "content": "SELECT name, description, url FROM trading_platform.dapps;"}], "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.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.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)\n"} +{"conversations": [{"role": "user", "content": "Find pairs of insurance plans that are offered by the same insurance provider. Show the provider name, and the names of the two plans."}, {"role": "assistant", "content": "SELECT p1.insurance_provider, p1.plan_name, p2.plan_name FROM healthcare.insurance_plans p1 JOIN healthcare.insurance_plans p2 ON p1.insurance_provider = p2.insurance_provider AND p1.plan_id < p2.plan_id ORDER BY p1.insurance_provider, p1.plan_name;"}, {"role": "user", "content": "Only show pairs where the provider name starts with 'B'."}, {"role": "assistant", "content": "SELECT p1.insurance_provider, p1.plan_name, p2.plan_name FROM healthcare.insurance_plans p1 JOIN healthcare.insurance_plans p2 ON p1.insurance_provider = p2.insurance_provider AND p1.plan_id < p2.plan_id WHERE p1.insurance_provider LIKE 'B%' ORDER BY p1.insurance_provider, p1.plan_name;"}, {"role": "user", "content": "Further filter to include only pairs where both plans have a website listed."}, {"role": "assistant", "content": "SELECT p1.insurance_provider, p1.plan_name, p2.plan_name FROM healthcare.insurance_plans p1 JOIN healthcare.insurance_plans p2 ON p1.insurance_provider = p2.insurance_provider AND p1.plan_id < p2.plan_id WHERE p1.insurance_provider LIKE 'B%' AND p1.website IS NOT NULL AND p2.website IS NOT NULL ORDER BY p1.insurance_provider, p1.plan_name;"}, {"role": "user", "content": "Also, include the plan type for both plans in the result."}, {"role": "assistant", "content": "SELECT p1.insurance_provider, p1.plan_name, p1.plan_type, p2.plan_name, p2.plan_type FROM healthcare.insurance_plans p1 JOIN healthcare.insurance_plans p2 ON p1.insurance_provider = p2.insurance_provider AND p1.plan_id < p2.plan_id WHERE p1.insurance_provider LIKE 'B%' AND p1.website IS NOT NULL AND p2.website IS NOT NULL ORDER BY p1.insurance_provider, p1.plan_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 healthcare.insurance_plans ( plan_id character varying(64) NOT NULL, plan_name character varying(200) NOT NULL, insurance_provider character varying(100) NOT NULL, plan_type character varying(50), contact_phone character varying(20), website character varying(255), PRIMARY KEY (plan_id) )\n"} +{"conversations": [{"role": "user", "content": "How many distinct posts does each hashtag appear in?"}, {"role": "assistant", "content": "SELECT hashtag_id, COUNT(DISTINCT post_id) AS post_count FROM social_media.post_hashtags GROUP BY hashtag_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 social_media.post_hashtags ( post_hashtag_id.text, post_id.text, hashtag_id.text )\n"} +{"conversations": [{"role": "user", "content": "How many lawyers are there in each specialization?"}, {"role": "assistant", "content": "SELECT specialization, COUNT(*) AS lawyer_count\nFROM legal_services.lawyers\nGROUP BY specialization;"}, {"role": "user", "content": "Only include specializations with more than 5 lawyers."}, {"role": "assistant", "content": "SELECT specialization, COUNT(*) AS lawyer_count\nFROM legal_services.lawyers\nGROUP BY specialization\nHAVING COUNT(*) > 5;"}, {"role": "user", "content": "Also display the average years since hire for each specialization."}, {"role": "assistant", "content": "SELECT specialization,\n COUNT(*) AS lawyer_count,\n AVG(EXTRACT(YEAR FROM AGE(CURRENT_DATE, hire_date)))::numeric(5,2) AS avg_years_since_hire\nFROM legal_services.lawyers\nGROUP BY specialization\nHAVING COUNT(*) > 5;"}, {"role": "user", "content": "Sort the results by lawyer_count descending and limit to the top 3 specializations."}, {"role": "assistant", "content": "SELECT specialization,\n COUNT(*) AS lawyer_count,\n AVG(EXTRACT(YEAR FROM AGE(CURRENT_DATE, hire_date)))::numeric(5,2) AS avg_years_since_hire\nFROM legal_services.lawyers\nGROUP BY specialization\nHAVING COUNT(*) > 5\nORDER BY lawyer_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 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": "Please list all doctors and their specialties, along with the phone numbers of any other doctors who share the same specialty."}, {"role": "assistant", "content": "SELECT d1.doctor_id, d1.first_name, d1.last_name, d1.specialty, d2.phone_number AS colleague_phone_number\nFROM healthcare.doctors d1\nJOIN healthcare.doctors d2 ON d1.specialty = d2.specialty AND d1.doctor_id <> d2.doctor_id\nORDER BY d1.specialty, d1.doctor_id;"}, {"role": "user", "content": "Can you update the query to only include specialties where there are more than 2 doctors sharing the same specialty?"}, {"role": "assistant", "content": "WITH specialty_counts AS (\n SELECT specialty, COUNT(*) AS cnt FROM healthcare.doctors GROUP BY specialty HAVING COUNT(*) > 2\n)\nSELECT d1.doctor_id, d1.first_name, d1.last_name, d1.specialty, d2.phone_number AS colleague_phone_number\nFROM healthcare.doctors d1\nJOIN healthcare.doctors d2 ON d1.specialty = d2.specialty AND d1.doctor_id <> d2.doctor_id\nJOIN specialty_counts sc ON d1.specialty = sc.specialty\nORDER BY d1.specialty, d1.doctor_id;"}, {"role": "user", "content": "Sorry, I got too many duplicate pairs. Can you adjust it to only show each unique pair of doctors per specialty once (doctor_id1 < doctor_id2)?"}, {"role": "assistant", "content": "WITH specialty_counts AS (\n SELECT specialty, COUNT(*) AS cnt FROM healthcare.doctors GROUP BY specialty HAVING COUNT(*) > 2\n)\nSELECT d1.specialty, d1.doctor_id AS doctor_id1, d1.first_name AS first_name1, d1.last_name AS last_name1, d1.phone_number AS phone1,\n d2.doctor_id AS doctor_id2, d2.first_name AS first_name2, d2.last_name AS last_name2, d2.phone_number AS phone2\nFROM healthcare.doctors d1\nJOIN healthcare.doctors d2 ON d1.specialty = d2.specialty AND d1.doctor_id < d2.doctor_id\nJOIN specialty_counts sc ON d1.specialty = sc.specialty\nORDER BY d1.specialty, d1.doctor_id1, d2.doctor_id2;"}], "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 )\n"} +{"conversations": [{"role": "user", "content": "List pairs of maintenance logs for the same vehicle where the service date is the same, showing the log IDs and service types."}, {"role": "assistant", "content": "SELECT T1.log_id AS log_id_1, T1.service_type AS service_type_1, T2.log_id AS log_id_2, T2.service_type AS service_type_2, T1.vehicle_id, T1.service_date FROM transportation.maintenance_logs AS T1 JOIN transportation.maintenance_logs AS T2 ON T1.vehicle_id = T2.vehicle_id AND T1.service_date = T2.service_date AND T1.log_id < T2.log_id;"}, {"role": "user", "content": "Filter this list to only include pairs where at least one of the logs has a cost greater than 500."