{"conversations": [{"role": "user", "content": "Show me a list of comments and the names of hashtags associated with the posts those comments are on."}, {"role": "assistant", "content": "SELECT T1.comment_id, T3.tag_name FROM comments AS T1 JOIN post_hashtags AS T2 ON T1.post_id = T2.post_id JOIN hashtags AS T3 ON T2.hashtag_id = T3.hashtag_id;"}, {"role": "user", "content": "Can you also include the content of the comment and filter the results to only show comments on posts tagged with 'photography'?"}, {"role": "assistant", "content": "SELECT T1.comment_id, T1.content, T3.tag_name FROM comments AS T1 JOIN post_hashtags AS T2 ON T1.post_id = T2.post_id JOIN hashtags AS T3 ON T2.hashtag_id = T3.hashtag_id WHERE T3.tag_name = 'photography';"}, {"role": "user", "content": "Please only list comments that are top-level, meaning they are not replies to other comments."}, {"role": "assistant", "content": "SELECT T1.comment_id, T1.content, T3.tag_name FROM comments AS T1 JOIN post_hashtags AS T2 ON T1.post_id = T2.post_id JOIN hashtags AS T3 ON T2.hashtag_id = T3.hashtag_id WHERE T3.tag_name = 'photography' AND T1.parent_comment_id IS NULL;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE social_media.comments ( comment_id.text, post_id.text, user_id.text, parent_comment_id.text, content.text, created_at.timestamp, updated_at.timestamp )\nCREATE TABLE social_media.follows ( follow_id.text, follower_user_id.text, following_user_id.text, created_at.timestamp )\nCREATE TABLE social_media.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.conversations ( conversation_id.text, created_at.timestamp, last_message_at.timestamp, is_group_chat.boolean, group_name.text )\n"} {"conversations": [{"role": "user", "content": "Show me the count of service orders for each distinct status."}, {"role": "assistant", "content": "SELECT status, COUNT(order_id) FROM hospitality_technology.service_orders GROUP BY status;"}, {"role": "user", "content": "Also, include the total quantity of items ordered for each status."}, {"role": "assistant", "content": "SELECT status, COUNT(order_id), SUM(quantity) FROM hospitality_technology.service_orders GROUP BY status;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE 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": "Can you list all replies along with their parent comment content for post_id 'P100'?"}, {"role": "assistant", "content": "SELECT reply.comment_id AS reply_id, parent.content AS parent_content, reply.content AS reply_content FROM comments AS reply JOIN comments AS parent ON reply.parent_comment_id = parent.comment_id WHERE reply.post_id = 'P100' AND reply.parent_comment_id IS NOT NULL;"}, {"role": "user", "content": "Actually, I only want replies made after '2024-07-01'."}, {"role": "assistant", "content": "SELECT reply.comment_id AS reply_id, parent.content AS parent_content, reply.content AS reply_content FROM comments AS reply JOIN comments AS parent ON reply.parent_comment_id = parent.comment_id WHERE reply.post_id = 'P100' AND reply.parent_comment_id IS NOT NULL AND reply.created_at > '2024-07-01';"}, {"role": "user", "content": "Now include the original comment's created_at timestamp as well."}, {"role": "assistant", "content": "SELECT reply.comment_id AS reply_id, parent.content AS parent_content, parent.created_at AS parent_created_at, reply.content AS reply_content FROM comments AS reply JOIN comments AS parent ON reply.parent_comment_id = parent.comment_id WHERE reply.post_id = 'P100' AND reply.parent_comment_id IS NOT NULL AND reply.created_at > '2024-07-01';"}, {"role": "user", "content": "Finally, order the results by reply creation time ascending."}, {"role": "assistant", "content": "SELECT reply.comment_id AS reply_id, parent.content AS parent_content, parent.created_at AS parent_created_at, reply.content AS reply_content FROM comments AS reply JOIN comments AS parent ON reply.parent_comment_id = parent.comment_id WHERE reply.post_id = 'P100' AND reply.parent_comment_id IS NOT NULL AND reply.created_at > '2024-07-01' ORDER BY reply.created_at 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 social_media.comments ( comment_id.text, post_id.text, user_id.text, parent_comment_id.text, content.text, created_at.timestamp, updated_at.timestamp )\n"} {"conversations": [{"role": "user", "content": "Find all medical records where the vitals JSON field contains a blood pressure reading with systolic higher than 140, and show the patient_id, record_date, and vitals."}, {"role": "assistant", "content": "SELECT patient_id, record_date, vitals FROM healthcare.medical_records WHERE (vitals->>'blood_pressure_systolic')::integer > 140;"}], "system": "You are an SQL statement expert. Given the table structure 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 full names and email addresses of staff members who have delivered at least one service order in the past 30 days, along with the count of orders they delivered. Sort by count descending."}, {"role": "assistant", "content": "SELECT st.staff_id,\n st.first_name || ' ' || st.last_name AS full_name,\n st.work_email,\n COUNT(so.order_id) AS delivered_count\nFROM hospitality_technology.staff st\nJOIN hospitality_technology.service_orders so\n ON st.staff_id = so.staff_id_delivered\nWHERE so.status = 'Delivered'\n AND so.delivery_timestamp >= CURRENT_DATE - INTERVAL '30 days'\nGROUP BY st.staff_id, st.first_name, st.last_name, st.work_email\nORDER BY delivered_count DESC;"}, {"role": "user", "content": "Actually, only include staff who delivered more than 5 orders in that period."}, {"role": "assistant", "content": "SELECT st.staff_id,\n st.first_name || ' ' || st.last_name AS full_name,\n st.work_email,\n COUNT(so.order_id) AS delivered_count\nFROM hospitality_technology.staff st\nJOIN hospitality_technology.service_orders so\n ON st.staff_id = so.staff_id_delivered\nWHERE so.status = 'Delivered'\n AND so.delivery_timestamp >= CURRENT_DATE - INTERVAL '30 days'\nGROUP BY st.staff_id, st.first_name, st.last_name, st.work_email\nHAVING COUNT(so.order_id) > 5\nORDER BY delivered_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.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 )\n"} {"conversations": [{"role": "user", "content": "Find cases where an address received tokens in one transfer and then sent tokens in another. List the receive transfer_id, the send transfer_id, the address, and both transfer values."}, {"role": "assistant", "content": "SELECT recv.transfer_id AS receive_transfer_id,\n send.transfer_id AS send_transfer_id,\n recv.to_address AS address,\n recv.value AS received_value,\n send.value AS sent_value\nFROM web3.token_transfers recv\nJOIN web3.token_transfers send\n ON recv.to_address = send.from_address;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE web3.token_transfers (\n transfer_id character varying(64) NOT NULL, -- unique identifier for the transfer\n token_id character varying(64) NOT NULL, -- identifier of the token being transferred\n from_address character varying(128) NOT NULL, -- address of the sender\n to_address character varying(128) NOT NULL, -- address of the receiver\n value numeric(38,14) NOT NULL, -- amount of tokens transferred\n transaction_id character varying(64) NOT NULL, -- identifier of the transaction containing the transfer\n log_index integer NOT NULL, -- index of the transfer log in the transaction\n PRIMARY KEY (transfer_id)\n)\n"} {"conversations": [{"role": "user", "content": "Show all insurance plans where the plan name includes the word 'Care'."}, {"role": "assistant", "content": "SELECT plan_id, plan_name, insurance_provider, plan_type\nFROM healthcare.insurance_plans\nWHERE plan_name ILIKE '%Care%';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.diagnoses ( diagnosis_id.text, record_id.text, patient_id.text, doctor_id.text, diagnosis_code.text, code_type.text, description.text, diagnosis_date.date, status.text, is_chronic.boolean )\nCREATE TABLE healthcare.insurance_plans ( plan_id.text, plan_name.text, insurance_provider.text, plan_type.text, contact_phone.text, website.text )\n"} {"conversations": [{"role": "user", "content": "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": "Count the number of posts that have a media URL but no textual content."}, {"role": "assistant", "content": "SELECT COUNT(*) FROM social_media.posts AS T1 WHERE T1.media_url IS NOT NULL AND (T1.content IS NULL OR T1.content = '');"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE social_media.users (\n user_id character varying(64) NOT NULL, -- unique identifier for the user\n username character varying(50) NOT NULL UNIQUE, -- user's unique handle\n email character varying(128) NOT NULL UNIQUE, -- user's email address\n password_hash text NOT NULL, -- hashed password\n full_name character varying(100), -- user's full name\n profile_picture_url text, -- URL to the profile picture\n bio text, -- short user biography\n location character varying(100), -- user's location\n created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of account creation\n updated_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of last profile update\n is_verified boolean NOT NULL DEFAULT false, -- verification status\n PRIMARY KEY (user_id)\n)\nCREATE TABLE social_media.posts (\n post_id character varying(64) NOT NULL, -- unique identifier for the post\n user_id character varying(64) NOT NULL, -- identifier of the user who created the post (FK to users.user_id)\n content text, -- textual content of the post\n media_url text, -- URL to attached media (image/video)\n media_type character varying(20), -- type of media ('image', 'video', null)\n created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of post creation\n updated_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of last post edit\n visibility character varying(20) NOT NULL DEFAULT 'public', -- visibility ('public', 'friends', 'private')\n location_lat numeric(9,6), -- latitude of post location\n location_lon numeric(9,6), -- longitude of post location\n PRIMARY KEY (post_id)\n)\nCREATE TABLE social_media.comments (\n comment_id character varying(64) NOT NULL, -- unique identifier for the comment\n post_id character varying(64) NOT NULL, -- identifier of the post being commented on (FK to posts.post_id)\n user_id character varying(64) NOT NULL, -- identifier of the user who made the comment (FK to users.user_id)\n parent_comment_id character varying(64), -- identifier of the parent comment if it's a reply (FK to comments.comment_id)\n content text NOT NULL, -- textual content of the comment\n created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of comment creation\n updated_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of last comment edit\n PRIMARY KEY (comment_id)\n)\nCREATE TABLE social_media.likes (\n like_id character varying(64) NOT NULL, -- unique identifier for the like\n user_id character varying(64) NOT NULL, -- identifier of the user who liked (FK to users.user_id)\n post_id character varying(64), -- identifier of the post being liked (FK to posts.post_id, nullable)\n comment_id character varying(64), -- identifier of the comment being liked (FK to comments.comment_id, nullable)\n created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of when the like occurred\n PRIMARY KEY (like_id),\n CONSTRAINT unique_user_like UNIQUE (user_id, post_id, comment_id), -- prevent duplicate likes\n CONSTRAINT check_like_target CHECK (post_id IS NOT NULL OR comment_id IS NOT NULL) -- ensure it likes something\n)\nCREATE TABLE social_media.follows (\n follow_id character varying(64) NOT NULL, -- unique identifier for the follow relationship\n follower_user_id character varying(64) NOT NULL, -- identifier of the user who is following (FK to users.user_id)\n following_user_id character varying(64) NOT NULL, -- identifier of the user being followed (FK to users.user_id)\n created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of when the follow started\n PRIMARY KEY (follow_id),\n CONSTRAINT unique_follow UNIQUE (follower_user_id, following_user_id) -- prevent duplicate follows\n)\nCREATE TABLE social_media.hashtags (\n hashtag_id character varying(64) NOT NULL, -- unique identifier for the hashtag\n tag_name character varying(100) NOT NULL UNIQUE, -- the actual hashtag text (without '#')\n created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp when the hashtag was first used\n PRIMARY KEY (hashtag_id)\n)\nCREATE TABLE social_media.messages (\n message_id character varying(64) NOT NULL, -- unique identifier for the message\n conversation_id character varying(64) NOT NULL, -- identifier for the conversation thread (FK to conversations.conversation_id)\n sender_user_id character varying(64) NOT NULL, -- identifier of the sender (FK to users.user_id)\n content text, -- textual content of the message\n media_url text, -- URL to attached media (image/video)\n media_type character varying(20), -- type of media ('image', 'video', null)\n sent_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp when message was sent\n read_at timestamp, -- timestamp when message was read by recipient(s)\n PRIMARY KEY (message_id)\n)\nCREATE TABLE social_media.conversations (\n conversation_id character varying(64) NOT NULL, -- unique identifier for the conversation\n created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp when conversation was initiated\n last_message_at timestamp, -- timestamp of the last message in the conversation\n is_group_chat boolean NOT NULL DEFAULT false, -- indicates if it's a group chat or direct message\n group_name character varying(100), -- name of the group chat (if applicable)\n PRIMARY KEY (conversation_id)\n)\nCREATE TABLE social_media.conversation_participants (\n participant_id character varying(64) NOT NULL, -- unique identifier for the participant entry\n conversation_id character varying(64) NOT NULL, -- identifier of the conversation (FK to conversations.conversation_id)\n user_id character varying(64) NOT NULL, -- identifier of the user in the conversation (FK to users.user_id)\n joined_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp when user joined the conversation\n last_read_at timestamp, -- timestamp indicating up to when the user has read messages\n PRIMARY KEY (participant_id),\n CONSTRAINT unique_user_conversation UNIQUE (conversation_id, user_id) -- prevent user being added multiple times\n)\nCREATE TABLE social_media.notifications (\n notification_id character varying(64) NOT NULL, -- unique identifier for the notification\n recipient_user_id character varying(64) NOT NULL, -- user receiving the notification (FK to users.user_id)\n sender_user_id character varying(64), -- user triggering the notification (FK to users.user_id, can be null for system notifications)\n notification_type character varying(30) NOT NULL, -- type of notification ('like', 'comment', 'follow', 'mention', 'message')\n target_entity_id character varying(64), -- ID of the related entity (post_id, comment_id, user_id, conversation_id)\n target_entity_type character varying(20), -- type of the related entity ('post', 'comment', 'user', 'conversation')\n created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp notification was created\n read_at timestamp, -- timestamp notification was marked as read\n PRIMARY KEY (notification_id)\n)\nCREATE TABLE social_media.user_settings (\n setting_id character varying(64) NOT NULL, -- unique identifier for the setting entry\n user_id character varying(64) NOT NULL UNIQUE, -- user the settings belong to (FK to users.user_id)\n theme character varying(20) DEFAULT 'light', -- UI theme ('light', 'dark')\n email_notifications_enabled boolean DEFAULT true, -- enable/disable email notifications\n push_notifications_enabled boolean DEFAULT true, -- enable/disable push notifications\n private_profile boolean DEFAULT false, -- is the user profile private\n updated_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of last setting change\n PRIMARY KEY (setting_id)\n)\n"} {"conversations": [{"role": "user", "content": "What are the safety ratings or crash statistics for the Boeing 787 Dreamliner?"}, {"role": "assistant", "content": "I'm sorry, but I don't have access to safety ratings or crash statistics for specific aircraft models like the Boeing 787 Dreamliner. My data is limited to the information in the aircraft_models table, which includes details such as model name, manufacturer, passenger capacity, and technical specifications. For safety-related information, I recommend consulting official aviation authorities or safety 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 ( 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": "Provide a report of each user with their username and the count of all log entries from the last 30 days."}, {"role": "assistant", "content": "SELECT u.user_id, u.username, COUNT(l.log_id) AS log_count\nFROM trading_platform.users u\nLEFT JOIN trading_platform.logs l\n ON u.user_id = l.user_id\n AND l.logged_at >= CURRENT_DATE - INTERVAL '30 days'\nGROUP BY u.user_id, u.username;"}, {"role": "user", "content": "Actually, show only logs where the action includes the word 'trade'."}, {"role": "assistant", "content": "SELECT u.user_id, u.username, COUNT(l.log_id) AS log_count\nFROM trading_platform.users u\nJOIN trading_platform.logs l\n ON u.user_id = l.user_id\nWHERE l.logged_at >= CURRENT_DATE - INTERVAL '30 days'\n AND l.action ILIKE '%trade%'\nGROUP BY u.user_id, u.username;"}, {"role": "user", "content": "Also include the earliest log date for each user in that period."}, {"role": "assistant", "content": "SELECT u.user_id,\n u.username,\n COUNT(l.log_id) AS log_count,\n MIN(l.logged_at) AS first_log_date\nFROM trading_platform.users u\nJOIN trading_platform.logs l\n ON u.user_id = l.user_id\nWHERE l.logged_at >= CURRENT_DATE - INTERVAL '30 days'\n AND l.action ILIKE '%trade%'\nGROUP BY u.user_id, u.username;"}, {"role": "user", "content": "Finally, sort the results by log_count descending and limit to the top 5 users."}, {"role": "assistant", "content": "SELECT u.user_id,\n u.username,\n COUNT(l.log_id) AS log_count,\n MIN(l.logged_at) AS first_log_date\nFROM trading_platform.users u\nJOIN trading_platform.logs l\n ON u.user_id = l.user_id\nWHERE l.logged_at >= CURRENT_DATE - INTERVAL '30 days'\n AND l.action ILIKE '%trade%'\nGROUP BY u.user_id, u.username\nORDER BY log_count DESC\nLIMIT 5;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE trading_platform.users (\n user_id character varying(64) NOT NULL, -- unique identifier for the user\n username character varying(128) NOT NULL, -- username of the user\n email character varying(128) NOT NULL, -- email address of the user\n password_hash text NOT NULL, -- hashed password of the user\n created_at timestamp NOT NULL, -- time when the user account was created\n PRIMARY KEY (user_id)\n)\nCREATE TABLE trading_platform.orders (\n order_id character varying(64) NOT NULL, -- unique identifier for the order\n user_id character varying(64) NOT NULL, -- identifier of the user placing the order\n wallet_id character varying(64) NOT NULL, -- identifier of the wallet used for the order\n asset_id character varying(64) NOT NULL, -- identifier of the asset being traded\n order_type character varying(32) NOT NULL, -- type of the order (e.g., buy, sell)\n quantity numeric(38,14) NOT NULL, -- quantity of the asset in the order\n price numeric(38,14) NOT NULL, -- price per unit of the asset\n status character varying(32) NOT NULL, -- status of the order (e.g., open, filled, canceled)\n created_at timestamp NOT NULL, -- time when the order was created\n PRIMARY KEY (order_id)\n)\nCREATE TABLE trading_platform.utxos (\n utxo_id character varying(64) NOT NULL, -- unique identifier for the UTXO\n transaction_id character varying(64) NOT NULL, -- identifier of the transaction that created the UTXO\n output_index integer NOT NULL, -- index of the output in the transaction\n address character varying(128) NOT NULL, -- address that can spend the UTXO\n amount numeric(38,14) NOT NULL, -- amount of the asset in the UTXO\n spent boolean NOT NULL, -- whether the UTXO has been spent\n PRIMARY KEY (utxo_id)\n)\nCREATE TABLE trading_platform.dapps (\n dapp_id character varying(64) NOT NULL, -- unique identifier for the DApp\n name character varying(128) NOT NULL, -- name of the DApp\n description text NOT NULL, -- description of the DApp\n url character varying(256) NOT NULL, -- URL of the DApp\n PRIMARY KEY (dapp_id)\n)\nCREATE TABLE trading_platform.peers (\n peer_id character varying(64) NOT NULL, -- unique identifier for the peer\n ip_address character varying(15) NOT NULL, -- IP address of the peer\n port integer NOT NULL, -- port number of the peer\n last_seen timestamp NOT NULL, -- last time the peer was active\n PRIMARY KEY (peer_id)\n)\nCREATE TABLE trading_platform.logs (\n log_id character varying(64) NOT NULL, -- unique identifier for the log entry\n user_id character varying(64), -- identifier of the user associated with the log entry\n action character varying(128) NOT NULL, -- action performed\n details text NOT NULL, -- details of the action\n logged_at timestamp NOT NULL, -- time when the log entry was created\n PRIMARY KEY (log_id)\n)\n"} {"conversations": [{"role": "user", "content": "Show 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": "Can you help me retrieve the details of all bookings for a specific route with route_id 'RT789', including the passenger names and the scheduled departure times?"}, {"role": "assistant", "content": "SELECT b.booking_id, p.first_name, p.last_name, s.departure_datetime, b.status, b.total_price\nFROM train_station_management.bookings b\nJOIN train_station_management.passengers p ON b.passenger_id = p.passenger_id\nJOIN train_station_management.schedules s ON b.schedule_id = s.schedule_id\nWHERE s.route_id = 'RT789';"}, {"role": "user", "content": "Can you modify the query to include only bookings with a status of 'Pending'?"}, {"role": "assistant", "content": "SELECT b.booking_id, p.first_name, p.last_name, s.departure_datetime, b.status, b.total_price\nFROM train_station_management.bookings b\nJOIN train_station_management.passengers p ON b.passenger_id = p.passenger_id\nJOIN train_station_management.schedules s ON b.schedule_id = s.schedule_id\nWHERE s.route_id = 'RT789' AND b.status = 'Pending';"}, {"role": "user", "content": "Can you also add the route name and origin station ID to the results?"}, {"role": "assistant", "content": "SELECT b.booking_id, p.first_name, p.last_name, s.departure_datetime, b.status, b.total_price, r.route_name, r.origin_station_id\nFROM train_station_management.bookings b\nJOIN train_station_management.passengers p ON b.passenger_id = p.passenger_id\nJOIN train_station_management.schedules s ON b.schedule_id = s.schedule_id\nJOIN train_station_management.routes r ON s.route_id = r.route_id\nWHERE s.route_id = 'RT789' AND b.status = 'Pending';"}, {"role": "user", "content": "Can you sort the results by departure datetime in descending order?"}, {"role": "assistant", "content": "SELECT b.booking_id, p.first_name, p.last_name, s.departure_datetime, b.status, b.total_price, r.route_name, r.origin_station_id\nFROM train_station_management.bookings b\nJOIN train_station_management.passengers p ON b.passenger_id = p.passenger_id\nJOIN train_station_management.schedules s ON b.schedule_id = s.schedule_id\nJOIN train_station_management.routes r ON s.route_id = r.route_id\nWHERE s.route_id = 'RT789' AND b.status = 'Pending'\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\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.route_stations (\n route_station_id character varying(64) NOT NULL, -- Unique ID for this route-station link\n route_id character varying(64) NOT NULL, -- Foreign key referencing routes\n station_id character varying(64) NOT NULL, -- Foreign key referencing stations\n sequence_order integer NOT NULL, -- Order of the station in the route (1 for origin, 2, 3...)\n distance_from_previous_km numeric(10, 2), -- Distance from the previous station in the sequence\n typical_stop_duration_minutes integer, -- Typical dwell time at this station\n PRIMARY KEY (route_station_id),\n UNIQUE (route_id, station_id),\n UNIQUE (route_id, sequence_order),\n FOREIGN KEY (route_id) REFERENCES train_station_management.routes(route_id),\n FOREIGN KEY (station_id) REFERENCES train_station_management.stations(station_id)\n)\nCREATE TABLE train_station_management.schedules (\n schedule_id character varying(64) NOT NULL, -- Unique identifier for a specific scheduled trip\n train_id character varying(64) NOT NULL, -- Foreign key referencing the train used\n route_id character varying(64) NOT NULL, -- Foreign key referencing the route taken\n departure_datetime timestamp with time zone NOT NULL, -- Scheduled departure time from origin station\n arrival_datetime timestamp with time zone NOT NULL, -- Scheduled arrival time at destination station\n status character varying(32) NOT NULL DEFAULT 'Scheduled', -- e.g., Scheduled, On Time, Delayed, Cancelled, Arrived\n notes text, -- Any notes regarding this specific trip (e.g., reason for delay)\n PRIMARY KEY (schedule_id),\n FOREIGN KEY (train_id) REFERENCES train_station_management.trains(train_id),\n FOREIGN KEY (route_id) REFERENCES train_station_management.routes(route_id)\n)\nCREATE TABLE train_station_management.passengers (\n passenger_id character varying(64) NOT NULL, -- Unique identifier for the passenger\n first_name character varying(100) NOT NULL, -- Passenger's first name\n last_name character varying(100) NOT NULL, -- Passenger's last name\n email character varying(128) UNIQUE, -- Passenger's email address\n phone_number character varying(32) UNIQUE, -- Passenger's phone number\n date_of_birth date, -- Passenger's date of birth\n loyalty_program_id character varying(64), -- ID for loyalty program, if applicable\n created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- When the passenger record was created\n PRIMARY KEY (passenger_id)\n)\nCREATE TABLE train_station_management.bookings (\n booking_id character varying(64) NOT NULL, -- Unique identifier for the booking\n passenger_id character varying(64) NOT NULL, -- Foreign key referencing the passenger\n schedule_id character varying(64) NOT NULL, -- Foreign key referencing the scheduled trip\n booking_datetime timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- When the booking was made\n status character varying(32) NOT NULL DEFAULT 'Confirmed', -- e.g., Confirmed, Cancelled, Pending\n total_price numeric(12, 2) NOT NULL, -- Total price for all tickets in this booking\n currency_code character varying(3) NOT NULL DEFAULT 'USD', -- Currency of the price\n special_requests text, -- Any special requests (e.g., wheelchair assistance)\n PRIMARY KEY (booking_id),\n FOREIGN KEY (passenger_id) REFERENCES train_station_management.passengers(passenger_id),\n FOREIGN KEY (schedule_id) REFERENCES train_station_management.schedules(schedule_id)\n)\nCREATE TABLE train_station_management.staff (\n staff_id character varying(64) NOT NULL, -- Unique identifier for the staff member\n first_name character varying(100) NOT NULL,\n last_name character varying(100) NOT NULL,\n role character varying(64) NOT NULL, -- e.g., Station Master, Ticket Agent, Conductor, Engineer, Maintenance Crew\n primary_station_id character varying(64), -- Base station for the staff member (nullable for mobile staff)\n employee_number character varying(32) UNIQUE NOT NULL, -- Unique employee identifier\n hire_date date NOT NULL,\n contact_email character varying(128) UNIQUE,\n contact_phone character varying(32),\n is_active boolean NOT NULL DEFAULT true, -- Is the staff member currently employed?\n PRIMARY KEY (staff_id),\n FOREIGN KEY (primary_station_id) REFERENCES train_station_management.stations(station_id)\n)\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": "Show me the name and type for all the locations."}, {"role": "assistant", "content": "SELECT name, type FROM transportation.locations"}, {"role": "user", "content": "Now, filter this list to only include locations whose type is either 'Distribution Center' or 'Warehouse'."}, {"role": "assistant", "content": "SELECT name, type FROM transportation.locations WHERE type IN ('Distribution Center', 'Warehouse')"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.locations ( location_id.text, name.text, type.text, address_line1.text, city.text, state_province.text, postal_code.text, country.text, latitude.numeric, longitude.numeric, timezone.text )\n"} {"conversations": [{"role": "user", "content": "I need to find all bookings for a specific schedule with schedule_id 'sched_1122' and include the passenger and ticket details."}, {"role": "assistant", "content": "SMEMBERS schedule:sched_1122:bookings\nHGETALL booking:book_*\nHGETALL passenger:pass_*\nSMEMBERS booking:book_*:tickets\nHGETALL ticket:tkt_*"}, {"role": "user", "content": "Can you filter the tickets to show only those that are not checked in?"}, {"role": "assistant", "content": "SMEMBERS schedule:sched_1122:bookings\nHGETALL booking:book_*\nHGETALL passenger:pass_*\nSMEMBERS booking:book_*:tickets\nHGET ticket:tkt_* is_checked_in\nIF is_checked_in == 0 THEN\nHGETALL ticket:tkt_*\nENDIF"}, {"role": "user", "content": "Can you also include the car details for each ticket?"}, {"role": "assistant", "content": "SMEMBERS schedule:sched_1122:bookings\nHGETALL booking:book_*\nHGETALL passenger:pass_*\nSMEMBERS booking:book_*:tickets\nHGET ticket:tkt_* is_checked_in\nIF is_checked_in == 0 THEN\nHGETALL ticket:tkt_*\nHGET ticket:tkt_* car_id\nHGETALL car:car_*\nENDIF"}], "system": "You are an expert in writing database language. You can write a corresponding database language query to answer the user's question based on the table structure described by the table creation statement. \n##Table Structure\n// Use Hashes for platform details. Key format: platform:\n// HSET platform:plat_123 platform_id \"plat_123\" station_id \"station_xyz\" platform_number \"1A\" track_number \"T1\" status \"Operational\" length_meters 250.50 accessible 1\n\n// To link platforms to stations (optional):\n// SADD station:station_xyz:platforms platform:plat_123 platform:plat_456\n// Use Hashes for train details. Key format: train:\n// HSET train:train_789 train_id \"train_789\" train_number \"Acela 2151\" model \"Siemens Velaro\" ... status \"Active\" ...\n\n// To find train by train_number (optional index):\n// SET train_number:\"Acela 2151\" train:train_789\n// Use Hashes for car details. Key format: car:\n// HSET car:car_abc car_id \"car_abc\" train_id \"train_789\" car_number \"C3\" car_type \"Passenger\" class \"Business\" capacity 60 features \"WiFi,Power Outlet\"\n\n// To link cars to trains (optional):\n// SADD train:train_789:cars car:car_abc car:car_def\n// Use Hashes for details. Key format: route_station:\n// HSET route_station:rs_ne_1 route_station_id \"rs_ne_1\" route_id \"route_ne_corr\" station_id \"station_bos\" sequence_order 1 ...\n\n// To find stops for a route, use a Sorted Set (score by sequence_order):\n// ZADD route:route_ne_corr:stops 1 route_station:rs_ne_1\n// ZADD route:route_ne_corr:stops 2 route_station:rs_ne_2\n// Use Hashes for schedule details. Key format: schedule:\n// HSET schedule:sched_1122 schedule_id \"sched_1122\" train_id \"train_789\" route_id \"route_ne_corr\" departure_datetime \"2024-05-10T08:00:00-04:00\" ... status \"Scheduled\"\n// Use Hashes for details. Key format: schedule_stop:\n// HSET schedule_stop:stop_sched1122_1 stop_id \"stop_sched1122_1\" schedule_id \"sched_1122\" station_id \"station_bos\" ...\n\n// To find stops for a schedule, use a Sorted Set (score by sequence_order):\n// ZADD schedule:sched_1122:stops 1 schedule_stop:stop_sched1122_1\n// ZADD schedule:sched_1122:stops 2 schedule_stop:stop_sched1122_2\n// Use Hashes for passenger details. Key format: passenger:\n// HSET passenger:pass_pqr passenger_id \"pass_pqr\" first_name \"Alice\" last_name \"Smith\" email \"alice.smith@example.com\" ...\n\n// To find passenger by email (optional index):\n// SET passenger_email:\"alice.smith@example.com\" passenger:pass_pqr\n// Use Hashes for booking details. Key format: booking:\n// HSET booking:book_zyx booking_id \"book_zyx\" passenger_id \"pass_pqr\" schedule_id \"sched_1122\" ... status \"Confirmed\" ...\n\n// To link bookings to passengers/schedules (optional):\n// SADD passenger:pass_pqr:bookings booking:book_zyx\n// SADD schedule:sched_1122:bookings booking:book_zyx\n// Use Hashes for ticket details. Key format: ticket:\n// HSET ticket:tkt_1a2b ticket_id \"tkt_1a2b\" booking_id \"book_zyx\" car_id \"car_abc\" seat_number \"12A\" ... is_checked_in 0 ...\n\n// To link tickets to bookings (optional):\n// SADD booking:book_zyx:tickets ticket:tkt_1a2b\n// Use Hashes for staff details. Key format: staff:\n// HSET staff:staff_mno staff_id \"staff_mno\" first_name \"Bob\" ... employee_number \"E12345\" ... is_active 1\n\n// To find staff by employee number (optional index):\n// SET staff_employee_number:\"E12345\" staff:staff_mno\n// Use Hashes for maintenance record details. Key format: maintenance_record:\n// HSET maintenance_record:maint_rec_001 record_id \"maint_rec_001\" asset_id \"train_789\" asset_type \"Train\" ... status \"Completed\"\n\n// To link records to assets (optional):\n// SADD train:train_789:maintenance maintenance_record:maint_rec_001\n// SADD platform:plat_123:maintenance maintenance_record:maint_rec_002\n"} {"conversations": [{"role": "user", "content": "List 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": "List all claims, including the claim ID, incident date, estimated loss, and the name of the insurance product associated with the policy under which the claim was made."}, {"role": "assistant", "content": "SELECT\n c.claim_id,\n c.incident_date,\n c.estimated_loss,\n ip.product_name\nFROM insurance.claims AS c\nJOIN insurance.policies AS p\n ON c.policy_id = p.policy_id\nJOIN insurance.insurance_products AS ip\n ON p.product_id = ip.product_id;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.customers ( customer_id text, first_name text, last_name text, date_of_birth date, ssn_hash text, address_line1 text, address_line2 text, city text, state text, zip_code text, country text, phone_number text, email text, created_at timestamp, updated_at timestamp, status text )\nCREATE TABLE insurance.claims (\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.claim_documents ( document_id character varying(64) NOT NULL, claim_id character varying(64) NOT NULL, document_type character varying(50) NOT NULL, file_name character varying(255) NOT NULL, file_path character varying(512) NOT NULL, file_size_bytes integer, mime_type character varying(100), uploaded_by character varying(64), uploaded_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, description text, PRIMARY KEY (document_id) )\n"} {"conversations": [{"role": "user", "content": "Show me the top 5 ERC20 tokens with the highest total supply, along with their names and contract addresses, but only include tokens where the price is greater than $0.10."}, {"role": "assistant", "content": "SELECT tm.name, tm.contract_address, tm.total_supply FROM token_metas tm JOIN token_prices_latest tpl ON tm.contract_address = tpl.address WHERE tm.is_erc20 = 1 AND tpl.price > 0.10 ORDER BY CAST(tm.total_supply AS decimal) DESC LIMIT 5;"}, {"role": "user", "content": "Can you also include the symbol and decimals for these tokens?"}, {"role": "assistant", "content": "SELECT tm.name, tm.symbol, tm.contract_address, tm.total_supply, tm.decimals FROM token_metas tm JOIN token_prices_latest tpl ON tm.contract_address = tpl.address WHERE tm.is_erc20 = 1 AND tpl.price > 0.10 ORDER BY CAST(tm.total_supply AS decimal) DESC LIMIT 5;"}, {"role": "user", "content": "Now filter these results to only show tokens with decimals equal to 18."