Dataset Viewer
Auto-converted to Parquet Duplicate
system
stringlengths
315
8.06k
conversations
listlengths
2
48
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. ##Table Structure "CREATE 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));"
[ { "role": "user", "content": "Which token symbol has the highest price among all tokens held by CEXes on the Polygon chain?", "sql": null }, { "role": "assistant", "content": "SELECT token_symbol, MAX(price) AS max_price FROM cex_token_balance WHERE chain = 'Polygon' GROUP BY token_symbol OR...
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. ##Table Structure CREATE 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 )
[ { "role": "user", "content": "List all failed transactions where the gas_used is greater than 100,000, including the transaction_id and timestamp.", "sql": null }, { "role": "assistant", "content": "SELECT transaction_id, timestamp FROM web3.transactions WHERE status = 'failed' AND gas_used ...
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. ##Table Structure CREATE 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) )
[ { "role": "user", "content": "Provide for each security its ticker_symbol, the most recent close_price and corresponding timestamp.", "sql": null }, { "role": "assistant", "content": "SELECT s.ticker_symbol, md.close_price, md.data_timestamp\nFROM financial_services.market_data md\nJOIN fina...
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. ##Table Structure CREATE 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 )
[ { "role": "user", "content": "Show the maximum and minimum current_players for each server status.", "sql": null }, { "role": "assistant", "content": "SELECT status, MAX(current_players) AS max_current_players, MIN(current_players) AS min_current_players FROM gaming_technology.servers GROUP ...
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. ##Table Structure CREATE 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 ) CREATE TABLE gaming_technology.games ( game_id uuid NOT NULL DEFAULT gen_random_uuid(), title character varying(200) NOT NULL, developer_id uuid NOT NULL, publisher_id uuid, genre character varying(100), release_date date, description text, platform character varying(50) NOT NULL, engine character varying(100), website character varying(255), PRIMARY KEY (game_id) ) CREATE TABLE gaming_technology.developers ( developer_id uuid PRIMARY KEY, name text, country text, founded_year int, website text, created_at timestamptz ) CREATE TABLE gaming_technology.game_sessions ( session_id uuid PRIMARY KEY, player_id uuid, game_id uuid, server_id uuid, start_time timestamptz, end_time timestamptz, duration_seconds int, score int, session_data jsonb ) CREATE TABLE gaming_technology.servers ( server_id.uuid, game_id.uuid, server_name.text, region.text, ip_address.text, port.integer, current_players.integer, max_players.integer, status.text, last_heartbeat.timestamptz ) CREATE TABLE gaming_technology.player_achievements ( player_achievement_id uuid NOT NULL DEFAULT gen_random_uuid(), player_id uuid NOT NULL, achievement_id uuid NOT NULL, unlocked_at timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP, PRIMARY KEY (player_achievement_id), UNIQUE (player_id, achievement_id) ) CREATE 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) ) CREATE TABLE gaming_technology.player_inventory ( inventory_id uuid NOT NULL DEFAULT gen_random_uuid(), player_id uuid NOT NULL, item_id uuid NOT NULL, quantity integer NOT NULL DEFAULT 1, acquired_at timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP, instance_data jsonb, PRIMARY KEY (inventory_id) )
[ { "role": "user", "content": "Show me a list of players and, for each, list all the different games where they have acquired items. Also include the number of unique item types they've acquired per game.", "sql": null }, { "role": "assistant", "content": "SELECT p.player_id, p.username, g.ti...
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. ##Table Structure CREATE 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 )
[ { "role": "user", "content": "List all service orders with quantity greater than 3, showing the order ID, total price, and the staff member who placed the order.", "sql": null }, { "role": "assistant", "content": "SELECT order_id, total_price, staff_id_ordered\nFROM hospitality_technology.se...
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. ##Table Structure CREATE 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) ) CREATE TABLE web3.events ( event_id.text, contract_id.text, event_name.text, data.text, emitted_at.timestamp, transaction_id.text, log_index.integer ) CREATE TABLE web3.tokens ( token_id character varying(64) NOT NULL, -- unique identifier for the token contract_address character varying(128) NOT NULL, -- address of the token contract token_name character varying(128) NOT NULL, -- name of the token token_symbol character varying(32) NOT NULL, -- symbol of the token decimals integer NOT NULL, -- number of decimals for the token total_supply numeric(38,14) NOT NULL, -- total supply of the token PRIMARY KEY (token_id) ) CREATE 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 ) CREATE TABLE web3.users ( user_id text, username text, email text, password_hash text, created_at timestamp )
[ { "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.", "sql": null }, { "role": "assistant", "content": "SELECT\n e.event_id,\n e.event_name,\n tt.transfer_id,\n tk.token_...