}, {"role": "assistant", "content": "SELECT T1.log_id AS log_id_1, T1.service_type AS service_type_1, T2.log_id AS log_id_2, T2.service_type AS service_type_2, T1.vehicle_id, T1.service_date FROM transportation.maintenance_logs AS T1 JOIN transportation.maintenance_logs AS T2 ON T1.vehicle_id = T2.vehicle_id AND T1.service_date = T2.service_date AND T1.log_id < T2.log_id WHERE T1.cost > 500 OR T2.cost > 500;"}], "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.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) )\n"} +{"conversations": [{"role": "user", "content": "Which projects raised funds in January 2022?"}, {"role": "assistant", "content": "SELECT project_name, rounds_name, investment_value, investment_date FROM project_fundraising_record WHERE investment_date >= '2022-01-01' AND investment_date < '2022-02-01';"}, {"role": "user", "content": "Please also show their introductions."}, {"role": "assistant", "content": "SELECT project_name, rounds_name, investment_value, investment_date, introduction FROM project_fundraising_record WHERE investment_date >= '2022-01-01' AND investment_date < '2022-02-01';"}], "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 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": "Show me the number of service orders placed for each service category."}, {"role": "assistant", "content": "SELECT s.category, COUNT(so.order_id) AS order_count\nFROM hospitality_technology.service_orders so\nJOIN hospitality_technology.services s ON so.service_id = s.service_id\nGROUP BY s.category;"}, {"role": "user", "content": "Only include categories with more than 10 orders and order by order_count descending."}, {"role": "assistant", "content": "SELECT s.category, COUNT(so.order_id) AS order_count\nFROM hospitality_technology.service_orders so\nJOIN hospitality_technology.services s ON so.service_id = s.service_id\nGROUP BY s.category\nHAVING COUNT(so.order_id) > 10\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 PRIMARY KEY, 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 int, num_children int, 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.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 text PRIMARY KEY, reservation_id text, guest_id text, service_id text, staff_id_ordered text, staff_id_delivered text, order_timestamp timestamp, delivery_timestamp timestamp, quantity int, unit_price numeric, total_price numeric, status text, notes text, bill_id 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": "Calculate the total billable hours spent by each lawyer for entries in March 2024."}, {"role": "assistant", "content": "SELECT lawyer_id,\n SUM(hours_spent) AS total_hours\nFROM legal_services.time_entries\nWHERE is_billable = TRUE\n AND date_worked BETWEEN '2024-03-01' AND '2024-03-31'\nGROUP BY lawyer_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 (\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 username and the total number of notifications each user has received, and also count how many of those are still unread."}, {"role": "assistant", "content": "SELECT u.username,\n COUNT(n.notification_id) AS total_notifications,\n SUM(CASE WHEN n.read_at IS NULL THEN 1 ELSE 0 END) AS unread_notifications\nFROM trading_platform.users u\nLEFT JOIN trading_platform.notifications n\n ON u.user_id = n.user_id\nGROUP BY u.username;"}, {"role": "user", "content": "Actually, limit it to notifications sent in the last 7 days and only show users with at least 1 unread notification."}, {"role": "assistant", "content": "SELECT u.username,\n COUNT(n.notification_id) AS total_notifications,\n SUM(CASE WHEN n.read_at IS NULL THEN 1 ELSE 0 END) AS unread_notifications\nFROM trading_platform.users u\nLEFT JOIN trading_platform.notifications n\n ON u.user_id = n.user_id\n AND n.sent_at >= NOW() - INTERVAL '7 days'\nGROUP BY u.username\nHAVING SUM(CASE WHEN n.read_at IS NULL THEN 1 ELSE 0 END) > 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 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.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.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 character varying(64) NOT NULL, user_id character varying(64), action character varying(128) NOT NULL, details text NOT NULL, logged_at timestamp NOT NULL, PRIMARY KEY (log_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": "List all policies where the premium_amount exceeds the base_premium of its insurance product. Display the policy_number, premium_amount, product_name, and base_premium. Sort the results by premium_amount descending."}, {"role": "assistant", "content": "SELECT p.policy_number, p.premium_amount, ip.product_name, ip.base_premium\nFROM insurance.policies p\nJOIN insurance.insurance_products ip ON p.product_id = ip.product_id\nORDER BY p.premium_amount DESC;"}, {"role": "user", "content": "Actually, I only want policies that are active and whose insurance products are also active."}, {"role": "assistant", "content": "SELECT p.policy_number, p.premium_amount, ip.product_name, ip.base_premium\nFROM insurance.policies p\nJOIN insurance.insurance_products ip ON p.product_id = ip.product_id\nWHERE p.status = 'active'\n AND ip.is_active = TRUE\nORDER BY p.premium_amount DESC;"}, {"role": "user", "content": "Also, limit the output to policies with a coverage_limit greater than 1000000."}, {"role": "assistant", "content": "SELECT p.policy_number, p.premium_amount, ip.product_name, ip.base_premium\nFROM insurance.policies p\nJOIN insurance.insurance_products ip ON p.product_id = ip.product_id\nWHERE p.status = 'active'\n AND ip.is_active = TRUE\n AND p.coverage_limit > 1000000\nORDER BY p.premium_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 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 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 )\nCREATE TABLE insurance.claims ( claim_id text PRIMARY KEY, 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 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 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.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 )\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": "List the top 5 most used services across all properties. Show service_name and total quantity ordered, ordered by quantity descending."}, {"role": "assistant", "content": "SELECT s.service_name,\n SUM(o.quantity) AS total_quantity\nFROM hospitality_technology.services s\nJOIN hospitality_technology.service_orders o ON s.service_id = o.service_id\nGROUP BY s.service_name\nORDER BY total_quantity DESC\nLIMIT 5;"}, {"role": "user", "content": "Now filter those to only include services in the 'Food & Beverage' category and sort by total_quantity descending."