}, {"role": "assistant", "content": "SELECT tm.name, tm.symbol, tm.contract_address, tm.total_supply, tm.decimals FROM token_metas tm JOIN token_prices_latest tpl ON tm.contract_address = tpl.address WHERE tm.is_erc20 = 1 AND tpl.price > 0.10 AND tm.decimals = 18 ORDER BY CAST(tm.total_supply AS decimal) DESC LIMIT 5;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE token_metas ( block_timestamp timestamp(6) NOT NULL, block_number bigint NOT NULL, transaction_hash varchar NOT NULL, transaction_index bigint NOT NULL, from_address varchar NOT NULL, contract_address varchar NOT NULL, symbol varchar NOT NULL, total_supply varchar NOT NULL, name varchar NOT NULL, decimals bigint NOT NULL, is_erc20 integer NOT NULL, is_erc721 integer NOT NULL, is_erc1155 integer NOT NULL, is_proxy integer NOT NULL, extra_info varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE erc1155_approval_for_all ( block_number bigint NOT NULL, block_timestamp timestamp(3) NOT NULL, transaction_index integer NOT NULL, transaction_hash varchar(66) NOT NULL, log_index integer NOT NULL, contract_address varchar(42) NOT NULL )\nCREATE TABLE erc20_balances ( block_number bigint NOT NULL, contract_address varchar NOT NULL, wallet_address varchar NOT NULL, amount varchar NOT NULL, pk varchar NOT NULL )\nCREATE TABLE erc20_balances_historical ( block_number bigint NOT NULL, contract_address varchar NOT NULL, wallet_address varchar NOT NULL, amount varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE nft_holders ( block_number bigint NOT NULL, contract_address varchar NOT NULL, wallet_address varchar NOT NULL, token_id varchar NOT NULL, contract_type varchar NOT NULL, amount varchar NOT NULL, pk varchar NOT NULL )\nCREATE TABLE nft_holder_historical ( block_number bigint NOT NULL, contract_address varchar NOT NULL, wallet_address varchar NOT NULL, token_id varchar NOT NULL, contract_type varchar NOT NULL, amount varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE sui_coins ( object_id varchar NOT NULL, status varchar NOT NULL, coin_type varchar NOT NULL, balance varchar NOT NULL, owner varchar NOT NULL )\nCREATE TABLE sui_coins_metadata ( object_id varchar NOT NULL, coin_type varchar NOT NULL, status varchar NOT NULL, decimals bigint NOT NULL, description varchar NOT NULL, icon_url varchar NOT NULL, symbol varchar NOT NULL, name varchar NOT NULL )\nCREATE TABLE sui_nfts ( object_id varchar NOT NULL, status varchar NOT NULL, collection_type varchar NOT NULL, package_id varchar NOT NULL, previous_transaction varchar NOT NULL, display varchar NOT NULL, owner varchar NOT NULL, name varchar NOT NULL )\nCREATE TABLE nft_metadata ( blockchain varchar NOT NULL, contract_address varchar NOT NULL, token_id varchar NOT NULL, contract_name varchar NOT NULL, erc_type varchar NOT NULL, amount bigint NOT NULL, minter varchar NOT NULL, owner varchar NOT NULL, mint_block_number bigint NOT NULL, mint_time bigint NOT NULL, mint_transaction_hash varchar NOT NULL, mint_price varchar NOT NULL, token_uri varchar NOT NULL, metadata varchar NOT NULL, name varchar NOT NULL, image_uri varchar NOT NULL, traits varchar NOT NULL, updated_at bigint NOT NULL, status varchar NOT NULL, rarity_score real NOT NULL, rarity_rank integer NOT NULL, unique_attribute_count integer NOT NULL, pk integer NOT NULL )\nCREATE TABLE nft_collections ( blockchain varchar NOT NULL, contract_address varchar NOT NULL, name varchar NOT NULL, symbol varchar NOT NULL, deploy_block_number bigint NOT NULL, deploy_block_time bigint NOT NULL, erc_type varchar NOT NULL, owner varchar NOT NULL, traits varchar NOT NULL, description varchar NOT NULL, slug varchar NOT NULL, media_info varchar NOT NULL, image_url varchar NOT NULL, banner_image_url varchar NOT NULL, updated_at bigint NOT NULL, banner varchar NOT NULL, token_count bigint NOT NULL, floor_price varchar NOT NULL, floor_price_symbol varchar NOT NULL, floor_price_contract varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE token_prices ( uuid varchar(36) NOT NULL, blockchain varchar(36) NOT NULL, address varchar(42) NOT NULL, decimals bigint NOT NULL, symbol varchar(36) NOT NULL, price real NOT NULL, timestamp timestamp(6) NOT NULL )\nCREATE TABLE token_prices_latest ( blockchain varchar(36) NOT NULL, address varchar(42) NOT NULL, decimals bigint NOT NULL, symbol varchar(36) NOT NULL, price real NOT NULL, timestamp timestamp(6) NOT NULL )\nCREATE TABLE erc20_approval ( block_number bigint NOT NULL, block_timestamp timestamp(6) NOT NULL, transaction_index integer NOT NULL, transaction_hash varchar NOT NULL, log_index integer NOT NULL, contract_address varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE token_balances ( block_number bigint NOT NULL, block_timestamp timestamp(3) NOT NULL, tick varchar NOT NULL, wallet_address varchar(42) NOT NULL, total_supply decimal(38,0) NOT NULL, amount decimal(38,0) NOT NULL )\nCREATE TABLE token_info ( block_timestamp timestamp(3) NOT NULL, block_number bigint NOT NULL, tx_index integer NOT NULL, tx_hash varchar(66) NOT NULL, tick varchar NOT NULL, max_supply decimal(38,0) NOT NULL, lim decimal(38,0) NOT NULL, wlim decimal(38,0) NOT NULL, dec integer NOT NULL, creator varchar(42) NOT NULL )\nCREATE TABLE token_activities ( block_timestamp timestamp(3) NOT NULL, block_number bigint NOT NULL, tx_index integer NOT NULL, tx_hash varchar(66) NOT NULL, log_index integer NOT NULL, type varchar NOT NULL, tick varchar NOT NULL, id varchar(255) NOT NULL, amt decimal(38,0) NOT NULL, from_address varchar(42) NOT NULL, to_address varchar(42) NOT NULL )\nCREATE TABLE mud_holesky_redstone ( address varchar NOT NULL, table_id varchar NOT NULL, key_bytes varchar NOT NULL, key0 varchar NOT NULL, key1 varchar NOT NULL, static_data varchar NOT NULL, encoded_lengths varchar NOT NULL, dynamic_data varchar NOT NULL, is_deleted boolean NOT NULL, block_number bigint NOT NULL, log_index bigint NOT NULL )\nCREATE TABLE token_balances_bitcoin ( block_number bigint NOT NULL, block_timestamp timestamp(3) NOT NULL, tick varchar(255) NOT NULL, wallet_address varchar(42) NOT NULL, total_supply varchar NOT NULL, amount varchar NOT NULL )\nCREATE TABLE token_activities_bitcoin ( block_timestamp timestamp(3) NOT NULL, block_number bigint NOT NULL, tx_index integer NOT NULL, tx_hash varchar(66) NOT NULL, log_index integer NOT NULL, type varchar(20) NOT NULL, tick varchar(255) NOT NULL, id varchar(255) NOT NULL, amt decimal(38,0) NOT NULL, from_address varchar(62) NOT NULL, to_address varchar(62) NOT NULL )\nCREATE TABLE token_activities_avalanche ( block_timestamp timestamp(3) NOT NULL, block_number bigint NOT NULL, tx_index integer NOT NULL, tx_hash varchar(66) NOT NULL, log_index integer NOT NULL, type varchar(20) NOT NULL, tick varchar(255) NOT NULL, id varchar(255) NOT NULL, amt decimal(38,0) NOT NULL, from_address varchar(42) NOT NULL, to_address varchar(42) NOT NULL )\nCREATE TABLE token_balances_avalanche ( block_number bigint NOT NULL, block_timestamp timestamp(3) NOT NULL, tick varchar(20) NOT NULL, wallet_address varchar(42) NOT NULL, total_supply decimal(38,0) NOT NULL, amount decimal(38,0) NOT NULL )\nCREATE TABLE token_info_avalanche ( block_timestamp timestamp(3) NOT NULL, block_number bigint NOT NULL, tx_index integer NOT NULL, tx_hash varchar(66) NOT NULL, tick varchar(20) NOT NULL, max_supply decimal(38,0) NOT NULL, lim decimal(38,0) NOT NULL, wlim decimal(38,0) NOT NULL, dec integer NOT NULL, creator varchar(42) NOT NULL, minted decimal(38,0) NOT NULL, holders decimal(38,0) NOT NULL, txs decimal(38,0) NOT NULL, updated_timestamp timestamp(3) NOT NULL, completed_timestamp timestamp(3) NOT NULL, id varchar(255) NOT NULL )\n"} {"conversations": [{"role": "user", "content": "How many payments were made using the payment method 'Credit Card'?"}, {"role": "assistant", "content": "SELECT COUNT(*) AS credit_card_payments\nFROM government_services.payments\nWHERE payment_method = 'Credit Card';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.citizens ( citizen_id text PRIMARY KEY, national_id_number text, first_name text, last_name text, date_of_birth date, gender text, primary_address text, contact_email text, contact_phone text, registration_date timestamp, is_verified boolean )\nCREATE TABLE government_services.applications ( application_id text PRIMARY KEY, citizen_id text, service_id text, submitted_at timestamp, status text, last_updated_at timestamp, assigned_employee_id text, decision_date date, notes text, reference_number text )\nCREATE TABLE government_services.payments ( payment_id text PRIMARY KEY, application_id text, citizen_id text, service_id text, amount numeric, currency text, payment_method text, payment_provider_reference text, payment_timestamp timestamp, status text, notes text )\nCREATE TABLE government_services.service_locations ( location_id text PRIMARY KEY, agency_id text, location_name text, address text, city text, state text, postal_code text, latitude numeric, longitude numeric, operating_hours text, contact_phone text, is_accessible boolean )\nCREATE TABLE government_services.appointments ( appointment_id text PRIMARY KEY, citizen_id text, employee_id text, location_id text, service_id text, scheduled_start_time timestamp, scheduled_end_time timestamp, purpose text, status text, booking_method text, created_at timestamp, notes text )\nCREATE TABLE government_services.notifications ( notification_id text PRIMARY KEY, citizen_id text, application_id text, message_subject text, message_body text, channel text, sent_at timestamp, status text, related_entity_type text, related_entity_id text )\n"} {"conversations": [{"role": "user", "content": "List 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": "What are the training programs or certifications completed by a staff member with the role of Platform Supervisor?"}, {"role": "assistant", "content": "I'm sorry, but I don't have access to information about the training programs or certifications completed by staff members. The data available to me only includes basic staff details such as name, role, and contact information. For details on training or certifications, please refer to the HR department or relevant training records."}], "system": "You are an SQL statement expert and you can refuse the user's question if the question is not related to the table structure. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE train_station_management.staff ( staff_id text PRIMARY KEY, first_name text, last_name text, role text, primary_station_id text, employee_number text UNIQUE, hire_date date, contact_email text UNIQUE, contact_phone text, is_active boolean )\n"} {"conversations": [{"role": "user", "content": "Return the number of top-level comments and the number of replies in the comments table."}, {"role": "assistant", "content": "SELECT\n SUM(CASE WHEN parent_comment_id IS NULL THEN 1 ELSE 0 END) AS top_level_comments,\n SUM(CASE WHEN parent_comment_id IS NOT NULL THEN 1 ELSE 0 END) AS reply_comments\nFROM social_media.comments;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE social_media.users ( user_id text, username text, email text, password_hash text, full_name text, profile_picture_url text, bio text, location text, created_at timestamp, updated_at timestamp, is_verified boolean )\nCREATE TABLE social_media.posts ( post_id text, user_id text, content text, media_url text, media_type text, created_at timestamp, updated_at timestamp, visibility text, location_lat numeric, location_lon numeric )\nCREATE TABLE social_media.comments ( comment_id text, post_id text, user_id text, parent_comment_id text, content text, created_at timestamp, updated_at timestamp )\nCREATE TABLE social_media.follows ( follow_id text, follower_user_id text, following_user_id text, created_at timestamp )\nCREATE TABLE social_media.post_hashtags ( post_hashtag_id text, post_id text, hashtag_id text )\nCREATE TABLE social_media.conversations ( conversation_id text, created_at timestamp, last_message_at timestamp, is_group_chat boolean, group_name text )\nCREATE TABLE social_media.notifications ( notification_id text, recipient_user_id text, sender_user_id text, notification_type text, target_entity_id text, target_entity_type text, created_at timestamp, read_at timestamp )\n"} {"conversations": [{"role": "user", "content": "I need to retrieve asset IDs along with their category and website metadata values for assets that have both entries."}, {"role": "assistant", "content": "SELECT m_cat.asset_id,\n m_cat.value AS category,\n m_web.value AS website_url\nFROM trading_platform.metadata m_cat\nJOIN trading_platform.metadata m_web\n ON m_cat.asset_id = m_web.asset_id\nWHERE m_cat.key = 'category'\n AND m_web.key = 'website';"}, {"role": "user", "content": "Actually, filter to include only those assets where the category value is 'defi'."}, {"role": "assistant", "content": "SELECT m_cat.asset_id,\n m_cat.value AS category,\n m_web.value AS website_url\nFROM trading_platform.metadata m_cat\nJOIN trading_platform.metadata m_web\n ON m_cat.asset_id = m_web.asset_id\nWHERE m_cat.key = 'category'\n AND m_web.key = 'website'\n AND m_cat.value = 'defi';"}], "system": "You are an SQL statement expert. Given the table structure 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.metadata ( metadata_id character varying(64) NOT NULL, asset_id character varying(64) NOT NULL, key character varying(128) NOT NULL, value text NOT NULL, PRIMARY KEY (metadata_id) )\n"} {"conversations": [{"role": "user", "content": "List all users whose password hash contains the substring 'abc'."}, {"role": "assistant", "content": "SELECT user_id, username, password_hash FROM blockchain.users WHERE password_hash LIKE '%abc%';"}, {"role": "user", "content": "Also include their email address."}, {"role": "assistant", "content": "SELECT user_id, username, password_hash, email FROM blockchain.users WHERE password_hash LIKE '%abc%';"}, {"role": "user", "content": "Filter to only show users whose username does *not* contain 'test'."}, {"role": "assistant", "content": "SELECT user_id, username, password_hash, email FROM blockchain.users WHERE password_hash LIKE '%abc%' AND username NOT LIKE '%test%';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE blockchain.wallets ( wallet_id.text, user_id.text, address_id.text, private_key.text )\nCREATE TABLE blockchain.users ( user_id.text, username.text, email.text, password_hash.text )\n"} {"conversations": [{"role": "user", "content": "List active policies where the premium amount is greater than the base premium of the linked insurance product. Show policy number, policy premium, product name, and product base premium."}, {"role": "assistant", "content": "SELECT T1.policy_number, T1.premium_amount, T2.product_name, T2.base_premium FROM insurance.policies AS T1 JOIN insurance.insurance_products AS T2 ON T1.product_id = T2.product_id WHERE T1.status = 'active' AND T1.premium_amount > T2.base_premium;"}, {"role": "user", "content": "Also, only include policies that were issued in the year 2023."}, {"role": "assistant", "content": "SELECT T1.policy_number, T1.premium_amount, T2.product_name, T2.base_premium FROM insurance.policies AS T1 JOIN insurance.insurance_products AS T2 ON T1.product_id = T2.product_id WHERE T1.status = 'active' AND T1.premium_amount > T2.base_premium AND EXTRACT(YEAR FROM T1.issued_at) = 2023;"}, {"role": "user", "content": "Could you sort the results by policy premium in descending order and limit to the top 10?"}, {"role": "assistant", "content": "SELECT T1.policy_number, T1.premium_amount, T2.product_name, T2.base_premium FROM insurance.policies AS T1 JOIN insurance.insurance_products AS T2 ON T1.product_id = T2.product_id WHERE T1.status = 'active' AND T1.premium_amount > T2.base_premium AND EXTRACT(YEAR FROM T1.issued_at) = 2023 ORDER BY T1.premium_amount 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 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 claims that were reported more than 30 days after the incident date."}, {"role": "assistant", "content": "SELECT claim_id, policy_id, customer_id, incident_date, reported_date FROM insurance.claims WHERE DATEDIFF(reported_date, incident_date) > 30;"}, {"role": "user", "content": "Now show only claims that are still pending (status = 'pending')."}, {"role": "assistant", "content": "SELECT claim_id, policy_id, customer_id, incident_date, reported_date FROM insurance.claims WHERE DATEDIFF(reported_date, incident_date) > 30 AND status = 'pending';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE 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 )\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 plan_id, plan_name, and plan_type for all insurance plans where the insurance_provider is 'Humana'."}, {"role": "assistant", "content": "SELECT\n plan_id,\n plan_name,\n plan_type\nFROM healthcare.insurance_plans\nWHERE\n insurance_provider = 'Humana';"}], "system": "You are an SQL statement expert. Given the table structure 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": "Show me the top 5 users by the total number of trades they participated in as sellers, along with their wallet addresses."}, {"role": "assistant", "content": "SELECT t.seller_id, w.address, COUNT(t.trade_id) AS total_trades FROM trading_platform.trades t JOIN trading_platform.wallets w ON t.seller_id = w.user_id GROUP BY t.seller_id, w.address ORDER BY total_trades DESC LIMIT 5;"}, {"role": "user", "content": "Now modify the query to include the total trade volume (quantity * price) for each of these sellers."}, {"role": "assistant", "content": "SELECT t.seller_id, w.address, COUNT(t.trade_id) AS total_trades, SUM(t.quantity * t.price) AS total_volume FROM trading_platform.trades t JOIN trading_platform.wallets w ON t.seller_id = w.user_id GROUP BY t.seller_id, w.address ORDER BY total_trades DESC LIMIT 5;"}, {"role": "user", "content": "Actually, I want to see the top 5 sellers by total trade volume instead of number of trades."}, {"role": "assistant", "content": "SELECT t.seller_id, w.address, SUM(t.quantity * t.price) AS total_volume FROM trading_platform.trades t JOIN trading_platform.wallets w ON t.seller_id = w.user_id GROUP BY t.seller_id, w.address ORDER BY total_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.wallets ( wallet_id character varying(64) NOT NULL, user_id character varying(64) NOT NULL, address character varying(128) NOT NULL, private_key text NOT NULL, created_at timestamp NOT NULL, PRIMARY KEY (wallet_id) )\nCREATE TABLE trading_platform.orders ( order_id character varying(64) NOT NULL, user_id character varying(64) NOT NULL, wallet_id character varying(64) NOT NULL, asset_id character varying(64) NOT NULL, order_type character varying(32) NOT NULL, quantity numeric(38,14) NOT NULL, price numeric(38,14) NOT NULL, status character varying(32) NOT NULL, created_at timestamp NOT NULL, PRIMARY KEY (order_id) )\nCREATE TABLE trading_platform.trades ( trade_id character varying(64) NOT NULL, order_id character varying(64) NOT NULL, buyer_id character varying(64) NOT NULL, seller_id character varying(64) NOT NULL, asset_id character varying(64) NOT NULL, quantity numeric(38,14) NOT NULL, price numeric(38,14) NOT NULL, traded_at timestamp NOT NULL, PRIMARY KEY (trade_id) )\nCREATE TABLE trading_platform.assets ( asset_id character varying(64) NOT NULL, name character varying(128) NOT NULL, symbol character varying(32) NOT NULL, type character varying(32) NOT NULL, PRIMARY KEY (asset_id) )\nCREATE TABLE trading_platform.utxos ( utxo_id character varying(64) NOT NULL, transaction_id character varying(64) NOT NULL, output_index integer NOT NULL, address character varying(128) NOT NULL, amount numeric(38,14) NOT NULL, spent boolean NOT NULL, PRIMARY KEY (utxo_id) )\nCREATE TABLE trading_platform.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": "Show each wallet address that has received token transfers of more than one type of token, along with the count of token types received."}, {"role": "assistant", "content": "SELECT tt.to_address, COUNT(DISTINCT tt.token_id) AS token_type_count\nFROM web3.token_transfers tt\nGROUP BY tt.to_address\nHAVING COUNT(DISTINCT tt.token_id) > 1;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE web3.contracts ( contract_id text PRIMARY KEY, address text, abi text, bytecode text, deployer_address text, deployed_at timestamp, network_id text, status text )\nCREATE TABLE web3.events ( event_id character varying(64) NOT NULL, contract_id character varying(64) NOT NULL, event_name character varying(128) NOT NULL, data text NOT NULL, emitted_at timestamp NOT NULL, transaction_id character varying(64) NOT NULL, log_index integer NOT NULL, PRIMARY KEY (event_id) )\nCREATE TABLE web3.tokens (\n token_id character varying(64) NOT NULL, -- unique identifier for the token\n contract_address character varying(128) NOT NULL, -- address of the token contract\n token_name character varying(128) NOT NULL, -- name of the token\n token_symbol character varying(32) NOT NULL, -- symbol of the token\n decimals integer NOT NULL, -- number of decimals for the token\n total_supply numeric(38,14) NOT NULL, -- total supply of the token\n PRIMARY KEY (token_id)\n)\nCREATE TABLE web3.token_transfers ( transfer_id character varying(64) NOT NULL, token_id character varying(64) NOT NULL, from_address character varying(128) NOT NULL, to_address character varying(128) NOT NULL, value numeric(38,14) NOT NULL, transaction_id character varying(64) NOT NULL, log_index integer NOT NULL, PRIMARY KEY (transfer_id) )\nCREATE TABLE web3.wallets (\n wallet_id character varying(64) NOT NULL, -- unique identifier for the wallet\n user_id character varying(64) NOT NULL, -- identifier of the user owning the wallet\n address character varying(128) NOT NULL, -- address of the wallet\n private_key text NOT NULL, -- private key of the wallet\n created_at timestamp NOT NULL, -- time when the wallet was created\n PRIMARY KEY (wallet_id)\n)\nCREATE TABLE web3.users (\n user_id character varying(64) NOT NULL, -- unique identifier for the user\n username character varying(128) NOT NULL, -- username of the user\n email character varying(128) NOT NULL, -- email address of the user\n password_hash text NOT NULL, -- hashed password of the user\n created_at timestamp NOT NULL, -- time when the user account was created\n PRIMARY KEY (user_id)\n)\n"} {"conversations": [{"role": "user", "content": "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": "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": "List user IDs of users who have private profiles and have liked any post or comment."}, {"role": "assistant", "content": "SELECT DISTINCT T1.user_id FROM social_media.user_settings AS T1 JOIN social_media.likes AS T2 ON T1.user_id = T2.user_id WHERE T1.private_profile = true;"}, {"role": "user", "content": "Now, only show those who have push notifications enabled as well."}, {"role": "assistant", "content": "SELECT DISTINCT T1.user_id FROM social_media.user_settings AS T1 JOIN social_media.likes AS T2 ON T1.user_id = T2.user_id WHERE T1.private_profile = true AND T1.push_notifications_enabled = 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.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.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.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": "List all beneficiaries added in the last 6 months, showing their full names and relationship to the policyholder."}, {"role": "assistant", "content": "SELECT first_name, last_name, relationship FROM insurance.policy_beneficiaries WHERE added_at >= NOW() - INTERVAL '6 months';"}, {"role": "user", "content": "Now include only those beneficiaries who have a contact_info field that contains an email address."}, {"role": "assistant", "content": "SELECT first_name, last_name, relationship FROM insurance.policy_beneficiaries WHERE added_at >= NOW() - INTERVAL '6 months' AND contact_info LIKE '%@%';"}], "system": "You are an SQL statement expert. Given the table structure 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.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 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": "List all medical record entries where the treatment_plan mentions a medication name. Return patient_id, record_id, and the matching medication_name."}, {"role": "assistant", "content": "SELECT mr.patient_id,\n mr.record_id,\n m.medication_name\nFROM healthcare.medical_records AS mr\nJOIN healthcare.medications AS m\n ON mr.treatment_plan ILIKE '%' || m.medication_name || '%';"}, {"role": "user", "content": "Actually, only include medications manufactured by 'Pfizer'."}, {"role": "assistant", "content": "SELECT mr.patient_id,\n mr.record_id,\n m.medication_name\nFROM healthcare.medical_records AS mr\nJOIN healthcare.medications AS m\n ON mr.treatment_plan ILIKE '%' || m.medication_name || '%'\nWHERE m.manufacturer = 'Pfizer';"}, {"role": "user", "content": "Also sort the results by record_date descending."}, {"role": "assistant", "content": "SELECT mr.patient_id,\n mr.record_id,\n m.medication_name\nFROM healthcare.medical_records AS mr\nJOIN healthcare.medications AS m\n ON mr.treatment_plan ILIKE '%' || m.medication_name || '%'\nWHERE m.manufacturer = 'Pfizer'\nORDER BY mr.record_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 healthcare.patients (\n patient_id character varying(64) NOT NULL, -- unique identifier for the patient\n first_name character varying(100) NOT NULL, -- patient's first name\n last_name character varying(100) NOT NULL, -- patient's last name\n date_of_birth date NOT NULL, -- patient's date of birth\n gender character varying(10), -- patient's gender (e.g., Male, Female, Other)\n address text, -- patient's home address\n phone_number character varying(20), -- patient's phone number\n email character varying(128) UNIQUE, -- patient's email address\n emergency_contact_name character varying(200), -- name of emergency contact\n emergency_contact_phone character varying(20), -- phone number of emergency contact\n created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, -- record creation time\n updated_at timestamp with time zone NOT NULL DEFAULT current_timestamp, -- record last update time\n PRIMARY KEY (patient_id)\n)\nCREATE TABLE healthcare.doctors (\n doctor_id character varying(64) NOT NULL, -- unique identifier for the doctor\n first_name character varying(100) NOT NULL, -- doctor's first name\n last_name character varying(100) NOT NULL, -- doctor's last name\n specialty character varying(100) NOT NULL, -- doctor's medical specialty\n license_number character varying(50) UNIQUE NOT NULL, -- doctor's medical license number\n phone_number character varying(20), -- doctor's contact phone\n email character varying(128) UNIQUE, -- doctor's contact email\n hospital_affiliation_id character varying(64), -- FK to hospitals table (optional)\n created_at timestamp with time zone NOT NULL DEFAULT current_timestamp,\n updated_at timestamp with time zone NOT NULL DEFAULT current_timestamp,\n PRIMARY KEY (doctor_id)\n)\nCREATE TABLE healthcare.appointments (\n appointment_id character varying(64) NOT NULL, -- unique identifier for the appointment\n patient_id character varying(64) NOT NULL, -- FK to patients table\n doctor_id character varying(64) NOT NULL, -- FK to doctors table\n appointment_time timestamp with time zone NOT NULL, -- date and time of the appointment\n duration_minutes integer NOT NULL, -- expected duration in minutes\n reason text, -- reason for the visit\n status character varying(32) NOT NULL, -- e.g., Scheduled, Completed, Cancelled, No-show\n location_id character varying(64), -- FK to a potential locations/clinics table\n notes text, -- notes related to scheduling\n created_at timestamp with time zone NOT NULL DEFAULT current_timestamp,\n PRIMARY KEY (appointment_id)\n)\nCREATE TABLE healthcare.medical_records (\n record_id character varying(64) NOT NULL, -- unique identifier for the medical record entry\n patient_id character varying(64) NOT NULL, -- FK to patients table\n appointment_id character varying(64) UNIQUE, -- FK to appointments table (can be null if record not tied to specific appt)\n doctor_id character varying(64) NOT NULL, -- FK to doctors table (doctor creating the record)\n record_date timestamp with time zone NOT NULL, -- date the record/observation was made\n chief_complaint text, -- patient's primary reason for visit\n present_illness_history text, -- detailed history of the current issue\n past_medical_history text, -- relevant past conditions/surgeries\n physical_examination_notes text, -- findings from the physical exam\n assessment text, -- doctor's assessment/diagnosis summary\n treatment_plan text, -- planned course of action\n vitals jsonb, -- store vitals like BP, HR, Temp as structured JSON\n created_at timestamp with time zone NOT NULL DEFAULT current_timestamp,\n PRIMARY KEY (record_id)\n)\nCREATE TABLE healthcare.medications (\n medication_id character varying(64) NOT NULL, -- unique identifier for the medication type\n medication_name character varying(255) NOT NULL, -- common or brand name\n generic_name character varying(255), -- generic chemical name\n manufacturer character varying(100), -- drug manufacturer\n ndc_code character varying(20) UNIQUE, -- National Drug Code (optional but useful)\n description text, -- description of the medication\n PRIMARY KEY (medication_id)\n)\nCREATE TABLE healthcare.insurance_plans (\n plan_id character varying(64) NOT NULL, -- unique identifier for the insurance plan\n plan_name character varying(200) NOT NULL, -- name of the insurance plan\n insurance_provider character varying(100) NOT NULL, -- name of the insurance company\n plan_type character varying(50), -- e.g., PPO, HMO, EPO\n contact_phone character varying(20), -- provider contact number\n website character varying(255), -- provider website\n PRIMARY KEY (plan_id)\n)\nCREATE TABLE healthcare.patient_insurance (\n patient_insurance_id character varying(64) NOT NULL, -- unique identifier for this patient-plan link\n patient_id character varying(64) NOT NULL, -- FK to patients table\n plan_id character varying(64) NOT NULL, -- FK to insurance_plans table\n policy_number character varying(100) NOT NULL, -- patient's policy number\n group_number character varying(100), -- group number, if applicable\n subscriber_name character varying(200), -- name of the primary policy holder\n effective_date date NOT NULL, -- date the coverage begins\n expiration_date date, -- date the coverage ends (if known)\n is_primary boolean NOT NULL DEFAULT true, -- indicates if this is the primary insurance\n PRIMARY KEY (patient_insurance_id),\n UNIQUE (patient_id, plan_id, policy_number) -- ensure a patient doesn't have the same policy twice\n)\n"} {"conversations": [{"role": "user", "content": "특정 품질 등급 이상의 공급업체를 조회하고 싶습니다. 품질 등급, 공급업체 이름, 국가를 포함해 주세요."}, {"role": "assistant", "content": "GET suppliers/_search\n{\n \"query\": {\n \"range\": {\n \"quality_rating\": {\n \"gte\": 4.0\n }\n }\n },\n \"_source\": [\"supplier_name\", \"country\", \"quality_rating\"]\n}"}, {"role": "user", "content": "특정 국가에 속한 공급업체만 추가로 필터링하고 싶습니다. 예를 들어, 일본 소속 공급업체로 제한하고 싶습니다."}, {"role": "assistant", "content": "GET suppliers/_search\n{\n \"query\": {\n \"bool\": {\n \"must\": [\n {\n \"range\": {\n \"quality_rating\": {\n \"gte\": 4.0\n }\n }\n },\n {\n \"term\": {\n \"country\": \"Japan\"\n }\n }\n ]\n }\n },\n \"_source\": [\"supplier_name\", \"country\", \"quality_rating\"]\n}"}, {"role": "user", "content": "연락처 담당자 이름과 인증 날짜도 결과에 포함해 주세요."}, {"role": "assistant", "content": "GET suppliers/_search\n{\n \"query\": {\n \"bool\": {\n \"must\": [\n {\n \"range\": {\n \"quality_rating\": {\n \"gte\": 4.0\n }\n }\n },\n {\n \"term\": {\n \"country\": \"Japan\"\n }\n }\n ]\n }\n },\n \"_source\": [\"supplier_name\", \"country\", \"quality_rating\", \"contact_person\", \"certified_date\"]\n}"}, {"role": "user", "content": "인증 날짜를 기준으로 오름차순 정렬을 추가해 주세요."}, {"role": "assistant", "content": "GET suppliers/_search\n{\n \"query\": {\n \"bool\": {\n \"must\": [\n {\n \"range\": {\n \"quality_rating\": {\n \"gte\": 4.0\n }\n }\n },\n {\n \"term\": {\n \"country\": \"Japan\"\n }\n }\n ]\n }\n },\n \"_source\": [\"supplier_name\", \"country\", \"quality_rating\", \"contact_person\", \"certified_date\"],\n \"sort\": [\n {\n \"certified_date\": {\n \"order\": \"asc\"\n }\n }\n ]\n}"}], "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\nIndex 'suppliers'. Mapping: { properties: { supplier_id: { type: 'keyword' }, supplier_name: { type: 'text', fields: { keyword: { type: 'keyword', ignore_above: 256 } } }, address: { type: 'text' }, country: { type: 'keyword' }, contact_person: { type: 'text', index: false }, contact_email: { type: 'keyword' }, quality_rating: { type: 'float' }, certified_date: { type: 'date' } } }. Document _id can be supplier_id.\n"} {"conversations": [{"role": "user", "content": "How many events were emitted on each date? List the date and the count of events."}, {"role": "assistant", "content": "SELECT DATE(emitted_at) AS emit_date,\n COUNT(*) AS event_count\nFROM web3.events\nGROUP BY DATE(emitted_at);"}, {"role": "user", "content": "Actually, only include dates where more than 10 events were emitted."}, {"role": "assistant", "content": "SELECT DATE(emitted_at) AS emit_date,\n COUNT(*) AS event_count\nFROM web3.events\nGROUP BY DATE(emitted_at)\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 web3.events ( event_id character varying(64) NOT NULL, contract_id character varying(64) NOT NULL, event_name character varying(128) NOT NULL, data text NOT NULL, emitted_at timestamp NOT NULL, transaction_id character varying(64) NOT NULL, log_index integer NOT NULL, PRIMARY KEY (event_id) )\n"} {"conversations": [{"role": "user", "content": "Can you help me get the total number of operational platforms across all stations?"}, {"role": "assistant", "content": "db.platforms.countDocuments({ status: 'Operational' });"}], "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// db.createCollection('platforms')\n// Optional: db.platforms.createIndex({ platform_id: 1 }, { unique: true })\n// Optional: db.platforms.createIndex({ station_id: 1 })\n{\n _id: ObjectId(),\n platform_id: \"plat_123\", // String (unique)\n station_id: \"station_xyz\", // String (references stations.station_id)\n platform_number: \"1A\", // String\n track_number: \"T1\", // String\n status: \"Operational\", // String ('Operational', 'Maintenance', 'Closed')\n length_meters: 250.50, // Decimal128 or Double\n accessible: true // Boolean\n}\n// db.createCollection('routes')\n// Optional: db.routes.createIndex({ route_id: 1 }, { unique: true })\n{\n _id: ObjectId(),\n route_id: \"route_ne_corr\", // String (unique)\n route_name: \"Northeast Corridor\", // String\n description: \"High-speed rail linking Boston and Washington D.C.\", // String\n origin_station_id: \"station_bos\", // String (references stations.station_id)\n destination_station_id: \"station_was\", // String (references stations.station_id)\n is_active: true // Boolean\n}\n// db.createCollection('route_stations')\n// Optional: db.route_stations.createIndex({ route_station_id: 1 }, { unique: true })\n// Optional: db.route_stations.createIndex({ route_id: 1, sequence_order: 1 }, { unique: true })\n{\n _id: ObjectId(),\n route_station_id: \"rs_ne_1\", // String (unique)\n route_id: \"route_ne_corr\", // String (references routes.route_id)\n station_id: \"station_bos\", // String (references stations.station_id)\n sequence_order: 1, // Int32\n distance_from_previous_km: null, // Decimal128 or Double (null for first stop)\n typical_stop_duration_minutes: null // Int32 (null for origin/destination or if no stop)\n}\n// --- OR --- Embed within the Route document:\n// {\n// _id: ObjectId(), route_id: \"route_ne_corr\", ...,\n// stations: [\n// { station_id: \"station_bos\", sequence_order: 1, distance_from_previous_km: null, typical_stop_duration_minutes: null },\n// { station_id: \"station_pvd\", sequence_order: 2, distance_from_previous_km: 70.5, typical_stop_duration_minutes: 5 },\n// ...\n// ]\n// }\n// db.createCollection('schedules')\n// Optional: db.schedules.createIndex({ schedule_id: 1 }, { unique: true })\n// Optional: db.schedules.createIndex({ route_id: 1, departure_datetime: 1 })\n{\n _id: ObjectId(),\n schedule_id: \"sched_1122\", // String (unique)\n train_id: \"train_789\", // String (references trains.train_id)\n route_id: \"route_ne_corr\", // String (references routes.route_id)\n departure_datetime: ISODate(\"2024-05-10T08:00:00-04:00\"), // Date (with timezone)\n arrival_datetime: ISODate(\"2024-05-10T15:30:00-04:00\"), // Date (with timezone)\n status: \"Scheduled\", // String ('Scheduled', 'On Time', 'Delayed', 'Cancelled', 'Arrived')\n notes: \"Track work expected near Philadelphia\" // String\n}\n// db.createCollection('schedule_stops')\n// Optional: db.schedule_stops.createIndex({ stop_id: 1 }, { unique: true })\n// Optional: db.schedule_stops.createIndex({ schedule_id: 1, sequence_order: 1 }, { unique: true })\n{\n _id: ObjectId(),\n stop_id: \"stop_sched1122_1\", // String (unique)\n schedule_id: \"sched_1122\", // String (references schedules.schedule_id)\n station_id: \"station_bos\", // String (references stations.station_id)\n platform_id: \"plat_bos_3\", // String (references platforms.platform_id, nullable)\n sequence_order: 1, // Int32\n scheduled_arrival_time: null, // Date\n scheduled_departure_time: ISODate(\"2024-05-10T08:00:00-04:00\"), // Date\n actual_arrival_time: null, // Date\n actual_departure_time: ISODate(\"2024-05-10T08:01:00-04:00\"), // Date\n status: \"On Time\" // String\n}\n// --- OR --- Embed within the Schedule document using an array 'stops'\n// db.createCollection('passengers')\n// Optional: db.passengers.createIndex({ passenger_id: 1 }, { unique: true })\n// Optional: db.passengers.createIndex({ email: 1 }, { unique: true, sparse: true })\n// Optional: db.passengers.createIndex({ phone_number: 1 }, { unique: true, sparse: true })\n{\n _id: ObjectId(),\n passenger_id: \"pass_pqr\", // String (unique)\n first_name: \"Alice\", // String\n last_name: \"Smith\", // String\n email: \"alice.smith@example.com\", // String (unique, sparse)\n phone_number: \"+15551234567\", // String (unique, sparse)\n date_of_birth: ISODate(\"1990-03-20\"), // Date\n loyalty_program_id: \"LOYALTY123\", // String\n created_at: ISODate(\"2023-02-01T11:00:00Z\") // Date\n}\n// db.createCollection('staff')\n// Optional: db.staff.createIndex({ staff_id: 1 }, { unique: true })\n// Optional: db.staff.createIndex({ employee_number: 1 }, { unique: true })\n// Optional: db.staff.createIndex({ contact_email: 1 }, { unique: true, sparse: true })\n{\n _id: ObjectId(),\n staff_id: \"staff_mno\", // String (unique)\n first_name: \"Bob\", // String\n last_name: \"Jones\", // String\n role: \"Conductor\", // String\n primary_station_id: null, // String (references stations.station_id, nullable)\n employee_number: \"E12345\", // String (unique)\n hire_date: ISODate(\"2018-06-01\"), // Date\n contact_email: \"bob.jones@example-rail.com\", // String (unique, sparse)\n contact_phone: \"+15559876543\", // String\n is_active: true // Boolean\n}\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": "For each route, list the route number, description, and the combined total maintenance cost for all vehicles that have ever operated on that route."}, {"role": "assistant", "content": "WITH VehicleTotalMaintenance AS ( SELECT vehicle_id, SUM(cost) AS total_cost FROM transportation.maintenance_logs GROUP BY vehicle_id ), RouteVehicles AS ( SELECT DISTINCT route_id, vehicle_id FROM transportation.trips ) SELECT R.route_number, R.description, SUM(VTM.total_cost) AS total_vehicle_maintenance_cost FROM transportation.routes AS R JOIN RouteVehicles AS RV ON R.route_id = RV.route_id JOIN VehicleTotalMaintenance AS VTM ON RV.vehicle_id = VTM.vehicle_id GROUP BY R.route_id, R.route_number, R.description;"}, {"role": "user", "content": "Refine this list to only show routes where the total combined vehicle maintenance cost exceeds 10000."}, {"role": "assistant", "content": "WITH VehicleTotalMaintenance AS ( SELECT vehicle_id, SUM(cost) AS total_cost FROM transportation.maintenance_logs GROUP BY vehicle_id ), RouteVehicles AS ( SELECT DISTINCT route_id, vehicle_id FROM transportation.trips ) SELECT R.route_number, R.description, SUM(VTM.total_cost) AS total_vehicle_maintenance_cost FROM transportation.routes AS R JOIN RouteVehicles AS RV ON R.route_id = RV.route_id JOIN VehicleTotalMaintenance AS VTM ON RV.vehicle_id = VTM.vehicle_id GROUP BY R.route_id, R.route_number, R.description HAVING SUM(VTM.total_cost) > 10000;"}, {"role": "user", "content": "For these routes with high maintenance costs, please also include the total number of completed trips associated with the route."