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. ##Table Structure CREATE TABLE legal_services.law_firms ( firm_id character varying(64) NOT NULL, firm_name character varying(200) NOT NULL, address text NOT NULL, phone character varying(32), website character varying(255), founded_date date, managing_partner_id character varying(64), PRIMARY KEY (firm_id) )
[ { "role": "user", "content": "Show me the names, founding dates, and websites of all law firms whose name contains the word 'Legal' and were founded after the year 2005. Sort the results by their founding date.", "sql": null }, { "role": "assistant", "content": "SELECT firm_name, founded_dat...
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. ##Table Structure CREATE TABLE web3.tokens ( token_id text PRIMARY KEY, contract_address text, token_name text, token_symbol text, decimals int, total_supply numeric )
[ { "role": "user", "content": "Find all pairs of tokens that have the same contract_address but different token_symbols. Show both token_ids, each token's symbol, and the shared contract_address.", "sql": null }, { "role": "assistant", "content": "SELECT t1.token_id AS token_id_1, t2.token_id...
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. ##Table Structure CREATE TABLE social_media.messages ( message_id character varying(64) NOT NULL, -- unique identifier for the message conversation_id character varying(64) NOT NULL, -- identifier for the conversation thread (FK to conversations.conversation_id) sender_user_id character varying(64) NOT NULL, -- identifier of the sender (FK to users.user_id) content text, -- textual content of the message media_url text, -- URL to attached media (image/video) media_type character varying(20), -- type of media ('image', 'video', null) sent_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp when message was sent read_at timestamp, -- timestamp when message was read by recipient(s) PRIMARY KEY (message_id) )
[ { "role": "user", "content": "How many messages currently have a media file attached?", "sql": null }, { "role": "assistant", "content": "SELECT COUNT(*) FROM social_media.messages WHERE media_url IS NOT NULL;", "sql": null }, { "role": "user", "content": "For each user, show...
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. ##Table Structure CREATE 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 ) CREATE 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 ) CREATE 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 ) CREATE 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 ) CREATE 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 )
[ { "role": "user", "content": "Which exchange holds the largest total USD value of the token with the highest 24h price increase in the 'AI' narrative, and what is that value?", "sql": null }, { "role": "assistant", "content": "SELECT ctb.exchange, SUM(ctb.usd_value) AS total_usd_value\nFROM ...
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. ##Table Structure CREATE 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 )
[ { "role": "user", "content": "What is the average and maximum standard fee for services in each category?", "sql": null }, { "role": "assistant", "content": "SELECT category, AVG(standard_fee) AS avg_standard_fee, MAX(standard_fee) AS max_standard_fee FROM government_services.services GROUP ...
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. ##Table Structure CREATE TABLE trading_platform.assets ( asset_id character varying(64) NOT NULL, -- unique identifier for the asset name character varying(128) NOT NULL, -- name of the asset symbol character varying(32) NOT NULL, -- symbol of the asset type character varying(32) NOT NULL, -- type of the asset (e.g., cryptocurrency, stock) PRIMARY KEY (asset_id) ) CREATE TABLE trading_platform.utxos ( utxo_id character varying(64) NOT NULL, -- unique identifier for the UTXO transaction_id character varying(64) NOT NULL, -- identifier of the transaction that created the UTXO output_index integer NOT NULL, -- index of the output in the transaction address character varying(128) NOT NULL, -- address that can spend the UTXO amount numeric(38,14) NOT NULL, -- amount of the asset in the UTXO spent boolean NOT NULL, -- whether the UTXO has been spent PRIMARY KEY (utxo_id) ) CREATE TABLE trading_platform.dapps ( dapp_id character varying(64) NOT NULL, -- unique identifier for the DApp name character varying(128) NOT NULL, -- name of the DApp description text NOT NULL, -- description of the DApp url character varying(256) NOT NULL, -- URL of the DApp PRIMARY KEY (dapp_id) )
[ { "role": "user", "content": "I want a list of DApp names and the asset symbols mentioned in their descriptions.", "sql": null }, { "role": "assistant", "content": "SELECT d.name AS dapp_name,\n a.symbol AS asset_symbol\nFROM trading_platform.dapps d\nJOIN trading_platform.assets a\n ...