}, {"role": "assistant", "content": "SELECT s.service_name,\n SUM(o.quantity) AS total_quantity\nFROM hospitality_technology.services s\nJOIN hospitality_technology.service_orders o ON s.service_id = o.service_id\nWHERE s.category = 'Food & Beverage'\nGROUP BY s.service_name\nORDER BY total_quantity 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 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.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) )\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 all achievements (name and ID) that have not been unlocked by any player."}, {"role": "assistant", "content": "SELECT a.achievement_id, a.name FROM gaming_technology.achievements a LEFT JOIN gaming_technology.player_achievements pa ON a.achievement_id = pa.achievement_id WHERE pa.player_achievement_id IS NULL;"}, {"role": "user", "content": "Also include the points for these achievements."}, {"role": "assistant", "content": "SELECT a.achievement_id, a.name, a.points FROM gaming_technology.achievements a LEFT JOIN gaming_technology.player_achievements pa ON a.achievement_id = pa.achievement_id WHERE pa.player_achievement_id IS NULL;"}, {"role": "user", "content": "Order the results by points in descending order."}, {"role": "assistant", "content": "SELECT a.achievement_id, a.name, a.points FROM gaming_technology.achievements a LEFT JOIN gaming_technology.player_achievements pa ON a.achievement_id = pa.achievement_id WHERE pa.player_achievement_id IS NULL ORDER BY a.points DESC;"}, {"role": "user", "content": "Only show achievements with points greater than 0."}, {"role": "assistant", "content": "SELECT a.achievement_id, a.name, a.points FROM gaming_technology.achievements a LEFT JOIN gaming_technology.player_achievements pa ON a.achievement_id = pa.achievement_id WHERE pa.player_achievement_id IS NULL AND a.points > 0 ORDER BY a.points 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.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.timestamptz )\nCREATE TABLE gaming_technology.player_inventory ( inventory_id.uuid, player_id.uuid, item_id.uuid, quantity.integer, acquired_at.timestamptz, instance_data.jsonb )\n"} +{"conversations": [{"role": "user", "content": "Show me the top 5 NFT collections with the highest number of unique owners, along with their names and contract addresses."}, {"role": "assistant", "content": "SELECT nc.name, nc.contract_address, COUNT(DISTINCT nh.wallet_address) AS unique_owners FROM nft_collections nc JOIN nft_holders nh ON nc.contract_address = nh.contract_address GROUP BY nc.name, nc.contract_address ORDER BY unique_owners DESC LIMIT 5;"}, {"role": "user", "content": "Can you modify the query to also include the floor price and filter to only show collections with more than 1000 unique owners?"}, {"role": "assistant", "content": "SELECT nc.name, nc.contract_address, nc.floor_price, COUNT(DISTINCT nh.wallet_address) AS unique_owners FROM nft_collections nc JOIN nft_holders nh ON nc.contract_address = nh.contract_address GROUP BY nc.name, nc.contract_address, nc.floor_price HAVING COUNT(DISTINCT nh.wallet_address) > 1000 ORDER BY unique_owners DESC LIMIT 5;"}, {"role": "user", "content": "Now 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, COUNT(DISTINCT nh.wallet_address) AS unique_owners, AVG(nm.rarity_score) AS avg_rarity_score FROM nft_collections nc JOIN nft_holders nh ON nc.contract_address = nh.contract_address JOIN nft_metadata nm ON nc.contract_address = nm.contract_address GROUP BY nc.name, nc.contract_address, nc.floor_price HAVING COUNT(DISTINCT nh.wallet_address) > 1000 ORDER BY unique_owners 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 erc20_balances_historical ( block_number bigint, contract_address varchar, wallet_address varchar, amount varchar, pk integer )\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 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_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_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 ( uuid varchar, blockchain varchar, address varchar, decimals bigint, symbol varchar, price real, timestamp timestamp )\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_info ( 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 ( 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_balances_avalanche ( block_number bigint, block_timestamp timestamp, tick varchar, wallet_address varchar, total_supply decimal, amount decimal )\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 user, show their username and the total number of completed orders they have placed, along with the name of the asset for each order."}, {"role": "assistant", "content": "SELECT u.username, a.name AS asset_name, COUNT(o.order_id) AS completed_order_count\nFROM trading_platform.users u\nJOIN trading_platform.orders o ON u.user_id = o.user_id\nJOIN trading_platform.assets a ON o.asset_id = a.asset_id\nWHERE o.status = 'completed'\nGROUP BY u.username, a.name;"}, {"role": "user", "content": "Actually, only show users who have completed orders for more than one different asset. Please also include their email in the results."}, {"role": "assistant", "content": "SELECT u.username, u.email, COUNT(DISTINCT o.asset_id) AS asset_count\nFROM trading_platform.users u\nJOIN trading_platform.orders o ON u.user_id = o.user_id\nWHERE o.status = 'completed'\nGROUP BY u.username, u.email\nHAVING COUNT(DISTINCT o.asset_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 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": "Show me all active customers from California who were born before 1980, along with their contact information."}, {"role": "assistant", "content": "SELECT first_name, last_name, phone_number, email, address_line1, city, zip_code FROM insurance.customers WHERE state = 'California' AND date_of_birth < '1980-01-01' AND status = 'Active';"}, {"role": "user", "content": "Now filter these results to only show customers who have provided both a phone number and an email address."}, {"role": "assistant", "content": "SELECT first_name, last_name, phone_number, email, address_line1, city, zip_code FROM insurance.customers WHERE state = 'California' AND date_of_birth < '1980-01-01' AND status = 'Active' AND phone_number IS NOT NULL AND email IS NOT NULL;"}, {"role": "user", "content": "I also want to see how long these customers have been in our system (difference between current date and created_at in years)."}, {"role": "assistant", "content": "SELECT first_name, last_name, phone_number, email, address_line1, city, zip_code, EXTRACT(YEAR FROM AGE(CURRENT_DATE, created_at)) AS years_in_system FROM insurance.customers WHERE state = 'California' AND date_of_birth < '1980-01-01' AND status = 'Active' AND phone_number IS NOT NULL AND email IS NOT NULL;"}, {"role": "user", "content": "Finally, order the results by the longest tenure in our system first, then by last name alphabetically."