}, {"role": "assistant", "content": "WITH VehicleTotalMaintenance AS ( SELECT vehicle_id, SUM(cost) AS total_cost FROM transportation.maintenance_logs GROUP BY vehicle_id ), RouteVehicles AS ( SELECT DISTINCT route_id, vehicle_id FROM transportation.trips ), RouteCompletedTrips AS ( SELECT route_id, COUNT(*) AS completed_trip_count FROM transportation.trips WHERE status = 'Completed' GROUP BY route_id ) SELECT R.route_number, R.description, SUM(VTM.total_cost) AS total_vehicle_maintenance_cost, RCT.completed_trip_count FROM transportation.routes AS R JOIN RouteVehicles AS RV ON R.route_id = RV.route_id JOIN VehicleTotalMaintenance AS VTM ON RV.vehicle_id = VTM.vehicle_id LEFT JOIN RouteCompletedTrips AS RCT ON R.route_id = RCT.route_id GROUP BY R.route_id, R.route_number, R.description, RCT.completed_trip_count HAVING SUM(VTM.total_cost) > 10000;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.drivers ( driver_id text PRIMARY KEY, employee_id text, first_name text, last_name text, license_number text, license_expiry_date date, contact_number text, email text, hire_date date, status text )\nCREATE TABLE transportation.routes ( route_id text PRIMARY KEY, route_number text, description text, origin_location_id text, destination_location_id text, distance_km numeric, estimated_duration_minutes int, type text )\nCREATE TABLE transportation.trips ( trip_id text PRIMARY KEY, route_id text, vehicle_id text, driver_id text, scheduled_departure timestamp, actual_departure timestamp, scheduled_arrival timestamp, actual_arrival timestamp, origin_location_id text, destination_location_id text, status text, passenger_count int, cargo_manifest_id text )\nCREATE TABLE transportation.locations ( location_id text PRIMARY KEY, name text, type text, address_line1 text, city text, state_province text, postal_code text, country text, latitude numeric, longitude numeric, timezone text )\nCREATE TABLE transportation.fuel_logs ( fuel_log_id text PRIMARY KEY, 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 int, location_id text )\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 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 ( 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 erc20_balances_historical ( block_number bigint, contract_address text, wallet_address text, amount text, pk integer )\nCREATE TABLE sui_coins ( object_id text, status text, coin_type text, balance text, owner text )\nCREATE TABLE sui_coins_metadata ( object_id text, coin_type text, status text, decimals bigint, description text, icon_url text, symbol text, name text )\nCREATE TABLE sui_nfts ( object_id text, status text, collection_type text, package_id text, previous_transaction text, display text, owner text, name text )\nCREATE TABLE nft_metadata ( blockchain text, contract_address text, token_id text, contract_name text, erc_type text, amount bigint, minter text, owner text, mint_block_number bigint, mint_time bigint, mint_transaction_hash text, mint_price text, token_uri text, metadata text, name text, image_uri text, traits text, updated_at bigint, status text, rarity_score real, rarity_rank integer, unique_attribute_count integer, pk integer )\nCREATE TABLE nft_collections ( blockchain text, contract_address text, name text, symbol text, deploy_block_number bigint, deploy_block_time bigint, erc_type text, owner text, traits text, description text, slug text, media_info text, image_url text, banner_image_url text, updated_at bigint, banner text, token_count bigint, floor_price text, floor_price_symbol text, floor_price_contract text, pk integer )\nCREATE TABLE token_prices_latest ( blockchain text, address text, decimals bigint, symbol text, price real, timestamp timestamp )\nCREATE TABLE erc20_approval ( block_number bigint, block_timestamp timestamp, transaction_index integer, transaction_hash text, log_index integer, contract_address text, pk integer )\nCREATE TABLE token_balances ( block_number bigint, block_timestamp timestamp, tick text, wallet_address text, total_supply decimal, amount decimal )\nCREATE TABLE token_info ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash text, tick text, max_supply decimal, lim decimal, wlim decimal, dec integer, creator text )\nCREATE TABLE token_activities ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash text, log_index integer, type text, tick text, id text, amt decimal, from_address text, to_address text )\nCREATE TABLE mud_holesky_redstone ( address text, table_id text, key_bytes text, key0 text, key1 text, static_data text, encoded_lengths text, dynamic_data text, is_deleted boolean, block_number bigint, log_index bigint )\nCREATE TABLE token_balances_bitcoin ( block_number bigint, block_timestamp timestamp, tick text, wallet_address text, total_supply text, amount text )\nCREATE TABLE token_info_bitcoin ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash text, tick text, max_supply decimal, lim decimal, wlim decimal, dec integer, creator text )\nCREATE TABLE token_activities_bitcoin ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash text, log_index integer, type text, tick text, id text, amt decimal, from_address text, to_address text )\nCREATE TABLE token_activities_avalanche ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash text, log_index integer, type text, tick text, id text, amt decimal, from_address text, to_address text )\nCREATE TABLE token_balances_avalanche ( block_number bigint, block_timestamp timestamp, tick text, wallet_address text, total_supply decimal, amount decimal )\nCREATE TABLE token_info_avalanche ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash text, tick text, max_supply decimal, lim decimal, wlim decimal, dec integer, creator text, minted decimal, holders decimal, txs decimal, updated_timestamp timestamp, completed_timestamp timestamp, id text )\n"} {"conversations": [{"role": "user", "content": "List all invoices issued between '2024-01-01' and '2024-06-30', including the invoice_number, issue_date, total_amount, client's first and last name, and the case_name. Order the results by issue_date ascending."}, {"role": "assistant", "content": "SELECT i.invoice_number,\n i.issue_date,\n i.total_amount,\n cl.first_name,\n cl.last_name,\n ca.case_name\nFROM legal_services.invoices i\nJOIN legal_services.clients cl ON i.client_id = cl.client_id\nJOIN legal_services.cases ca ON i.case_id = ca.case_id\nWHERE i.issue_date BETWEEN '2024-01-01' AND '2024-06-30'\nORDER BY i.issue_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 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.cases ( case_id text, case_number text, case_name text, client_id text, lead_lawyer_id text, case_type text, status text, date_opened timestamp, date_closed timestamp, description text, court_jurisdiction text )\nCREATE TABLE legal_services.documents ( document_id.text, case_id.text, document_name.text, document_type.text, storage_path.text, uploaded_by_lawyer_id.text, upload_timestamp.timestamp, version.integer, description.text )\nCREATE TABLE legal_services.time_entries ( entry_id text PRIMARY KEY, case_id text, lawyer_id text, date_worked date, hours_spent numeric, billing_rate numeric, description text, is_billable bool, is_billed bool, invoice_id text, created_at timestamp )\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 all vehicles and their last maintenance service date along with the odometer reading, including only those that have not had a fuel refill in the past 30 days."}, {"role": "assistant", "content": "SELECT m.vehicle_id,\n m.last_service_date,\n m.last_odometer\nFROM (\n SELECT l.vehicle_id,\n MAX(l.service_date) AS last_service_date,\n (SELECT odometer_reading\n FROM transportation.maintenance_logs\n WHERE vehicle_id = l.vehicle_id\n ORDER BY service_date DESC\n LIMIT 1) AS last_odometer\n FROM transportation.maintenance_logs l\n GROUP BY l.vehicle_id\n) AS m\nLEFT JOIN (\n SELECT fl.vehicle_id,\n MAX(fl.log_timestamp) AS last_fuel_date\n FROM transportation.fuel_logs fl\n GROUP BY fl.vehicle_id\n) AS f ON m.vehicle_id = f.vehicle_id\nWHERE COALESCE(f.last_fuel_date, '1900-01-01'::timestamp) < NOW() - 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 transportation.routes ( route_id character varying(64) NOT NULL, route_number character varying(32) NOT NULL UNIQUE, description text, origin_location_id character varying(64) NOT NULL, destination_location_id character varying(64) NOT NULL, distance_km numeric(10, 2), estimated_duration_minutes integer, type character varying(32) NOT NULL, PRIMARY KEY (route_id) )\nCREATE TABLE transportation.trips ( trip_id character varying(64) NOT NULL, route_id character varying(64), vehicle_id character varying(64) NOT NULL, driver_id character varying(64) NOT NULL, scheduled_departure timestamp with time zone NOT NULL, actual_departure timestamp with time zone, scheduled_arrival timestamp with time zone NOT NULL, actual_arrival timestamp with time zone, origin_location_id character varying(64) NOT NULL, destination_location_id character varying(64) NOT NULL, status character varying(32) NOT NULL, passenger_count integer, cargo_manifest_id character varying(64), PRIMARY KEY (trip_id) )\nCREATE TABLE transportation.locations ( location_id character varying(64) NOT NULL, name character varying(255) NOT NULL, type character varying(64) NOT NULL, address_line1 character varying(255), city character varying(128), state_province character varying(128), postal_code character varying(32), country character varying(64) NOT NULL, latitude numeric(9, 6), longitude numeric(9, 6), timezone character varying(64), PRIMARY KEY (location_id) )\nCREATE TABLE transportation.maintenance_logs ( log_id character varying(64) NOT NULL, vehicle_id character varying(64) NOT NULL, service_date date NOT NULL, odometer_reading integer, service_type character varying(128) NOT NULL, description text NOT NULL, cost numeric(10, 2), mechanic_name character varying(128), next_service_due_date date, PRIMARY KEY (log_id) )\nCREATE TABLE transportation.fuel_logs ( fuel_log_id character varying(64) NOT NULL, vehicle_id character varying(64) NOT NULL, trip_id character varying(64), log_timestamp timestamp with time zone NOT NULL, fuel_type character varying(32) NOT NULL, quantity numeric(10, 3) NOT NULL, unit character varying(16) NOT NULL, cost_per_unit numeric(8, 4), total_cost numeric(10, 2) NOT NULL, odometer_reading integer, location_id character varying(64), PRIMARY KEY (fuel_log_id) )\nCREATE TABLE transportation.passengers ( passenger_id character varying(64) NOT NULL, first_name character varying(128) NOT NULL, last_name character varying(128) NOT NULL, email character varying(128) UNIQUE, phone_number character varying(32) UNIQUE, date_of_birth date, loyalty_program_id character varying(64), created_at timestamp with time zone NOT NULL, PRIMARY KEY (passenger_id) )\nCREATE TABLE transportation.bookings ( booking_id character varying(64) NOT NULL, passenger_id character varying(64) NOT NULL, trip_id character varying(64) NOT NULL, seat_number character varying(16), booking_time timestamp with time zone NOT NULL, status character varying(32) NOT NULL, fare numeric(10, 2) NOT NULL, payment_transaction_id character varying(128), special_requests text, PRIMARY KEY (booking_id) )\n"} {"conversations": [{"role": "user", "content": "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": "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": "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": "Give me the total billed amount for each invoice in 2024."}, {"role": "assistant", "content": "SELECT invoice_id, SUM(hours_spent * billing_rate) AS total_billed_amount FROM legal_services.time_entries WHERE is_billed = TRUE AND EXTRACT(YEAR FROM date_worked) = 2024 GROUP BY invoice_id;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.time_entries ( entry_id text PRIMARY KEY, case_id text, lawyer_id text, date_worked date, hours_spent numeric, billing_rate numeric, description text, is_billable bool, is_billed bool, invoice_id text, created_at timestamp )\n"} {"conversations": [{"role": "user", "content": "Show me all securities (security_id, ticker_symbol, security_name) that are traded on the NASDAQ exchange and have a daily trading volume exceeding 1 million shares, along with the employee details (employee_id, first_name, last_name) who last updated these securities."}, {"role": "assistant", "content": "SELECT s.security_id, s.ticker_symbol, s.security_name, e.employee_id, e.first_name, e.last_name FROM financial_services.securities s JOIN financial_services.employees e ON s.last_updated = e.employee_id WHERE s.exchange = 'NASDAQ' AND s.security_id IN (SELECT security_id FROM financial_services.market_data WHERE volume > 1000000);"}, {"role": "user", "content": "Now modify the query to only include securities from the 'Technology' sector and sort them by ticker_symbol in ascending order."}, {"role": "assistant", "content": "SELECT s.security_id, s.ticker_symbol, s.security_name, e.employee_id, e.first_name, e.last_name FROM financial_services.securities s JOIN financial_services.employees e ON s.last_updated = e.employee_id WHERE s.exchange = 'NASDAQ' AND s.sector = 'Technology' AND s.security_id IN (SELECT security_id FROM financial_services.market_data WHERE volume > 1000000) ORDER BY s.ticker_symbol ASC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE financial_services.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.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 )\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": "Show me all customers who have missing contact information (either phone number or email is null), along with their state and city."}, {"role": "assistant", "content": "SELECT first_name, last_name, state, city FROM insurance.customers WHERE phone_number IS NULL OR email IS NULL;"}, {"role": "user", "content": "Now filter these to only show customers from Florida or New York who were created in the last year."}, {"role": "assistant", "content": "SELECT first_name, last_name, state, city FROM insurance.customers WHERE (phone_number IS NULL OR email IS NULL) AND state IN ('Florida', 'New York') AND created_at >= CURRENT_DATE - INTERVAL '1 year';"}, {"role": "user", "content": "I also want to see when these customers were last updated (updated_at field)."}, {"role": "assistant", "content": "SELECT first_name, last_name, state, city, updated_at FROM insurance.customers WHERE (phone_number IS NULL OR email IS NULL) AND state IN ('Florida', 'New York') AND created_at >= CURRENT_DATE - INTERVAL '1 year';"}, {"role": "user", "content": "Finally, order the results by state first, then by the most recently updated customers first."}, {"role": "assistant", "content": "SELECT first_name, last_name, state, city, updated_at FROM insurance.customers WHERE (phone_number IS NULL OR email IS NULL) AND state IN ('Florida', 'New York') AND created_at >= CURRENT_DATE - INTERVAL '1 year' ORDER BY state, updated_at DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.customers (\n customer_id character varying(64) NOT NULL, -- unique identifier for the customer\n first_name character varying(100) NOT NULL, -- customer's first name\n last_name character varying(100) NOT NULL, -- customer's last name\n date_of_birth date NOT NULL, -- customer's date of birth\n ssn_hash character varying(128), -- Hashed social security number (or national ID)\n address_line1 character varying(255) NOT NULL,\n address_line2 character varying(255),\n city character varying(100) NOT NULL,\n state character varying(50) NOT NULL,\n zip_code character varying(20) NOT NULL,\n country character varying(50) NOT NULL DEFAULT 'USA',\n phone_number character varying(30),\n email character varying(128) UNIQUE, -- unique email address\n created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- when the customer record was created\n updated_at timestamp, -- when the customer record was last updated\n status character varying(20) NOT NULL DEFAULT 'Active', -- e.g., Active, Inactive, Prospect\n PRIMARY KEY (customer_id)\n)\n"} {"conversations": [{"role": "user", "content": "List all claims that are still pending (status = 'pending') and were reported more than 30 days ago."}, {"role": "assistant", "content": "SELECT claim_id, policy_id, customer_id, reported_date FROM insurance.claims WHERE status = 'pending' AND reported_date < CURRENT_DATE - INTERVAL '30 days';"}, {"role": "user", "content": "Now include only claims with estimated loss values and sort them by the oldest reported date first."}, {"role": "assistant", "content": "SELECT claim_id, policy_id, customer_id, reported_date, estimated_loss FROM insurance.claims WHERE status = 'pending' AND reported_date < CURRENT_DATE - INTERVAL '30 days' AND estimated_loss IS NOT NULL ORDER BY reported_date ASC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.claims ( claim_id character varying(64) NOT NULL, policy_id character varying(64) NOT NULL, customer_id character varying(64) NOT NULL, incident_date timestamp NOT NULL, reported_date timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, description text NOT NULL, estimated_loss numeric(15, 2), status character varying(30) NOT NULL, settlement_amount numeric(15, 2), settlement_date date, claim_handler_id character varying(64), police_report_number character varying(100), PRIMARY KEY (claim_id) )\n"} {"conversations": [{"role": "user", "content": "What is the average processing time in days for each service category?"}, {"role": "assistant", "content": "SELECT category, AVG(average_processing_time_days) AS avg_processing_time\nFROM government_services.services\nGROUP BY category;"}, {"role": "user", "content": "Only include categories where the average_processing_time_days is greater than 5."}, {"role": "assistant", "content": "SELECT category, AVG(average_processing_time_days) AS avg_processing_time\nFROM government_services.services\nGROUP BY category\nHAVING AVG(average_processing_time_days) > 5;"}, {"role": "user", "content": "Also include only active services in the calculation."}, {"role": "assistant", "content": "SELECT category, AVG(average_processing_time_days) AS avg_processing_time\nFROM government_services.services\nWHERE is_active = TRUE\nGROUP BY category\nHAVING AVG(average_processing_time_days) > 5;"}, {"role": "user", "content": "Sort the results by avg_processing_time in descending order."}, {"role": "assistant", "content": "SELECT category, AVG(average_processing_time_days) AS avg_processing_time\nFROM government_services.services\nWHERE is_active = TRUE\nGROUP BY category\nHAVING AVG(average_processing_time_days) > 5\nORDER BY avg_processing_time 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.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 )\n"} {"conversations": [{"role": "user", "content": "Show me the number of unique achievements unlocked by each player."}, {"role": "assistant", "content": "SELECT player_id, COUNT(DISTINCT achievement_id) AS unique_achievements_unlocked\nFROM gaming_technology.player_achievements\nGROUP BY player_id;"}, {"role": "user", "content": "Can you include only players who unlocked more than 3 unique achievements?"}, {"role": "assistant", "content": "SELECT player_id, COUNT(DISTINCT achievement_id) AS unique_achievements_unlocked\nFROM gaming_technology.player_achievements\nGROUP BY player_id\nHAVING COUNT(DISTINCT achievement_id) > 3;"}, {"role": "user", "content": "Add another column to show the date when each player unlocked their first achievement."}, {"role": "assistant", "content": "SELECT player_id, COUNT(DISTINCT achievement_id) AS unique_achievements_unlocked,\n MIN(unlocked_at) AS first_achievement_unlocked_at\nFROM gaming_technology.player_achievements\nGROUP BY player_id\nHAVING COUNT(DISTINCT achievement_id) > 3;"}, {"role": "user", "content": "Now order the results by unique_achievements_unlocked descending, then by first_achievement_unlocked_at ascending."}, {"role": "assistant", "content": "SELECT player_id, COUNT(DISTINCT achievement_id) AS unique_achievements_unlocked,\n MIN(unlocked_at) AS first_achievement_unlocked_at\nFROM gaming_technology.player_achievements\nGROUP BY player_id\nHAVING COUNT(DISTINCT achievement_id) > 3\nORDER BY unique_achievements_unlocked DESC, first_achievement_unlocked_at 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.player_achievements ( player_achievement_id uuid, player_id uuid, achievement_id uuid, unlocked_at timestamp with time zone )\n"} {"conversations": [{"role": "user", "content": "Show me all intercity routes with their origin and destination locations, including the city and country for each location."}, {"role": "assistant", "content": "SELECT r.route_id, r.route_number, r.type, orig.name AS origin_name, orig.city AS origin_city, orig.country AS origin_country, dest.name AS destination_name, dest.city AS destination_city, dest.country AS destination_country FROM transportation.routes r JOIN transportation.locations orig ON r.origin_location_id = orig.location_id JOIN transportation.locations dest ON r.destination_location_id = dest.location_id WHERE r.type = 'Intercity Train';"}, {"role": "user", "content": "Now filter these results to only show routes where both origin and destination are in the same country, and include the distance in kilometers."}, {"role": "assistant", "content": "SELECT r.route_id, r.route_number, r.distance_km, orig.city AS origin_city, dest.city AS destination_city, orig.country FROM transportation.routes r JOIN transportation.locations orig ON r.origin_location_id = orig.location_id JOIN transportation.locations dest ON r.destination_location_id = dest.location_id WHERE r.type = 'Intercity Train' AND orig.country = dest.country;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.routes (\n route_id character varying(64) NOT NULL, -- unique identifier for the route\n route_number character varying(32) NOT NULL UNIQUE, -- public-facing route number/name\n description text, -- description of the route\n origin_location_id character varying(64) NOT NULL, -- identifier of the starting location\n destination_location_id character varying(64) NOT NULL, -- identifier of the ending location\n distance_km numeric(10, 2), -- estimated distance in kilometers\n estimated_duration_minutes integer, -- estimated travel time in minutes\n type character varying(32) NOT NULL, -- e.g., City Bus, Intercity Train, Cargo Delivery\n PRIMARY KEY (route_id)\n)\nCREATE TABLE transportation.trips ( trip_id.text, route_id.text, vehicle_id.text, driver_id.text, scheduled_departure.timestamp, actual_departure.timestamp, scheduled_arrival.timestamp, actual_arrival.timestamp, origin_location_id.text, destination_location_id.text, status.text, passenger_count.integer, cargo_manifest_id.text )\nCREATE TABLE transportation.locations ( location_id.text, name.text, type.text, address_line1.text, city.text, state_province.text, postal_code.text, country.text, latitude.numeric, longitude.numeric, timezone.text )\nCREATE TABLE transportation.maintenance_logs ( log_id.text, vehicle_id.text, service_date.date, odometer_reading.integer, service_type.text, description.text, cost.numeric, mechanic_name.text, next_service_due_date.date )\nCREATE TABLE transportation.passengers ( passenger_id character varying(64) NOT NULL, first_name character varying(128) NOT NULL, last_name character varying(128) NOT NULL, email character varying(128) UNIQUE, phone_number character varying(32) UNIQUE, date_of_birth date, loyalty_program_id character varying(64), created_at timestamp with time zone NOT NULL, PRIMARY KEY (passenger_id) )\nCREATE TABLE transportation.bookings ( booking_id text PRIMARY KEY, passenger_id text, trip_id text, seat_number text, booking_time timestamp, status text, fare numeric, payment_transaction_id text, special_requests text )\n"} {"conversations": [{"role": "user", "content": "Can you show, for each employee, the full name and job title of their direct manager, as well as the employee's department and branch_id?"}, {"role": "assistant", "content": "SELECT e.employee_id, e.first_name AS employee_first_name, e.last_name AS employee_last_name, e.department AS employee_department, e.branch_id AS employee_branch_id, m.first_name AS manager_first_name, m.last_name AS manager_last_name, m.job_title AS manager_job_title\nFROM financial_services.employees e\nLEFT JOIN financial_services.employees m ON e.manager_id = m.employee_id;"}, {"role": "user", "content": "Actually, show only employees who have a manager assigned, and include only those where the manager works at a different branch than the employee."}, {"role": "assistant", "content": "SELECT e.employee_id, e.first_name AS employee_first_name, e.last_name AS employee_last_name, e.department AS employee_department, e.branch_id AS employee_branch_id, m.first_name AS manager_first_name, m.last_name AS manager_last_name, m.job_title AS manager_job_title, m.branch_id AS manager_branch_id\nFROM financial_services.employees e\nINNER JOIN financial_services.employees m ON e.manager_id = m.employee_id\nWHERE e.branch_id IS DISTINCT FROM m.branch_id;"}, {"role": "user", "content": "Now, only include employees who were hired after 2021-01-01."}, {"role": "assistant", "content": "SELECT e.employee_id, e.first_name AS employee_first_name, e.last_name AS employee_last_name, e.department AS employee_department, e.branch_id AS employee_branch_id, m.first_name AS manager_first_name, m.last_name AS manager_last_name, m.job_title AS manager_job_title, m.branch_id AS manager_branch_id\nFROM financial_services.employees e\nINNER JOIN financial_services.employees m ON e.manager_id = m.employee_id\nWHERE e.branch_id IS DISTINCT FROM m.branch_id\n AND e.hire_date > '2021-01-01';"}], "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 financial_services.accounts ( account_id text, customer_id text, account_number text, account_type text, balance numeric, currency text, opened_date date, status text, interest_rate numeric, last_updated_at timestamp )\nCREATE TABLE financial_services.transactions (\n transaction_id character varying(64) NOT NULL, -- unique identifier for the transaction\n account_id character varying(64) NOT NULL, -- account involved in the transaction\n related_account_id character varying(64), -- counterpart account for transfers\n transaction_type character varying(50) NOT NULL, -- e.g., Deposit, Withdrawal, Transfer, Payment, Fee, Interest\n amount numeric(19, 4) NOT NULL, -- transaction amount\n currency character varying(3) NOT NULL, -- transaction currency\n transaction_date timestamp NOT NULL, -- exact time of the transaction\n effective_date date NOT NULL, -- date the transaction affects the balance\n description text, -- description or memo of the transaction\n status character varying(32) NOT NULL, -- e.g., Pending, Completed, Failed, Reversed\n reference_number character varying(128), -- external reference if applicable (e.g., check number)\n PRIMARY KEY (transaction_id),\n FOREIGN KEY (account_id) REFERENCES financial_services.accounts(account_id),\n FOREIGN KEY (related_account_id) REFERENCES financial_services.accounts(account_id)\n)\nCREATE TABLE financial_services.trades ( trade_id text PRIMARY KEY, account_id text, security_id text, order_id text, trade_type text, quantity numeric, price_per_unit numeric, total_amount numeric, commission numeric, trade_timestamp timestamp, settlement_date date, status text, execution_venue text )\nCREATE TABLE financial_services.market_data ( data_point_id.bigint, security_id.text, data_timestamp.timestamp, open_price.numeric, high_price.numeric, low_price.numeric, close_price.numeric, adjusted_close_price.numeric, volume.bigint, source.text )\nCREATE TABLE financial_services.employees (\n employee_id character varying(64) NOT NULL, -- unique identifier for the employee\n first_name character varying(100) NOT NULL,\n last_name character varying(100) NOT NULL,\n job_title character varying(100) NOT NULL, -- e.g., Teller, Branch Manager, Financial Advisor, Analyst\n department character varying(100), -- e.g., Retail Banking, Wealth Management, IT\n branch_id character varying(64), -- Identifier for the branch they work at (if applicable)\n email character varying(128) NOT NULL UNIQUE,\n phone_extension character varying(20),\n hire_date date NOT NULL,\n termination_date date, -- Date of termination, null if currently employed\n manager_id character varying(64), -- Self-referencing key for manager relationship\n status character varying(32) NOT NULL, -- e.g., Active, Terminated, On Leave\n PRIMARY KEY (employee_id),\n FOREIGN KEY (branch_id) REFERENCES financial_services.branches(branch_id), -- Assuming a branches table exists\n FOREIGN KEY (manager_id) REFERENCES financial_services.employees(employee_id)\n)\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": "For each claim, show the corresponding product_type of the insurance product for the related policy."}, {"role": "assistant", "content": "SELECT cl.claim_id, ip.product_type\nFROM insurance.claims cl\nJOIN insurance.policies p ON cl.policy_id = p.policy_id\nJOIN insurance.insurance_products ip ON p.product_id = ip.product_id;"}, {"role": "user", "content": "Sorry, there is no policies table, I got an error. Can you try joining claims to insurance_products another way?"}, {"role": "assistant", "content": "-- Unable to join directly since there is no 'policies' table connecting claims to insurance_products. If policy_id equals product_id, you may try:\nSELECT claim_id, policy_id, product_type\nFROM insurance.claims\nJOIN insurance.insurance_products ON claims.policy_id = insurance_products.product_id;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.customers ( customer_id.text, first_name.text, last_name.text, date_of_birth.date, ssn_hash.text, address_line1.text, address_line2.text, city.text, state.text, zip_code.text, country.text, phone_number.text, email.text, created_at.timestamp, updated_at.timestamp, status.text )\nCREATE TABLE insurance.claims ( claim_id.text, policy_id.text, customer_id.text, incident_date.timestamp, reported_date.timestamp, description.text, estimated_loss.numeric, status.text, settlement_amount.numeric, settlement_date.date, claim_handler_id.text, police_report_number.text )\nCREATE TABLE insurance.insurance_products ( product_id.text, product_name.text, product_type.text, description.text, base_premium.numeric, coverage_details.text, underwriting_rules.text, is_active.boolean, created_at.timestamp, updated_at.timestamp )\nCREATE TABLE insurance.claim_documents ( document_id.text, claim_id.text, document_type.text, file_name.text, file_path.text, file_size_bytes.integer, mime_type.text, uploaded_by.text, uploaded_at.timestamp, description.text )\n"} {"conversations": [{"role": "user", "content": "Show me all maintenance logs for 'Oil Change' services performed in the last 3 months, including the vehicle ID, service date, and cost."}, {"role": "assistant", "content": "SELECT vehicle_id, service_date, cost FROM transportation.maintenance_logs WHERE service_type = 'Oil Change' AND service_date >= CURRENT_DATE - INTERVAL '3 months';"}, {"role": "user", "content": "Can you also include the mechanic name and filter to only show services that cost more than $100?"}, {"role": "assistant", "content": "SELECT vehicle_id, service_date, cost, mechanic_name FROM transportation.maintenance_logs WHERE service_type = 'Oil Change' AND service_date >= CURRENT_DATE - INTERVAL '3 months' AND cost > 100;"}, {"role": "user", "content": "Now order these results by service date with the most recent first and limit to 10 records."}, {"role": "assistant", "content": "SELECT vehicle_id, service_date, cost, mechanic_name FROM transportation.maintenance_logs WHERE service_type = 'Oil Change' AND service_date >= CURRENT_DATE - INTERVAL '3 months' AND cost > 100 ORDER BY service_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 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)\n"} {"conversations": [{"role": "user", "content": "List transactions where the description includes another transaction's reference_number, showing both transaction IDs and the referenced reference_number."}, {"role": "assistant", "content": "SELECT t1.transaction_id AS source_id, t2.transaction_id AS referenced_id, t2.reference_number\nFROM financial_services.transactions t1\nJOIN financial_services.transactions t2\n ON t1.description LIKE '%' || t2.reference_number || '%';"}, {"role": "user", "content": "Only include cases where the referenced transaction has status 'COMPLETED'."}, {"role": "assistant", "content": "SELECT t1.transaction_id AS source_id, t2.transaction_id AS referenced_id, t2.reference_number\nFROM financial_services.transactions t1\nJOIN financial_services.transactions t2\n ON t1.description LIKE '%' || t2.reference_number || '%'\nWHERE t2.status = 'COMPLETED';"}, {"role": "user", "content": "Finally, order the output by the source transaction date ascending."}, {"role": "assistant", "content": "SELECT t1.transaction_id AS source_id, t2.transaction_id AS referenced_id, t2.reference_number\nFROM financial_services.transactions t1\nJOIN financial_services.transactions t2\n ON t1.description LIKE '%' || t2.reference_number || '%'\nWHERE t2.status = 'COMPLETED'\nORDER BY t1.transaction_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 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 )\n"} {"conversations": [{"role": "user", "content": "Show me the first name, last name, and email address for all passengers who are part of the loyalty program with ID 'Gold'."}, {"role": "assistant", "content": "SELECT first_name , last_name , email FROM transportation.passengers WHERE loyalty_program_id = 'Gold'"}, {"role": "user", "content": "Now, narrow this list to only include those passengers whose record was created after January 1, 2023."}, {"role": "assistant", "content": "SELECT first_name , last_name , email FROM transportation.passengers WHERE loyalty_program_id = 'Gold' AND created_at > '2023-01-01'"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.routes ( route_id text PRIMARY KEY, route_number text, description text, origin_location_id text, destination_location_id text, distance_km numeric, estimated_duration_minutes int, type text )\nCREATE TABLE transportation.maintenance_logs ( log_id.text, vehicle_id.text, service_date.date, odometer_reading.integer, service_type.text, description.text, cost.numeric, mechanic_name.text, next_service_due_date.date )\nCREATE TABLE transportation.fuel_logs ( fuel_log_id text, vehicle_id text, trip_id text, log_timestamp timestamp, fuel_type text, quantity numeric, unit text, cost_per_unit numeric, total_cost numeric, odometer_reading integer, location_id text )\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": "For projects that have completed more than one fundraising round, calculate the average investment value across all their recorded rounds. Display the project name and this average value."}, {"role": "assistant", "content": "SELECT project_name, AVG(investment_value) AS average_investment FROM project_fundraising_record GROUP BY project_name HAVING COUNT(*) > 1;"}, {"role": "user", "content": "Can you modify this to only show projects where the average investment value is greater than 10 million USD and order the results by average investment value descending?"}, {"role": "assistant", "content": "SELECT project_name, AVG(investment_value) AS average_investment FROM project_fundraising_record GROUP BY project_name HAVING COUNT(*) > 1 AND AVG(investment_value) > 10000000 ORDER BY average_investment DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE project_fundraising_record ( id character varying(32) NOT NULL, -- fundraising record id project_id character varying(32) NOT NULL, -- the invested project's id project_name character varying(128) NOT NULL, -- name of the invested project rounds_name character varying(32), -- name of the fundraising round investment_value numeric(38,14), -- amount of the fundraising in USD investment_date character varying(128), -- the date of the investment happened introduction character varying(128), -- the introduction of the invested project valuation numeric(38,14), -- the valuation of the project in USD when invested )\n"} {"conversations": [{"role": "user", "content": "Show me asset IDs and DApp names for metadata entries linking assets to DApps where metadata.value matches a dapp_id."}, {"role": "assistant", "content": "SELECT m.asset_id, d.name AS dapp_name\nFROM trading_platform.metadata m\nJOIN trading_platform.dapps d\n ON m.value = d.dapp_id;"}, {"role": "user", "content": "Filter where metadata.key starts with 'link'."}, {"role": "assistant", "content": "SELECT m.asset_id, d.name AS dapp_name\nFROM trading_platform.metadata m\nJOIN trading_platform.dapps d\n ON m.value = d.dapp_id\nWHERE m.key LIKE 'link%';"}, {"role": "user", "content": "Include the metadata.key in the select list."}, {"role": "assistant", "content": "SELECT m.asset_id, d.name AS dapp_name, m.key AS metadata_key\nFROM trading_platform.metadata m\nJOIN trading_platform.dapps d\n ON m.value = d.dapp_id\nWHERE m.key LIKE 'link%';"}, {"role": "user", "content": "Order the final result by asset_id and limit to 5."}, {"role": "assistant", "content": "SELECT m.asset_id, d.name AS dapp_name, m.key AS metadata_key\nFROM trading_platform.metadata m\nJOIN trading_platform.dapps d\n ON m.value = d.dapp_id\nWHERE m.key LIKE 'link%'\nORDER BY m.asset_id\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.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.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.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": "For each patient, find the next appointment after each one. Return patient_id, appointment_id, next_appointment_id, and the waiting time in minutes between them."}, {"role": "assistant", "content": "SELECT A.patient_id,\n A.appointment_id AS current_id,\n B.appointment_id AS next_id,\n EXTRACT(EPOCH FROM (B.appointment_time - A.appointment_time)) / 60 AS wait_minutes\nFROM healthcare.appointments A\nJOIN healthcare.appointments B\n ON A.patient_id = B.patient_id\n AND B.appointment_time = (\n SELECT MIN(appointment_time)\n FROM healthcare.appointments\n WHERE patient_id = A.patient_id\n AND appointment_time > A.appointment_time\n );"}, {"role": "user", "content": "Now include only the pairs where the waiting time is less than 30 minutes."}, {"role": "assistant", "content": "SELECT A.patient_id,\n A.appointment_id AS current_id,\n B.appointment_id AS next_id,\n EXTRACT(EPOCH FROM (B.appointment_time - A.appointment_time)) / 60 AS wait_minutes\nFROM healthcare.appointments A\nJOIN healthcare.appointments B\n ON A.patient_id = B.patient_id\n AND B.appointment_time = (\n SELECT MIN(appointment_time)\n FROM healthcare.appointments\n WHERE patient_id = A.patient_id\n AND appointment_time > A.appointment_time\n )\nWHERE EXTRACT(EPOCH FROM (B.appointment_time - A.appointment_time)) / 60 < 30;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE 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 )\n"} {"conversations": [{"role": "user", "content": "Show the total number of customers in each state."}, {"role": "assistant", "content": "SELECT\n state,\n COUNT(customer_id)\nFROM insurance.customers\nGROUP BY\n state;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.customers ( customer_id text, first_name text, last_name text, date_of_birth date, ssn_hash text, address_line1 text, address_line2 text, city text, state text, zip_code text, country text, phone_number text, email text, created_at timestamp, updated_at timestamp, status text )\nCREATE TABLE insurance.claims (\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.claim_documents ( document_id character varying(64) NOT NULL, claim_id character varying(64) NOT NULL, document_type character varying(50) NOT NULL, file_name character varying(255) NOT NULL, file_path character varying(512) NOT NULL, file_size_bytes integer, mime_type character varying(100), uploaded_by character varying(64), uploaded_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, description text, PRIMARY KEY (document_id) )\n"} {"conversations": [{"role": "user", "content": "List all spa services (category = 'Wellness') with their names, prices, and units, ordered by price in descending order."}, {"role": "assistant", "content": "SELECT service_name, price, unit FROM hospitality_technology.services WHERE category = 'Wellness' ORDER BY price DESC;"}, {"role": "user", "content": "Now, include only services with a price above $100 and show the property ID as well."}, {"role": "assistant", "content": "SELECT service_name, price, unit, property_id FROM hospitality_technology.services WHERE category = 'Wellness' AND price > 100 ORDER BY price DESC;"}, {"role": "user", "content": "The query is missing the service description. Can you include that as well?"}, {"role": "assistant", "content": "SELECT service_name, description, price, unit, property_id FROM hospitality_technology.services WHERE category = 'Wellness' AND price > 100 ORDER BY price DESC;"}, {"role": "user", "content": "Actually, I only need services from properties with ID starting with 'PROP1', and order by property_id first, then by price."