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. ##Table Structure CREATE TABLE insurance.claims ( claim_id.text, policy_id.text, customer_id.text, incident_date.timestamp, reported_date.timestamp, description.text, estimated_loss.numeric, status.text, settlement_amount.numeric, settlement_date.date, claim_handler_id.text, police_report_number.text )
[ { "role": "user", "content": "List the claim ID, incident date, estimated loss, and the first and last name of the customer for all claims with an estimated loss greater than 5000.", "sql": null }, { "role": "assistant", "content": "SELECT T1.claim_id, T1.incident_date, T1.estimated_loss, T2...
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. ##Table Structure CREATE TABLE social_media.users ( user_id character varying(64) NOT NULL, -- unique identifier for the user username character varying(50) NOT NULL UNIQUE, -- user's unique handle email character varying(128) NOT NULL UNIQUE, -- user's email address password_hash text NOT NULL, -- hashed password full_name character varying(100), -- user's full name profile_picture_url text, -- URL to the profile picture bio text, -- short user biography location character varying(100), -- user's location created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of account creation updated_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of last profile update is_verified boolean NOT NULL DEFAULT false, -- verification status PRIMARY KEY (user_id) ) CREATE TABLE social_media.posts ( post_id character varying(64) NOT NULL, -- unique identifier for the post user_id character varying(64) NOT NULL, -- identifier of the user who created the post (FK to users.user_id) content text, -- textual content of the post media_url text, -- URL to attached media (image/video) media_type character varying(20), -- type of media ('image', 'video', null) created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of post creation updated_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of last post edit visibility character varying(20) NOT NULL DEFAULT 'public', -- visibility ('public', 'friends', 'private') location_lat numeric(9,6), -- latitude of post location location_lon numeric(9,6), -- longitude of post location PRIMARY KEY (post_id) ) CREATE TABLE social_media.comments ( comment_id character varying(64) NOT NULL, -- unique identifier for the comment post_id character varying(64) NOT NULL, -- identifier of the post being commented on (FK to posts.post_id) user_id character varying(64) NOT NULL, -- identifier of the user who made the comment (FK to users.user_id) parent_comment_id character varying(64), -- identifier of the parent comment if it's a reply (FK to comments.comment_id) content text NOT NULL, -- textual content of the comment created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of comment creation updated_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of last comment edit PRIMARY KEY (comment_id) ) CREATE TABLE social_media.likes ( like_id character varying(64) NOT NULL, -- unique identifier for the like user_id character varying(64) NOT NULL, -- identifier of the user who liked (FK to users.user_id) post_id character varying(64), -- identifier of the post being liked (FK to posts.post_id, nullable) comment_id character varying(64), -- identifier of the comment being liked (FK to comments.comment_id, nullable) created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of when the like occurred PRIMARY KEY (like_id), CONSTRAINT unique_user_like UNIQUE (user_id, post_id, comment_id), -- prevent duplicate likes CONSTRAINT check_like_target CHECK (post_id IS NOT NULL OR comment_id IS NOT NULL) -- ensure it likes something ) CREATE TABLE social_media.follows ( follow_id character varying(64) NOT NULL, -- unique identifier for the follow relationship follower_user_id character varying(64) NOT NULL, -- identifier of the user who is following (FK to users.user_id) following_user_id character varying(64) NOT NULL, -- identifier of the user being followed (FK to users.user_id) created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of when the follow started PRIMARY KEY (follow_id), CONSTRAINT unique_follow UNIQUE (follower_user_id, following_user_id) -- prevent duplicate follows ) CREATE TABLE social_media.hashtags ( hashtag_id character varying(64) NOT NULL, -- unique identifier for the hashtag tag_name character varying(100) NOT NULL UNIQUE, -- the actual hashtag text (without '#') created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp when the hashtag was first used PRIMARY KEY (hashtag_id) ) CREATE TABLE social_media.messages ( message_id character varying(64) NOT NULL, -- unique identifier for the message conversation_id character varying(64) NOT