}, {"role": "assistant", "content": "SELECT first_name, last_name, phone_number, email, address_line1, city, zip_code, EXTRACT(YEAR FROM AGE(CURRENT_DATE, created_at)) AS years_in_system FROM insurance.customers WHERE state = 'California' AND date_of_birth < '1980-01-01' AND status = 'Active' AND phone_number IS NOT NULL AND email IS NOT NULL ORDER BY years_in_system DESC, last_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 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": "Find pairs of insurance policies where the plan_id is the same, but they belong to different patients. Show the plan_id, and the patient_id and policy_number for both policies in the pair."}, {"role": "assistant", "content": "SELECT T1.plan_id, T1.patient_id AS patient_id_1, T1.policy_number AS policy_number_1, T2.patient_id AS patient_id_2, T2.policy_number AS policy_number_2 FROM healthcare.patient_insurance AS T1 JOIN healthcare.patient_insurance AS T2 ON T1.plan_id = T2.plan_id WHERE T1.patient_id <> T2.patient_id AND T1.patient_insurance_id < T2.patient_insurance_id;"}, {"role": "user", "content": "Refine this to only include policies that are currently active (expiration_date IS NULL or > CURRENT_DATE) for both policies in the pair."}, {"role": "assistant", "content": "SELECT T1.plan_id, T1.patient_id AS patient_id_1, T1.policy_number AS policy_number_1, T2.patient_id AS patient_id_2, T2.policy_number AS policy_number_2 FROM healthcare.patient_insurance AS T1 JOIN healthcare.patient_insurance AS T2 ON T1.plan_id = T2.plan_id WHERE T1.patient_id <> T2.patient_id AND T1.patient_insurance_id < T2.patient_insurance_id AND (T1.expiration_date IS NULL OR T1.expiration_date > CURRENT_DATE) AND (T2.expiration_date IS NULL OR T2.expiration_date > CURRENT_DATE);"}, {"role": "user", "content": "Also, only show pairs where one policy is primary and the other is not primary (is_primary = TRUE for one, is_primary = FALSE for the other)."}, {"role": "assistant", "content": "SELECT T1.plan_id, T1.patient_id AS patient_id_1, T1.policy_number AS policy_number_1, T2.patient_id AS patient_id_2, T2.policy_number AS policy_number_2 FROM healthcare.patient_insurance AS T1 JOIN healthcare.patient_insurance AS T2 ON T1.plan_id = T2.plan_id WHERE T1.patient_id <> T2.patient_id AND T1.patient_insurance_id < T2.patient_insurance_id AND (T1.expiration_date IS NULL OR T1.expiration_date > CURRENT_DATE) AND (T2.expiration_date IS NULL OR T2.expiration_date > CURRENT_DATE) AND ((T1.is_primary = TRUE AND T2.is_primary = FALSE) OR (T1.is_primary = FALSE AND T2.is_primary = TRUE));"}, {"role": "user", "content": "Filter further to only show pairs where the shared plan_id starts with 'HMO'."}, {"role": "assistant", "content": "SELECT T1.plan_id, T1.patient_id AS patient_id_1, T1.policy_number AS policy_number_1, T2.patient_id AS patient_id_2, T2.policy_number AS policy_number_2 FROM healthcare.patient_insurance AS T1 JOIN healthcare.patient_insurance AS T2 ON T1.plan_id = T2.plan_id WHERE T1.patient_id <> T2.patient_id AND T1.patient_insurance_id < T2.patient_insurance_id AND (T1.expiration_date IS NULL OR T1.expiration_date > CURRENT_DATE) AND (T2.expiration_date IS NULL OR T2.expiration_date > CURRENT_DATE) AND ((T1.is_primary = TRUE AND T2.is_primary = FALSE) OR (T1.is_primary = FALSE AND T2.is_primary = TRUE)) AND T1.plan_id LIKE 'HMO%';"}], "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.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 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": "Show me the total transaction amount sent by each sender address, along with their current balance from the addresses table."}, {"role": "assistant", "content": "SELECT t.sender_address, SUM(t.amount) AS total_sent, a.balance FROM blockchain.transactions t JOIN blockchain.addresses a ON t.sender_address = a.address_id GROUP BY t.sender_address, a.balance;"}, {"role": "user", "content": "Now filter this to only show sender addresses that have sent more than 1000 in total and have a balance greater than 500."}, {"role": "assistant", "content": "SELECT t.sender_address, SUM(t.amount) AS total_sent, a.balance FROM blockchain.transactions t JOIN blockchain.addresses a ON t.sender_address = a.address_id GROUP BY t.sender_address, a.balance HAVING SUM(t.amount) > 1000 AND a.balance > 500;"}], "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 PRIMARY KEY, previous_block_id text, timestamp timestamp, nonce int, merkle_root text, difficulty int )\nCREATE TABLE blockchain.transactions ( transaction_id text PRIMARY KEY, block_id text, sender_address text, receiver_address text, amount numeric, timestamp timestamp, signature text )\nCREATE TABLE blockchain.addresses ( address_id text PRIMARY KEY, public_key text, balance numeric )\nCREATE TABLE blockchain.nodes ( node_id text PRIMARY KEY, ip_address text, port int, last_seen timestamp )\nCREATE TABLE blockchain.users ( user_id text PRIMARY KEY, username text, email text, password_hash text )\nCREATE TABLE blockchain.smart_contracts ( contract_id text PRIMARY KEY, creator_address text, code text, timestamp timestamp )\n"} +{"conversations": [{"role": "user", "content": "Show all claims and the full name of the customer who filed each claim."}, {"role": "assistant", "content": "SELECT T1.claim_id, T1.incident_date, T1.description, T2.first_name, T2.last_name FROM insurance.claims AS T1 JOIN insurance.customers AS T2 ON T1.customer_id = T2.customer_id"}, {"role": "user", "content": "Can you also include the ID of the claim handler for each claim?"}, {"role": "assistant", "content": "SELECT T1.claim_id, T1.incident_date, T1.description, T2.first_name, T2.last_name, T1.claim_handler_id FROM insurance.claims AS T1 JOIN insurance.customers AS T2 ON T1.customer_id = T2.customer_id"}, {"role": "user", "content": "Actually, only show claims with status 'Open' and an estimated loss greater than $10,000."}, {"role": "assistant", "content": "SELECT T1.claim_id, T1.incident_date, T1.description, T2.first_name, T2.last_name, T1.claim_handler_id FROM insurance.claims AS T1 JOIN insurance.customers AS T2 ON T1.customer_id = T2.customer_id WHERE T1.status = 'Open' AND T1.estimated_loss > 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 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.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.