}, {"role": "assistant", "content": "SELECT service_name, description, price, unit, property_id FROM hospitality_technology.services WHERE category = 'Wellness' AND price > 100 AND property_id LIKE 'PROP1%' ORDER BY property_id, price 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 (\n guest_id character varying(64) NOT NULL, -- unique identifier for the guest profile\n first_name character varying(100) NOT NULL, -- guest's first name\n last_name character varying(100) NOT NULL, -- guest's last name\n email character varying(255) UNIQUE, -- guest's email address (unique identifier?)\n phone_number character varying(30), -- guest's phone number\n date_of_birth date, -- guest's date of birth\n address_line1 character varying(255), -- guest's home address\n city character varying(100),\n state_province character varying(100),\n postal_code character varying(20),\n country_code character varying(3),\n preferences text, -- notes on guest preferences (e.g., allergies, room location)\n loyalty_member_id character varying(64) UNIQUE, -- FK to loyalty_members table\n communication_consent boolean DEFAULT true, -- consent for marketing communications\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 (guest_id)\n)\nCREATE TABLE hospitality_technology.services (\n service_id character varying(64) NOT NULL, -- unique identifier for a chargeable service\n property_id character varying(64) NOT NULL, -- FK to properties table\n service_name character varying(150) NOT NULL, -- e.g., Room Service - Burger, Spa - Massage 60min, Laundry - Shirt\n description text,\n category character varying(100), -- e.g., Food & Beverage, Wellness, Business Center, Activities\n price numeric(10, 2) NOT NULL, -- price per unit/instance\n unit character varying(30), -- e.g., Per Item, Per Hour, Per Day\n is_available boolean NOT NULL DEFAULT true, -- is the service currently offered?\n department character varying(100), -- department responsible (e.g., F&B, Spa, Housekeeping)\n PRIMARY KEY (service_id),\n FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id)\n)\n"} {"conversations": [{"role": "user", "content": "List all invoices that were paid within 7 days of their issue date. Show invoice number, issue date, payment date, and total amount."}, {"role": "assistant", "content": "SELECT invoice_number, issue_date, payment_date, total_amount FROM legal_services.invoices WHERE status = 'Paid' AND payment_date IS NOT NULL AND (payment_date::DATE - issue_date) <= 7;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.lawyers ( lawyer_id.text, first_name.text, last_name.text, bar_number.text, firm_id.text, email.text, phone.text, specialization.text, hire_date.timestamp, is_partner.boolean )\nCREATE TABLE legal_services.invoices ( invoice_id text, invoice_number text, client_id text, case_id text, issue_date date, due_date date, total_amount numeric, amount_paid numeric, status text, payment_date timestamp, notes text, created_at timestamp )\n"} {"conversations": [{"role": "user", "content": "Count the number of staff members for each position."}, {"role": "assistant", "content": "SELECT\n position,\n COUNT(staff_id) AS staff_count\nFROM hospitality_technology.staff\nGROUP BY\n position;"}, {"role": "user", "content": "Only show positions that have more than 10 staff members and order the results by the count descending."}, {"role": "assistant", "content": "SELECT\n position,\n COUNT(staff_id) AS staff_count\nFROM hospitality_technology.staff\nGROUP BY\n position\nHAVING\n COUNT(staff_id) > 10\nORDER BY\n staff_count DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE hospitality_technology.properties (\n property_id character varying(64) NOT NULL, -- unique identifier for the property (hotel, resort, etc.)\n property_name character varying(255) NOT NULL, -- name of the property\n address_line1 character varying(255) NOT NULL, -- primary address line\n address_line2 character varying(255), -- secondary address line\n city character varying(100) NOT NULL, -- city\n state_province character varying(100), -- state or province\n postal_code character varying(20) NOT NULL, -- zip or postal code\n country_code character varying(3) NOT NULL, -- ISO country code (e.g., USA, CAN)\n phone_number character varying(30), -- main contact phone\n email_address character varying(255), -- main contact email\n property_type character varying(50) NOT NULL, -- e.g., Hotel, Resort, B&B, Motel\n star_rating numeric(2,1), -- star rating (e.g., 4.5)\n timezone character varying(64) NOT NULL, -- IANA timezone ID (e.g., America/New_York)\n manager_staff_id character varying(64), -- FK to staff table for the general manager\n created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, -- record creation time\n updated_at timestamp with time zone NOT NULL DEFAULT current_timestamp, -- record last update time\n PRIMARY KEY (property_id)\n)\nCREATE TABLE hospitality_technology.reservations ( reservation_id text, property_id text, guest_id text, room_id text, room_type_id text, check_in_date date, check_out_date date, actual_check_in_ts timestamp, actual_check_out_ts timestamp, num_adults integer, num_children integer, status text, booking_source text, rate_plan_id text, total_amount numeric, amount_paid numeric, special_requests text, created_at timestamp, updated_at timestamp )\nCREATE TABLE hospitality_technology.staff ( staff_id text PRIMARY KEY, property_id text, first_name text, last_name text, position text, work_email text, work_phone text, hire_date date, termination_date date, is_active boolean, access_level int, manager_id text, created_at timestamp )\nCREATE TABLE hospitality_technology.payments ( payment_id text, reservation_id text, guest_id text, bill_id text, amount numeric, currency_code text, payment_method text, card_type text, card_last_four text, transaction_ref text, payment_timestamp timestamp, status text, staff_id_processed text, notes text )\n"} {"conversations": [{"role": "user", "content": "For each guest, list reservation_id, guest_id, check_in_date, and the next reservation_id and its check_in_date."}, {"role": "assistant", "content": "SELECT r1.reservation_id,\n r1.guest_id,\n r1.check_in_date,\n r2.reservation_id AS next_reservation_id,\n r2.check_in_date AS next_check_in_date\nFROM reservations r1\nLEFT JOIN reservations r2\n ON r1.guest_id = r2.guest_id\n AND r2.check_in_date = (\n SELECT MIN(check_in_date)\n FROM reservations\n WHERE guest_id = r1.guest_id\n AND check_in_date > r1.check_in_date\n );"}, {"role": "user", "content": "Only include guests who have at least two reservations."}, {"role": "assistant", "content": "SELECT r1.reservation_id,\n r1.guest_id,\n r1.check_in_date,\n r2.reservation_id AS next_reservation_id,\n r2.check_in_date AS next_check_in_date\nFROM reservations r1\nLEFT JOIN reservations r2\n ON r1.guest_id = r2.guest_id\n AND r2.check_in_date = (\n SELECT MIN(check_in_date)\n FROM reservations\n WHERE guest_id = r1.guest_id\n AND check_in_date > r1.check_in_date\n )\nWHERE r1.guest_id IN (\n SELECT guest_id\n FROM reservations\n GROUP BY guest_id\n HAVING COUNT(*) >= 2\n);"}, {"role": "user", "content": "Also, only show next reservations that occur within 30 days of the current reservation."}, {"role": "assistant", "content": "SELECT r1.reservation_id,\n r1.guest_id,\n r1.check_in_date,\n r2.reservation_id AS next_reservation_id,\n r2.check_in_date AS next_check_in_date\nFROM reservations r1\nLEFT JOIN reservations r2\n ON r1.guest_id = r2.guest_id\n AND r2.check_in_date = (\n SELECT MIN(check_in_date)\n FROM reservations\n WHERE guest_id = r1.guest_id\n AND check_in_date > r1.check_in_date\n )\n AND r2.check_in_date <= r1.check_in_date + INTERVAL '30 days'\nWHERE r1.guest_id IN (\n SELECT guest_id\n FROM reservations\n GROUP BY guest_id\n HAVING COUNT(*) >= 2\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 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": "I want to find the total number of ERC1155 \"approval-for-all\" events per contract. Show contract_address and the approval_count."}, {"role": "assistant", "content": "SELECT contract_address, COUNT(*) AS approval_count\nFROM erc1155_approval_for_all\nGROUP BY contract_address;"}, {"role": "user", "content": "Also show the number of unique wallet holders currently holding any token from those contracts by joining to nft_holders."}, {"role": "assistant", "content": "SELECT a.contract_address,\n a.approval_count,\n COALESCE(b.holder_count, 0) AS holder_count\nFROM (\n SELECT contract_address, COUNT(*) AS approval_count\n FROM erc1155_approval_for_all\n GROUP BY contract_address\n) a\nLEFT JOIN (\n SELECT contract_address, COUNT(DISTINCT wallet_address) AS holder_count\n FROM nft_holders\n GROUP BY contract_address\n) b\n ON a.contract_address = b.contract_address;"}, {"role": "user", "content": "Filter to only include contracts where holder_count is greater than 50."}, {"role": "assistant", "content": "SELECT a.contract_address,\n a.approval_count,\n b.holder_count\nFROM (\n SELECT contract_address, COUNT(*) AS approval_count\n FROM erc1155_approval_for_all\n GROUP BY contract_address\n) a\nJOIN (\n SELECT contract_address, COUNT(DISTINCT wallet_address) AS holder_count\n FROM nft_holders\n GROUP BY contract_address\n HAVING COUNT(DISTINCT wallet_address) > 50\n) b\n ON a.contract_address = b.contract_address;"}, {"role": "user", "content": "Sort results by approval_count descending and limit to the top 10."}, {"role": "assistant", "content": "SELECT a.contract_address,\n a.approval_count,\n b.holder_count\nFROM (\n SELECT contract_address, COUNT(*) AS approval_count\n FROM erc1155_approval_for_all\n GROUP BY contract_address\n) a\nJOIN (\n SELECT contract_address, COUNT(DISTINCT wallet_address) AS holder_count\n FROM nft_holders\n GROUP BY contract_address\n HAVING COUNT(DISTINCT wallet_address) > 50\n) b\n ON a.contract_address = b.contract_address\nORDER BY a.approval_count 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 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_historical ( block_number.bigint, contract_address.text, wallet_address.text, amount.text, pk.integer )\nCREATE TABLE nft_holders ( block_number.bigint, contract_address.text, wallet_address.text, token_id.text, contract_type.text, amount.text, pk.text )\nCREATE TABLE sui_coins_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 (\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 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, block_number bigint, tx_index integer, tx_hash text, tick text, max_supply decimal, lim decimal, wlim decimal, dec integer, creator text )\nCREATE TABLE token_activities_avalanche ( block_timestamp timestamp(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 )\n"} {"conversations": [{"role": "user", "content": "For each guest, list each review and its immediately following review, including guest_id, first_review_id, first_review_date, second_review_id, and second_review_date."}, {"role": "assistant", "content": "SELECT r1.guest_id, r1.review_id AS first_review_id, r1.review_date AS first_review_date, r2.review_id AS second_review_id, r2.review_date AS second_review_date\nFROM hospitality_technology.reviews r1\nJOIN hospitality_technology.reviews r2\n ON r1.guest_id = r2.guest_id\n AND r2.review_date = (\n SELECT MIN(r3.review_date)\n FROM hospitality_technology.reviews r3\n WHERE r3.guest_id = r1.guest_id\n AND r3.review_date > r1.review_date\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 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": "What is the average price of tokens held by Binance exchange across all chains in the cex_token_balance table?"}, {"role": "assistant", "content": "SELECT AVG(price) AS average_price FROM cex_token_balance WHERE exchange = 'Binance';"}], "system": "You are an SQL statement expert. Given the 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) )\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"} {"conversations": [{"role": "user", "content": "List the name of each agency and the total number of service locations it operates in New York State."}, {"role": "assistant", "content": "SELECT a.agency_name, COUNT(sl.location_id) AS location_count\nFROM government_services.agencies a\nLEFT JOIN government_services.service_locations sl ON a.agency_id = sl.agency_id\nWHERE sl.state = 'NY'\nGROUP BY a.agency_name;"}, {"role": "user", "content": "Actually, only include those service locations that are accessible."}, {"role": "assistant", "content": "SELECT a.agency_name, COUNT(sl.location_id) AS location_count\nFROM government_services.agencies a\nLEFT JOIN government_services.service_locations sl ON a.agency_id = sl.agency_id\nWHERE sl.state = 'NY' AND sl.is_accessible = TRUE\nGROUP BY a.agency_name;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.agencies ( agency_id text PRIMARY KEY, agency_name text, jurisdiction_level text, primary_contact_email text, main_phone_number text, website_url text, established_date date, parent_agency_id text )\nCREATE TABLE government_services.service_locations ( location_id text PRIMARY KEY, agency_id text, location_name text, address text, city text, state text, postal_code text, latitude numeric, longitude numeric, operating_hours text, contact_phone text, is_accessible boolean )\nCREATE TABLE government_services.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 all insurance plans that have more than 5 patients enrolled as their primary insurance, along with the provider name and count of patients."}, {"role": "assistant", "content": "SELECT ip.plan_id, ip.plan_name, ip.insurance_provider, COUNT(pi.patient_id) AS patient_count FROM healthcare.insurance_plans ip JOIN healthcare.patient_insurance pi ON ip.plan_id = pi.plan_id WHERE pi.is_primary = true GROUP BY ip.plan_id, ip.plan_name, ip.insurance_provider HAVING COUNT(pi.patient_id) > 5 ORDER BY patient_count DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.doctors ( doctor_id 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) )\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 ( 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": "Show me each doctor and the total number of unique patients they have prescribed medications to. Include the doctor's full name and the patient count."}, {"role": "assistant", "content": "SELECT d.doctor_id, d.first_name, d.last_name, COUNT(DISTINCT p.patient_id) AS unique_patient_count\nFROM healthcare.prescriptions p\nJOIN healthcare.doctors d ON p.doctor_id = d.doctor_id\nGROUP BY d.doctor_id, 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 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.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 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 )\n"} {"conversations": [{"role": "user", "content": "List tokens that have a 24-hour trading volume greater than $10,000,000 and a negative price change percentage over the last 24 hours. Show the token symbol, chain, total volume, and the 24-hour price change percentage."}, {"role": "assistant", "content": "SELECT token_symbol, chain, total_volume, price_change_percentage_24h FROM token_basic_info WHERE CAST(REPLACE(total_volume, ',', '') AS numeric) > 10000000 AND price_change_percentage_24h < 0"}, {"role": "user", "content": "From those results, filter further to only include tokens with a market cap rank of 100 or better. Order the results by 24-hour trading volume in descending order."}, {"role": "assistant", "content": "SELECT token_symbol, chain, total_volume, price_change_percentage_24h FROM token_basic_info WHERE CAST(REPLACE(total_volume, ',', '') AS numeric) > 10000000 AND price_change_percentage_24h < 0 AND market_cap_rank IS NOT NULL AND market_cap_rank <= 100 ORDER BY CAST(REPLACE(total_volume, ',', '') AS numeric) 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_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": "Find all pairs of transactions that occurred in the same block and were sent to the same address. Show both transaction IDs, the shared recipient address, and the block number."}, {"role": "assistant", "content": "SELECT t1.transaction_id AS tx1,\n t2.transaction_id AS tx2,\n t1.to_address,\n t1.block_number\nFROM transactions t1\nJOIN transactions t2\n ON t1.to_address = t2.to_address\n AND t1.block_number = t2.block_number\n AND t1.transaction_id < t2.transaction_id;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE web3.transactions ( transaction_id text, from_address text, to_address text, value numeric, gas_used integer, gas_price numeric, block_number integer, timestamp timestamp, input_data text, status text, nonce integer )\n"} {"conversations": [{"role": "user", "content": "能否帮我统计特定车站(station_id 为 'station_xyz')的所有工作人员数量？"}, {"role": "assistant", "content": "MATCH (s:Station {station_id: 'station_xyz'})<-[:BASED_AT]-(staff:Staff)\nRETURN COUNT(staff) AS total_staff"}], "system": "You are an expert in writing database language. You can write a corresponding database language query to answer the user's question based on the table structure described by the table creation statement. \n##Table Structure\n// Node Label: :Station\n// Properties:\n// station_id: String (Constraint: UNIQUE)\n// station_name: String\n// city: String (Index recommended)\n// state_province: String\n// country_code: String\n// address: String\n// timezone: String\n// number_of_platforms: Integer\n// created_at: DateTime\n// last_updated_at: DateTime\n// Example Cypher CREATE:\n// CREATE (:Station {station_id: 'station_xyz', station_name: 'Grand Central Terminal', city: 'New York', ...})\n// Node Label: :Platform\n// Properties:\n// platform_id: String (Constraint: UNIQUE)\n// platform_number: String\n// track_number: String\n// status: String\n// length_meters: Float\n// accessible: Boolean\n// Relationship: (:Platform)-[:LOCATED_AT]->(:Station)\n// Example Cypher CREATE:\n// MATCH (s:Station {station_id: 'station_xyz'})\n// CREATE (p:Platform {platform_id: 'plat_123', ...})-[:LOCATED_AT]->(s)\n// Node Label: :Train\n// Properties:\n// train_id: String (Constraint: UNIQUE)\n// train_number: String (Constraint: UNIQUE)\n// model: String\n// manufacturer: String\n// year_manufactured: Integer\n// capacity: Integer\n// status: String\n// last_maintenance_date: Date\n// next_maintenance_date: Date\n// Example Cypher CREATE:\n// CREATE (:Train {train_id: 'train_789', train_number: 'Acela 2151', ...})\n// Node Label: :TrainCar\n// Properties:\n// car_id: String (Constraint: UNIQUE)\n// car_number: String\n// car_type: String\n// class: String\n// capacity: Integer\n// features: String (Or List if driver supports)\n// Relationship: (:TrainCar)-[:PART_OF_TRAIN]->(:Train)\n// Example Cypher CREATE:\n// MATCH (t:Train {train_id: 'train_789'})\n// CREATE (c:TrainCar {car_id: 'car_abc', ...})-[:PART_OF_TRAIN]->(t)\n// Node Label: :Route\n// Properties:\n// route_id: String (Constraint: UNIQUE)\n// route_name: String\n// description: String\n// is_active: Boolean\n// Relationships:\n// (:Route)-[:STARTS_AT]->(:Station)\n// (:Route)-[:ENDS_AT]->(:Station)\n// Example Cypher CREATE:\n// MATCH (origin:Station {station_id: 'station_bos'}), (dest:Station {station_id: 'station_was'})\n// CREATE (r:Route {route_id: 'route_ne_corr', ...})-[:STARTS_AT]->(origin), (r)-[:ENDS_AT]->(dest)\n// Relationship: (:Route)-[rel:HAS_STOP]->(:Station)\n// Relationship Properties on :HAS_STOP:\n// sequence_order: Integer\n// distance_from_previous_km: Float\n// typical_stop_duration_minutes: Integer\n// Example Cypher CREATE:\n// MATCH (r:Route {route_id: 'route_ne_corr'}), (s:Station {station_id: 'station_pvd'})\n// CREATE (r)-[:HAS_STOP {sequence_order: 2, distance_from_previous_km: 70.5, ...}]->(s)\n// Node Label: :ScheduledTrip (or just :Trip)\n// Properties:\n// schedule_id: String (Constraint: UNIQUE)\n// departure_datetime: DateTime\n// arrival_datetime: DateTime\n// status: String\n// notes: String\n// Relationships:\n// (:ScheduledTrip)-[:USES_TRAIN]->(:Train)\n// (:ScheduledTrip)-[:FOLLOWS_ROUTE]->(:Route)\n// Example Cypher CREATE:\n// MATCH (t:Train {train_id: 'train_789'}), (r:Route {route_id: 'route_ne_corr'})\n// CREATE (sched:ScheduledTrip {schedule_id: 'sched_1122', ...})-[:USES_TRAIN]->(t), (sched)-[:FOLLOWS_ROUTE]->(r)\n// Relationship: (:ScheduledTrip)-[rel:SCHEDULED_STOP]->(:Station)\n// Relationship Properties on :SCHEDULED_STOP:\n// sequence_order: Integer\n// platform_id: String (references Platform node if modeled, or just store ID)\n// scheduled_arrival_time: DateTime\n// scheduled_departure_time: DateTime\n// actual_arrival_time: DateTime\n// actual_departure_time: DateTime\n// status: String\n// Example Cypher CREATE:\n// MATCH (sched:ScheduledTrip {schedule_id: 'sched_1122'}), (s:Station {station_id: 'station_pvd'})\n// CREATE (sched)-[:SCHEDULED_STOP {sequence_order: 2, platform_id: 'plat_pvd_1', ...}]->(s)\n// Node Label: :Passenger\n// Properties:\n// passenger_id: String (Constraint: UNIQUE)\n// first_name: String\n// last_name: String\n// email: String (Constraint: UNIQUE, if not null)\n// phone_number: String (Constraint: UNIQUE, if not null)\n// date_of_birth: Date\n// loyalty_program_id: String\n// created_at: DateTime\n// Example Cypher CREATE:\n// CREATE (:Passenger {passenger_id: 'pass_pqr', first_name: 'Alice', ...})\n// Node Label: :Booking\n// Properties:\n// booking_id: String (Constraint: UNIQUE)\n// booking_datetime: DateTime\n// status: String\n// total_price: Float\n// currency_code: String\n// special_requests: String\n// Relationships:\n// (:Passenger)-[:MADE_BOOKING]->(:Booking)\n// (:Booking)-[:FOR_TRIP]->(:ScheduledTrip)\n// Example Cypher CREATE:\n// MATCH (p:Passenger {passenger_id: 'pass_pqr'}), (sched:ScheduledTrip {schedule_id: 'sched_1122'})\n// CREATE (p)-[:MADE_BOOKING]->(b:Booking {booking_id: 'book_zyx', ...})-[:FOR_TRIP]->(sched)\n// Node Label: :Ticket\n// Properties:\n// ticket_id: String (Constraint: UNIQUE)\n// seat_number: String\n// ticket_type: String\n// price: Float\n// is_checked_in: Boolean\n// qr_code_data: String\n// Relationships:\n// (:Ticket)-[:PART_OF_BOOKING]->(:Booking)\n// (:Ticket)-[:ASSIGNED_TO_CAR]->(:TrainCar)\n// Example Cypher CREATE:\n// MATCH (b:Booking {booking_id: 'book_zyx'}), (c:TrainCar {car_id: 'car_abc'})\n// CREATE (t:Ticket {ticket_id: 'tkt_1a2b', ...})-[:PART_OF_BOOKING]->(b), (t)-[:ASSIGNED_TO_CAR]->(c)\n// Node Label: :Staff\n// Properties:\n// staff_id: String (Constraint: UNIQUE)\n// first_name: String\n// last_name: String\n// role: String\n// employee_number: String (Constraint: UNIQUE)\n// hire_date: Date\n// contact_email: String (Constraint: UNIQUE, if not null)\n// contact_phone: String\n// is_active: Boolean\n// Relationship (Optional):\n// (:Staff)-[:BASED_AT]->(:Station)\n// Example Cypher CREATE:\n// CREATE (:Staff {staff_id: 'staff_mno', first_name: 'Bob', ...})\n// OPTIONAL MATCH (s:Station {station_id: 'station_xyz'}) // If primary_station_id exists\n// WITH s, staff_mno // Need to get the created staff node reference\n// WHERE s IS NOT NULL\n// CREATE (staff_mno)-[:BASED_AT]->(s)\n"} {"conversations": [{"role": "user", "content": "What is the total USD value held by all centralized exchanges (CEX) for the token with the symbol 'BTC'?"}, {"role": "assistant", "content": "SELECT SUM(usd_value) AS total_btc_cex_value FROM cex_token_balance WHERE token_symbol = 'BTC';"}, {"role": "user", "content": "Can you break down the total USD value for 'BTC' held by CEXes by chain?"}, {"role": "assistant", "content": "SELECT chain, SUM(usd_value) AS total_btc_cex_value FROM cex_token_balance WHERE token_symbol = 'BTC' GROUP BY chain ORDER BY total_btc_cex_value DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE project_fundraising_record ( id character varying(32) NOT NULL, -- fundraising record id project_id character varying(32) NOT NULL, -- the invested project's id project_name character varying(128) NOT NULL, -- name of the invested project rounds_name character varying(32), -- name of the fundraising round investment_value numeric(38,14), -- amount of the fundraising in USD investment_date character varying(128), -- the date of the investment happened introduction character varying(128), -- the introduction of the invested project valuation numeric(38,14), -- the valuation of the project in USD when invested )\nCREATE TABLE token_basic_info ( coin_id character varying(100) NOT NULL, -- the id of the token token_name character varying(100) NOT NULL, -- the token's name token_symbol character varying(100) NOT NULL, -- the token's symbol token_address character varying(100) NOT NULL, -- the token's address chain text, -- the chain that the token resides price double precision, -- the current price of the token price_change_percentage_1h double precision, -- change in value divided by the absolute price value of the original token price in 1 hour price_change_percentage_24h double precision, -- change in value divided by the absolute price value of the original token price in 24 hours price_change_percentage_7d double precision, -- change in value divided by the absolute price value of the original token price in 7 days highest_price_24h double precision, -- the highest price of the token in 24 hours lowest_price_24h double precision, -- the lowest price of the token in 24 hours market_cap double precision, -- the market cap of the token market_cap_rank bigint, -- the rank of the token market cap in desc market_cap_change_percentage_24h text, -- the percentage of market cap changes in 24 hours total_volume text, -- the trade volum of the token both in decentralized exchange(DEX) and centralized exchange(CEX) narrative text, -- the category or narrative of the token trend_rank biging, -- the trending rank of the token, value 1 expresses the most popular token. ,PRIMARY KEY (coin_id, chain) )\nCREATE TABLE token_dexpool_info ( pair_address.text, token_name.text, token_symbol.text, chain.text, price.numeric, price_change_percentage_1h.numeric, price_change_percentage_6h.numeric, price_change_percentage_24h.numeric, makers_24h.numeric, volume_24h.numeric, liquidity.numeric, market_cap.numeric, trend_rank.numeric )\nCREATE TABLE cex_token_balance ( snapshot_time character varying(32) NOT NULL, -- the snapshot time of record, converted from original timestamp chain character varying(128) NOT NULL, -- the chain that the token resides address character varying(128) NOT NULL, -- the address that holds the assets, owned by a CEX exchange character varying(512) NOT NULL, -- a centralized exchange name token_address character varying(128) NOT NULL, -- token contract address token_symbol character varying(512), --token symbol balance numeric(38,10), -- token balance usd_value numeric(38,14), -- value of the token held in USD price double precision, --price of the token in USD ,PRIMARY KEY (snapshot_time, exchange, address, chain, token_address) )\nCREATE TABLE smart_money_profit ( address text, rank numeric, profit numeric, roi numeric, realized_ratio numeric, most_profit_token text, last_trade_time text, chain text )\nCREATE TABLE smart_money_token_performance ( token_address.text, token_symbol.text, pnl.numeric, net_flow.numeric, avg_cost.numeric, price.numeric, realized_ratio.numeric, roi.numeric, chain.text )\nCREATE TABLE smart_money_token_inflow ( token_address.text, token_symbol.text, token_amount.numeric, usd_value.numeric, avg_price.numeric, type.numeric, address_amount.numeric, narrative.text, chain.text )\n"} {"conversations": [{"role": "user", "content": "For each citizen who has made at least one payment, show the citizen's full name, number of payments, and total amount paid, grouped by currency."}, {"role": "assistant", "content": "SELECT\n c.first_name || ' ' || c.last_name AS full_name,\n p.currency,\n COUNT(*) AS payment_count,\n SUM(p.amount) AS total_amount\nFROM government_services.citizens c\nJOIN government_services.payments p ON c.citizen_id = p.citizen_id\nGROUP BY full_name, p.currency;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.citizens ( citizen_id character varying(64) NOT NULL, national_id_number character varying(128) NOT NULL UNIQUE, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, date_of_birth date NOT NULL, gender character varying(20), primary_address text NOT NULL, contact_email character varying(128) UNIQUE, contact_phone character varying(32), registration_date timestamp NOT NULL, is_verified boolean DEFAULT false, PRIMARY KEY (citizen_id) )\nCREATE TABLE government_services.payments ( payment_id character varying(64) NOT NULL, application_id character varying(64), citizen_id character varying(64) NOT NULL, service_id character varying(64), amount numeric(12, 2) NOT NULL, currency character varying(3) NOT NULL DEFAULT 'USD', payment_method character varying(50), payment_provider_reference character varying(128), payment_timestamp timestamp NOT NULL, status character varying(30) NOT NULL, notes text, PRIMARY KEY (payment_id) )\nCREATE TABLE government_services.employees ( employee_id character varying(64) NOT NULL, agency_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, job_title character varying(150) NOT NULL, department character varying(100), work_email character varying(128) NOT NULL UNIQUE, work_phone character varying(32), hire_date date NOT NULL, termination_date date, access_level character varying(50), manager_employee_id character varying(64), PRIMARY KEY (employee_id) )\nCREATE TABLE government_services.service_locations ( location_id character varying(64) NOT NULL, agency_id character varying(64) NOT NULL, location_name character varying(200), address text NOT NULL, city character varying(100), state character varying(50), postal_code character varying(20), latitude numeric(9, 6), longitude numeric(9, 6), operating_hours text, contact_phone character varying(32), is_accessible boolean, PRIMARY KEY (location_id) )\nCREATE TABLE government_services.appointments ( appointment_id character varying(64) NOT NULL, citizen_id character varying(64) NOT NULL, employee_id character varying(64), location_id character varying(64), service_id character varying(64), scheduled_start_time timestamp NOT NULL, scheduled_end_time timestamp, purpose text NOT NULL, status character varying(30) NOT NULL, booking_method character varying(50), created_at timestamp NOT NULL, notes text, PRIMARY KEY (appointment_id) )\nCREATE TABLE government_services.notifications ( notification_id character varying(64) NOT NULL, citizen_id character varying(64) NOT NULL, application_id character varying(64), message_subject character varying(255), message_body text NOT NULL, channel character varying(30) NOT NULL, sent_at timestamp NOT NULL, status character varying(30) NOT NULL, related_entity_type character varying(50), related_entity_id character varying(64), PRIMARY KEY (notification_id) )\n"} {"conversations": [{"role": "user", "content": "What is the total sum of amounts paid for all invoices?"}, {"role": "assistant", "content": "SELECT SUM(amount_paid) FROM invoices;"}, {"role": "user", "content": "Group this total by the status of the invoice."}, {"role": "assistant", "content": "SELECT status, SUM(amount_paid) FROM invoices GROUP BY status;"}, {"role": "user", "content": "Only show statuses where the total amount paid is greater than 50000."}, {"role": "assistant", "content": "SELECT status, SUM(amount_paid) FROM invoices GROUP BY status HAVING SUM(amount_paid) > 50000;"}, {"role": "user", "content": "Order the results by the total paid amount in descending order."}, {"role": "assistant", "content": "SELECT status, SUM(amount_paid) FROM invoices GROUP BY status HAVING SUM(amount_paid) > 50000 ORDER BY SUM(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 legal_services.law_firms ( firm_id text, firm_name text, address text, phone text, website text, founded_date date, managing_partner_id text )\nCREATE TABLE legal_services.cases ( case_id 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 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": "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": "Which exchanges on the Ethereum chain hold the highest total USD value of tokens, and what are their top 3 tokens by USD value?"}, {"role": "assistant", "content": "SELECT exchange, token_symbol, usd_value FROM cex_token_balance WHERE chain = 'Ethereum' ORDER BY usd_value DESC LIMIT 3;"}, {"role": "user", "content": "Can you modify this to show the top 5 exchanges instead of top 3 tokens, and include their total balance across all tokens?"}, {"role": "assistant", "content": "SELECT exchange, SUM(usd_value) as total_usd_value, SUM(balance) as total_balance FROM cex_token_balance WHERE chain = 'Ethereum' GROUP BY exchange ORDER BY total_usd_value 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 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 \"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": "Find the total number of documents uploaded by each citizen along with their first and last names."}, {"role": "assistant", "content": "SELECT c.citizen_id, c.first_name, c.last_name, COUNT(d.document_id) AS document_count\nFROM government_services.citizens c\nLEFT JOIN government_services.documents d ON c.citizen_id = d.citizen_id\nGROUP BY c.citizen_id, c.first_name, c.last_name;"}, {"role": "user", "content": "Actually, I only want to include those citizens who have uploaded documents in the last 30 days."}, {"role": "assistant", "content": "SELECT c.citizen_id, c.first_name, c.last_name, COUNT(d.document_id) AS document_count\nFROM government_services.citizens c\nJOIN government_services.documents d ON c.citizen_id = d.citizen_id\nWHERE d.upload_timestamp >= NOW() - INTERVAL '30 days'\nGROUP BY c.citizen_id, c.first_name, c.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 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.services (\n service_id character varying(64) NOT NULL, -- unique identifier for the service\n agency_id character varying(64) NOT NULL, -- FK to agencies table\n service_name character varying(255) NOT NULL, -- name of the service (e.g., Driver's License Renewal)\n description text,\n category character varying(100), -- e.g., Licensing, Benefits, Taxation, Permits\n eligibility_criteria text, -- description of who is eligible\n standard_fee numeric(10, 2) DEFAULT 0.00, -- typical fee for the service\n average_processing_time_days integer, -- estimated processing time\n is_active boolean DEFAULT true, -- whether the service is currently offered\n online_application_url character varying(255),\n PRIMARY KEY (service_id)\n)\nCREATE TABLE government_services.documents ( document_id text PRIMARY KEY, application_id text, citizen_id text, document_type text, file_reference text, upload_timestamp timestamp, expiry_date date, verification_status text, verified_by_employee_id text, verification_timestamp timestamp )\nCREATE TABLE government_services.payments ( payment_id text, 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) )\n"} {"conversations": [{"role": "user", "content": "Show me the total market cap and the total smart money inflow USD value for each narrative. Join the `token_basic_info` and `smart_money_token_inflow` tables based on narrative."}, {"role": "assistant", "content": "WITH Narratives AS ( SELECT DISTINCT narrative FROM token_basic_info WHERE narrative IS NOT NULL UNION SELECT DISTINCT narrative FROM smart_money_token_inflow WHERE narrative IS NOT NULL ) SELECT n.narrative, SUM(tbi.market_cap) AS total_market_cap, SUM(smi.usd_value) AS total_inflow_usd FROM Narratives n LEFT JOIN token_basic_info tbi ON n.narrative = tbi.narrative LEFT JOIN smart_money_token_inflow smi ON n.narrative = smi.narrative GROUP BY n.narrative ORDER BY total_inflow_usd DESC NULLS LAST;"}, {"role": "user", "content": "From that list, only show narratives where the total market cap is greater than 1,000,000,000."}, {"role": "assistant", "content": "WITH Narratives AS ( SELECT DISTINCT narrative FROM token_basic_info WHERE narrative IS NOT NULL UNION SELECT DISTINCT narrative FROM smart_money_token_inflow WHERE narrative IS NOT NULL ) SELECT n.narrative, SUM(tbi.market_cap) AS total_market_cap, SUM(smi.usd_value) AS total_inflow_usd FROM Narratives n LEFT JOIN token_basic_info tbi ON n.narrative = tbi.narrative LEFT JOIN smart_money_token_inflow smi ON n.narrative = smi.narrative GROUP BY n.narrative HAVING SUM(tbi.market_cap) > 1000000000 ORDER BY total_inflow_usd DESC NULLS LAST;"}], "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 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 smart_money_profit ( address text, rank numeric, profit numeric, roi numeric, realized_ratio numeric, most_profit_token text, last_trade_time text, chain text )\nCREATE TABLE smart_money_token_performance ( token_address text, token_symbol text, pnl numeric, net_flow numeric, avg_cost numeric, price numeric, realized_ratio numeric, roi numeric, chain text )\nCREATE TABLE smart_money_token_inflow ( token_address text, token_symbol text, token_amount numeric, usd_value numeric, avg_price numeric, type numeric, address_amount numeric, narrative text, chain text )\n"} {"conversations": [{"role": "user", "content": "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": "What are the specific tools or equipment used during the maintenance with record_id 'REC456'?"}, {"role": "assistant", "content": "I'm sorry, but I can't provide information about the specific tools or equipment used during a maintenance record. The data in the maintenance_records table does not include details about tools or equipment used."}], "system": "You are an SQL statement expert and you can refuse the user's question if the question is not related to the table structure. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE train_station_management.maintenance_records ( record_id text PRIMARY KEY, asset_id text, asset_type text, maintenance_type text, staff_id text, start_datetime timestamp, end_datetime timestamp, description text, cost numeric, status text )\n"} {"conversations": [{"role": "user", "content": "Provide a breakdown of the total number of conversations, showing how many are group chats and how many are not. Also, show the count of conversations that have a recorded last message time."}, {"role": "assistant", "content": "SELECT COUNT(*) AS total_conversations, COUNT(CASE WHEN is_group_chat = true THEN 1 END) AS group_chat_count, COUNT(CASE WHEN is_group_chat = false THEN 1 END) AS private_chat_count, COUNT(last_message_at) AS conversations_with_messages_count FROM social_media.conversations;"}], "system": "You are an SQL statement expert. Given the table structure 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": "List every diagnosis description paired with every insurance plan's website."}, {"role": "assistant", "content": "SELECT T1.description, T2.website FROM healthcare.diagnoses AS T1 CROSS JOIN healthcare.insurance_plans AS T2;"}, {"role": "user", "content": "Only include chronic diagnoses and plans whose website ends with '.org'."}, {"role": "assistant", "content": "SELECT T1.description, T2.website FROM healthcare.diagnoses AS T1 CROSS JOIN healthcare.insurance_plans AS T2 WHERE T1.is_chronic = true AND T2.website LIKE '%.org';"}], "system": "You are an SQL statement expert. Given the table structure 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.insurance_plans ( plan_id text PRIMARY KEY, plan_name text, insurance_provider text, plan_type text, contact_phone text, website text )\n"} {"conversations": [{"role": "user", "content": "What is the schedule of trains arriving at platform 1A at station XYZ on December 25th, 2023?"