NULL, -- identifier for the conversation thread (FK to conversations.conversation_id) sender_user_id character varying(64) NOT NULL, -- identifier of the sender (FK to users.user_id) content text, -- textual content of the message media_url text, -- URL to attached media (image/video) media_type character varying(20), -- type of media ('image', 'video', null) sent_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp when message was sent read_at timestamp, -- timestamp when message was read by recipient(s) PRIMARY KEY (message_id) ) CREATE TABLE social_media.conversations ( conversation_id character varying(64) NOT NULL, -- unique identifier for the conversation created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp when conversation was initiated last_message_at timestamp, -- timestamp of the last message in the conversation is_group_chat boolean NOT NULL DEFAULT false, -- indicates if it's a group chat or direct message group_name character varying(100), -- name of the group chat (if applicable) PRIMARY KEY (conversation_id) ) CREATE TABLE social_media.conversation_participants ( participant_id character varying(64) NOT NULL, -- unique identifier for the participant entry conversation_id character varying(64) NOT NULL, -- identifier of the conversation (FK to conversations.conversation_id) user_id character varying(64) NOT NULL, -- identifier of the user in the conversation (FK to users.user_id) joined_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp when user joined the conversation last_read_at timestamp, -- timestamp indicating up to when the user has read messages PRIMARY KEY (participant_id), CONSTRAINT unique_user_conversation UNIQUE (conversation_id, user_id) -- prevent user being added multiple times ) CREATE TABLE social_media.notifications ( notification_id character varying(64) NOT NULL, -- unique identifier for the notification recipient_user_id character varying(64) NOT NULL, -- user receiving the notification (FK to users.user_id) sender_user_id character varying(64), -- user triggering the notification (FK to users.user_id, can be null for system notifications) notification_type character varying(30) NOT NULL, -- type of notification ('like', 'comment', 'follow', 'mention', 'message') target_entity_id character varying(64), -- ID of the related entity (post_id, comment_id, user_id, conversation_id) target_entity_type character varying(20), -- type of the related entity ('post', 'comment', 'user', 'conversation') created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp notification was created read_at timestamp, -- timestamp notification was marked as read PRIMARY KEY (notification_id) ) CREATE TABLE social_media.user_settings ( setting_id character varying(64) NOT NULL, -- unique identifier for the setting entry user_id character varying(64) NOT NULL UNIQUE, -- user the settings belong to (FK to users.user_id) theme character varying(20) DEFAULT 'light', -- UI theme ('light', 'dark') email_notifications_enabled boolean DEFAULT true, -- enable/disable email notifications push_notifications_enabled boolean DEFAULT true, -- enable/disable push notifications private_profile boolean DEFAULT false, -- is the user profile private updated_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of last setting change PRIMARY KEY (setting_id) )
[ { "role": "user", "content": "List users who commented on posts and the content of the post they commented on. Show commenter username and post content.", "sql": null }, { "role": "assistant", "content": "SELECT T1.username, T2.content FROM social_media.users AS T1 JOIN social_media.comments...
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. ##Table Structure CREATE TABLE web3.users ( user_id text PRIMARY KEY, username text, email text, password_hash text, created_at timestamp )
[ { "role": "user", "content": "Show the user_id, username, and email for users who registered at the same timestamp as another user.", "sql": null }, { "role": "assistant", "content": "SELECT u1.user_id, u1.username, u1.email FROM web3.users u1 JOIN web3.users u2 ON u1.created_at = u2.created...
You are an expert in writing database language and you can refuse the user's question if the question is not related to the table structure. 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. ##Table Structure CREATE TABLE manufacturing.employees ( employee_id text PRIMARY KEY, 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 )
[ { "role": "user", "content": "What is the total number of vacation days taken by employee with ID 'EMP101' in the past year?", "sql": null }, { "role": "assistant", "content": "I'm sorry, but I can't provide information on the vacation days taken by an employee as this data is not stored in ...