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.policy_beneficiaries (\n beneficiary_id character varying(64) NOT NULL, -- unique identifier for the beneficiary entry\n policy_id character varying(64) NOT NULL, -- identifier of the life/relevant policy (FK to policies)\n customer_id character varying(64) NOT NULL, -- identifier of the beneficiary (could be FK to customers or store info directly)\n first_name character varying(100) NOT NULL, -- beneficiary first name (if not linking to customers table)\n last_name character varying(100) NOT NULL, -- beneficiary last name\n relationship character varying(50) NOT NULL, -- relationship to the policyholder (e.g., Spouse, Child, Parent)\n percentage_share numeric(5, 2) NOT NULL CHECK (percentage_share > 0 AND percentage_share <= 100), -- percentage of payout\n contact_info text, -- contact details for the beneficiary\n added_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP,\n PRIMARY KEY (beneficiary_id),\n UNIQUE (policy_id, customer_id) -- Ensure a person is listed only once per policy\n)\n"} +{"conversations": [{"role": "user", "content": "Find all pairs of distinct medications manufactured by the same company, showing med1.medication_id, med1.medication_name, med2.medication_id, med2.medication_name, and the manufacturer."}, {"role": "assistant", "content": "SELECT m1.medication_id AS med1_id, m1.medication_name AS med1_name, m2.medication_id AS med2_id, m2.medication_name AS med2_name, m1.manufacturer\nFROM healthcare.medications m1\nJOIN healthcare.medications m2\n ON m1.manufacturer = m2.manufacturer\n AND m1.medication_id <> m2.medication_id;"}, {"role": "user", "content": "Actually, exclude duplicate pairs by ensuring med1_id is less than med2_id."}, {"role": "assistant", "content": "SELECT m1.medication_id AS med1_id, m1.medication_name AS med1_name, m2.medication_id AS med2_id, m2.medication_name AS med2_name, m1.manufacturer\nFROM healthcare.medications m1\nJOIN healthcare.medications m2\n ON m1.manufacturer = m2.manufacturer\n AND m1.medication_id < m2.medication_id;"}, {"role": "user", "content": "Also, sort the results by manufacturer ascending and then med1_id ascending."}, {"role": "assistant", "content": "SELECT m1.medication_id AS med1_id, m1.medication_name AS med1_name, m2.medication_id AS med2_id, m2.medication_name AS med2_name, m1.manufacturer\nFROM healthcare.medications m1\nJOIN healthcare.medications m2\n ON m1.manufacturer = m2.manufacturer\n AND m1.medication_id < m2.medication_id\nORDER BY m1.manufacturer ASC, m1.medication_id 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.medications ( medication_id.text, medication_name.text, generic_name.text, manufacturer.text, ndc_code.text, description.text )\n"} +{"conversations": [{"role": "user", "content": "List the first and last names, email, and loyalty program ID of all passengers who joined after January 1, 2024."}, {"role": "assistant", "content": "SELECT first_name, last_name, email, loyalty_program_id\nFROM transportation.passengers\nWHERE created_at > '2024-01-01';"}, {"role": "user", "content": "Include only those passengers who are enrolled in any loyalty program (loyalty_program_id is not null), and order the results by last name."}, {"role": "assistant", "content": "SELECT first_name, last_name, email, loyalty_program_id\nFROM transportation.passengers\nWHERE created_at > '2024-01-01' AND loyalty_program_id IS NOT NULL\nORDER BY 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 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.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": "Find all pairs of bookings on the same trip, showing both booking IDs, passenger IDs, and booking times."}, {"role": "assistant", "content": "SELECT b1.booking_id AS booking_id1,\n b1.passenger_id AS passenger1,\n b1.booking_time AS time1,\n b2.booking_id AS booking_id2,\n b2.passenger_id AS passenger2,\n b2.booking_time AS time2\nFROM transportation.bookings b1\nJOIN transportation.bookings b2\n ON b1.trip_id = b2.trip_id\n AND b1.booking_id < b2.booking_id;"}, {"role": "user", "content": "Now limit to only those pairs where both fares exceed 100."}, {"role": "assistant", "content": "SELECT b1.booking_id AS booking_id1,\n b1.passenger_id AS passenger1,\n b1.booking_time AS time1,\n b2.booking_id AS booking_id2,\n b2.passenger_id AS passenger2,\n b2.booking_time AS time2\nFROM transportation.bookings b1\nJOIN transportation.bookings b2\n ON b1.trip_id = b2.trip_id\n AND b1.booking_id < b2.booking_id\nWHERE b1.fare > 100\n AND b2.fare > 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 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 guests who have made at least one reservation. Show their first and last names and the number of reservations they have made."}, {"role": "assistant", "content": "SELECT g.first_name, g.last_name, COUNT(r.reservation_id) AS reservation_count\nFROM hospitality_technology.guests g\nJOIN hospitality_technology.reservations r ON g.guest_id = r.guest_id\nGROUP BY g.guest_id, g.first_name, g.last_name;"}, {"role": "user", "content": "Show only the guests who made 3 or more reservations and order by reservation_count descending."}, {"role": "assistant", "content": "SELECT g.first_name, g.last_name, COUNT(r.reservation_id) AS reservation_count\nFROM hospitality_technology.guests g\nJOIN hospitality_technology.reservations r ON g.guest_id = r.guest_id\nGROUP BY g.guest_id, g.first_name, g.last_name\nHAVING COUNT(r.reservation_id) >= 3\nORDER BY reservation_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.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.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) )\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": "Now, sort the results by the date opened, oldest first, and show only the top 10."}, {"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' ORDER BY date_opened ASC 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 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": "For each country code, what is the earliest registration date of a player?"}, {"role": "assistant", "content": "SELECT country_code, MIN(registration_date) AS earliest_reg_date FROM gaming_technology.players GROUP BY country_code;"}, {"role": "user", "content": "Only list countries where the earliest registration occurred before January 1st, 2020."}, {"role": "assistant", "content": "SELECT country_code, MIN(registration_date) AS earliest_reg_date FROM gaming_technology.players GROUP BY country_code HAVING MIN(registration_date) < '2020-01-01';"}, {"role": "user", "content": "Also include the total count of players for each of these countries."}, {"role": "assistant", "content": "SELECT country_code, MIN(registration_date) AS earliest_reg_date, COUNT(player_id) AS total_players FROM gaming_technology.players GROUP BY country_code HAVING MIN(registration_date) < '2020-01-01';"}, {"role": "user", "content": "Sort the results by the earliest registration date in ascending order."