}, {"role": "assistant", "content": "I'm sorry, but I can't provide information about train schedules or specific arrival times as this data is not included in the platform management table. For train schedules, please refer to the train timetable or contact the station's customer service."}], "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 (\n platform_id character varying(64) NOT NULL, -- Unique identifier for the platform\n station_id character varying(64) NOT NULL, -- Foreign key referencing stations\n platform_number character varying(10) NOT NULL, -- Platform identifier (e.g., '1A', '5')\n track_number character varying(10), -- Associated track number, if different\n status character varying(32) NOT NULL DEFAULT 'Operational', -- e.g., Operational, Maintenance, Closed\n length_meters numeric(8,2), -- Length of the platform in meters\n accessible boolean NOT NULL DEFAULT false, -- Is the platform accessible (e.g., wheelchair)?\n PRIMARY KEY (platform_id),\n FOREIGN KEY (station_id) REFERENCES train_station_management.stations(station_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": "How many unique patient records are there for each gender?"}, {"role": "assistant", "content": "SELECT gender, COUNT(DISTINCT patient_id) AS patient_count FROM healthcare.patients GROUP BY gender;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE 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 properties that have more than 10 service orders delivered in the last month. Include the property_name and the number of delivered orders."}, {"role": "assistant", "content": "SELECT p.property_name,\n COUNT(o.order_id) AS delivered_orders\nFROM hospitality_technology.properties p\nJOIN hospitality_technology.services s ON p.property_id = s.property_id\nJOIN hospitality_technology.service_orders o ON s.service_id = o.service_id\nWHERE o.status = 'Delivered'\n AND o.delivery_timestamp >= current_date - interval '1 month'\nGROUP BY p.property_name\nHAVING COUNT(o.order_id) > 10;"}, {"role": "user", "content": "Actually, only include those properties where the average total_price per delivered order exceeds 50, and sort by that average descending."}, {"role": "assistant", "content": "SELECT p.property_name,\n COUNT(o.order_id) AS delivered_orders,\n AVG(o.total_price) AS avg_price\nFROM hospitality_technology.properties p\nJOIN hospitality_technology.services s ON p.property_id = s.property_id\nJOIN hospitality_technology.service_orders o ON s.service_id = o.service_id\nWHERE o.status = 'Delivered'\n AND o.delivery_timestamp >= current_date - interval '1 month'\nGROUP BY p.property_name\nHAVING COUNT(o.order_id) > 10\n AND AVG(o.total_price) > 50\nORDER BY avg_price DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE hospitality_technology.properties (\n property_id character varying(64) NOT NULL, -- unique identifier for the property (hotel, resort, etc.)\n property_name character varying(255) NOT NULL, -- name of the property\n address_line1 character varying(255) NOT NULL, -- primary address line\n address_line2 character varying(255), -- secondary address line\n city character varying(100) NOT NULL, -- city\n state_province character varying(100), -- state or province\n postal_code character varying(20) NOT NULL, -- zip or postal code\n country_code character varying(3) NOT NULL, -- ISO country code (e.g., USA, CAN)\n phone_number character varying(30), -- main contact phone\n email_address character varying(255), -- main contact email\n property_type character varying(50) NOT NULL, -- e.g., Hotel, Resort, B&B, Motel\n star_rating numeric(2,1), -- star rating (e.g., 4.5)\n timezone character varying(64) NOT NULL, -- IANA timezone ID (e.g., America/New_York)\n manager_staff_id character varying(64), -- FK to staff table for the general manager\n created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, -- record creation time\n updated_at timestamp with time zone NOT NULL DEFAULT current_timestamp, -- record last update time\n PRIMARY KEY (property_id)\n)\nCREATE TABLE hospitality_technology.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": "Could you list the trip ID, scheduled and actual arrival times, and the associated vehicle's make and model for all trips where the actual arrival was more than 30 minutes later than scheduled?"}, {"role": "assistant", "content": "SELECT T1.trip_id, T1.scheduled_arrival, T1.actual_arrival, T2.make, T2.model FROM transportation.trips AS T1 JOIN transportation.vehicles AS T2 ON T1.vehicle_id = T2.vehicle_id WHERE T1.actual_arrival IS NOT NULL AND T1.scheduled_arrival IS NOT NULL AND T1.actual_arrival > T1.scheduled_arrival + INTERVAL '30 minutes';"}, {"role": "user", "content": "Now, filter this list to only include trips that were completed within the last 6 months."}, {"role": "assistant", "content": "SELECT T1.trip_id, T1.scheduled_arrival, T1.actual_arrival, T2.make, T2.model FROM transportation.trips AS T1 JOIN transportation.vehicles AS T2 ON T1.vehicle_id = T2.vehicle_id WHERE T1.actual_arrival IS NOT NULL AND T1.scheduled_arrival IS NOT NULL AND T1.actual_arrival > T1.scheduled_arrival + INTERVAL '30 minutes' AND T1.actual_arrival >= NOW() - INTERVAL '6 months';"}], "system": "You are an SQL statement expert. Given the table structure 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.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.fuel_logs ( fuel_log_id text PRIMARY KEY, 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 int, location_id text )\n"} {"conversations": [{"role": "user", "content": "Show me a list of all doctors who have made at least one diagnosis along with the total number of diagnoses they have made."}, {"role": "assistant", "content": "SELECT d.doctor_id, d.first_name, d.last_name, COUNT(di.diagnosis_id) AS diagnosis_count\nFROM healthcare.doctors d\nJOIN healthcare.diagnoses di ON d.doctor_id = di.doctor_id\nGROUP BY d.doctor_id, d.first_name, d.last_name\nHAVING COUNT(di.diagnosis_id) > 0;"}, {"role": "user", "content": "Now, limit the list to doctors with fewer than 10 diagnoses and order them by diagnosis_count ascending."}, {"role": "assistant", "content": "SELECT d.doctor_id, d.first_name, d.last_name, COUNT(di.diagnosis_id) AS diagnosis_count\nFROM healthcare.doctors d\nJOIN healthcare.diagnoses di ON d.doctor_id = di.doctor_id\nGROUP BY d.doctor_id, d.first_name, d.last_name\nHAVING COUNT(di.diagnosis_id) > 0 AND COUNT(di.diagnosis_id) < 10\nORDER BY diagnosis_count ASC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.patients ( patient_id.text, first_name.text, last_name.text, date_of_birth.date, gender.text, address.text, phone_number.text, email.text, emergency_contact_name.text, emergency_contact_phone.text, created_at.timestamp, updated_at.timestamp )\nCREATE TABLE healthcare.medical_records (\n record_id character varying(64) NOT NULL, -- unique identifier for the medical record entry\n patient_id character varying(64) NOT NULL, -- FK to patients table\n appointment_id character varying(64) UNIQUE, -- FK to appointments table (can be null if record not tied to specific appt)\n doctor_id character varying(64) NOT NULL, -- FK to doctors table (doctor creating the record)\n record_date timestamp with time zone NOT NULL, -- date the record/observation was made\n chief_complaint text, -- patient's primary reason for visit\n present_illness_history text, -- detailed history of the current issue\n past_medical_history text, -- relevant past conditions/surgeries\n physical_examination_notes text, -- findings from the physical exam\n assessment text, -- doctor's assessment/diagnosis summary\n treatment_plan text, -- planned course of action\n vitals jsonb, -- store vitals like BP, HR, Temp as structured JSON\n created_at timestamp with time zone NOT NULL DEFAULT current_timestamp,\n PRIMARY KEY (record_id)\n)\nCREATE TABLE healthcare.diagnoses (\n diagnosis_id character varying(64) NOT NULL, -- unique identifier for the diagnosis entry\n record_id character varying(64) NOT NULL, -- FK linking to the specific medical record entry\n patient_id character varying(64) NOT NULL, -- FK to patients table\n doctor_id character varying(64) NOT NULL, -- FK to doctors table (diagnosing doctor)\n diagnosis_code character varying(20) NOT NULL, -- standard code (e.g., ICD-10)\n code_type character varying(10) NOT NULL DEFAULT 'ICD-10', -- type of code used\n description text, -- textual description of the diagnosis\n diagnosis_date date NOT NULL, -- date the diagnosis was made\n status character varying(32) NOT NULL, -- e.g., Active, Resolved, Ruled Out\n is_chronic boolean DEFAULT false, -- flag for chronic conditions\n PRIMARY KEY (diagnosis_id)\n)\nCREATE TABLE healthcare.medications ( medication_id text, medication_name text, generic_name text, manufacturer text, ndc_code text, description text )\nCREATE TABLE healthcare.prescriptions ( prescription_id text, record_id text, patient_id text, doctor_id text, medication_id text, dosage text, frequency text, route text, start_date date, end_date date, quantity_dispensed numeric, refills_allowed integer, prescription_date timestamp )\nCREATE TABLE healthcare.insurance_plans ( plan_id text, plan_name text, insurance_provider text, plan_type text, contact_phone text, website text )\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": "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": "I need a summary of the number of cases by case_type. Please show the case_type and how many cases exist for each."}, {"role": "assistant", "content": "SELECT case_type, COUNT(*) AS case_count FROM legal_services.cases GROUP BY case_type;"}, {"role": "user", "content": "Now exclude any case_type that has only one case."}, {"role": "assistant", "content": "SELECT case_type, COUNT(*) AS case_count FROM legal_services.cases GROUP BY case_type HAVING COUNT(*) > 1;"}, {"role": "user", "content": "Can you also provide the most recent date_opened for cases in each case_type?"}, {"role": "assistant", "content": "SELECT case_type, COUNT(*) AS case_count, MAX(date_opened) AS most_recent_opened FROM legal_services.cases GROUP BY case_type HAVING COUNT(*) > 1;"}, {"role": "user", "content": "Lastly, just show those case_types where the most recent case was opened after January 1, 2023."}, {"role": "assistant", "content": "SELECT case_type, COUNT(*) AS case_count, MAX(date_opened) AS most_recent_opened FROM legal_services.cases GROUP BY case_type HAVING COUNT(*) > 1 AND MAX(date_opened) > '2023-01-01';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE 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) )\n"} {"conversations": [{"role": "user", "content": "Show me all SUI coins with a balance greater than 1000, including their symbol and name."}, {"role": "assistant", "content": "SELECT sc.object_id, sc.coin_type, sc.balance, scm.symbol, scm.name FROM sui_coins sc JOIN sui_coins_metadata scm ON sc.coin_type = scm.coin_type WHERE CAST(sc.balance AS DECIMAL) > 1000;"}, {"role": "user", "content": "Also, include the owner address for each coin in the result."}, {"role": "assistant", "content": "SELECT sc.object_id, sc.coin_type, sc.balance, sc.owner, scm.symbol, scm.name FROM sui_coins sc JOIN sui_coins_metadata scm ON sc.coin_type = scm.coin_type WHERE CAST(sc.balance AS DECIMAL) > 1000;"}, {"role": "user", "content": "Only show coins which are currently 'active', and add the coin description."}, {"role": "assistant", "content": "SELECT sc.object_id, sc.coin_type, sc.balance, sc.owner, scm.symbol, scm.name, scm.description FROM sui_coins sc JOIN sui_coins_metadata scm ON sc.coin_type = scm.coin_type WHERE CAST(sc.balance AS DECIMAL) > 1000 AND sc.status = 'active' AND scm.status = 'active';"}, {"role": "user", "content": "Actually, limit the result to just 10 coins and sort them by balance descending."}, {"role": "assistant", "content": "SELECT sc.object_id, sc.coin_type, sc.balance, sc.owner, scm.symbol, scm.name, scm.description FROM sui_coins sc JOIN sui_coins_metadata scm ON sc.coin_type = scm.coin_type WHERE CAST(sc.balance AS DECIMAL) > 1000 AND sc.status = 'active' AND scm.status = 'active' ORDER BY CAST(sc.balance AS DECIMAL) DESC LIMIT 10;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE erc20_balances ( block_number bigint, contract_address varchar, wallet_address varchar, amount varchar, pk varchar )\nCREATE TABLE erc20_balances_historical ( block_number bigint, contract_address varchar, wallet_address varchar, amount varchar, pk integer )\nCREATE TABLE nft_holder_historical ( block_number bigint, contract_address varchar, wallet_address varchar, token_id varchar, contract_type varchar, amount varchar, pk integer )\nCREATE TABLE sui_coins ( object_id varchar, status varchar, coin_type varchar, balance varchar, owner varchar )\nCREATE TABLE sui_coins_metadata ( object_id varchar, coin_type varchar, status varchar, decimals bigint, description varchar, icon_url varchar, symbol varchar, name varchar )\nCREATE TABLE nft_metadata ( blockchain varchar, contract_address varchar, token_id varchar, contract_name varchar, erc_type varchar, amount bigint, minter varchar, owner varchar, mint_block_number bigint, mint_time bigint, mint_transaction_hash varchar, mint_price varchar, token_uri varchar, metadata varchar, name varchar, image_uri varchar, traits varchar, updated_at bigint, status varchar, rarity_score real, rarity_rank integer, unique_attribute_count integer, pk integer )\nCREATE TABLE nft_collections ( blockchain varchar, contract_address varchar, name varchar, symbol varchar, deploy_block_number bigint, deploy_block_time bigint, erc_type varchar, owner varchar, traits varchar, description varchar, slug varchar, media_info varchar, image_url varchar, banner_image_url varchar, updated_at bigint, banner varchar, token_count bigint, floor_price varchar, floor_price_symbol varchar, floor_price_contract varchar, pk integer )\nCREATE TABLE token_prices_latest ( blockchain varchar, address varchar, decimals bigint, symbol varchar, price real, timestamp timestamp )\nCREATE TABLE erc20_approval ( block_number bigint, block_timestamp timestamp, transaction_index integer, transaction_hash varchar, log_index integer, contract_address varchar, pk integer )\nCREATE TABLE token_activities ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash varchar, log_index integer, type varchar, tick varchar, id varchar, amt decimal, from_address varchar, to_address varchar )\nCREATE TABLE mud_holesky_redstone ( address varchar, table_id varchar, key_bytes varchar, key0 varchar, key1 varchar, static_data varchar, encoded_lengths varchar, dynamic_data varchar, is_deleted boolean, block_number bigint, log_index bigint )\nCREATE TABLE token_info_bitcoin ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash varchar, tick varchar, max_supply decimal, lim decimal, wlim decimal, dec integer, creator varchar )\nCREATE TABLE token_info_avalanche ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash varchar, tick varchar, max_supply decimal, lim decimal, wlim decimal, dec integer, creator varchar, minted decimal, holders decimal, txs decimal, updated_timestamp timestamp, completed_timestamp timestamp, id varchar )\n"} {"conversations": [{"role": "user", "content": "List all premium payments for policy 'POL123'. Show payment ID, payment date, amount paid, and status."}, {"role": "assistant", "content": "SELECT payment_id, payment_date, amount_paid, status FROM insurance.premium_payments WHERE policy_id = 'POL123';"}, {"role": "user", "content": "Only show payments made on or after January 1, 2024."}, {"role": "assistant", "content": "SELECT payment_id, payment_date, amount_paid, status FROM insurance.premium_payments WHERE policy_id = 'POL123' AND 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 (\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)\n"} {"conversations": [{"role": "user", "content": "I want to know, for each conversation participant, how many unread messages they have. Return participant_id, conversation_id, and unread_count."}, {"role": "assistant", "content": "SELECT cp.participant_id,\n cp.conversation_id,\n COUNT(m.message_id) AS unread_count\nFROM social_media.conversation_participants cp\nJOIN social_media.messages m\n ON m.conversation_id = cp.conversation_id\nWHERE m.sent_at > COALESCE(cp.last_read_at, '1970-01-01'::timestamp)\nGROUP BY cp.participant_id, cp.conversation_id;"}, {"role": "user", "content": "Can you filter the results to only include participants who joined the conversation before the earliest unread message was sent?"}, {"role": "assistant", "content": "SELECT cp.participant_id,\n cp.conversation_id,\n COUNT(m.message_id) AS unread_count\nFROM social_media.conversation_participants cp\nJOIN social_media.messages m\n ON m.conversation_id = cp.conversation_id\nWHERE m.sent_at > COALESCE(cp.last_read_at, '1970-01-01'::timestamp)\nGROUP BY cp.participant_id, cp.conversation_id\nHAVING cp.joined_at < MIN(m.sent_at);"}, {"role": "user", "content": "Also, include the timestamp of the most recent unread message for each participant as last_unread_at."}, {"role": "assistant", "content": "SELECT cp.participant_id,\n cp.conversation_id,\n COUNT(m.message_id) AS unread_count,\n MAX(m.sent_at) AS last_unread_at\nFROM social_media.conversation_participants cp\nJOIN social_media.messages m\n ON m.conversation_id = cp.conversation_id\nWHERE m.sent_at > COALESCE(cp.last_read_at, '1970-01-01'::timestamp)\nGROUP BY cp.participant_id, cp.conversation_id\nHAVING cp.joined_at < MIN(m.sent_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.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.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.post_hashtags (\n post_hashtag_id character varying(64) NOT NULL, -- unique identifier for the post-hashtag link\n post_id character varying(64) NOT NULL, -- identifier of the post (FK to posts.post_id)\n hashtag_id character varying(64) NOT NULL, -- identifier of the hashtag (FK to hashtags.hashtag_id)\n PRIMARY KEY (post_hashtag_id),\n CONSTRAINT unique_post_hashtag UNIQUE (post_id, hashtag_id) -- prevent duplicate tags on a post\n)\nCREATE TABLE social_media.messages (\n message_id character varying(64) NOT NULL, -- unique identifier for the message\n conversation_id character varying(64) NOT NULL, -- identifier for the conversation thread (FK to conversations.conversation_id)\n sender_user_id character varying(64) NOT NULL, -- identifier of the sender (FK to users.user_id)\n content text, -- textual content of the message\n media_url text, -- URL to attached media (image/video)\n media_type character varying(20), -- type of media ('image', 'video', null)\n sent_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp when message was sent\n read_at timestamp, -- timestamp when message was read by recipient(s)\n PRIMARY KEY (message_id)\n)\nCREATE TABLE social_media.conversation_participants (\n participant_id character varying(64) NOT NULL, -- unique identifier for the participant entry\n conversation_id character varying(64) NOT NULL, -- identifier of the conversation (FK to conversations.conversation_id)\n user_id character varying(64) NOT NULL, -- identifier of the user in the conversation (FK to users.user_id)\n joined_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp when user joined the conversation\n last_read_at timestamp, -- timestamp indicating up to when the user has read messages\n PRIMARY KEY (participant_id),\n CONSTRAINT unique_user_conversation UNIQUE (conversation_id, user_id) -- prevent user being added multiple times\n)\nCREATE TABLE social_media.notifications (\n notification_id character varying(64) NOT NULL, -- unique identifier for the notification\n recipient_user_id character varying(64) NOT NULL, -- user receiving the notification (FK to users.user_id)\n sender_user_id character varying(64), -- user triggering the notification (FK to users.user_id, can be null for system notifications)\n notification_type character varying(30) NOT NULL, -- type of notification ('like', 'comment', 'follow', 'mention', 'message')\n target_entity_id character varying(64), -- ID of the related entity (post_id, comment_id, user_id, conversation_id)\n target_entity_type character varying(20), -- type of the related entity ('post', 'comment', 'user', 'conversation')\n created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp notification was created\n read_at timestamp, -- timestamp notification was marked as read\n PRIMARY KEY (notification_id)\n)\nCREATE TABLE social_media.user_settings (\n setting_id character varying(64) NOT NULL, -- unique identifier for the setting entry\n user_id character varying(64) NOT NULL UNIQUE, -- user the settings belong to (FK to users.user_id)\n theme character varying(20) DEFAULT 'light', -- UI theme ('light', 'dark')\n email_notifications_enabled boolean DEFAULT true, -- enable/disable email notifications\n push_notifications_enabled boolean DEFAULT true, -- enable/disable push notifications\n private_profile boolean DEFAULT false, -- is the user profile private\n updated_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of last setting change\n PRIMARY KEY (setting_id)\n)\n"} {"conversations": [{"role": "user", "content": "List 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": "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": "What is the detailed repair history of the equipment used by the staff with staff_id 'STAFF123' during maintenance tasks?"}, {"role": "assistant", "content": "I'm sorry, but I can't provide information on the detailed repair history of equipment used by staff members. The data in the maintenance_records table only includes information about maintenance tasks, such as record_id, asset_id, maintenance type, and staff_id, but does not cover equipment repair histories."}], "system": "You are an SQL statement expert and you can refuse the user's question if the question is not related to the table structure. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE train_station_management.maintenance_records ( record_id.text, asset_id.text, asset_type.text, maintenance_type.text, staff_id.text, start_datetime.timestamp, end_datetime.timestamp, description.text, cost.numeric, status.text )\n"} {"conversations": [{"role": "user", "content": "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": "Identify all instances where a vehicle's odometer_reading increased by more than 500 miles between two consecutive fuel log entries."}, {"role": "assistant", "content": "SELECT a.vehicle_id,\n a.fuel_log_id AS previous_log_id,\n b.fuel_log_id AS next_log_id,\n a.log_timestamp AS previous_time,\n b.log_timestamp AS next_time,\n b.odometer_reading - a.odometer_reading AS mile_increase\nFROM transportation.fuel_logs a\nJOIN transportation.fuel_logs b\n ON a.vehicle_id = b.vehicle_id\n AND b.log_timestamp = (\n SELECT MIN(log_timestamp)\n FROM transportation.fuel_logs\n WHERE vehicle_id = a.vehicle_id\n AND log_timestamp > a.log_timestamp\n )\nWHERE b.odometer_reading - a.odometer_reading > 500;"}, {"role": "user", "content": "Now restrict these increases to those where the time difference between entries is less than 7 days."}, {"role": "assistant", "content": "SELECT a.vehicle_id,\n a.fuel_log_id AS previous_log_id,\n b.fuel_log_id AS next_log_id,\n a.log_timestamp AS previous_time,\n b.log_timestamp AS next_time,\n b.odometer_reading - a.odometer_reading AS mile_increase,\n EXTRACT(epoch FROM (b.log_timestamp - a.log_timestamp))/3600 AS hours_diff\nFROM transportation.fuel_logs a\nJOIN transportation.fuel_logs b\n ON a.vehicle_id = b.vehicle_id\n AND b.log_timestamp = (\n SELECT MIN(log_timestamp)\n FROM transportation.fuel_logs\n WHERE vehicle_id = a.vehicle_id\n AND log_timestamp > a.log_timestamp\n )\nWHERE b.odometer_reading - a.odometer_reading > 500\n AND b.log_timestamp - a.log_timestamp < INTERVAL '7 days';"}, {"role": "user", "content": "Also include both the mile increase and the time difference in hours in the final output columns."}, {"role": "assistant", "content": "SELECT a.vehicle_id,\n a.fuel_log_id AS previous_log_id,\n b.fuel_log_id AS next_log_id,\n b.odometer_reading - a.odometer_reading AS mile_increase,\n EXTRACT(epoch FROM (b.log_timestamp - a.log_timestamp))/3600 AS hours_difference\nFROM transportation.fuel_logs a\nJOIN transportation.fuel_logs b\n ON a.vehicle_id = b.vehicle_id\n AND b.log_timestamp = (\n SELECT MIN(log_timestamp)\n FROM transportation.fuel_logs\n WHERE vehicle_id = a.vehicle_id\n AND log_timestamp > a.log_timestamp\n )\nWHERE b.odometer_reading - a.odometer_reading > 500\n AND b.log_timestamp - a.log_timestamp < INTERVAL '7 days';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.fuel_logs ( fuel_log_id.text, vehicle_id.text, trip_id.text, log_timestamp.timestamp, fuel_type.text, quantity.numeric, unit.text, cost_per_unit.numeric, total_cost.numeric, odometer_reading.integer, location_id.text )\n"} {"conversations": [{"role": "user", "content": "Show me the top 5 narratives by market cap, along with their 24-hour trading volume and 7-day price change percentage."}, {"role": "assistant", "content": "SELECT narrative.text, volume_24h.numeric, price_change_percentage_7d.numeric FROM narrative_info ORDER BY market_cap.numeric DESC LIMIT 5;"}, {"role": "user", "content": "Can you also include the top 3 coins for each of these narratives?"}, {"role": "assistant", "content": "SELECT narrative.text, volume_24h.numeric, price_change_percentage_7d.numeric, top_3_coins.text FROM narrative_info ORDER BY market_cap.numeric DESC LIMIT 5;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE narrative_info ( narrative.text, top_3_coins.text, price_change_percentage_1h.numeric, price_change_percentage_24h.numeric, price_change_percentage_7d.numeric, market_cap.numeric, volume_24h.numeric, trend_rank.numeric, token_num.numeric )\n"} {"conversations": [{"role": "user", "content": "Find all patients along with the number of unique diagnoses each has received. Only include patients who have at least two diagnoses."}, {"role": "assistant", "content": "SELECT p.patient_id, p.first_name, p.last_name, COUNT(DISTINCT d.diagnosis_id) AS num_diagnoses\nFROM healthcare.patients p\nJOIN healthcare.diagnoses d ON p.patient_id = d.patient_id\nGROUP BY p.patient_id, p.first_name, p.last_name\nHAVING COUNT(DISTINCT d.diagnosis_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 healthcare.patients ( patient_id text, first_name text, last_name text, date_of_birth date, gender text, address text, phone_number text, email text, emergency_contact_name text, emergency_contact_phone text, created_at timestamp, updated_at timestamp )\nCREATE TABLE healthcare.appointments ( appointment_id text, patient_id text, doctor_id text, appointment_time timestamp, duration_minutes integer, reason text, status text, location_id text, notes text, created_at timestamp )\nCREATE TABLE healthcare.diagnoses ( diagnosis_id text, record_id text, patient_id text, doctor_id text, diagnosis_code text, code_type text, description text, diagnosis_date date, status text, is_chronic boolean )\nCREATE TABLE healthcare.medications ( medication_id text, medication_name text, generic_name text, manufacturer text, ndc_code text, description text )\n"} {"conversations": [{"role": "user", "content": "Show me all patients who have been prescribed medications with dosage greater than 200mg, along with their full names and the medication details, including the prescribing doctor's last name."}, {"role": "assistant", "content": "SELECT p.first_name, p.last_name, m.medication_name, m.description, pr.dosage, d.last_name AS doctor_last_name FROM healthcare.patients p JOIN healthcare.prescriptions pr ON p.patient_id = pr.patient_id JOIN healthcare.medications m ON pr.medication_id = m.medication_id JOIN healthcare.doctors d ON pr.doctor_id = d.doctor_id WHERE CAST(SUBSTRING(pr.dosage FROM '[0-9]+') AS INTEGER) > 200;"}], "system": "You are an SQL statement expert. Given the table structure 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 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.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 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) )\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 text PRIMARY KEY, plan_name text, insurance_provider text, plan_type text, contact_phone text, website text )\nCREATE TABLE healthcare.patient_insurance ( patient_insurance_id character varying(64) NOT NULL, patient_id character varying(64) NOT NULL, plan_id character varying(64) NOT NULL, policy_number character varying(100) NOT NULL, group_number character varying(100), subscriber_name character varying(200), effective_date date NOT NULL, expiration_date date, is_primary boolean NOT NULL DEFAULT true, PRIMARY KEY (patient_insurance_id), UNIQUE (patient_id, plan_id, policy_number) )\n"} {"conversations": [{"role": "user", "content": "List the total number of notifications sent through each channel for appointments."}, {"role": "assistant", "content": "SELECT n.channel, COUNT(*) AS notification_count\nFROM government_services.notifications n\nWHERE n.related_entity_type = 'Appointment'\nGROUP BY n.channel;"}, {"role": "user", "content": "Please only include notifications that were sent after March 1, 2024."}, {"role": "assistant", "content": "SELECT n.channel, COUNT(*) AS notification_count\nFROM government_services.notifications n\nWHERE n.related_entity_type = 'Appointment' AND n.sent_at > '2024-03-01'\nGROUP BY n.channel;"}, {"role": "user", "content": "Exclude any channels where the count is less than 5."}, {"role": "assistant", "content": "SELECT n.channel, COUNT(*) AS notification_count\nFROM government_services.notifications n\nWHERE n.related_entity_type = 'Appointment' AND n.sent_at > '2024-03-01'\nGROUP BY n.channel\nHAVING COUNT(*) >= 5;"}, {"role": "user", "content": "Can you order the results by notification_count in ascending order?"}, {"role": "assistant", "content": "SELECT n.channel, COUNT(*) AS notification_count\nFROM government_services.notifications n\nWHERE n.related_entity_type = 'Appointment' AND n.sent_at > '2024-03-01'\nGROUP BY n.channel\nHAVING COUNT(*) >= 5\nORDER BY notification_count 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 government_services.services (\n service_id character varying(64) NOT NULL, -- unique identifier for the service\n agency_id character varying(64) NOT NULL, -- FK to agencies table\n service_name character varying(255) NOT NULL, -- name of the service (e.g., Driver's License Renewal)\n description text,\n category character varying(100), -- e.g., Licensing, Benefits, Taxation, Permits\n eligibility_criteria text, -- description of who is eligible\n standard_fee numeric(10, 2) DEFAULT 0.00, -- typical fee for the service\n average_processing_time_days integer, -- estimated processing time\n is_active boolean DEFAULT true, -- whether the service is currently offered\n online_application_url character varying(255),\n PRIMARY KEY (service_id)\n)\nCREATE TABLE government_services.documents ( 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.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 (\n notification_id character varying(64) NOT NULL, -- unique identifier for the notification\n citizen_id character varying(64) NOT NULL, -- FK to citizens table\n application_id character varying(64), -- FK to applications table (optional)\n message_subject character varying(255),\n message_body text NOT NULL,\n channel character varying(30) NOT NULL, -- e.g., Email, SMS, Portal Message, Mail\n sent_at timestamp NOT NULL,\n status character varying(30) NOT NULL, -- e.g., Queued, Sent, Delivered, Failed, Read\n related_entity_type character varying(50), -- e.g., Application, Appointment, Document Request\n related_entity_id character varying(64), -- ID of the related entity\n PRIMARY KEY (notification_id)\n)\n"} {"conversations": [{"role": "user", "content": "What is the average age of customers created in the last year?"}, {"role": "assistant", "content": "SELECT AVG(DATE_PART('year', CURRENT_DATE) - DATE_PART('year', date_of_birth)) FROM financial_services.customers WHERE created_at >= CURRENT_DATE - INTERVAL '1 year';"}, {"role": "user", "content": "Also show the count of such customers."}, {"role": "assistant", "content": "SELECT AVG(DATE_PART('year', CURRENT_DATE) - DATE_PART('year', date_of_birth)) AS average_age, COUNT(*) AS customer_count FROM financial_services.customers WHERE created_at >= CURRENT_DATE - INTERVAL '1 year';"}, {"role": "user", "content": "Only include customers whose email is not null."}, {"role": "assistant", "content": "SELECT AVG(DATE_PART('year', CURRENT_DATE) - DATE_PART('year', date_of_birth)) AS average_age, COUNT(*) AS customer_count FROM financial_services.customers WHERE created_at >= CURRENT_DATE - INTERVAL '1 year' AND 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 financial_services.customers ( customer_id text PRIMARY KEY, first_name text, last_name text, date_of_birth date, ssn_hash text, address text, city text, state text, zip_code text, country text, email text, phone_number text, created_at timestamp, status text, risk_profile text )\n"} {"conversations": [{"role": "user", "content": "Show me the top 5 projects by valuation that completed fundraising rounds in the last 12 months, along with their token symbol and price from the token_basic_info table."}, {"role": "assistant", "content": "SELECT pfr.project_name, pfr.valuation, tbi.token_symbol, tbi.price FROM project_fundraising_record pfr LEFT JOIN token_basic_info tbi ON pfr.project_name = tbi.token_name WHERE pfr.investment_date >= DATE_SUB(CURRENT_DATE, INTERVAL 12 MONTH) ORDER BY pfr.valuation DESC LIMIT 5;"}, {"role": "user", "content": "Can you also include the 24-hour trading volume for these projects' tokens and filter to only include projects with valuation over $100 million?"}, {"role": "assistant", "content": "SELECT pfr.project_name, pfr.valuation, tbi.token_symbol, tbi.price, tbi.total_volume FROM project_fundraising_record pfr LEFT JOIN token_basic_info tbi ON pfr.project_name = tbi.token_name WHERE pfr.investment_date >= DATE_SUB(CURRENT_DATE, INTERVAL 12 MONTH) AND pfr.valuation > 100000000 ORDER BY pfr.valuation DESC LIMIT 5;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\n \"CREATE TABLE project_fundraising_record (\",\n \"id character varying(32) NOT NULL, -- fundraising record id\",\n \"project_id character varying(32) NOT NULL, -- the invested project's id\",\n \"project_name character varying(128) NOT NULL, -- name of the invested project\",\n \"rounds_name character varying(32), -- name of the fundraising round\",\n \"investment_value numeric(38,14), -- amount of the fundraising in USD\",\n \"investment_date character varying(128), -- the date of the investment happened\",\n \"introduction character varying(128), -- the introduction of the invested project\",\n \"valuation numeric(38,14), -- the valuation of the project in USD when invested\",\n\nCREATE TABLE token_basic_info ( coin_id character varying(100) NOT NULL, -- the id of the token token_name character varying(100) NOT NULL, -- the token's name token_symbol character varying(100) NOT NULL, -- the token's symbol token_address character varying(100) NOT NULL, -- the token's address chain text, -- the chain that the token resides price double precision, -- the current price of the token price_change_percentage_1h double precision, -- change in value divided by the absolute price value of the original token price in 1 hour price_change_percentage_24h double precision, -- change in value divided by the absolute price value of the original token price in 24 hours price_change_percentage_7d double precision, -- change in value divided by the absolute price value of the original token price in 7 days highest_price_24h double precision, -- the highest price of the token in 24 hours lowest_price_24h double precision, -- the lowest price of the token in 24 hours market_cap double precision, -- the market cap of the token market_cap_rank bigint, -- the rank of the token market cap in desc market_cap_change_percentage_24h text, -- the percentage of market cap changes in 24 hours total_volume text, -- the trade volum of the token both in decentralized exchange(DEX) and centralized exchange(CEX) narrative text, -- the category or narrative of the token trend_rank biging, -- the trending rank of the token, value 1 expresses the most popular token. ,PRIMARY KEY (coin_id, chain) )\nCREATE TABLE narrative_info ( narrative character varying(512) NOT NULL, -- the id of narrative top_3_coins text, -- the top 3 tokens in the narrative price_change_percentage_1h double precision, -- change in value divided by the absolute price value of the original token price in 1 hour in the narrative price_change_percentage_24h double precision, -- change in value divided by the absolute price value of the original token price in 24 hours in the narrative price_change_percentage_7d double precision, -- change in value divided by the absolute price value of the original token price in 7 days in the narrative market_cap double precision, -- the market cap of the narrative volume_24h double precision, -- the trade volume of the narrative trend_rank bigint, -- the trending rank of the narrative, value 1 expresses the most popular narrative token_num bigint, -- total token number in the narrative ,PRIMARY KEY (narrative) )\nCREATE TABLE token_dexpool_info ( pair_address character varying(512) NOT NULL, token_name character varying(100) NOT NULL, token_symbol character varying(100) NOT NULL, chain text, price double precision, price_change_percentage_1h double precision, price_change_percentage_6h double precision, price_change_percentage_24h double precision, makers_24h double precision, volume_24h double precision, liquidity double precision, market_cap double precision, trend_rank bigint )\nCREATE TABLE smart_money_profit ( address character varying(100) NOT NULL, rank INT, profit numeric(38,6), roi numeric(38,2), realized_ratio numeric(38,2), most_profit_token character varying(100), last_trade_time character varying(100), chain character varying(100) )\n \"CREATE TABLE smart_money_token_performance (\",\n \"token_address character varying(100) NOT NULL, -- the token's address\",\n \"token_symbol character varying(100), -- the tokens's symbol\",\n \"pnl numeric(38,2), -- the profit users made on this token\",\n \"net_flow numeric(38,2), -- the netflow of the token, means the money user spent minus the the money user sold of this token\",\n \"avg_cost numeric(38,16), -- the average cost price of user spent on this token\",\n \"price double precision, -- the current price of the token\",\n \"realized_ratio numeric(10,2), -- the ratio user sold of the token\",\n \"roi numeric(10,2), -- the roi users made of this token\",\n \"chain character varying(100), -- the chain that the token resides\",\n \"PRIMARY KEY (token_address, chain));\",\n\n \"CREATE TABLE smart_money_token_inflow (\",\n \"token_address character varying(100) NOT NULL, -- the token's address\",\n \"token_symbol character varying(100), -- the tokens's symbol\",\n \"token_amount numeric(38,2), -- the absolute value of the amount if user bought minus the amount user sold of this token\",\n \"usd_value numeric(38,2), -- the absolute usd value of the bought token minus sold token\",\n \"avg_price numeric(38,6), -- the average cost price of user spent on this token\",\n \"type int, -- the direction of the trade on this token. 