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. ##Table Structure CREATE 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) ) CREATE 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 ) CREATE TABLE trading_platform.utxos ( utxo_id.text, transaction_id.text, output_index.integer, address.text, amount.numeric, spent.boolean ) CREATE TABLE trading_platform.dapps ( dapp_id.text, name.text, description.text, url.text ) CREATE TABLE trading_platform.peers ( peer_id.text, ip_address.text, port.integer, last_seen.timestamp ) CREATE TABLE trading_platform.metadata ( metadata_id character varying(64) NOT NULL, -- unique identifier for the metadata asset_id character varying(64) NOT NULL, -- identifier of the asset the metadata is associated with key character varying(128) NOT NULL, -- key of the metadata value text NOT NULL, -- value of the metadata PRIMARY KEY (metadata_id) ) CREATE TABLE trading_platform.kyc_audit ( kyc_audit_id character varying(64) NOT NULL, -- unique identifier for the KYC audit user_id character varying(64) NOT NULL, -- identifier of the user being audited status character varying(32) NOT NULL, -- status of the KYC audit (e.g., pending, approved, rejected) reviewed_at timestamp NOT NULL, -- time when the KYC audit was reviewed PRIMARY KEY (kyc_audit_id) )
[ { "role": "user", "content": "Count the number of metadata entries for each asset.", "sql": null }, { "role": "assistant", "content": "SELECT asset_id, COUNT(*) AS metadata_count\nFROM trading_platform.metadata\nGROUP BY asset_id;", "sql": null }, { "role": "user", "content":...
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. ##Table Structure CREATE TABLE transportation.routes ( route_id character varying(64) NOT NULL, route_number character varying(32) NOT NULL UNIQUE, description text, origin_location_id character varying(64) NOT NULL, destination_location_id character varying(64) NOT NULL, distance_km numeric(10, 2), estimated_duration_minutes integer, type character varying(32) NOT NULL, PRIMARY KEY (route_id) ) CREATE 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) ) CREATE 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) ) CREATE 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) ) CREATE TABLE transportation.fuel_logs ( fuel_log_id character varying(64) NOT NULL, vehicle_id character varying(64) NOT NULL, trip_id character varying(64), log_timestamp timestamp with time zone NOT NULL, fuel_type character varying(32) NOT NULL, quantity numeric(10, 3) NOT NULL, unit character varying(16) NOT NULL, cost_per_unit numeric(8, 4), total_cost numeric(10, 2) NOT NULL, odometer_reading integer, location_id character varying(64), PRIMARY KEY (fuel_log_id) ) CREATE TABLE transportation.passengers ( passenger_id character varying(64) NOT NULL, first_name character varying(128) NOT NULL, last_name character varying(128) NOT NULL, email character varying(128) UNIQUE, phone_number character varying(32) UNIQUE, date_of_birth date, loyalty_program_id character varying(64), created_at timestamp with time zone NOT NULL, PRIMARY KEY (passenger_id) ) CREATE TABLE transportation.bookings ( booking_id character varying(64) NOT NULL, passenger_id character varying(64) NOT NULL, trip_id character varying(64) NOT NULL, seat_number character varying(16), booking_time timestamp with time zone NOT NULL, status character varying(32) NOT NULL, fare numeric(10, 2) NOT NULL, payment_transaction_id character varying(128), special_requests text, PRIMARY KEY (booking_id) )
[ { "role": "user", "content": "I need a report showing each passenger's total number of bookings and the date of their most recent booking.", "sql": null }, { "role": "assistant", "content": "SELECT b.passenger_id,\n COUNT(*) AS total_bookings,\n MAX(b.booking_time) AS last_bookin...
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. ##Table Structure CREATE 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 )
[ { "role": "user", "content": "For each prescription, find the next prescription for the same patient. Return current prescription_id, next_prescription_id, patient_id, and days between start dates.", "sql": null }, { "role": "assistant", "content": "SELECT p1.patient_id,\n p1.prescript...
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. ##Table Structure CREATE 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 )
[ { "role": "user", "content": "Please list the full name and status of clients who have not provided a company name.", "sql": null }, { "role": "assistant", "content": "SELECT first_name, last_name, status\nFROM legal_services.clients\nWHERE company_name IS NULL;", "sql": null }, { ...