}, {"role": "assistant", "content": "SELECT country_code, MIN(registration_date) AS earliest_reg_date, COUNT(player_id) AS total_players FROM gaming_technology.players GROUP BY country_code HAVING MIN(registration_date) < '2020-01-01' ORDER BY earliest_reg_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 gaming_technology.players ( player_id uuid PRIMARY KEY, username text, email text, password_hash text, registration_date timestamptz, last_login timestamptz, country_code text, status text, profile_data jsonb )\n"} +{"conversations": [{"role": "user", "content": "Give me a breakdown of the number of reviews per day for the last 14 days, including the review_date and review count."}, {"role": "assistant", "content": "SELECT DATE(review_date) AS review_day, COUNT(*) AS review_count\nFROM hospitality_technology.reviews\nWHERE review_date >= CURRENT_DATE - INTERVAL '14 days'\nGROUP BY DATE(review_date)\nORDER BY review_day ASC;"}, {"role": "user", "content": "Add the number of public reviews for each day in a separate column named public_review_count."}, {"role": "assistant", "content": "SELECT DATE(review_date) AS review_day,\n COUNT(*) AS review_count,\n SUM(CASE WHEN is_public THEN 1 ELSE 0 END) AS public_review_count\nFROM hospitality_technology.reviews\nWHERE review_date >= CURRENT_DATE - INTERVAL '14 days'\nGROUP BY DATE(review_date)\nORDER BY review_day ASC;"}, {"role": "user", "content": "Now, also include the number of reviews per day with a rating_overall below 3 as a column called low_rating_count."}, {"role": "assistant", "content": "SELECT DATE(review_date) AS review_day,\n COUNT(*) AS review_count,\n SUM(CASE WHEN is_public THEN 1 ELSE 0 END) AS public_review_count,\n SUM(CASE WHEN rating_overall < 3 THEN 1 ELSE 0 END) AS low_rating_count\nFROM hospitality_technology.reviews\nWHERE review_date >= CURRENT_DATE - INTERVAL '14 days'\nGROUP BY DATE(review_date)\nORDER BY review_day 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.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": "Find pairs of citizens who share the same gender but registered in different years. Show each citizen's first and last name along with their registration year."}, {"role": "assistant", "content": "SELECT c1.first_name AS first_name_1,\n c1.last_name AS last_name_1,\n EXTRACT(YEAR FROM c1.registration_date) AS reg_year_1,\n c2.first_name AS first_name_2,\n c2.last_name AS last_name_2,\n EXTRACT(YEAR FROM c2.registration_date) AS reg_year_2\nFROM government_services.citizens c1\nJOIN government_services.citizens c2\n ON c1.gender = c2.gender\n AND EXTRACT(YEAR FROM c1.registration_date) <> EXTRACT(YEAR FROM c2.registration_date)\n AND c1.citizen_id < c2.citizen_id;"}, {"role": "user", "content": "Exclude any pairs where either citizen is not verified."}, {"role": "assistant", "content": "SELECT c1.first_name AS first_name_1,\n c1.last_name AS last_name_1,\n EXTRACT(YEAR FROM c1.registration_date) AS reg_year_1,\n c2.first_name AS first_name_2,\n c2.last_name AS last_name_2,\n EXTRACT(YEAR FROM c2.registration_date) AS reg_year_2\nFROM government_services.citizens c1\nJOIN government_services.citizens c2\n ON c1.gender = c2.gender\n AND EXTRACT(YEAR FROM c1.registration_date) <> EXTRACT(YEAR FROM c2.registration_date)\n AND c1.citizen_id < c2.citizen_id\nWHERE c1.is_verified = TRUE\n AND c2.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 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 )\n"} +{"conversations": [{"role": "user", "content": "List all patients who have non-primary insurance plans from providers containing 'Care' in their name, including the policy number and expiration date."}, {"role": "assistant", "content": "SELECT pi.patient_id, pi.policy_number, pi.expiration_date FROM healthcare.patient_insurance pi JOIN healthcare.insurance_plans ip ON pi.plan_id = ip.plan_id WHERE pi.is_primary = false AND ip.insurance_provider LIKE '%Care%';"}, {"role": "user", "content": "Actually, I need to see only those plans that will expire within the next 90 days."}, {"role": "assistant", "content": "SELECT pi.patient_id, pi.policy_number, pi.expiration_date FROM healthcare.patient_insurance pi JOIN healthcare.insurance_plans ip ON pi.plan_id = ip.plan_id WHERE pi.is_primary = false AND ip.insurance_provider LIKE '%Care%' AND pi.expiration_date BETWEEN CURRENT_DATE AND (CURRENT_DATE + INTERVAL '90 days');"}, {"role": "user", "content": "Can you also include the insurance provider name in the results?"}, {"role": "assistant", "content": "SELECT pi.patient_id, ip.insurance_provider, pi.policy_number, pi.expiration_date FROM healthcare.patient_insurance pi JOIN healthcare.insurance_plans ip ON pi.plan_id = ip.plan_id WHERE pi.is_primary = false AND ip.insurance_provider LIKE '%Care%' AND pi.expiration_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 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.diagnoses ( diagnosis_id character varying(64) NOT NULL, record_id character varying(64) NOT NULL, patient_id character varying(64) NOT NULL, doctor_id character varying(64) NOT NULL, diagnosis_code character varying(20) NOT NULL, code_type character varying(10) NOT NULL DEFAULT 'ICD-10', description text, diagnosis_date date NOT NULL, status character varying(32) NOT NULL, is_chronic boolean DEFAULT false, PRIMARY KEY (diagnosis_id) )\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 (\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": "List all premium payments made by Bank Transfer where the amount_paid is greater than 5000. Show payment_id, policy_id, customer_id, amount_paid, and payment_date, ordered by amount_paid descending."}, {"role": "assistant", "content": "SELECT payment_id,\n policy_id,\n customer_id,\n amount_paid,\n payment_date\nFROM insurance.premium_payments\nWHERE payment_method = 'Bank Transfer'\n AND amount_paid > 5000\nORDER BY amount_paid 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 (\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.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 (\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)\nCREATE TABLE insurance.agents (\n agent_id character varying(64) NOT NULL, -- unique identifier for the agent\n first_name character varying(100) NOT NULL,\n last_name character varying(100) NOT NULL,\n agency_name character varying(150),\n license_number character varying(100) NOT NULL UNIQUE, -- state insurance license number\n license_state character varying(50) NOT NULL,\n contact_email character varying(128) UNIQUE,\n contact_phone character varying(30),\n hire_date date,\n termination_date date,\n status character varying(20) NOT NULL DEFAULT 'Active', -- e.g., Active, Terminated, On Leave\n commission_rate numeric(5, 4) NOT NULL DEFAULT 0.05, -- percentage commission\n manager_id character varying(64), -- identifier for the agent's manager (FK to agents or employees)\n PRIMARY KEY (agent_id)\n)\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 (\n document_id character varying(64) NOT NULL, -- unique identifier for the