1 means buying, 2 means selling\",\n \"address_amount integer, -- the amount of the user bought this token\",\n \"narrative character varying(100), -- the category or narrative of the token\",\n \"chain character varying(100), -- the chain that the token resides\",\n \",PRIMARY KEY (token_address, chain)\",\n\n"} {"conversations": [{"role": "user", "content": "List all ERC20 tokens where the price is between $1 and $10, including their names, symbols, and contract addresses."}, {"role": "assistant", "content": "SELECT tm.name, tm.symbol, tm.contract_address FROM token_metas tm JOIN token_prices_latest tpl ON tm.contract_address = tpl.contract_address WHERE tm.is_erc20 = 1 AND tpl.price BETWEEN 1 AND 10;"}, {"role": "user", "content": "I think there's an error in your query - the token_prices_latest table isn't in the schema. Can you modify it to use the token_balances table instead?"}, {"role": "assistant", "content": "SELECT tm.name, tm.symbol, tm.contract_address FROM token_metas tm JOIN token_balances tb ON tm.contract_address = tb.wallet_address WHERE tm.is_erc20 = 1 AND CAST(tb.amount AS decimal) BETWEEN 1 AND 10;"}, {"role": "user", "content": "That doesn't seem right either. Let's just get the basic ERC20 token information without price filtering for now."}, {"role": "assistant", "content": "SELECT name, symbol, contract_address FROM token_metas WHERE is_erc20 = 1 LIMIT 100;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE token_metas ( block_timestamp.timestamp, block_number.bigint, transaction_hash.text, transaction_index.bigint, from_address.text, contract_address.text, symbol.text, total_supply.text, name.text, decimals.bigint, is_erc20.integer, is_erc721.integer, is_erc1155.integer, is_proxy.integer, extra_info.text, pk.integer )\nCREATE TABLE erc1155_approval_for_all ( block_number bigint NOT NULL, block_timestamp timestamp(3) NOT NULL, transaction_index integer NOT NULL, transaction_hash varchar(66) NOT NULL, log_index integer NOT NULL, contract_address varchar(42) NOT NULL )\nCREATE TABLE erc20_balances ( block_number bigint NOT NULL, contract_address varchar NOT NULL, wallet_address varchar NOT NULL, amount varchar NOT NULL, pk varchar NOT NULL )\nCREATE TABLE erc20_balances_historical ( block_number bigint, contract_address text, wallet_address text, amount text, pk integer )\nCREATE TABLE nft_holders ( block_number bigint, contract_address text, wallet_address text, token_id text, contract_type text, amount text, pk text )\nCREATE TABLE nft_holder_historical ( block_number.bigint, contract_address.text, wallet_address.text, token_id.text, contract_type.text, amount.text, pk.integer )\nCREATE TABLE sui_nfts ( object_id text, status text, collection_type text, package_id text, previous_transaction text, display text, owner text, name text )\nCREATE TABLE nft_collections ( blockchain text, contract_address text, name text, symbol text, deploy_block_number bigint, deploy_block_time bigint, erc_type text, owner text, traits text, description text, slug text, media_info text, image_url text, banner_image_url text, updated_at bigint, banner text, token_count bigint, floor_price text, floor_price_symbol text, floor_price_contract text, pk integer )\nCREATE TABLE erc20_approval ( block_number bigint NOT NULL, block_timestamp timestamp(6) NOT NULL, transaction_index integer NOT NULL, transaction_hash varchar NOT NULL, log_index integer NOT NULL, contract_address varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE token_balances ( block_number bigint, block_timestamp timestamp, tick text, wallet_address text, total_supply decimal, amount decimal )\nCREATE TABLE token_info (\n block_timestamp timestamp(3) NOT NULL, -- Timestamp of the block containing the inscription (matches block_timestamp in transactions table)\n block_number bigint NOT NULL, -- Block number containing the inscription (matches block_number in transactions table)\n tx_index integer NOT NULL, -- Index of the transaction containing the inscription (matches transaction_index in transactions table)\n tx_hash varchar(66) NOT NULL, -- Unique identifier of the transaction containing the inscription (matches hash in transactions table)\n tick varchar NOT NULL, -- Token tick\n max_supply decimal(38,0) NOT NULL, -- Max supply\n lim decimal(38,0) NOT NULL, -- Limit of each mint\n wlim decimal(38,0) NOT NULL, -- Limit of each address can maximum mint\n dec integer NOT NULL, -- Decimal for minimum divie\n creator varchar(42) NOT NULL -- Address originating the inscription (matches from_address in transactions table)\n)\nCREATE TABLE token_activities ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash varchar, log_index integer, type varchar, tick varchar, id varchar, amt decimal, from_address varchar, to_address varchar )\nCREATE TABLE mud_holesky_redstone ( address varchar NOT NULL, table_id varchar NOT NULL, key_bytes varchar NOT NULL, key0 varchar NOT NULL, key1 varchar NOT NULL, static_data varchar NOT NULL, encoded_lengths varchar NOT NULL, dynamic_data varchar NOT NULL, is_deleted boolean NOT NULL, block_number bigint NOT NULL, log_index bigint NOT NULL )\nCREATE TABLE token_balances_bitcoin ( block_number bigint, block_timestamp timestamp, tick varchar, wallet_address varchar, total_supply varchar, amount varchar )\nCREATE TABLE token_info_bitcoin ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash varchar, tick varchar, max_supply decimal, lim decimal, wlim decimal, dec integer, creator varchar )\nCREATE TABLE token_activities_avalanche ( block_timestamp.timestamp, block_number.bigint, tx_index.integer, tx_hash.text, log_index.integer, type.text, tick.text, id.text, amt.decimal, from_address.text, to_address.text )\nCREATE TABLE token_balances_avalanche (\n block_number bigint NOT NULL, -- Block number containing the transaction\n block_timestamp timestamp(3) NOT NULL, -- Block timestamp containing the transaction\n tick varchar(20) NOT NULL, -- Ticker: Identifier of the inscription\n wallet_address varchar(42) NOT NULL, -- Address of owner\n total_supply decimal(38,0) NOT NULL, -- Max supply: Set max supply of the inscription\n amount decimal(38,0) NOT NULL -- The balance of wallet balance at the corresponding block height\n)\nCREATE TABLE token_info_avalanche ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash varchar, tick varchar, max_supply decimal, lim decimal, wlim decimal, dec integer, creator varchar, minted decimal, holders decimal, txs decimal, updated_timestamp timestamp, completed_timestamp timestamp, id varchar )\n"} {"conversations": [{"role": "user", "content": "List the last 20 messages that have a media_url, showing message_id, sender_user_id, media_type, and sent_at, ordered by sent_at descending."}, {"role": "assistant", "content": "SELECT message_id,\n sender_user_id,\n media_type,\n sent_at\nFROM social_media.messages\nWHERE media_url IS NOT NULL\nORDER BY sent_at 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 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": "List each payment method, the total amount paid, and the number of payments for each method for services in the 'Education' category."}, {"role": "assistant", "content": "SELECT p.payment_method, SUM(p.amount) AS total_amount, COUNT(p.payment_id) AS payment_count\nFROM government_services.payments p\nJOIN government_services.services s ON p.service_id = s.service_id\nWHERE s.category = 'Education'\nGROUP BY p.payment_method;"}, {"role": "user", "content": "Only include payment methods with total amounts greater than 1000."}, {"role": "assistant", "content": "SELECT p.payment_method, SUM(p.amount) AS total_amount, COUNT(p.payment_id) AS payment_count\nFROM government_services.payments p\nJOIN government_services.services s ON p.service_id = s.service_id\nWHERE s.category = 'Education'\nGROUP BY p.payment_method\nHAVING SUM(p.amount) > 1000;"}, {"role": "user", "content": "Exclude payments that are not completed."}, {"role": "assistant", "content": "SELECT p.payment_method, SUM(p.amount) AS total_amount, COUNT(p.payment_id) AS payment_count\nFROM government_services.payments p\nJOIN government_services.services s ON p.service_id = s.service_id\nWHERE s.category = 'Education' AND p.status = 'Completed'\nGROUP BY p.payment_method\nHAVING SUM(p.amount) > 1000;"}, {"role": "user", "content": "Show only the payment method with the highest total paid."}, {"role": "assistant", "content": "SELECT payment_method, total_amount, payment_count FROM (\n SELECT p.payment_method, SUM(p.amount) AS total_amount, COUNT(p.payment_id) AS payment_count,\n RANK() OVER (ORDER BY SUM(p.amount) DESC) AS method_rank\n FROM government_services.payments p\n JOIN government_services.services s ON p.service_id = s.service_id\n WHERE s.category = 'Education' AND p.status = 'Completed'\n GROUP BY p.payment_method\n HAVING SUM(p.amount) > 1000\n) ranked\nWHERE method_rank = 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.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, agency_id.text, service_name.text, description.text, category.text, eligibility_criteria.text, standard_fee.numeric, average_processing_time_days.integer, is_active.boolean, online_application_url.text )\nCREATE TABLE government_services.applications ( application_id.text, citizen_id.text, service_id.text, submitted_at.timestamp, status.text, last_updated_at.timestamp, assigned_employee_id.text, decision_date.date, notes.text, reference_number.text )\nCREATE TABLE government_services.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.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 )\nCREATE TABLE government_services.appointments ( appointment_id.text, citizen_id.text, employee_id.text, location_id.text, service_id.text, scheduled_start_time.timestamp, scheduled_end_time.timestamp, purpose.text, status.text, booking_method.text, created_at.timestamp, notes.text )\nCREATE TABLE government_services.notifications ( notification_id.text, citizen_id.text, application_id.text, message_subject.text, message_body.text, channel.text, sent_at.timestamp, status.text, related_entity_type.text, related_entity_id.text )\n"} {"conversations": [{"role": "user", "content": "For each case type, calculate the average time to close cases in days, only including cases that have been closed."}, {"role": "assistant", "content": "SELECT case_type,\n AVG(EXTRACT(EPOCH FROM (date_closed - date_opened)) / 86400) AS avg_close_days\nFROM legal_services.cases\nWHERE status = 'Closed'\n AND date_closed IS NOT NULL\nGROUP BY case_type;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.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": "Find appointments that are longer than 30 minutes."}, {"role": "assistant", "content": "SELECT * FROM legal_services.appointments WHERE end_time IS NOT NULL AND start_time IS NOT NULL AND end_time > start_time + INTERVAL '30 minutes'"}], "system": "You are an SQL statement expert. Given the table structure 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.appointments ( appointment_id.text, client_id.text, lawyer_id.text, case_id.text, start_time.timestamp, end_time.timestamp, location.text, subject.text, notes.text, status.text, created_at.timestamp )\n"} {"conversations": [{"role": "user", "content": "For each passenger, compute the count of bookings and average fare for bookings made in February 2024."}, {"role": "assistant", "content": "SELECT p.passenger_id, COUNT(b.booking_id) AS booking_count, AVG(b.fare) AS avg_fare\nFROM transportation.passengers p\nJOIN transportation.bookings b ON p.passenger_id = b.passenger_id\nWHERE b.booking_time >= '2024-02-01' AND b.booking_time < '2024-03-01'\nGROUP BY p.passenger_id;"}, {"role": "user", "content": "I need to see the passengers' first and last names instead of IDs and only include those with an average fare greater than 75."}, {"role": "assistant", "content": "SELECT p.first_name, p.last_name, COUNT(b.booking_id) AS booking_count, AVG(b.fare) AS avg_fare\nFROM transportation.passengers p\nJOIN transportation.bookings b ON p.passenger_id = b.passenger_id\nWHERE b.booking_time >= '2024-02-01' AND b.booking_time < '2024-03-01'\nGROUP BY p.first_name, p.last_name\nHAVING AVG(b.fare) > 75;"}, {"role": "user", "content": "Also, order the results by booking_count descending and limit the output to the top 5 passengers."}, {"role": "assistant", "content": "SELECT p.first_name, p.last_name, COUNT(b.booking_id) AS booking_count, AVG(b.fare) AS avg_fare\nFROM transportation.passengers p\nJOIN transportation.bookings b ON p.passenger_id = b.passenger_id\nWHERE b.booking_time >= '2024-02-01' AND b.booking_time < '2024-03-01'\nGROUP BY p.first_name, p.last_name\nHAVING AVG(b.fare) > 75\nORDER BY booking_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 transportation.vehicles ( vehicle_id character varying(64) NOT NULL, license_plate character varying(32) NOT NULL UNIQUE, vin character varying(17) UNIQUE, make character varying(64) NOT NULL, model character varying(64) NOT NULL, year integer NOT NULL, type character varying(32) NOT NULL, capacity integer, fuel_type character varying(32) NOT NULL, status character varying(32) NOT NULL, depot_id character varying(64), acquisition_date date, PRIMARY KEY (vehicle_id) )\nCREATE TABLE transportation.drivers ( driver_id 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.passengers ( passenger_id.text, first_name.text, last_name.text, email.text, phone_number.text, date_of_birth.date, loyalty_program_id.text, created_at.timestamp )\nCREATE TABLE transportation.bookings ( booking_id.text, passenger_id.text, trip_id.text, seat_number.text, booking_time.timestamp, status.text, fare.numeric, payment_transaction_id.text, special_requests.text )\n"} {"conversations": [{"role": "user", "content": "Show me the total payment amount processed by each staff member for EUR payments, including their staff_id_processed and the count of successful transactions."}, {"role": "assistant", "content": "SELECT staff_id_processed, SUM(amount) AS total_amount_eur, COUNT(*) AS successful_transactions\nFROM hospitality_technology.payments\nWHERE currency_code = 'EUR' AND status = 'Succeeded'\nGROUP BY staff_id_processed;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE hospitality_technology.payments ( payment_id text, reservation_id text, guest_id text, bill_id text, amount numeric, currency_code text, payment_method text, card_type text, card_last_four text, transaction_ref text, payment_timestamp timestamp, status text, staff_id_processed text, notes text )\n"} {"conversations": [{"role": "user", "content": "Show me all items of rarity 'Epic', displaying the item's name and type, along with the title of the game it is part of."}, {"role": "assistant", "content": "SELECT igi.item_name, igi.item_type, g.title FROM gaming_technology.in_game_items igi JOIN gaming_technology.games g ON igi.game_id = g.game_id WHERE igi.rarity = 'Epic';"}, {"role": "user", "content": "Only include games released after the year 2020."}, {"role": "assistant", "content": "SELECT igi.item_name, igi.item_type, g.title FROM gaming_technology.in_game_items igi JOIN gaming_technology.games g ON igi.game_id = g.game_id WHERE igi.rarity = 'Epic' AND g.release_date > '2020-12-31';"}, {"role": "user", "content": "For these items, also show the total quantity of each item across all player inventories."}, {"role": "assistant", "content": "SELECT igi.item_name, igi.item_type, g.title, SUM(pi.quantity) AS total_inventory_quantity FROM gaming_technology.in_game_items igi JOIN gaming_technology.games g ON igi.game_id = g.game_id JOIN gaming_technology.player_inventory pi ON igi.item_id = pi.item_id WHERE igi.rarity = 'Epic' AND g.release_date > '2020-12-31' GROUP BY igi.item_name, igi.item_type, g.title;"}, {"role": "user", "content": "Only show items where the total inventory quantity is at least 100."}, {"role": "assistant", "content": "SELECT igi.item_name, igi.item_type, g.title, SUM(pi.quantity) AS total_inventory_quantity FROM gaming_technology.in_game_items igi JOIN gaming_technology.games g ON igi.game_id = g.game_id JOIN gaming_technology.player_inventory pi ON igi.item_id = pi.item_id WHERE igi.rarity = 'Epic' AND g.release_date > '2020-12-31' GROUP BY igi.item_name, igi.item_type, g.title HAVING SUM(pi.quantity) >= 100;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE gaming_technology.player_inventory (\n inventory_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for an inventory entry\n player_id uuid NOT NULL, -- FK linking to the player owning the item\n item_id uuid NOT NULL, -- FK linking to the item definition\n quantity integer NOT NULL DEFAULT 1, -- number of items held (for stackable items)\n acquired_at timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP, -- when the item was acquired\n instance_data jsonb, -- data specific to this instance (e.g., weapon mods, durability)\n PRIMARY KEY (inventory_id),\n -- Optional unique constraint if items are non-stackable or unique instances\n -- UNIQUE (player_id, item_id) -- Use if quantity is always 1\n -- FOREIGN KEY (player_id) REFERENCES gaming_technology.players(player_id),\n -- FOREIGN KEY (item_id) REFERENCES gaming_technology.in_game_items(item_id)\n)\n"} {"conversations": [{"role": "user", "content": "List all appointments that are currently scheduled and show their appointment time."}, {"role": "assistant", "content": "SELECT appointment_id, patient_id, doctor_id, appointment_time FROM healthcare.appointments WHERE status = 'Scheduled';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.patients ( patient_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, date_of_birth date NOT NULL, gender character varying(10), address text, phone_number character varying(20), email character varying(128) UNIQUE, emergency_contact_name character varying(200), emergency_contact_phone character varying(20), created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, updated_at timestamp with time zone NOT NULL DEFAULT current_timestamp, PRIMARY KEY (patient_id) )\nCREATE TABLE healthcare.appointments ( appointment_id 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.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": "Get the number of agents grouped by status. Return status and agent_count."}, {"role": "assistant", "content": "SELECT status,\n COUNT(*) AS agent_count\n FROM insurance.agents\n GROUP BY status;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.agents ( agent_id text PRIMARY KEY, first_name text, last_name text, agency_name text, license_number text, license_state text, contact_email text, contact_phone text, hire_date date, termination_date date, status text, commission_rate numeric, manager_id text )\n"} {"conversations": [{"role": "user", "content": "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": "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": "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": "For each asset, calculate the total quantity and average price of orders that have status 'filled'."}, {"role": "assistant", "content": "SELECT o.asset_id,\n SUM(o.quantity) AS total_quantity,\n AVG(o.price) AS average_price\nFROM trading_platform.orders o\nWHERE o.status = 'filled'\nGROUP BY o.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.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": "Count the number of logs for each action type."}, {"role": "assistant", "content": "SELECT action,\n COUNT(*) AS count\nFROM trading_platform.logs\nGROUP BY action;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE trading_platform.logs ( log_id text PRIMARY KEY, user_id text, action text, details text, logged_at timestamp )\n"} {"conversations": [{"role": "user", "content": "For each event, display its event_id, the event_id of the previous event in the same transaction (if any), and the log_index of both events."}, {"role": "assistant", "content": "SELECT curr.event_id AS current_event_id,\n prev.event_id AS previous_event_id,\n curr.log_index AS current_log_index,\n prev.log_index AS previous_log_index,\n curr.transaction_id\nFROM web3.events curr\nLEFT JOIN web3.events prev\n ON curr.transaction_id = prev.transaction_id\n AND curr.log_index = prev.log_index + 1;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE web3.events ( event_id character varying(64) NOT NULL, contract_id character varying(64) NOT NULL, event_name character varying(128) NOT NULL, data text NOT NULL, emitted_at timestamp NOT NULL, transaction_id character varying(64) NOT NULL, log_index integer NOT NULL, PRIMARY KEY (event_id) )\n"} {"conversations": [{"role": "user", "content": "Show me all notifications that are related to posts created by users who have a verified profile. Include the notification type, the recipient username, and the post ID."}, {"role": "assistant", "content": "SELECT\n n.notification_type,\n u_recipient.username AS recipient_username,\n n.target_entity_id AS post_id\nFROM social_media.notifications AS n\nJOIN social_media.posts AS p\n ON n.target_entity_id = p.post_id\nJOIN social_media.users AS u_creator\n ON p.user_id = u_creator.user_id\nJOIN social_media.users AS u_recipient\n ON n.recipient_user_id = u_recipient.user_id\nWHERE\n n.target_entity_type = 'post' AND u_creator.is_verified = true;"}, {"role": "user", "content": "Actually, I only want to see notifications of type 'like' or 'comment'."}, {"role": "assistant", "content": "SELECT\n n.notification_type,\n u_recipient.username AS recipient_username,\n n.target_entity_id AS post_id\nFROM social_media.notifications AS n\nJOIN social_media.posts AS p\n ON n.target_entity_id = p.post_id\nJOIN social_media.users AS u_creator\n ON p.user_id = u_creator.user_id\nJOIN social_media.users AS u_recipient\n ON n.recipient_user_id = u_recipient.user_id\nWHERE\n n.target_entity_type = 'post' AND u_creator.is_verified = true AND n.notification_type IN ('like', 'comment');"}, {"role": "user", "content": "Can you also include the creation timestamp of the notification and order the results with the most recent notifications first?"}, {"role": "assistant", "content": "SELECT\n n.notification_type,\n u_recipient.username AS recipient_username,\n n.target_entity_id AS post_id,\n n.created_at AS notification_created_at\nFROM social_media.notifications AS n\nJOIN social_media.posts AS p\n ON n.target_entity_id = p.post_id\nJOIN social_media.users AS u_creator\n ON p.user_id = u_creator.user_id\nJOIN social_media.users AS u_recipient\n ON n.recipient_user_id = u_recipient.user_id\nWHERE\n n.target_entity_type = 'post' AND u_creator.is_verified = true AND n.notification_type IN ('like', 'comment')\nORDER BY\n n.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.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.hashtags (\n hashtag_id character varying(64) NOT NULL, -- unique identifier for the hashtag\n tag_name character varying(100) NOT NULL UNIQUE, -- the actual hashtag text (without '#')\n created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp when the hashtag was first used\n PRIMARY KEY (hashtag_id)\n)\nCREATE TABLE social_media.post_hashtags (\n post_hashtag_id character varying(64) NOT NULL, -- unique identifier for the post-hashtag link\n post_id character varying(64) NOT NULL, -- identifier of the post (FK to posts.post_id)\n hashtag_id character varying(64) NOT NULL, -- identifier of the hashtag (FK to hashtags.hashtag_id)\n PRIMARY KEY (post_hashtag_id),\n CONSTRAINT unique_post_hashtag UNIQUE (post_id, hashtag_id) -- prevent duplicate tags on a post\n)\nCREATE TABLE social_media.messages (\n message_id character varying(64) NOT NULL, -- unique identifier for the message\n conversation_id character varying(64) NOT NULL, -- identifier for the conversation thread (FK to conversations.conversation_id)\n sender_user_id character varying(64) NOT NULL, -- identifier of the sender (FK to users.user_id)\n content text, -- textual content of the message\n media_url text, -- URL to attached media (image/video)\n media_type character varying(20), -- type of media ('image', 'video', null)\n sent_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp when message was sent\n read_at timestamp, -- timestamp when message was read by recipient(s)\n PRIMARY KEY (message_id)\n)\nCREATE TABLE social_media.conversations (\n conversation_id character varying(64) NOT NULL, -- unique identifier for the conversation\n created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp when conversation was initiated\n last_message_at timestamp, -- timestamp of the last message in the conversation\n is_group_chat boolean NOT NULL DEFAULT false, -- indicates if it's a group chat or direct message\n group_name character varying(100), -- name of the group chat (if applicable)\n PRIMARY KEY (conversation_id)\n)\nCREATE TABLE social_media.conversation_participants (\n participant_id character varying(64) NOT NULL, -- unique identifier for the participant entry\n conversation_id character varying(64) NOT NULL, -- identifier of the conversation (FK to conversations.conversation_id)\n user_id character varying(64) NOT NULL, -- identifier of the user in the conversation (FK to users.user_id)\n joined_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp when user joined the conversation\n last_read_at timestamp, -- timestamp indicating up to when the user has read messages\n PRIMARY KEY (participant_id),\n CONSTRAINT unique_user_conversation UNIQUE (conversation_id, user_id) -- prevent user being added multiple times\n)\nCREATE TABLE social_media.notifications (\n notification_id character varying(64) NOT NULL, -- unique identifier for the notification\n recipient_user_id character varying(64) NOT NULL, -- user receiving the notification (FK to users.user_id)\n sender_user_id character varying(64), -- user triggering the notification (FK to users.user_id, can be null for system notifications)\n notification_type character varying(30) NOT NULL, -- type of notification ('like', 'comment', 'follow', 'mention', 'message')\n target_entity_id character varying(64), -- ID of the related entity (post_id, comment_id, user_id, conversation_id)\n target_entity_type character varying(20), -- type of the related entity ('post', 'comment', 'user', 'conversation')\n created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp notification was created\n read_at timestamp, -- timestamp notification was marked as read\n PRIMARY KEY (notification_id)\n)\n"} {"conversations": [{"role": "user", "content": "Show me all electric vehicles that have completed trips in the last month, along with the count of trips each vehicle has completed."}, {"role": "assistant", "content": "SELECT v.vehicle_id, v.make, v.model, COUNT(t.trip_id) AS trip_count FROM transportation.vehicles v JOIN transportation.trips t ON v.vehicle_id = t.vehicle_id WHERE v.fuel_type = 'electric' AND t.status = 'completed' AND t.actual_arrival >= NOW() - INTERVAL '1 month' GROUP BY v.vehicle_id, v.make, v.model ORDER BY trip_count DESC;"}, {"role": "user", "content": "Now include the average passenger count for these trips per vehicle."}, {"role": "assistant", "content": "SELECT v.vehicle_id, v.make, v.model, COUNT(t.trip_id) AS trip_count, AVG(t.passenger_count) AS avg_passengers FROM transportation.vehicles v JOIN transportation.trips t ON v.vehicle_id = t.vehicle_id WHERE v.fuel_type = 'electric' AND t.status = 'completed' AND t.actual_arrival >= NOW() - INTERVAL '1 month' GROUP BY v.vehicle_id, v.make, v.model ORDER BY trip_count DESC;"}, {"role": "user", "content": "Filter this to only show vehicles that have completed more than 5 trips and had an average passenger count greater than 10."}, {"role": "assistant", "content": "SELECT v.vehicle_id, v.make, v.model, COUNT(t.trip_id) AS trip_count, AVG(t.passenger_count) AS avg_passengers FROM transportation.vehicles v JOIN transportation.trips t ON v.vehicle_id = t.vehicle_id WHERE v.fuel_type = 'electric' AND t.status = 'completed' AND t.actual_arrival >= NOW() - INTERVAL '1 month' GROUP BY v.vehicle_id, v.make, v.model HAVING COUNT(t.trip_id) > 5 AND AVG(t.passenger_count) > 10 ORDER BY trip_count DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.vehicles ( vehicle_id character varying(64) NOT NULL, license_plate character varying(32) NOT NULL UNIQUE, vin character varying(17) UNIQUE, make character varying(64) NOT NULL, model character varying(64) NOT NULL, year integer NOT NULL, type character varying(32) NOT NULL, capacity integer, fuel_type character varying(32) NOT NULL, status character varying(32) NOT NULL, depot_id character varying(64), acquisition_date date, PRIMARY KEY (vehicle_id) )\nCREATE TABLE transportation.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.fuel_logs ( fuel_log_id character varying(64) NOT NULL, vehicle_id character varying(64) NOT NULL, trip_id character varying(64), log_timestamp timestamp with time zone NOT NULL, fuel_type character varying(32) NOT NULL, quantity numeric(10, 3) NOT NULL, unit character varying(16) NOT NULL, cost_per_unit numeric(8, 4), total_cost numeric(10, 2) NOT NULL, odometer_reading integer, location_id character varying(64), PRIMARY KEY (fuel_log_id) )\nCREATE TABLE transportation.bookings ( booking_id character varying(64) NOT NULL, passenger_id character varying(64) NOT NULL, trip_id character varying(64) NOT NULL, seat_number character varying(16), booking_time timestamp with time zone NOT NULL, status character varying(32) NOT NULL, fare numeric(10, 2) NOT NULL, payment_transaction_id character varying(128), special_requests text, PRIMARY KEY (booking_id) )\n"} {"conversations": [{"role": "user", "content": "For the 'DeFi' narrative, what is the average ROI and the total net inflow (usd_value where type=1) from smart money token inflow?"}, {"role": "assistant", "content": "SELECT AVG(sm.roi) AS avg_roi, SUM(smt.usd_value) AS total_net_inflow\nFROM smart_money_token_inflow smt\nJOIN smart_money_profit sm ON smt.chain = sm.chain\nWHERE smt.narrative = 'DeFi' AND smt.type = 1;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE token_basic_info ( coin_id text, token_name text, token_symbol text, token_address text, chain text, price numeric, price_change_percentage_1h numeric, price_change_percentage_24h numeric, price_change_percentage_7d numeric, highest_price_24h numeric, lowest_price_24h numeric, market_cap numeric, market_cap_rank numeric, market_cap_change_percentage_24h text, total_volume text, narrative text, trend_rank numeric )\nCREATE TABLE narrative_info ( narrative text, top_3_coins text, price_change_percentage_1h numeric, price_change_percentage_24h numeric, price_change_percentage_7d numeric, market_cap numeric, volume_24h numeric, trend_rank numeric, token_num numeric )\nCREATE TABLE cex_token_balance ( snapshot_time text, chain text, address text, exchange text, token_address text, token_symbol text, balance numeric, usd_value numeric, price numeric )\nCREATE TABLE smart_money_profit ( address text, rank numeric, profit numeric, roi numeric, realized_ratio numeric, most_profit_token text, last_trade_time text, chain text )\nCREATE TABLE smart_money_token_inflow ( token_address text, token_symbol text, token_amount numeric, usd_value numeric, avg_price numeric, type numeric, address_amount numeric, narrative text, chain text )\n"} {"conversations": [{"role": "user", "content": "For each route, show the route_number, origin and destination location names with their cities, and the average departure delay (in minutes) for trips where actual_departure was later than scheduled_departure."}, {"role": "assistant", "content": "SELECT r.route_number,\n lo.name AS origin_name,\n lo.city AS origin_city,\n ld.name AS destination_name,\n ld.city AS destination_city,\n AVG(EXTRACT(EPOCH FROM (t.actual_departure - t.scheduled_departure)) / 60) AS avg_delay_minutes\nFROM transportation.routes r\nJOIN transportation.trips t\n ON r.route_id = t.route_id\nJOIN transportation.locations lo\n ON r.origin_location_id = lo.location_id\nJOIN transportation.locations ld\n ON r.destination_location_id = ld.location_id\nWHERE t.actual_departure > t.scheduled_departure\nGROUP BY r.route_number, origin_name, origin_city, destination_name, destination_city;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.vehicles (\n vehicle_id character varying(64) NOT NULL, -- unique identifier for the vehicle\n license_plate character varying(32) NOT NULL UNIQUE, -- vehicle license plate\n vin character varying(17) UNIQUE, -- vehicle identification number\n make character varying(64) NOT NULL, -- manufacturer of the vehicle\n model character varying(64) NOT NULL, -- model of the vehicle\n year integer NOT NULL, -- manufacturing year\n type character varying(32) NOT NULL, -- type of vehicle (e.g., Bus, Train, Truck, Car, Van)\n capacity integer, -- passenger or cargo capacity\n fuel_type character varying(32) NOT NULL, -- e.g., Diesel, Gasoline, Electric, Hydrogen\n status character varying(32) NOT NULL, -- e.g., Active, Maintenance, Decommissioned\n depot_id character varying(64), -- identifier of the home depot/base\n acquisition_date date, -- date the vehicle was acquired\n PRIMARY KEY (vehicle_id)\n)\nCREATE TABLE transportation.drivers ( driver_id character varying(64) NOT NULL, employee_id character varying(64) NOT NULL UNIQUE, first_name character varying(128) NOT NULL, last_name character varying(128) NOT NULL, license_number character varying(64) NOT NULL UNIQUE, license_expiry_date date NOT NULL, contact_number character varying(32), email character varying(128) UNIQUE, hire_date date NOT NULL, status character varying(32) NOT NULL, PRIMARY KEY (driver_id) )\nCREATE TABLE transportation.routes ( route_id text, route_number text, description text, origin_location_id text, destination_location_id text, distance_km numeric, estimated_duration_minutes integer, type text )\nCREATE TABLE transportation.trips (\n trip_id character varying(64) NOT NULL, -- unique identifier for a specific trip instance\n route_id character varying(64), -- identifier of the route being followed (can be null for ad-hoc trips)\n vehicle_id character varying(64) NOT NULL, -- identifier of the vehicle used\n driver_id character varying(64) NOT NULL, -- identifier of the driver operating\n scheduled_departure timestamp with time zone NOT NULL, -- planned departure time\n actual_departure timestamp with time zone, -- actual departure time\n scheduled_arrival timestamp with time zone NOT NULL, -- planned arrival time\n actual_arrival timestamp with time zone, -- actual arrival time\n origin_location_id character varying(64) NOT NULL, -- actual starting location (could differ from route origin)\n destination_location_id character varying(64) NOT NULL, -- actual ending location (could differ from route destination)\n status character varying(32) NOT NULL, -- e.g., Scheduled, In Progress, Completed, Delayed, Cancelled\n passenger_count integer, -- number of passengers (if applicable)\n cargo_manifest_id character varying(64), -- link to cargo details (if applicable)\n PRIMARY KEY (trip_id)\n)\nCREATE TABLE transportation.locations ( location_id.text, name.text, type.text, address_line1.text, city.text, state_province.text, postal_code.text, country.text, latitude.numeric, longitude.numeric, timezone.text )\nCREATE TABLE transportation.passengers ( passenger_id text PRIMARY KEY, first_name text, last_name text, email text, phone_number text, date_of_birth date, loyalty_program_id text, created_at timestamp )\nCREATE TABLE transportation.bookings (\n booking_id character varying(64) NOT NULL, -- unique identifier for the booking\n passenger_id character varying(64) NOT NULL, -- identifier of the passenger making the booking\n trip_id character varying(64) NOT NULL, -- identifier of the trip being booked\n seat_number character varying(16), -- assigned seat number (if applicable)\n booking_time timestamp with time zone NOT NULL, -- time when the booking was made\n status character varying(32) NOT NULL, -- e.g., Confirmed, Cancelled, Pending Payment\n fare numeric(10, 2) NOT NULL, -- price paid for the booking\n payment_transaction_id character varying(128), -- reference to the payment transaction\n special_requests text, -- any special requests from the passenger\n PRIMARY KEY (booking_id)\n)\n"} {"conversations": [{"role": "user", "content": "List each patient's first and last name along with their total number of appointments in 2024."}, {"role": "assistant", "content": "SELECT p.first_name, p.last_name, COUNT(a.appointment_id) AS appointment_count\nFROM healthcare.patients p\nLEFT JOIN healthcare.appointments a\n ON p.patient_id = a.patient_id\n AND a.appointment_time BETWEEN '2024-01-01' AND '2024-12-31'\nGROUP BY p.first_name, p.last_name;"}, {"role": "user", "content": "Now exclude all 'Cancelled' appointments from the count."}, {"role": "assistant", "content": "SELECT p.first_name, p.last_name, COUNT(a.appointment_id) AS appointment_count\nFROM healthcare.patients p\nLEFT JOIN healthcare.appointments a\n ON p.patient_id = a.patient_id\n AND a.appointment_time BETWEEN '2024-01-01' AND '2024-12-31'\n AND a.status <> 'Cancelled'\nGROUP BY p.first_name, p.last_name;"}, {"role": "user", "content": "Also, only show patients who have more than 2 appointments and sort the result by appointment_count in descending order."}, {"role": "assistant", "content": "SELECT p.first_name, p.last_name, COUNT(a.appointment_id) AS appointment_count\nFROM healthcare.patients p\nLEFT JOIN healthcare.appointments a\n ON p.patient_id = a.patient_id\n AND a.appointment_time BETWEEN '2024-01-01' AND '2024-12-31'\n AND a.status <> 'Cancelled'\nGROUP BY p.first_name, p.last_name\nHAVING COUNT(a.appointment_id) > 2\nORDER BY appointment_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.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.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)\n"} {"conversations": [{"role": "user", "content": "For each agent, show their agent_id, first and last name, and the total estimated loss for all claims they have handled as a claim handler."}, {"role": "assistant", "content": "SELECT a.agent_id, a.first_name, a.last_name, SUM(c.estimated_loss) AS total_estimated_loss\nFROM insurance.agents a\nJOIN insurance.claims c ON a.agent_id = c.claim_handler_id\nGROUP BY a.agent_id, a.first_name, a.last_name;"}, {"role": "user", "content": "Actually, please only show agents with a total estimated loss above 100000."