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. ##Table Structure CREATE TABLE gaming_technology.games ( game_id uuid PRIMARY KEY, title text, developer_id uuid, publisher_id uuid, genre text, release_date date, description text, platform text, engine text, website text ) CREATE TABLE gaming_technology.developers ( developer_id.uuid, name.text, country.text, founded_year.integer, website.text, created_at.timestamptz ) CREATE TABLE gaming_technology.game_sessions ( session_id uuid NOT NULL DEFAULT gen_random_uuid(), player_id uuid NOT NULL, game_id uuid NOT NULL, server_id uuid, start_time timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP, end_time timestamp with time zone, duration_seconds integer, score integer, session_data jsonb, PRIMARY KEY (session_id) )
[ { "role": "user", "content": "List all game sessions that lasted longer than 30 minutes. Show the session_id, player_id, game_id, and duration_seconds.", "sql": null }, { "role": "assistant", "content": "SELECT session_id, player_id, game_id, duration_seconds FROM gaming_technology.game_sess...
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. ##Table Structure CREATE 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) )
[ { "role": "user", "content": "What is the average overall rating for each property?", "sql": null }, { "role": "assistant", "content": "SELECT property_id, AVG(rating_overall) AS avg_rating\nFROM hospitality_technology.reviews\nGROUP BY property_id;", "sql": null }, { "role": "us...
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. ##Table Structure CREATE TABLE social_media.likes ( like_id.text, user_id.text, post_id.text, comment_id.text, created_at.timestamp )
[ { "role": "user", "content": "I need to find users who have liked both a post and a comment on the same day. For each such user and date, list user_id, date, post_id, and comment_id.", "sql": null }, { "role": "assistant", "content": "SELECT p.user_id, DATE(p.created_at) AS like_date, p.post...
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. ##Table Structure CREATE TABLE financial_services.securities ( security_id text PRIMARY KEY, 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 )
[ { "role": "user", "content": "I want to list each security alongside another security issued by the same issuer.", "sql": null }, { "role": "assistant", "content": "SELECT a.security_id, a.ticker_symbol, b.security_id AS other_security_id, b.ticker_symbol AS other_ticker, a.issuer_name\nFROM...
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. ##Table Structure CREATE TABLE blockchain.addresses ( address_id text PRIMARY KEY, public_key text, balance numeric ) CREATE TABLE blockchain.wallets ( wallet_id character varying(64) NOT NULL, -- unique identifier for the wallet user_id character varying(64) NOT NULL, -- identifier of the user owning the wallet address_id character varying(128) NOT NULL, -- identifier of the address associated with the wallet private_key text NOT NULL, -- private key of the wallet PRIMARY KEY (wallet_id) ) CREATE TABLE blockchain.users ( user_id character varying(64) NOT NULL, -- unique identifier for the user username character varying(128) NOT NULL, -- username of the user email character varying(128) NOT NULL, -- email address of the user password_hash text NOT NULL, -- hashed password of the user PRIMARY KEY (user_id) ) CREATE TABLE blockchain.smart_contracts ( contract_id text PRIMARY KEY, creator_address text, code text, timestamp timestamp )
[ { "role": "user", "content": "Find users whose username contains 'admin'.", "sql": null }, { "role": "assistant", "content": "SELECT user_id, username, email FROM blockchain.users WHERE username LIKE '%admin%';", "sql": null }, { "role": "user", "content": "For these users, l...
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. ##Table Structure CREATE TABLE web3.token_transfers ( transfer_id character varying(64) NOT NULL, -- unique identifier for the transfer token_id character varying(64) NOT NULL, -- identifier of the token being transferred from_address character varying(128) NOT NULL, -- address of the sender to_address character varying(128) NOT NULL, -- address of the receiver value numeric(38,14) NOT NULL, -- amount of tokens transferred transaction_id character varying(64) NOT NULL, -- identifier of the transaction containing the transfer log_index integer NOT NULL, -- index of the transfer log in the transaction PRIMARY KEY (transfer_id) )
[ { "role": "user", "content": "Find cases where an address received tokens in one transfer and then sent tokens in another. List the receive transfer_id, the send transfer_id, the address, and both transfer values.", "sql": null }, { "role": "assistant", "content": "SELECT recv.transfer_id AS...
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. ##Table Structure CREATE 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 )
[ { "role": "user", "content": "List pairs of distinct locations in the same city that share the same location type. Show both location IDs, names, city, and the shared type.", "sql": null }, { "role": "assistant", "content": "SELECT L1.location_id AS location1_id, L1.name AS location1_name, L...
End of preview. Expand in Data Studio

No dataset card yet

Downloads last month
5