document\n claim_id character varying(64) NOT NULL, -- identifier of the claim this document relates to (FK to claims)\n document_type character varying(50) NOT NULL, -- e.g., Police Report, Photo, Invoice, Medical Bill\n file_name character varying(255) NOT NULL, -- original name of the uploaded file\n file_path character varying(512) NOT NULL, -- storage path (e.g., S3 URL, network path)\n file_size_bytes integer, -- size of the file in bytes\n mime_type character varying(100), -- MIME type of the file (e.g., 'image/jpeg', 'application/pdf')\n uploaded_by character varying(64), -- identifier of the user/system who uploaded (FK to users/customers)\n uploaded_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- time of upload\n description text, -- optional description of the document\n PRIMARY KEY (document_id)\n)\nCREATE TABLE insurance.policy_beneficiaries (\n beneficiary_id character varying(64) NOT NULL, -- unique identifier for the beneficiary entry\n policy_id character varying(64) NOT NULL, -- identifier of the life/relevant policy (FK to policies)\n customer_id character varying(64) NOT NULL, -- identifier of the beneficiary (could be FK to customers or store info directly)\n first_name character varying(100) NOT NULL, -- beneficiary first name (if not linking to customers table)\n last_name character varying(100) NOT NULL, -- beneficiary last name\n relationship character varying(50) NOT NULL, -- relationship to the policyholder (e.g., Spouse, Child, Parent)\n percentage_share numeric(5, 2) NOT NULL CHECK (percentage_share > 0 AND percentage_share <= 100), -- percentage of payout\n contact_info text, -- contact details for the beneficiary\n added_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP,\n PRIMARY KEY (beneficiary_id),\n UNIQUE (policy_id, customer_id) -- Ensure a person is listed only once per policy\n)\n"} +{"conversations": [{"role": "user", "content": "Can you list each developer's name along with the number of games they have published by joining developers and games?"}, {"role": "assistant", "content": "SELECT d.name AS developer_name,\n COUNT(g.game_id) AS games_published\nFROM gaming_technology.developers d\nLEFT JOIN gaming_technology.games g\n ON d.developer_id = g.developer_id\nGROUP BY d.name;"}, {"role": "user", "content": "Also, only include developers who have published more than 3 games and show the latest release_date of their games."}, {"role": "assistant", "content": "SELECT d.name AS developer_name,\n COUNT(g.game_id) AS games_published,\n MAX(g.release_date) AS latest_release\nFROM gaming_technology.developers d\nJOIN gaming_technology.games g\n ON d.developer_id = g.developer_id\nGROUP BY d.name\nHAVING COUNT(g.game_id) > 3\nORDER BY latest_release 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 ( player_id uuid, username text, email text, password_hash text, registration_date timestamp with time zone, last_login timestamp with time zone, country_code text, status text, profile_data jsonb )\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 )\n"} +{"conversations": [{"role": "user", "content": "List the names of employees and the names of the cities where their agency operates service locations."}, {"role": "assistant", "content": "SELECT e.first_name, e.last_name, sl.city\nFROM government_services.employees e\nJOIN government_services.service_locations sl ON e.agency_id = sl.agency_id;"}, {"role": "user", "content": "Only show employees who work in locations that are accessible."}, {"role": "assistant", "content": "SELECT e.first_name, e.last_name, sl.city\nFROM government_services.employees e\nJOIN government_services.service_locations sl ON e.agency_id = sl.agency_id\nWHERE sl.is_accessible = 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 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": "I want to find total PNL and average ROI of smart money token performance for each narrative category. Only include narratives with average ROI greater than 0.5."}, {"role": "assistant", "content": "SELECT bi.narrative,\n SUM(smtp.pnl) AS total_pnl,\n AVG(smtp.roi) AS avg_roi\nFROM smart_money_token_performance AS smtp\nJOIN token_basic_info AS bi\n ON smtp.token_symbol = bi.token_symbol\nGROUP BY bi.narrative\nHAVING AVG(smtp.roi) > 0.5;"}, {"role": "user", "content": "Exclude narratives with total net_flow below zero and show only the top 3 narratives by total PNL."}, {"role": "assistant", "content": "SELECT bi.narrative,\n SUM(smtp.pnl) AS total_pnl,\n AVG(smtp.roi) AS avg_roi,\n SUM(smtp.net_flow) AS total_net_flow\nFROM smart_money_token_performance AS smtp\nJOIN token_basic_info AS bi\n ON smtp.token_symbol = bi.token_symbol\nGROUP BY bi.narrative\nHAVING AVG(smtp.roi) > 0.5\n AND SUM(smtp.net_flow) >= 0\nORDER BY total_pnl 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 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 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.text, chain.text, address.text, exchange.text, token_address.text, token_symbol.text, balance.numeric, usd_value.numeric, price.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": "Show me all trades (trade_id, security_id, total_amount) executed by employees in the 'Investment' department, along with their employee_id and first_name."}, {"role": "assistant", "content": "SELECT t.trade_id, t.security_id, t.total_amount, e.employee_id, e.first_name FROM financial_services.trades t JOIN financial_services.employees e ON t.account_id = e.employee_id WHERE e.department = 'Investment';"}, {"role": "user", "content": "Now modify the query to only include trades with a total_amount greater than $10,000 and sort them by trade_timestamp in descending order."}, {"role": "assistant", "content": "SELECT t.trade_id, t.security_id, t.total_amount, e.employee_id, e.first_name FROM financial_services.trades t JOIN financial_services.employees e ON t.account_id = e.employee_id WHERE e.department = 'Investment' AND t.total_amount > 10000 ORDER BY t.trade_timestamp 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.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.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": "Which hashtags appear on the most posts? Return hashtag_id, tag_name, and the number of posts each hashtag is used in, sorted descending, limited to the top 3."}, {"role": "assistant", "content": "SELECT\n h.hashtag_id,\n h.tag_name,\n COUNT(ph.post_id) AS post_count\nFROM social_media.hashtags h\nJOIN social_media.post_hashtags ph\n ON h.hashtag_id = ph.hashtag_id\nGROUP BY h.hashtag_id, h.tag_name\nORDER BY post_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 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.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.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.