}, {"role": "assistant", "content": "SELECT a.agent_id, a.first_name, a.last_name, SUM(c.estimated_loss) AS total_estimated_loss\nFROM insurance.agents a\nJOIN insurance.claims c ON a.agent_id = c.claim_handler_id\nGROUP BY a.agent_id, a.first_name, a.last_name\nHAVING SUM(c.estimated_loss) > 100000;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.policies ( policy_id character varying(64) NOT NULL, customer_id character varying(64) NOT NULL, product_id character varying(64) NOT NULL, agent_id character varying(64), policy_number character varying(100) NOT NULL UNIQUE, start_date date NOT NULL, end_date date NOT NULL, premium_amount numeric(12, 2) NOT NULL, coverage_limit numeric(15, 2) NOT NULL, deductible numeric(10, 2) NOT NULL, status character varying(30) NOT NULL, issued_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, cancellation_date date, cancellation_reason text, PRIMARY KEY (policy_id) )\nCREATE TABLE insurance.claims ( claim_id character varying(64) NOT NULL, policy_id character varying(64) NOT NULL, customer_id character varying(64) NOT NULL, incident_date timestamp NOT NULL, reported_date timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, description text NOT NULL, estimated_loss numeric(15, 2), status character varying(30) NOT NULL, settlement_amount numeric(15, 2), settlement_date date, claim_handler_id character varying(64), police_report_number character varying(100), PRIMARY KEY (claim_id) )\nCREATE TABLE insurance.agents ( agent_id text PRIMARY KEY, first_name text, last_name text, agency_name text, license_number text, license_state text, contact_email text, contact_phone text, hire_date date, termination_date date, status text, commission_rate numeric, manager_id text )\n"} {"conversations": [{"role": "user", "content": "List the usernames and user IDs of all users whose bio contains the word 'developer'."}, {"role": "assistant", "content": "SELECT user_id, username\nFROM social_media.users\nWHERE bio ILIKE '%developer%';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE social_media.users (\n user_id character varying(64) NOT NULL, -- unique identifier for the user\n username character varying(50) NOT NULL UNIQUE, -- user's unique handle\n email character varying(128) NOT NULL UNIQUE, -- user's email address\n password_hash text NOT NULL, -- hashed password\n full_name character varying(100), -- user's full name\n profile_picture_url text, -- URL to the profile picture\n bio text, -- short user biography\n location character varying(100), -- user's location\n created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of account creation\n updated_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of last profile update\n is_verified boolean NOT NULL DEFAULT false, -- verification status\n PRIMARY KEY (user_id)\n)\nCREATE TABLE social_media.comments (\n comment_id character varying(64) NOT NULL, -- unique identifier for the comment\n post_id character varying(64) NOT NULL, -- identifier of the post being commented on (FK to posts.post_id)\n user_id character varying(64) NOT NULL, -- identifier of the user who made the comment (FK to users.user_id)\n parent_comment_id character varying(64), -- identifier of the parent comment if it's a reply (FK to comments.comment_id)\n content text NOT NULL, -- textual content of the comment\n created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of comment creation\n updated_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of last comment edit\n PRIMARY KEY (comment_id)\n)\nCREATE TABLE social_media.likes (\n like_id character varying(64) NOT NULL, -- unique identifier for the like\n user_id character varying(64) NOT NULL, -- identifier of the user who liked (FK to users.user_id)\n post_id character varying(64), -- identifier of the post being liked (FK to posts.post_id, nullable)\n comment_id character varying(64), -- identifier of the comment being liked (FK to comments.comment_id, nullable)\n created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of when the like occurred\n PRIMARY KEY (like_id),\n CONSTRAINT unique_user_like UNIQUE (user_id, post_id, comment_id), -- prevent duplicate likes\n CONSTRAINT check_like_target CHECK (post_id IS NOT NULL OR comment_id IS NOT NULL) -- ensure it likes something\n)\nCREATE TABLE social_media.follows (\n follow_id character varying(64) NOT NULL, -- unique identifier for the follow relationship\n follower_user_id character varying(64) NOT NULL, -- identifier of the user who is following (FK to users.user_id)\n following_user_id character varying(64) NOT NULL, -- identifier of the user being followed (FK to users.user_id)\n created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of when the follow started\n PRIMARY KEY (follow_id),\n CONSTRAINT unique_follow UNIQUE (follower_user_id, following_user_id) -- prevent duplicate follows\n)\nCREATE TABLE social_media.hashtags (\n hashtag_id character varying(64) NOT NULL, -- unique identifier for the hashtag\n tag_name character varying(100) NOT NULL UNIQUE, -- the actual hashtag text (without '#')\n created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp when the hashtag was first used\n PRIMARY KEY (hashtag_id)\n)\nCREATE TABLE social_media.conversations (\n conversation_id character varying(64) NOT NULL, -- unique identifier for the conversation\n created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp when conversation was initiated\n last_message_at timestamp, -- timestamp of the last message in the conversation\n is_group_chat boolean NOT NULL DEFAULT false, -- indicates if it's a group chat or direct message\n group_name character varying(100), -- name of the group chat (if applicable)\n PRIMARY KEY (conversation_id)\n)\nCREATE TABLE social_media.conversation_participants (\n participant_id character varying(64) NOT NULL, -- unique identifier for the participant entry\n conversation_id character varying(64) NOT NULL, -- identifier of the conversation (FK to conversations.conversation_id)\n user_id character varying(64) NOT NULL, -- identifier of the user in the conversation (FK to users.user_id)\n joined_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp when user joined the conversation\n last_read_at timestamp, -- timestamp indicating up to when the user has read messages\n PRIMARY KEY (participant_id),\n CONSTRAINT unique_user_conversation UNIQUE (conversation_id, user_id) -- prevent user being added multiple times\n)\nCREATE TABLE social_media.notifications (\n notification_id character varying(64) NOT NULL, -- unique identifier for the notification\n recipient_user_id character varying(64) NOT NULL, -- user receiving the notification (FK to users.user_id)\n sender_user_id character varying(64), -- user triggering the notification (FK to users.user_id, can be null for system notifications)\n notification_type character varying(30) NOT NULL, -- type of notification ('like', 'comment', 'follow', 'mention', 'message')\n target_entity_id character varying(64), -- ID of the related entity (post_id, comment_id, user_id, conversation_id)\n target_entity_type character varying(20), -- type of the related entity ('post', 'comment', 'user', 'conversation')\n created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp notification was created\n read_at timestamp, -- timestamp notification was marked as read\n PRIMARY KEY (notification_id)\n)\nCREATE TABLE social_media.user_settings (\n setting_id character varying(64) NOT NULL, -- unique identifier for the setting entry\n user_id character varying(64) NOT NULL UNIQUE, -- user the settings belong to (FK to users.user_id)\n theme character varying(20) DEFAULT 'light', -- UI theme ('light', 'dark')\n email_notifications_enabled boolean DEFAULT true, -- enable/disable email notifications\n push_notifications_enabled boolean DEFAULT true, -- enable/disable push notifications\n private_profile boolean DEFAULT false, -- is the user profile private\n updated_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of last setting change\n PRIMARY KEY (setting_id)\n)\n"} {"conversations": [{"role": "user", "content": "Find all pairs of policies for the same customer where their coverage periods overlap. Show customer_id, policy1_id, policy2_id, overlap_start, and overlap_end."}, {"role": "assistant", "content": "SELECT p1.customer_id,\n p1.policy_id AS policy1_id,\n p2.policy_id AS policy2_id,\n GREATEST(p1.start_date, p2.start_date) AS overlap_start,\n LEAST(p1.end_date, p2.end_date) AS overlap_end\nFROM insurance.policies p1\nJOIN insurance.policies p2\n ON p1.customer_id = p2.customer_id\n AND p1.policy_id < p2.policy_id\n AND p1.start_date <= p2.end_date\n AND p2.start_date <= p1.end_date;"}, {"role": "user", "content": "Actually, I only want those overlapping pairs where both policies are currently active."}, {"role": "assistant", "content": "SELECT p1.customer_id,\n p1.policy_id AS policy1_id,\n p2.policy_id AS policy2_id,\n GREATEST(p1.start_date, p2.start_date) AS overlap_start,\n LEAST(p1.end_date, p2.end_date) AS overlap_end\nFROM insurance.policies p1\nJOIN insurance.policies p2\n ON p1.customer_id = p2.customer_id\n AND p1.policy_id < p2.policy_id\n AND p1.start_date <= p2.end_date\n AND p2.start_date <= p1.end_date\nWHERE p1.status = 'active'\n AND p2.status = 'active';"}, {"role": "user", "content": "Also include the policy numbers for both policies in the output."}, {"role": "assistant", "content": "SELECT p1.customer_id,\n p1.policy_id AS policy1_id,\n p1.policy_number AS policy1_number,\n p2.policy_id AS policy2_id,\n p2.policy_number AS policy2_number,\n GREATEST(p1.start_date, p2.start_date) AS overlap_start,\n LEAST(p1.end_date, p2.end_date) AS overlap_end\nFROM insurance.policies p1\nJOIN insurance.policies p2\n ON p1.customer_id = p2.customer_id\n AND p1.policy_id < p2.policy_id\n AND p1.start_date <= p2.end_date\n AND p2.start_date <= p1.end_date\nWHERE p1.status = 'active'\n AND p2.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 character varying(64) NOT NULL, customer_id character varying(64) NOT NULL, product_id character varying(64) NOT NULL, agent_id character varying(64), policy_number character varying(100) NOT NULL UNIQUE, start_date date NOT NULL, end_date date NOT NULL, premium_amount numeric(12, 2) NOT NULL, coverage_limit numeric(15, 2) NOT NULL, deductible numeric(10, 2) NOT NULL, status character varying(30) NOT NULL, issued_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, cancellation_date date, cancellation_reason text, PRIMARY KEY (policy_id) )\n"} {"conversations": [{"role": "user", "content": "List the full names and dates of birth for all patients who do not have a phone number on record."}, {"role": "assistant", "content": "SELECT first_name, last_name, date_of_birth FROM healthcare.patients WHERE phone_number IS NULL OR TRIM(phone_number) = '';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.patients ( patient_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, date_of_birth date NOT NULL, gender character varying(10), address text, phone_number character varying(20), email character varying(128) UNIQUE, emergency_contact_name character varying(200), emergency_contact_phone character varying(20), created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, updated_at timestamp with time zone NOT NULL DEFAULT current_timestamp, PRIMARY KEY (patient_id) )\nCREATE TABLE healthcare.appointments ( appointment_id.text, patient_id.text, doctor_id.text, appointment_time.timestamp, duration_minutes.integer, reason.text, status.text, location_id.text, notes.text, created_at.timestamp )\nCREATE TABLE healthcare.diagnoses (\n diagnosis_id character varying(64) NOT NULL, -- unique identifier for the diagnosis entry\n record_id character varying(64) NOT NULL, -- FK linking to the specific medical record entry\n patient_id character varying(64) NOT NULL, -- FK to patients table\n doctor_id character varying(64) NOT NULL, -- FK to doctors table (diagnosing doctor)\n diagnosis_code character varying(20) NOT NULL, -- standard code (e.g., ICD-10)\n code_type character varying(10) NOT NULL DEFAULT 'ICD-10', -- type of code used\n description text, -- textual description of the diagnosis\n diagnosis_date date NOT NULL, -- date the diagnosis was made\n status character varying(32) NOT NULL, -- e.g., Active, Resolved, Ruled Out\n is_chronic boolean DEFAULT false, -- flag for chronic conditions\n PRIMARY KEY (diagnosis_id)\n)\nCREATE TABLE healthcare.prescriptions ( prescription_id text, record_id text, patient_id text, doctor_id text, medication_id text, dosage text, frequency text, route text, start_date date, end_date date, quantity_dispensed numeric, refills_allowed integer, prescription_date timestamp )\nCREATE TABLE healthcare.insurance_plans ( plan_id text, plan_name text, insurance_provider text, plan_type text, contact_phone text, website text )\nCREATE TABLE healthcare.patient_insurance ( patient_insurance_id.text, patient_id.text, plan_id.text, policy_number.text, group_number.text, subscriber_name.text, effective_date.date, expiration_date.date, is_primary.boolean )\n"} {"conversations": [{"role": "user", "content": "I need a report of patients who have received prescriptions for medications manufactured by 'Pfizer'. Include patient ID, first name, last name, medication_name, and prescription_date."}, {"role": "assistant", "content": "SELECT p.patient_id,\n p.first_name,\n p.last_name,\n m.medication_name,\n pr.prescription_date\nFROM healthcare.patients AS p\nJOIN healthcare.prescriptions AS pr ON p.patient_id = pr.patient_id\nJOIN healthcare.medications AS m ON pr.medication_id = m.medication_id\nWHERE m.manufacturer = 'Pfizer';"}, {"role": "user", "content": "Actually, only include prescriptions with a dosage containing 'mg' and sort by prescription_date descending."}, {"role": "assistant", "content": "SELECT p.patient_id,\n p.first_name,\n p.last_name,\n m.medication_name,\n pr.prescription_date\nFROM healthcare.patients AS p\nJOIN healthcare.prescriptions AS pr ON p.patient_id = pr.patient_id\nJOIN healthcare.medications AS m ON pr.medication_id = m.medication_id\nWHERE m.manufacturer = 'Pfizer'\n AND pr.dosage ILIKE '%mg%'\nORDER BY pr.prescription_date DESC;"}, {"role": "user", "content": "Also, include the patient's primary insurance policy number and plan name in the report."}, {"role": "assistant", "content": "SELECT p.patient_id,\n p.first_name,\n p.last_name,\n m.medication_name,\n pr.prescription_date,\n pi.policy_number,\n ip.plan_name\nFROM healthcare.patients AS p\nJOIN healthcare.prescriptions AS pr ON p.patient_id = pr.patient_id\nJOIN healthcare.medications AS m ON pr.medication_id = m.medication_id\nJOIN healthcare.patient_insurance AS pi\n ON p.patient_id = pi.patient_id AND pi.is_primary = true\nJOIN healthcare.insurance_plans AS ip ON pi.plan_id = ip.plan_id\nWHERE m.manufacturer = 'Pfizer'\n AND pr.dosage ILIKE '%mg%'\nORDER BY pr.prescription_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 healthcare.patients ( patient_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, date_of_birth date NOT NULL, gender character varying(10), address text, phone_number character varying(20), email character varying(128) UNIQUE, emergency_contact_name character varying(200), emergency_contact_phone character varying(20), created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, updated_at timestamp with time zone NOT NULL DEFAULT current_timestamp, PRIMARY KEY (patient_id) )\nCREATE TABLE healthcare.appointments ( appointment_id text, patient_id text, doctor_id text, appointment_time timestamp, duration_minutes integer, reason text, status text, location_id text, notes text, created_at timestamp )\nCREATE TABLE healthcare.medical_records ( record_id character varying(64) NOT NULL, patient_id character varying(64) NOT NULL, appointment_id character varying(64) UNIQUE, doctor_id character varying(64) NOT NULL, record_date timestamp with time zone NOT NULL, chief_complaint text, present_illness_history text, past_medical_history text, physical_examination_notes text, assessment text, treatment_plan text, vitals jsonb, created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, PRIMARY KEY (record_id) )\nCREATE TABLE healthcare.diagnoses ( diagnosis_id text PRIMARY KEY, record_id text, patient_id text, doctor_id text, diagnosis_code text, code_type text, description text, diagnosis_date date, status text, is_chronic boolean )\nCREATE TABLE healthcare.medications ( medication_id text, medication_name text, generic_name text, manufacturer text, ndc_code text, description text )\nCREATE TABLE healthcare.prescriptions ( prescription_id.text, record_id.text, patient_id.text, doctor_id.text, medication_id.text, dosage.text, frequency.text, route.text, start_date.date, end_date.date, quantity_dispensed.numeric, refills_allowed.integer, prescription_date.timestamp )\nCREATE TABLE healthcare.insurance_plans ( plan_id.text, plan_name.text, insurance_provider.text, plan_type.text, contact_phone.text, website.text )\nCREATE TABLE healthcare.patient_insurance ( patient_insurance_id character varying(64) NOT NULL, patient_id character varying(64) NOT NULL, plan_id character varying(64) NOT NULL, policy_number character varying(100) NOT NULL, group_number character varying(100), subscriber_name character varying(200), effective_date date NOT NULL, expiration_date date, is_primary boolean NOT NULL DEFAULT true, PRIMARY KEY (patient_insurance_id), UNIQUE (patient_id, plan_id, policy_number) )\n"} {"conversations": [{"role": "user", "content": "What is the current market price of a Boeing 737 MAX aircraft?"}, {"role": "assistant", "content": "I'm sorry, but I don't have access to the current market price of aircraft models. The data I have is limited to technical specifications and general information about aircraft models such as passenger capacity, range, and status. For pricing information, you may need to consult with manufacturers or industry reports."}], "system": "You are an SQL statement expert and you can refuse the user's question if the question is not related to the table structure. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE manufacturing.aircraft_models (\n model_id character varying(64) NOT NULL, -- unique identifier for the aircraft model\n model_name character varying(128) NOT NULL, -- commercial name of the model (e.g., 737 MAX, A320neo)\n manufacturer character varying(128) NOT NULL, -- manufacturer name (e.g., Boeing, Airbus)\n passenger_capacity integer, -- typical passenger capacity\n max_range_km integer, -- maximum flight range in kilometers\n engine_type character varying(100), -- type of engines used\n wingspan_m numeric(6,2), -- wingspan in meters\n status character varying(50) NOT NULL, -- e.g., 'In Production', 'Development', 'Discontinued'\n first_flight_date date, -- date of the model's first flight\n PRIMARY KEY (model_id)\n)\n"} {"conversations": [{"role": "user", "content": "List the full name (first name and last name) of all citizens who have uploaded documents whose expiry date is in the past."}, {"role": "assistant", "content": "SELECT DISTINCT T1.first_name, T1.last_name FROM government_services.citizens AS T1 INNER JOIN government_services.documents AS T2 ON T1.citizen_id = T2.citizen_id WHERE T2.expiry_date < CURRENT_DATE;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.citizens ( citizen_id text PRIMARY KEY, national_id_number text, first_name text, last_name text, date_of_birth date, gender text, primary_address text, contact_email text, contact_phone text, registration_date timestamp, is_verified boolean )\nCREATE TABLE government_services.agencies ( agency_id text PRIMARY KEY, agency_name text, jurisdiction_level text, primary_contact_email text, main_phone_number text, website_url text, established_date date, parent_agency_id text )\nCREATE TABLE government_services.documents ( document_id text PRIMARY KEY, application_id text, citizen_id text, document_type text, file_reference text, upload_timestamp timestamp, expiry_date date, verification_status text, verified_by_employee_id text, verification_timestamp timestamp )\nCREATE TABLE government_services.payments ( payment_id text PRIMARY KEY, application_id text, citizen_id text, service_id text, amount numeric, currency text, payment_method text, payment_provider_reference text, payment_timestamp timestamp, status text, notes text )\nCREATE TABLE government_services.service_locations ( location_id text PRIMARY KEY, agency_id text, location_name text, address text, city text, state text, postal_code text, latitude numeric, longitude numeric, operating_hours text, contact_phone text, is_accessible boolean )\nCREATE TABLE government_services.appointments ( appointment_id text PRIMARY KEY, citizen_id text, employee_id text, location_id text, service_id text, scheduled_start_time timestamp, scheduled_end_time timestamp, purpose text, status text, booking_method text, created_at timestamp, notes text )\n"} {"conversations": [{"role": "user", "content": "Show the names and cities of all service locations, along with the agency ID, for locations whose postal code starts with '10'."}, {"role": "assistant", "content": "SELECT location_name, city, agency_id FROM government_services.service_locations WHERE postal_code LIKE '10%';"}, {"role": "user", "content": "Actually, only include those locations that are marked as accessible."}, {"role": "assistant", "content": "SELECT location_name, city, agency_id FROM government_services.service_locations WHERE postal_code LIKE '10%' AND 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.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": "Find the address that has the highest total amount across all its UTXOs."}, {"role": "assistant", "content": "SELECT address FROM utxos GROUP BY address ORDER BY SUM(amount) DESC LIMIT 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.trades ( trade_id.text, order_id.text, buyer_id.text, seller_id.text, asset_id.text, quantity.numeric, price.numeric, traded_at.timestamp )\nCREATE TABLE trading_platform.assets ( asset_id.text, 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.peers ( peer_id.text, ip_address.text, port.integer, last_seen.timestamp )\nCREATE TABLE trading_platform.metadata ( metadata_id.text, asset_id.text, key.text, value.text )\nCREATE TABLE trading_platform.kyc_audit ( kyc_audit_id.text, user_id.text, status.text, reviewed_at.timestamp )\n"} {"conversations": [{"role": "user", "content": "List all customers who share an address with another customer. Show both customer IDs, their full names, and the shared address."}, {"role": "assistant", "content": "SELECT a.customer_id AS customer_id_a, a.first_name AS first_name_a, a.last_name AS last_name_a, \n b.customer_id AS customer_id_b, b.first_name AS first_name_b, b.last_name AS last_name_b, \n a.address\nFROM financial_services.customers a\nJOIN financial_services.customers b ON a.address = b.address AND a.customer_id <> b.customer_id;"}, {"role": "user", "content": "Only include pairs where both customers are in the same city and state."}, {"role": "assistant", "content": "SELECT a.customer_id AS customer_id_a, a.first_name AS first_name_a, a.last_name AS last_name_a, \n b.customer_id AS customer_id_b, b.first_name AS first_name_b, b.last_name AS last_name_b, \n a.address, a.city, a.state\nFROM financial_services.customers a\nJOIN financial_services.customers b ON a.address = b.address AND a.city = b.city AND a.state = b.state AND a.customer_id <> b.customer_id;"}, {"role": "user", "content": "Now, show only unique unordered pairs (i.e., only one (A,B) or (B,A) per pair) and order by address ascending."}, {"role": "assistant", "content": "SELECT a.customer_id AS customer_id_a, a.first_name AS first_name_a, a.last_name AS last_name_a, \n b.customer_id AS customer_id_b, b.first_name AS first_name_b, b.last_name AS last_name_b, \n a.address, a.city, a.state\nFROM financial_services.customers a\nJOIN financial_services.customers b ON a.address = b.address AND a.city = b.city AND a.state = b.state AND a.customer_id < b.customer_id\nORDER BY a.address ASC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE financial_services.customers ( customer_id text, first_name text, last_name text, date_of_birth date, ssn_hash text, address text, city text, state text, zip_code text, country text, email text, phone_number text, created_at timestamp, status text, risk_profile text )\nCREATE TABLE financial_services.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": "I need a list of claim_ids that have at least one document of type 'Photo' and at least one of type 'Invoice'."}, {"role": "assistant", "content": "SELECT DISTINCT cd.claim_id\nFROM insurance.claim_documents cd\nWHERE cd.document_type IN ('Photo', 'Invoice');"}, {"role": "user", "content": "It returns claim_ids that have either a Photo or an Invoice but not necessarily both. I need only those with both types."}, {"role": "assistant", "content": "SELECT cd.claim_id\nFROM insurance.claim_documents cd\nWHERE cd.document_type IN ('Photo', 'Invoice')\nGROUP BY cd.claim_id\nHAVING COUNT(DISTINCT cd.document_type) = 2;"}, {"role": "user", "content": "Actually, I only want those documents uploaded in 2024."}, {"role": "assistant", "content": "SELECT cd.claim_id\nFROM insurance.claim_documents cd\nWHERE cd.document_type IN ('Photo', 'Invoice')\n AND cd.uploaded_at >= '2024-01-01'\nGROUP BY cd.claim_id\nHAVING COUNT(DISTINCT cd.document_type) = 2;"}, {"role": "user", "content": "Also, I'd like to see the policy_number and incident_date for these claims."}, {"role": "assistant", "content": "SELECT c.claim_id, p.policy_number, c.incident_date\nFROM (\n SELECT cd.claim_id\n FROM insurance.claim_documents cd\n WHERE cd.document_type IN ('Photo', 'Invoice')\n AND cd.uploaded_at >= '2024-01-01'\n GROUP BY cd.claim_id\n HAVING COUNT(DISTINCT cd.document_type) = 2\n) AS filtered\nJOIN insurance.claims c ON filtered.claim_id = c.claim_id\nJOIN insurance.policies p ON c.policy_id = p.policy_id;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.customers (\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.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.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": "Show me all trips that were delayed by more than 1 hour, including their vehicle and driver IDs, along with the origin and destination location IDs."}, {"role": "assistant", "content": "SELECT trip_id, vehicle_id, driver_id, origin_location_id, destination_location_id FROM transportation.trips WHERE EXTRACT(EPOCH FROM (actual_departure - scheduled_departure))/3600 > 1 AND status = 'Completed';"}, {"role": "user", "content": "Now include the passenger count for these trips, but only show trips that had more than 5 passengers."}, {"role": "assistant", "content": "SELECT trip_id, vehicle_id, driver_id, origin_location_id, destination_location_id, passenger_count FROM transportation.trips WHERE EXTRACT(EPOCH FROM (actual_departure - scheduled_departure))/3600 > 1 AND status = 'Completed' AND passenger_count > 5;"}, {"role": "user", "content": "Can you order these results by the delay time in descending order, showing the longest delays first?"}, {"role": "assistant", "content": "SELECT trip_id, vehicle_id, driver_id, origin_location_id, destination_location_id, passenger_count, (actual_departure - scheduled_departure) AS delay_time FROM transportation.trips WHERE EXTRACT(EPOCH FROM (actual_departure - scheduled_departure))/3600 > 1 AND status = 'Completed' AND passenger_count > 5 ORDER BY delay_time DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.trips (\n trip_id character varying(64) NOT NULL, -- unique identifier for a specific trip instance\n route_id character varying(64), -- identifier of the route being followed (can be null for ad-hoc trips)\n vehicle_id character varying(64) NOT NULL, -- identifier of the vehicle used\n driver_id character varying(64) NOT NULL, -- identifier of the driver operating\n scheduled_departure timestamp with time zone NOT NULL, -- planned departure time\n actual_departure timestamp with time zone, -- actual departure time\n scheduled_arrival timestamp with time zone NOT NULL, -- planned arrival time\n actual_arrival timestamp with time zone, -- actual arrival time\n origin_location_id character varying(64) NOT NULL, -- actual starting location (could differ from route origin)\n destination_location_id character varying(64) NOT NULL, -- actual ending location (could differ from route destination)\n status character varying(32) NOT NULL, -- e.g., Scheduled, In Progress, Completed, Delayed, Cancelled\n passenger_count integer, -- number of passengers (if applicable)\n cargo_manifest_id character varying(64), -- link to cargo details (if applicable)\n PRIMARY KEY (trip_id)\n)\n"} {"conversations": [{"role": "user", "content": "List all post IDs and their corresponding hashtag names for posts that include media."}, {"role": "assistant", "content": "SELECT ph.post_id, h.tag_name\nFROM social_media.post_hashtags ph\nJOIN social_media.hashtags h ON ph.hashtag_id = h.hashtag_id\nJOIN social_media.posts p ON ph.post_id = p.post_id\nWHERE p.media_url IS NOT NULL AND p.media_url != '';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE social_media.posts ( post_id text PRIMARY KEY, user_id text, content text, media_url text, media_type text, created_at timestamp, updated_at timestamp, visibility text, location_lat numeric, location_lon numeric )\nCREATE TABLE social_media.follows (\n follow_id character varying(64) NOT NULL, -- unique identifier for the follow relationship\n follower_user_id character varying(64) NOT NULL, -- identifier of the user who is following (FK to users.user_id)\n following_user_id character varying(64) NOT NULL, -- identifier of the user being followed (FK to users.user_id)\n created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of when the follow started\n PRIMARY KEY (follow_id),\n CONSTRAINT unique_follow UNIQUE (follower_user_id, following_user_id) -- prevent duplicate follows\n)\nCREATE TABLE social_media.hashtags ( hashtag_id character varying(64) NOT NULL, tag_name character varying(100) NOT NULL UNIQUE, created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, PRIMARY KEY (hashtag_id) )\nCREATE TABLE social_media.post_hashtags (\n post_hashtag_id character varying(64) NOT NULL, -- unique identifier for the post-hashtag link\n post_id character varying(64) NOT NULL, -- identifier of the post (FK to posts.post_id)\n hashtag_id character varying(64) NOT NULL, -- identifier of the hashtag (FK to hashtags.hashtag_id)\n PRIMARY KEY (post_hashtag_id),\n CONSTRAINT unique_post_hashtag UNIQUE (post_id, hashtag_id) -- prevent duplicate tags on a post\n)\nCREATE TABLE social_media.messages (\n message_id character varying(64) NOT NULL, -- unique identifier for the message\n conversation_id character varying(64) NOT NULL, -- identifier for the conversation thread (FK to conversations.conversation_id)\n sender_user_id character varying(64) NOT NULL, -- identifier of the sender (FK to users.user_id)\n content text, -- textual content of the message\n media_url text, -- URL to attached media (image/video)\n media_type character varying(20), -- type of media ('image', 'video', null)\n sent_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp when message was sent\n read_at timestamp, -- timestamp when message was read by recipient(s)\n PRIMARY KEY (message_id)\n)\nCREATE TABLE social_media.conversations ( conversation_id text PRIMARY KEY, created_at timestamp, last_message_at timestamp, is_group_chat bool, group_name text )\nCREATE TABLE social_media.conversation_participants (\n participant_id character varying(64) NOT NULL, -- unique identifier for the participant entry\n conversation_id character varying(64) NOT NULL, -- identifier of the conversation (FK to conversations.conversation_id)\n user_id character varying(64) NOT NULL, -- identifier of the user in the conversation (FK to users.user_id)\n joined_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp when user joined the conversation\n last_read_at timestamp, -- timestamp indicating up to when the user has read messages\n PRIMARY KEY (participant_id),\n CONSTRAINT unique_user_conversation UNIQUE (conversation_id, user_id) -- prevent user being added multiple times\n)\nCREATE TABLE social_media.notifications (\n notification_id character varying(64) NOT NULL, -- unique identifier for the notification\n recipient_user_id character varying(64) NOT NULL, -- user receiving the notification (FK to users.user_id)\n sender_user_id character varying(64), -- user triggering the notification (FK to users.user_id, can be null for system notifications)\n notification_type character varying(30) NOT NULL, -- type of notification ('like', 'comment', 'follow', 'mention', 'message')\n target_entity_id character varying(64), -- ID of the related entity (post_id, comment_id, user_id, conversation_id)\n target_entity_type character varying(20), -- type of the related entity ('post', 'comment', 'user', 'conversation')\n created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp notification was created\n read_at timestamp, -- timestamp notification was marked as read\n PRIMARY KEY (notification_id)\n)\nCREATE TABLE social_media.user_settings ( setting_id character varying(64) NOT NULL, user_id character varying(64) NOT NULL UNIQUE, theme character varying(20) DEFAULT 'light', email_notifications_enabled boolean DEFAULT true, push_notifications_enabled boolean DEFAULT true, private_profile boolean DEFAULT false, updated_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, PRIMARY KEY (setting_id) )\n"} {"conversations": [{"role": "user", "content": "Find all contracts where the deployer address is the same as the contract address, indicating self-deployed contracts, and show their network IDs and deployment timestamps."}, {"role": "assistant", "content": "SELECT address, network_id, deployed_at 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 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) )\n"} {"conversations": [{"role": "user", "content": "What is the average price of tokens held by Binance exchange across all chains?"}, {"role": "assistant", "content": "SELECT AVG(price) as average_price FROM cex_token_balance WHERE exchange = 'Binance';"}], "system": "You are an SQL statement expert. Given the table structure 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 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 )\n"} {"conversations": [{"role": "user", "content": "Could you show me the usernames of users who have received likes on their posts, along with the total number of likes each user's posts have received?"}, {"role": "assistant", "content": "SELECT T1.username, count(T3.like_id) AS total_likes_received FROM social_media.users AS T1 JOIN social_media.posts AS T2 ON T1.user_id = T2.user_id JOIN social_media.likes AS T3 ON T2.post_id = T3.post_id GROUP BY T1.username;"}, {"role": "user", "content": "Okay, now could you filter this to only include users who have received more than 5 likes across their posts, and order the results by the number of likes in descending order?"}, {"role": "assistant", "content": "SELECT T1.username, count(T3.like_id) AS total_likes_received FROM social_media.users AS T1 JOIN social_media.posts AS T2 ON T1.user_id = T2.user_id JOIN social_media.likes AS T3 ON T2.post_id = T3.post_id GROUP BY T1.username HAVING count(T3.like_id) > 5 ORDER BY total_likes_received 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.post_hashtags (\n post_hashtag_id character varying(64) NOT NULL, -- unique identifier for the post-hashtag link\n post_id character varying(64) NOT NULL, -- identifier of the post (FK to posts.post_id)\n hashtag_id character varying(64) NOT NULL, -- identifier of the hashtag (FK to hashtags.hashtag_id)\n PRIMARY KEY (post_hashtag_id),\n CONSTRAINT unique_post_hashtag UNIQUE (post_id, hashtag_id) -- prevent duplicate tags on a post\n)\nCREATE TABLE social_media.messages (\n message_id character varying(64) NOT NULL, -- unique identifier for the message\n conversation_id character varying(64) NOT NULL, -- identifier for the conversation thread (FK to conversations.conversation_id)\n sender_user_id character varying(64) NOT NULL, -- identifier of the sender (FK to users.user_id)\n content text, -- textual content of the message\n media_url text, -- URL to attached media (image/video)\n media_type character varying(20), -- type of media ('image', 'video', null)\n sent_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp when message was sent\n read_at timestamp, -- timestamp when message was read by recipient(s)\n PRIMARY KEY (message_id)\n)\nCREATE TABLE social_media.conversations (\n conversation_id character varying(64) NOT NULL, -- unique identifier for the conversation\n created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp when conversation was initiated\n last_message_at timestamp, -- timestamp of the last message in the conversation\n is_group_chat boolean NOT NULL DEFAULT false, -- indicates if it's a group chat or direct message\n group_name character varying(100), -- name of the group chat (if applicable)\n PRIMARY KEY (conversation_id)\n)\nCREATE TABLE social_media.conversation_participants (\n participant_id character varying(64) NOT NULL, -- unique identifier for the participant entry\n conversation_id character varying(64) NOT NULL, -- identifier of the conversation (FK to conversations.conversation_id)\n user_id character varying(64) NOT NULL, -- identifier of the user in the conversation (FK to users.user_id)\n joined_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp when user joined the conversation\n last_read_at timestamp, -- timestamp indicating up to when the user has read messages\n PRIMARY KEY (participant_id),\n CONSTRAINT unique_user_conversation UNIQUE (conversation_id, user_id) -- prevent user being added multiple times\n)\nCREATE TABLE social_media.notifications (\n notification_id character varying(64) NOT NULL, -- unique identifier for the notification\n recipient_user_id character varying(64) NOT NULL, -- user receiving the notification (FK to users.user_id)\n sender_user_id character varying(64), -- user triggering the notification (FK to users.user_id, can be null for system notifications)\n notification_type character varying(30) NOT NULL, -- type of notification ('like', 'comment', 'follow', 'mention', 'message')\n target_entity_id character varying(64), -- ID of the related entity (post_id, comment_id, user_id, conversation_id)\n target_entity_type character varying(20), -- type of the related entity ('post', 'comment', 'user', 'conversation')\n created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp notification was created\n read_at timestamp, -- timestamp notification was marked as read\n PRIMARY KEY (notification_id)\n)\n"} {"conversations": [{"role": "user", "content": "Retrieve the names of all properties that have listed room types, along with the name of each room type available at that property."}, {"role": "assistant", "content": "SELECT t1.property_name, t2.type_name FROM hospitality_technology.properties AS t1 INNER JOIN hospitality_technology.room_types AS t2 ON t1.property_id = t2.property_id;"}, {"role": "user", "content": "Now, filter this list to only include room types with a base rate above 300."}, {"role": "assistant", "content": "SELECT t1.property_name, t2.type_name FROM hospitality_technology.properties AS t1 INNER JOIN hospitality_technology.room_types AS t2 ON t1.property_id = t2.property_id WHERE t2.base_rate > 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.