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": "List each citizen's first and last name along with the first and last name of another citizen who shares the same last name. Show each pair only once."}, {"role": "assistant", "content": "SELECT c1.first_name || ' ' || c1.last_name AS citizen_name,\n c2.first_name || ' ' || c2.last_name AS other_citizen_name\nFROM government_services.citizens c1\nJOIN government_services.citizens c2\n ON c1.last_name = c2.last_name\n AND c1.citizen_id < c2.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.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": "How many service locations do we have in each state?"}, {"role": "assistant", "content": "SELECT state, COUNT(*) AS location_count FROM government_services.service_locations GROUP BY state;"}, {"role": "user", "content": "Only show states where there are at least 3 locations."}, {"role": "assistant", "content": "SELECT state, COUNT(*) AS location_count FROM government_services.service_locations GROUP BY state HAVING COUNT(*) >= 3;"}, {"role": "user", "content": "Can you also show the number of accessible locations in each of those states?"}, {"role": "assistant", "content": "SELECT state, COUNT(*) AS location_count, SUM(CASE WHEN is_accessible = TRUE THEN 1 ELSE 0 END) AS accessible_location_count FROM government_services.service_locations GROUP BY state HAVING COUNT(*) >= 3;"}, {"role": "user", "content": "Order the results by accessible location count in descending order."}, {"role": "assistant", "content": "SELECT state, COUNT(*) AS location_count, SUM(CASE WHEN is_accessible = TRUE THEN 1 ELSE 0 END) AS accessible_location_count FROM government_services.service_locations GROUP BY state HAVING COUNT(*) >= 3 ORDER BY accessible_location_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 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)\n"} +{"conversations": [{"role": "user", "content": "List claims along with the name of the insurance product associated with the policy under which the claim was filed. Show claim_id, incident_date, and product_name."}, {"role": "assistant", "content": "SELECT T1.claim_id, T1.incident_date, T3.product_name FROM insurance.claims AS T1 JOIN policies AS T2 ON T1.policy_id = T2.policy_id JOIN insurance.insurance_products AS T3 ON T2.product_id = T3.product_id;"}, {"role": "user", "content": "Only show claims related to 'auto' insurance products."}, {"role": "assistant", "content": "SELECT T1.claim_id, T1.incident_date, T3.product_name FROM insurance.claims AS T1 JOIN policies AS T2 ON T1.policy_id = T2.policy_id JOIN insurance.insurance_products AS T3 ON T2.product_id = T3.product_id WHERE T3.product_type = 'Auto';"}, {"role": "user", "content": "Further filter the results to only include claims with status 'Settled' or 'Closed'."}, {"role": "assistant", "content": "SELECT T1.claim_id, T1.incident_date, T3.product_name FROM insurance.claims AS T1 JOIN policies AS T2 ON T1.policy_id = T2.policy_id JOIN insurance.insurance_products AS T3 ON T2.product_id = T3.product_id WHERE T3.product_type = 'Auto' AND T1.status IN ('Settled', '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 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 (\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)\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.policy_beneficiaries (\n beneficiary_id character varying(64) NOT NULL, -- unique identifier for the beneficiary entry\n policy_id character varying(64) NOT NULL, -- identifier of the life/relevant policy (FK to policies)\n customer_id character varying(64) NOT NULL, -- identifier of the beneficiary (could be FK to customers or store info directly)\n first_name character varying(100) NOT NULL, -- beneficiary first name (if not linking to customers table)\n last_name character varying(100) NOT NULL, -- beneficiary last name\n relationship character varying(50) NOT NULL, -- relationship to the policyholder (e.g., Spouse, Child, Parent)\n percentage_share numeric(5, 2) NOT NULL CHECK (percentage_share > 0 AND percentage_share <= 100), -- percentage of payout\n contact_info text, -- contact details for the beneficiary\n added_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP,\n PRIMARY KEY (beneficiary_id),\n UNIQUE (policy_id, customer_id) -- Ensure a person is listed only once per policy\n)\n"} +{"conversations": [{"role": "user", "content": "Get a list of all policies that have at least two beneficiaries with a percentage_share greater than 20%. Include policy_id, policy_number, and beneficiary_count."}, {"role": "assistant", "content": "SELECT p.policy_id, p.policy_number, COUNT(pb.beneficiary_id) AS beneficiary_count\nFROM insurance.policies p\nJOIN insurance.policy_beneficiaries pb\n ON p.policy_id = pb.policy_id\nWHERE pb.percentage_share > 20\nGROUP BY p.policy_id, p.policy_number\nHAVING COUNT(pb.beneficiary_id) >= 2;"}, {"role": "user", "content": "Also include the names of those beneficiaries concatenated as a comma-separated string labeled beneficiaries."}, {"role": "assistant", "content": "SELECT p.policy_id, p.policy_number,\n COUNT(pb.beneficiary_id) AS beneficiary_count,\n STRING_AGG(pb.first_name || ' ' || pb.last_name, ', ') AS beneficiaries\nFROM insurance.policies p\nJOIN insurance.policy_beneficiaries pb\n ON p.policy_id = pb.policy_id\nWHERE pb.percentage_share > 20\nGROUP BY p.policy_id, p.policy_number\nHAVING COUNT(pb.beneficiary_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 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.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.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.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": "Show the usernames and registration dates for all players whose status is 'inactive'."}, {"role": "assistant", "content": "SELECT username, registration_date FROM players WHERE status = 'inactive';"}, {"role": "user", "content": "Refine the list to only include players registered after '2023-01-01'."}, {"role": "assistant", "content": "SELECT username, registration_date FROM players WHERE status = 'inactive' AND registration_date >= '2023-01-01';"}, {"role": "user", "content": "Instead, find the number of unique players who registered before '2020-01-01' and have never logged in (last_login is NULL)."}, {"role": "assistant", "content": "SELECT count(player_id) FROM players WHERE registration_date < '2020-01-01' AND last_login IS NULL;"}, {"role": "user", "content": "List the usernames and registration dates for those specific players instead of just the count."}, {"role": "assistant", "content": "SELECT username, registration_date FROM players WHERE registration_date < '2020-01-01' AND last_login 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 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"}