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 (\n reservation_id character varying(64) NOT NULL, -- unique identifier for the booking\n property_id character varying(64) NOT NULL, -- FK to properties table\n guest_id character varying(64) NOT NULL, -- FK to guests table (primary guest)\n room_id character varying(64), -- FK to rooms table (assigned room, might be null initially)\n room_type_id character varying(64) NOT NULL, -- FK to room_types table (booked room type)\n check_in_date date NOT NULL, -- scheduled check-in date\n check_out_date date NOT NULL, -- scheduled check-out date\n actual_check_in_ts timestamp with time zone, -- actual check-in time\n actual_check_out_ts timestamp with time zone, -- actual check-out time\n num_adults integer NOT NULL, -- number of adults\n num_children integer DEFAULT 0, -- number of children\n status character varying(50) NOT NULL, -- e.g., Pending, Confirmed, CheckedIn, CheckedOut, Cancelled, NoShow\n booking_source character varying(100), -- e.g., Website, OTA (Expedia, Booking.com), Phone, WalkIn\n rate_plan_id character varying(64), -- FK to rate_plans table (optional)\n total_amount numeric(12, 2), -- estimated or final total cost\n amount_paid numeric(12, 2) DEFAULT 0.00, -- amount already paid\n special_requests text, -- specific guest requests for this booking\n created_at timestamp with time zone NOT NULL DEFAULT current_timestamp,\n updated_at timestamp with time zone NOT NULL DEFAULT current_timestamp,\n PRIMARY KEY (reservation_id),\n FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id),\n FOREIGN KEY (guest_id) REFERENCES hospitality_technology.guests(guest_id),\n FOREIGN KEY (room_id) REFERENCES hospitality_technology.rooms(room_id),\n FOREIGN KEY (room_type_id) REFERENCES hospitality_technology.room_types(room_type_id)\n)\nCREATE TABLE hospitality_technology.services ( service_id.text, property_id.text, service_name.text, description.text, category.text, price.numeric, unit.text, is_available.boolean, department.text )\nCREATE TABLE hospitality_technology.service_orders ( order_id 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 (\n review_id character varying(64) NOT NULL, -- unique identifier for the review\n property_id character varying(64) NOT NULL, -- FK to properties table\n reservation_id character varying(64) UNIQUE, -- FK to reservations (link review to a specific stay, optional but good)\n guest_id character varying(64) NOT NULL, -- FK to guests table\n rating_overall integer, -- overall score (e.g., 1-5 or 1-10)\n rating_cleanliness integer,\n rating_service integer,\n rating_location integer,\n rating_value integer,\n comment text, -- guest's written feedback\n review_source character varying(100), -- e.g., DirectSurvey, TripAdvisor, Google, Booking.com\n review_date timestamp with time zone NOT NULL DEFAULT current_timestamp, -- when the review was submitted\n is_public boolean DEFAULT true, -- whether the review is publicly visible\n staff_response text, -- official response from the property\n response_staff_id character varying(64), -- FK to staff (who responded)\n response_date timestamp with time zone, -- when the response was posted\n PRIMARY KEY (review_id),\n FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id),\n FOREIGN KEY (reservation_id) REFERENCES hospitality_technology.reservations(reservation_id),\n FOREIGN KEY (guest_id) REFERENCES hospitality_technology.guests(guest_id),\n FOREIGN KEY (response_staff_id) REFERENCES hospitality_technology.staff(staff_id)\n)\n"} {"conversations": [{"role": "user", "content": "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": "Get the number of direct reports for each manager, showing manager_id and report_count."}, {"role": "assistant", "content": "SELECT manager_id,\n COUNT(*) AS report_count\nFROM hospitality_technology.staff\nWHERE manager_id IS NOT NULL\nGROUP BY manager_id;"}, {"role": "user", "content": "Exclude managers who have fewer than 2 direct reports."}, {"role": "assistant", "content": "SELECT manager_id,\n COUNT(*) AS report_count\nFROM hospitality_technology.staff\nWHERE manager_id IS NOT NULL\nGROUP BY manager_id\nHAVING COUNT(*) >= 2;"}, {"role": "user", "content": "Also include the manager's full name alongside their ID."}, {"role": "assistant", "content": "SELECT m.staff_id AS manager_id,\n m.first_name || ' ' || m.last_name AS manager_full_name,\n COUNT(s.staff_id) AS report_count\nFROM hospitality_technology.staff s\nJOIN hospitality_technology.staff m\n ON s.manager_id = m.staff_id\nGROUP BY m.staff_id, m.first_name, m.last_name\nHAVING COUNT(s.staff_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 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) )\n"} {"conversations": [{"role": "user", "content": "List all lawyers who have never had a time entry that was billed, showing lawyer_id, first_name, and last_name."}, {"role": "assistant", "content": "SELECT l.lawyer_id, l.first_name, l.last_name \nFROM legal_services.lawyers l \nLEFT JOIN legal_services.time_entries te \n ON l.lawyer_id = te.lawyer_id \n AND te.is_billed = true \nWHERE te.entry_id IS NULL;"}, {"role": "user", "content": "Actually, I only want lawyers who have at least one time entry overall but none of those entries are billed."}, {"role": "assistant", "content": "SELECT l.lawyer_id, l.first_name, l.last_name \nFROM legal_services.lawyers l \nJOIN legal_services.time_entries te ON l.lawyer_id = te.lawyer_id \nGROUP BY l.lawyer_id, l.first_name, l.last_name \nHAVING COUNT(te.entry_id) > 0 \n AND SUM(CASE WHEN te.is_billed = true THEN 1 ELSE 0 END) = 0;"}, {"role": "user", "content": "Now also include the count of unbilled entries and total unbilled hours for each lawyer."}, {"role": "assistant", "content": "SELECT l.lawyer_id, \n l.first_name, \n l.last_name, \n COUNT(te.entry_id) FILTER (WHERE te.is_billed = false) AS unbilled_entries, \n SUM(te.hours_spent) FILTER (WHERE te.is_billed = false) AS total_unbilled_hours \nFROM legal_services.lawyers l \nJOIN legal_services.time_entries te ON l.lawyer_id = te.lawyer_id \nGROUP BY l.lawyer_id, l.first_name, l.last_name \nHAVING COUNT(te.entry_id) > 0 \n AND SUM(CASE WHEN te.is_billed = true 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 legal_services.lawyers ( lawyer_id.text, first_name.text, last_name.text, bar_number.text, firm_id.text, email.text, phone.text, specialization.text, hire_date.timestamp, is_partner.boolean )\nCREATE TABLE legal_services.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 ( entry_id character varying(64) NOT NULL, case_id character varying(64) NOT NULL, lawyer_id character varying(64) NOT NULL, date_worked date NOT NULL, hours_spent numeric(5, 2) NOT NULL CHECK (hours_spent > 0), billing_rate numeric(10, 2) NOT NULL, description text NOT NULL, is_billable boolean DEFAULT true, is_billed boolean DEFAULT false, invoice_id character varying(64), created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, PRIMARY KEY (entry_id) )\nCREATE TABLE legal_services.appointments ( appointment_id text, client_id text, lawyer_id text, case_id text, start_time timestamp, end_time timestamp, location text, subject text, notes text, status text, created_at timestamp )\n"} {"conversations": [{"role": "user", "content": "What is the total revenue generated by ticket sales at the station with ID 'ST101' for the past month?"}, {"role": "assistant", "content": "I'm sorry, but I can't provide information on the revenue generated by ticket sales as this data is not available in the current database table. The table only contains details about station information such as name, location, and platform count. If you have another question or need assistance with something else related to the station data, I'm happy to help."}], "system": "You are an SQL statement expert and you can refuse the user's question if the question is not related to the table structure. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE train_station_management.stations ( station_id.text, station_name.text, city.text, state_province.text, country_code.text, address.text, timezone.text, number_of_platforms.integer, created_at.timestamp, last_updated_at.timestamp )\n"} {"conversations": [{"role": "user", "content": "Show me each product_type along with the count of products for that type, but only include types where the average base_premium exceeds 500. Order the results by the product count in descending order."}, {"role": "assistant", "content": "SELECT product_type,\n COUNT(*) AS product_count\nFROM insurance.insurance_products\nGROUP BY product_type\nHAVING AVG(base_premium) > 500\nORDER BY product_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.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": "Can you give me the list of server names and their regions, along with the total number of players currently online in each region?"}, {"role": "assistant", "content": "SELECT region, SUM(current_players) AS total_current_players, STRING_AGG(server_name, ', ') AS server_names\nFROM gaming_technology.servers\nWHERE status = 'online'\nGROUP BY region;"}, {"role": "user", "content": "I want to include the count of servers in each region as well. Can you modify the query?"}, {"role": "assistant", "content": "SELECT region, COUNT(server_id) AS server_count, SUM(current_players) AS total_current_players, STRING_AGG(server_name, ', ') AS server_names\nFROM gaming_technology.servers\nWHERE status = 'online'\nGROUP BY region;"}, {"role": "user", "content": "Add only those regions where the server count is more than 2."}, {"role": "assistant", "content": "SELECT region, COUNT(server_id) AS server_count, SUM(current_players) AS total_current_players, STRING_AGG(server_name, ', ') AS server_names\nFROM gaming_technology.servers\nWHERE status = 'online'\nGROUP BY region\nHAVING COUNT(server_id) > 2;"}, {"role": "user", "content": "Can you also sort the results by total_current_players in descending order?"}, {"role": "assistant", "content": "SELECT region, COUNT(server_id) AS server_count, SUM(current_players) AS total_current_players, STRING_AGG(server_name, ', ') AS server_names\nFROM gaming_technology.servers\nWHERE status = 'online'\nGROUP BY region\nHAVING COUNT(server_id) > 2\nORDER BY total_current_players DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE gaming_technology.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 )\n"} {"conversations": [{"role": "user", "content": "Give me the total number of doctors for each specialty."}, {"role": "assistant", "content": "SELECT specialty, COUNT(*) AS doctor_count\nFROM healthcare.doctors\nGROUP BY specialty;"}], "system": "You are an SQL statement expert. Given the table structure 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": "Can you list all achievement names and their point values, along with the name of the developer for each achievement's game?"}, {"role": "assistant", "content": "SELECT a.name AS achievement_name, a.points, d.name AS developer_name\nFROM gaming_technology.achievements a\nJOIN gaming_technology.developers d ON a.game_id = d.developer_id;"}, {"role": "user", "content": "Actually, only include achievements with more than 100 points."}, {"role": "assistant", "content": "SELECT a.name AS achievement_name, a.points, d.name AS developer_name\nFROM gaming_technology.achievements a\nJOIN gaming_technology.developers d ON a.game_id = d.developer_id\nWHERE a.points > 100;"}, {"role": "user", "content": "Please exclude hidden achievements from the result."}, {"role": "assistant", "content": "SELECT a.name AS achievement_name, a.points, d.name AS developer_name\nFROM gaming_technology.achievements a\nJOIN gaming_technology.developers d ON a.game_id = d.developer_id\nWHERE a.points > 100 AND a.hidden = false;"}, {"role": "user", "content": "I only want to see achievements that belong to games developed in Japan."}, {"role": "assistant", "content": "SELECT a.name AS achievement_name, a.points, d.name AS developer_name\nFROM gaming_technology.achievements a\nJOIN gaming_technology.developers d ON a.game_id = d.developer_id\nWHERE a.points > 100 AND a.hidden = false AND d.country = 'Japan';"}], "system": "You are an SQL statement expert. Given the table structure 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 NOT NULL DEFAULT gen_random_uuid(), name character varying(150) NOT NULL UNIQUE, country character varying(100), founded_year integer, website character varying(255), created_at timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP, PRIMARY KEY (developer_id) )\nCREATE TABLE gaming_technology.achievements ( achievement_id uuid NOT NULL DEFAULT gen_random_uuid(), game_id uuid NOT NULL, name character varying(150) NOT NULL, description text NOT NULL, icon_url character varying(255), points integer DEFAULT 0, hidden boolean DEFAULT false, PRIMARY KEY (achievement_id) )\n"} {"conversations": [{"role": "user", "content": "Find all pairs of contracts deployed by the same deployer on the same day, showing the deployer_address, the deployment date, and both contract IDs."}, {"role": "assistant", "content": "SELECT c1.deployer_address,\n DATE(c1.deployed_at) AS deploy_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 ( 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": "How many insurance policies does each patient have? Return patient_id and policy_count."}, {"role": "assistant", "content": "SELECT patient_id,\n COUNT(*) AS policy_count\nFROM healthcare.patient_insurance\nGROUP BY patient_id;"}, {"role": "user", "content": "Only show patients with more than 2 policies and order by policy_count descending."}, {"role": "assistant", "content": "SELECT patient_id,\n COUNT(*) AS policy_count\nFROM healthcare.patient_insurance\nGROUP BY patient_id\nHAVING COUNT(*) > 2\nORDER BY 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 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 ( 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": "What is the current location of train number Acela 2151?"}, {"role": "assistant", "content": "I'm sorry, but I don't have access to real-time location data for trains. The database only contains static information such as train ID, model, capacity, and maintenance schedules. For current location updates, please check with the train operator or a tracking service."}], "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 (\n train_id character varying(64) NOT NULL, -- Unique identifier for the train set\n train_number character varying(32) NOT NULL, -- Operational number of the train (e.g., 'Acela 2151')\n model character varying(128), -- Model of the train (e.g., 'Siemens Velaro')\n manufacturer character varying(128), -- Manufacturer of the train\n year_manufactured integer, -- Year the train was built\n capacity integer NOT NULL, -- Total passenger capacity\n status character varying(32) NOT NULL DEFAULT 'Active', -- e.g., Active, Maintenance, Retired\n last_maintenance_date date, -- Date of last scheduled maintenance\n next_maintenance_date date, -- Date of next scheduled maintenance\n PRIMARY KEY (train_id),\n UNIQUE (train_number)\n)\n"} {"conversations": [{"role": "user", "content": "List all overdue premium payments with their policy IDs and due dates, sorted by due date in ascending order."}, {"role": "assistant", "content": "SELECT policy_id, due_date FROM insurance.premium_payments WHERE status = 'overdue' ORDER BY due_date ASC;"}, {"role": "user", "content": "Now include only those overdue payments where the due date was more than 60 days ago."}, {"role": "assistant", "content": "SELECT policy_id, due_date FROM insurance.premium_payments WHERE status = 'overdue' AND due_date < CURRENT_DATE - INTERVAL '60 days' ORDER BY due_date ASC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.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": "List patient_id, first_name, last_name, and date_of_birth for all patients older than 65 years."}, {"role": "assistant", "content": "SELECT patient_id, first_name, last_name, date_of_birth\nFROM healthcare.patients\nWHERE date_of_birth < CURRENT_DATE - INTERVAL '65 years';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.patients ( patient_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, date_of_birth date NOT NULL, gender character varying(10), address text, phone_number character varying(20), email character varying(128) UNIQUE, emergency_contact_name character varying(200), emergency_contact_phone character varying(20), created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, updated_at timestamp with time zone NOT NULL DEFAULT current_timestamp, PRIMARY KEY (patient_id) )\nCREATE TABLE healthcare.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 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 (\n diagnosis_id character varying(64) NOT NULL, -- unique identifier for the diagnosis entry\n record_id character varying(64) NOT NULL, -- FK linking to the specific medical record entry\n patient_id character varying(64) NOT NULL, -- FK to patients table\n doctor_id character varying(64) NOT NULL, -- FK to doctors table (diagnosing doctor)\n diagnosis_code character varying(20) NOT NULL, -- standard code (e.g., ICD-10)\n code_type character varying(10) NOT NULL DEFAULT 'ICD-10', -- type of code used\n description text, -- textual description of the diagnosis\n diagnosis_date date NOT NULL, -- date the diagnosis was made\n status character varying(32) NOT NULL, -- e.g., Active, Resolved, Ruled Out\n is_chronic boolean DEFAULT false, -- flag for chronic conditions\n PRIMARY KEY (diagnosis_id)\n)\nCREATE TABLE healthcare.medications ( medication_id text PRIMARY KEY, medication_name text, generic_name text, manufacturer text, ndc_code text, description text )\nCREATE TABLE healthcare.prescriptions ( prescription_id text, record_id text, patient_id text, doctor_id text, medication_id text, dosage text, frequency text, route text, start_date date, end_date date, quantity_dispensed numeric, refills_allowed integer, prescription_date timestamp )\nCREATE TABLE healthcare.insurance_plans ( plan_id text, plan_name text, insurance_provider text, plan_type text, contact_phone text, website text )\n"} {"conversations": [{"role": "user", "content": "Show me a list of all notifications that are related to comments. Include the notification ID, the recipient user ID, and the target entity ID, which corresponds to the comment ID."}, {"role": "assistant", "content": "SELECT notification_id, recipient_user_id, target_entity_id FROM social_media.notifications WHERE target_entity_type = 'comment';"}, {"role": "user", "content": "Please expand that list to include the username of the notification recipient and the content of the comment that the notification is about."}, {"role": "assistant", "content": "SELECT n.notification_id, u.username, c.content FROM social_media.notifications n JOIN social_media.users u ON n.recipient_user_id = u.user_id JOIN social_media.comments c ON n.target_entity_id = c.comment_id WHERE n.target_entity_type = 'comment';"}, {"role": "user", "content": "Okay, filter this down to only show notifications where the comment content is not empty, and the notification type is either 'like' or 'comment'."}, {"role": "assistant", "content": "SELECT n.notification_id, u.username, c.content FROM social_media.notifications n JOIN social_media.users u ON n.recipient_user_id = u.user_id JOIN social_media.comments c ON n.target_entity_id = c.comment_id WHERE n.target_entity_type = 'comment' AND (c.content IS NOT NULL AND c.content != '') AND n.notification_type IN ('like', 'comment');"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE social_media.users ( user_id.text, username.text, email.text, password_hash.text, full_name.text, profile_picture_url.text, bio.text, location.text, created_at.timestamp, updated_at.timestamp, is_verified.boolean )\nCREATE TABLE social_media.posts ( post_id.text, user_id.text, content.text, media_url.text, media_type.text, created_at.timestamp, updated_at.timestamp, visibility.text, location_lat.numeric, location_lon.numeric )\nCREATE TABLE social_media.comments ( comment_id.text, post_id.text, user_id.text, parent_comment_id.text, content.text, created_at.timestamp, updated_at.timestamp )\nCREATE TABLE social_media.follows ( follow_id.text, follower_user_id.text, following_user_id.text, created_at.timestamp )\nCREATE TABLE social_media.hashtags ( hashtag_id.text, tag_name.text, created_at.timestamp )\nCREATE TABLE social_media.conversation_participants ( participant_id.text, conversation_id.text, user_id.text, joined_at.timestamp, last_read_at.timestamp )\nCREATE TABLE social_media.notifications ( notification_id.text, recipient_user_id.text, sender_user_id.text, notification_type.text, target_entity_id.text, target_entity_type.text, created_at.timestamp, read_at.timestamp )\nCREATE TABLE social_media.user_settings ( setting_id.text, user_id.text, theme.text, email_notifications_enabled.boolean, push_notifications_enabled.boolean, private_profile.boolean, updated_at.timestamp )\n"} {"conversations": [{"role": "user", "content": "Can you show the total quantity of all in-game items held by each player?"}, {"role": "assistant", "content": "SELECT player_id, SUM(quantity) AS total_quantity\nFROM gaming_technology.player_inventory\nGROUP BY player_id;"}, {"role": "user", "content": "I'd like to see only players whose total quantity is over 20."}, {"role": "assistant", "content": "SELECT player_id, SUM(quantity) AS total_quantity\nFROM gaming_technology.player_inventory\nGROUP BY player_id\nHAVING SUM(quantity) > 20;"}, {"role": "user", "content": "Also, can you include the number of different unique items each player owns?"}, {"role": "assistant", "content": "SELECT player_id, COUNT(DISTINCT item_id) AS unique_items, SUM(quantity) AS total_quantity\nFROM gaming_technology.player_inventory\nGROUP BY player_id\nHAVING SUM(quantity) > 20;"}, {"role": "user", "content": "Order the final result by unique_items descending, then by total_quantity descending."}, {"role": "assistant", "content": "SELECT player_id, COUNT(DISTINCT item_id) AS unique_items, SUM(quantity) AS total_quantity\nFROM gaming_technology.player_inventory\nGROUP BY player_id\nHAVING SUM(quantity) > 20\nORDER BY unique_items DESC, 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 (\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": "How many documents of type 'Pleading' were uploaded for case 'case_abc'?"}, {"role": "assistant", "content": "SELECT COUNT(*) FROM legal_services.documents WHERE document_type = 'Pleading' AND case_id = 'case_abc';"}], "system": "You are an SQL statement expert. Given the table structure 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.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)\nCREATE TABLE legal_services.invoices ( invoice_id.text, invoice_number.text, client_id.text, case_id.text, issue_date.date, due_date.date, total_amount.numeric, amount_paid.numeric, status.text, payment_date.timestamp, notes.text, created_at.timestamp )\n"} {"conversations": [{"role": "user", "content": "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": "Show the IDs and registration dates of all verified citizens who could be eligible for at least one active service. Display the citizen ID and registration date."}, {"role": "assistant", "content": "SELECT DISTINCT c.citizen_id, c.registration_date\nFROM government_services.citizens c\nJOIN government_services.services s ON s.is_active = true\nWHERE c.is_verified = true;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.citizens ( citizen_id character varying(64) NOT NULL, national_id_number character varying(128) NOT NULL UNIQUE, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, date_of_birth date NOT NULL, gender character varying(20), primary_address text NOT NULL, contact_email character varying(128) UNIQUE, contact_phone character varying(32), registration_date timestamp NOT NULL, is_verified boolean DEFAULT false, PRIMARY KEY (citizen_id) )\nCREATE TABLE government_services.services ( service_id.text, agency_id.text, service_name.text, description.text, category.text, eligibility_criteria.text, standard_fee.numeric, average_processing_time_days.integer, is_active.boolean, online_application_url.text )\n"} {"conversations": [{"role": "user", "content": "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 me all cryptocurrency assets that have been traded more than 50 times but have never been traded in quantities greater than 100, along with their average trade price."}, {"role": "assistant", "content": "SELECT a.asset_id, a.name, a.symbol, COUNT(t.trade_id) AS trade_count, AVG(t.price) AS avg_price FROM trading_platform.assets a JOIN trading_platform.trades t ON a.asset_id = t.asset_id WHERE a.type = 'cryptocurrency' GROUP BY a.asset_id, a.name, a.symbol HAVING COUNT(t.trade_id) > 50 AND MAX(t.quantity) <= 100;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE trading_platform.users ( user_id character varying(64) NOT NULL, username character varying(128) NOT NULL, email character varying(128) NOT NULL, password_hash text NOT NULL, created_at timestamp NOT NULL, PRIMARY KEY (user_id) )\nCREATE TABLE trading_platform.wallets ( wallet_id character varying(64) NOT NULL, user_id character varying(64) NOT NULL, address character varying(128) NOT NULL, private_key text NOT NULL, created_at timestamp NOT NULL, PRIMARY KEY (wallet_id) )\nCREATE TABLE trading_platform.orders ( order_id character varying(64) NOT NULL, user_id character varying(64) NOT NULL, wallet_id character varying(64) NOT NULL, asset_id character varying(64) NOT NULL, order_type character varying(32) NOT NULL, quantity numeric(38,14) NOT NULL, price numeric(38,14) NOT NULL, status character varying(32) NOT NULL, created_at timestamp NOT NULL, PRIMARY KEY (order_id) )\nCREATE TABLE trading_platform.trades ( trade_id character varying(64) NOT NULL, order_id character varying(64) NOT NULL, buyer_id character varying(64) NOT NULL, seller_id character varying(64) NOT NULL, asset_id character varying(64) NOT NULL, quantity numeric(38,14) NOT NULL, price numeric(38,14) NOT NULL, traded_at timestamp NOT NULL, PRIMARY KEY (trade_id) )\nCREATE TABLE trading_platform.assets ( asset_id character varying(64) NOT NULL, name character varying(128) NOT NULL, symbol character varying(32) NOT NULL, type character varying(32) NOT NULL, PRIMARY KEY (asset_id) )\nCREATE TABLE trading_platform.utxos ( utxo_id character varying(64) NOT NULL, transaction_id character varying(64) NOT NULL, output_index integer NOT NULL, address character varying(128) NOT NULL, amount numeric(38,14) NOT NULL, spent boolean NOT NULL, PRIMARY KEY (utxo_id) )\nCREATE TABLE trading_platform.dapps ( dapp_id character varying(64) NOT NULL, name character varying(128) NOT NULL, description text NOT NULL, url character varying(256) NOT NULL, PRIMARY KEY (dapp_id) )\nCREATE TABLE trading_platform.peers ( peer_id character varying(64) NOT NULL, ip_address character varying(15) NOT NULL, port integer NOT NULL, last_seen timestamp NOT NULL, PRIMARY KEY (peer_id) )\nCREATE TABLE trading_platform.metadata ( metadata_id character varying(64) NOT NULL, asset_id character varying(64) NOT NULL, key character varying(128) NOT NULL, value text NOT NULL, PRIMARY KEY (metadata_id) )\nCREATE TABLE trading_platform.kyc_audit ( kyc_audit_id character varying(64) NOT NULL, user_id character varying(64) NOT NULL, status character varying(32) NOT NULL, reviewed_at timestamp NOT NULL, PRIMARY KEY (kyc_audit_id) )\nCREATE TABLE trading_platform.notifications ( notification_id character varying(64) NOT NULL, user_id character varying(64) NOT NULL, message text NOT NULL, sent_at timestamp NOT NULL, read_at timestamp, PRIMARY KEY (notification_id) )\n"} {"conversations": [{"role": "user", "content": "Show the total amount paid for services in each category."}, {"role": "assistant", "content": "SELECT T2.category , SUM(T1.amount) FROM government_services.payments AS T1 JOIN government_services.services AS T2 ON T1.service_id = T2.service_id GROUP BY T2.category"}, {"role": "user", "content": "Can you only include payments with a status of 'Completed'?"}, {"role": "assistant", "content": "SELECT T2.category , SUM(T1.amount) FROM government_services.payments AS T1 JOIN government_services.services AS T2 ON T1.service_id = T2.service_id WHERE T1.status = 'Completed' GROUP BY T2.category"}, {"role": "user", "content": "Now only show categories where the total paid is greater than 500."}, {"role": "assistant", "content": "SELECT T2.category , SUM(T1.amount) FROM government_services.payments AS T1 JOIN government_services.services AS T2 ON T1.service_id = T2.service_id WHERE T1.status = 'Completed' GROUP BY T2.category HAVING SUM(T1.amount) > 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 government_services.citizens ( citizen_id character varying(64) NOT NULL, national_id_number character varying(128) NOT NULL UNIQUE, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, date_of_birth date NOT NULL, gender character varying(20), primary_address text NOT NULL, contact_email character varying(128) UNIQUE, contact_phone character varying(32), registration_date timestamp NOT NULL, is_verified boolean DEFAULT false, PRIMARY KEY (citizen_id) )\nCREATE TABLE government_services.agencies ( agency_id character varying(64) NOT NULL, agency_name character varying(255) NOT NULL, jurisdiction_level character varying(50) NOT NULL, primary_contact_email character varying(128), main_phone_number character varying(32), website_url character varying(255), established_date date, parent_agency_id character varying(64), PRIMARY KEY (agency_id) )\nCREATE TABLE government_services.services ( service_id character varying(64) NOT NULL, agency_id character varying(64) NOT NULL, service_name character varying(255) NOT NULL, description text, category character varying(100), eligibility_criteria text, standard_fee numeric(10, 2) DEFAULT 0.00, average_processing_time_days integer, is_active boolean DEFAULT true, online_application_url character varying(255), PRIMARY KEY (service_id) )\nCREATE TABLE government_services.applications ( application_id character varying(64) NOT NULL, citizen_id character varying(64) NOT NULL, service_id character varying(64) NOT NULL, submitted_at timestamp NOT NULL, status character varying(50) NOT NULL, last_updated_at timestamp NOT NULL, assigned_employee_id character varying(64), decision_date date, notes text, reference_number character varying(100) UNIQUE, PRIMARY KEY (application_id) )\nCREATE TABLE government_services.payments ( payment_id character varying(64) NOT NULL, application_id character varying(64), citizen_id character varying(64) NOT NULL, service_id character varying(64), amount numeric(12, 2) NOT NULL, currency character varying(3) NOT NULL DEFAULT 'USD', payment_method character varying(50), payment_provider_reference character varying(128), payment_timestamp timestamp NOT NULL, status character varying(30) NOT NULL, notes text, PRIMARY KEY (payment_id) )\nCREATE TABLE government_services.employees ( employee_id character varying(64) NOT NULL, agency_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, job_title character varying(150) NOT NULL, department character varying(100), work_email character varying(128) NOT NULL UNIQUE, work_phone character varying(32), hire_date date NOT NULL, termination_date date, access_level character varying(50), manager_employee_id character varying(64), PRIMARY KEY (employee_id) )\nCREATE TABLE government_services.service_locations ( location_id character varying(64) NOT NULL, agency_id character varying(64) NOT NULL, location_name character varying(200), address text NOT NULL, city character varying(100), state character varying(50), postal_code character varying(20), latitude numeric(9, 6), longitude numeric(9, 6), operating_hours text, contact_phone character varying(32), is_accessible boolean, PRIMARY KEY (location_id) )\nCREATE TABLE government_services.appointments ( appointment_id character varying(64) NOT NULL, citizen_id character varying(64) NOT NULL, employee_id character varying(64), location_id character varying(64), service_id character varying(64), scheduled_start_time timestamp NOT NULL, scheduled_end_time timestamp, purpose text NOT NULL, status character varying(30) NOT NULL, booking_method character varying(50), created_at timestamp NOT NULL, notes text, PRIMARY KEY (appointment_id) )\nCREATE TABLE government_services.notifications ( notification_id character varying(64) NOT NULL, citizen_id character varying(64) NOT NULL, application_id character varying(64), message_subject character varying(255), message_body text NOT NULL, channel character varying(30) NOT NULL, sent_at timestamp NOT NULL, status character varying(30) NOT NULL, related_entity_type character varying(50), related_entity_id character varying(64), PRIMARY KEY (notification_id) )\n"} {"conversations": [{"role": "user", "content": "Find agents whose commission_rate is higher than their manager's commission_rate. Show agent_id, agent first_name, agent last_name, commission_rate, manager_id, and the manager's commission_rate."}, {"role": "assistant", "content": "SELECT a.agent_id,\n a.first_name,\n a.last_name,\n a.commission_rate,\n a.manager_id,\n m.commission_rate AS manager_commission_rate\n FROM insurance.agents a\n JOIN insurance.agents m\n ON a.manager_id = m.agent_id\n WHERE a.commission_rate > m.commission_rate;"}, {"role": "user", "content": "Now restrict to agents hired before January 1, 2023."}, {"role": "assistant", "content": "SELECT a.agent_id,\n a.first_name,\n a.last_name,\n a.commission_rate,\n a.manager_id,\n m.commission_rate AS manager_commission_rate\n FROM insurance.agents a\n JOIN insurance.agents m\n ON a.manager_id = m.agent_id\n WHERE a.commission_rate > m.commission_rate\n AND a.hire_date < '2023-01-01';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.agents ( agent_id text PRIMARY KEY, first_name text, last_name text, agency_name text, license_number text, license_state text, contact_email text, contact_phone text, hire_date date, termination_date date, status text, commission_rate numeric, manager_id text )\n"} {"conversations": [{"role": "user", "content": "List document names and versions for documents that share the same case_id, showing each pair of versions."}, {"role": "assistant", "content": "SELECT d1.case_id, d1.document_name AS doc_name_v1, d1.version AS version1, d2.document_name AS doc_name_v2, d2.version AS version2 FROM legal_services.documents d1 JOIN legal_services.documents d2 ON d1.case_id = d2.case_id AND d1.version < d2.version;"}, {"role": "user", "content": "Actually, I only want to compare the highest version against the second highest version per case."}, {"role": "assistant", "content": "SELECT d_prev.case_id, d_prev.document_name AS prev_doc, d_prev.version AS prev_version, d_latest.document_name AS latest_doc, d_latest.version AS latest_version FROM legal_services.documents d_latest JOIN legal_services.documents d_prev ON d_latest.case_id = d_prev.case_id AND d_prev.version = d_latest.version - 1 WHERE d_latest.version = (SELECT MAX(version) FROM legal_services.documents d WHERE d.case_id = d_latest.case_id);"}, {"role": "user", "content": "Also include the upload timestamps and restrict to cases with at least three versions."}, {"role": "assistant", "content": "SELECT d_latest.case_id, d_prev.document_name AS prev_doc, d_prev.upload_timestamp AS prev_upload, d_latest.document_name AS latest_doc, d_latest.upload_timestamp AS latest_upload FROM legal_services.documents d_latest JOIN legal_services.documents d_prev ON d_latest.case_id = d_prev.case_id AND d_prev.version = d_latest.version - 1 WHERE d_latest.version = (SELECT MAX(version) FROM legal_services.documents d WHERE d.case_id = d_latest.case_id) AND (SELECT COUNT(*) FROM legal_services.documents d2 WHERE d2.case_id = d_latest.case_id) >= 3;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.documents (\n document_id character varying(64) NOT NULL, -- unique identifier for the document\n case_id character varying(64) NOT NULL, -- FK to cases table\n document_name character varying(255) NOT NULL, -- name of the document file\n document_type character varying(100), -- e.g., Pleading, Contract, Evidence, Correspondence\n storage_path text NOT NULL, -- path or reference to the document storage location\n uploaded_by_lawyer_id character varying(64), -- FK to lawyers table (who uploaded it)\n upload_timestamp timestamp NOT NULL, -- time the document was uploaded\n version integer DEFAULT 1, -- document version number\n description text, -- brief description or notes about the document\n PRIMARY KEY (document_id)\n)\n"} {"conversations": [{"role": "user", "content": "List the first name, last name, license number, and status for all drivers whose license expires in the next 6 months."}, {"role": "assistant", "content": "SELECT\n first_name,\n last_name,\n license_number,\n status\nFROM transportation.drivers\nWHERE\n license_expiry_date BETWEEN CURRENT_DATE AND CURRENT_DATE + INTERVAL '6 month'\nORDER BY\n license_expiry_date;"}, {"role": "user", "content": "Now, count how many drivers from that list have an 'Active' status."}, {"role": "assistant", "content": "SELECT\n COUNT(*)\nFROM transportation.drivers\nWHERE\n license_expiry_date BETWEEN CURRENT_DATE AND CURRENT_DATE + INTERVAL '6 month' AND status = 'Active';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.drivers ( driver_id text PRIMARY KEY, employee_id text, first_name text, last_name text, license_number text, license_expiry_date date, contact_number text, email text, hire_date date, status text )\n"} {"conversations": [{"role": "user", "content": "For each achievement, show its name, the game_id it belongs to, and the number of distinct players who have played a session for that game."}, {"role": "assistant", "content": "SELECT a.name, a.game_id, COUNT(DISTINCT gs.player_id) AS players_with_sessions\nFROM gaming_technology.achievements a\nLEFT JOIN gaming_technology.game_sessions gs ON a.game_id = gs.game_id\nGROUP BY a.achievement_id, a.name, a.game_id;"}, {"role": "user", "content": "Now, filter to only include achievements for games that have at least 50 players who have played a session."}, {"role": "assistant", "content": "SELECT a.name, a.game_id, COUNT(DISTINCT gs.player_id) AS players_with_sessions\nFROM gaming_technology.achievements a\nLEFT JOIN gaming_technology.game_sessions gs ON a.game_id = gs.game_id\nGROUP BY a.achievement_id, a.name, a.game_id\nHAVING COUNT(DISTINCT gs.player_id) >= 50;"}, {"role": "user", "content": "Please also include the number of times each achievement has been unlocked by unique players, labeled as unique_unlocks."}, {"role": "assistant", "content": "SELECT a.name, a.game_id, COUNT(DISTINCT gs.player_id) AS players_with_sessions,\n (SELECT COUNT(DISTINCT gs2.player_id)\n FROM gaming_technology.game_sessions gs2\n WHERE gs2.game_id = a.game_id) AS unique_unlocks\nFROM gaming_technology.achievements a\nLEFT JOIN gaming_technology.game_sessions gs ON a.game_id = gs.game_id\nGROUP BY a.achievement_id, a.name, a.game_id\nHAVING COUNT(DISTINCT gs.player_id) >= 50;"}, {"role": "user", "content": "I think unique_unlocks should be the count of distinct players who have unlocked each specific achievement, not just played a session. Can you correct that?"}, {"role": "assistant", "content": "-- With the provided tables, there is no direct record of players unlocking a specific achievement, unless unlocking is inferred elsewhere. If you have an achievement unlocks table, you could join it here. Otherwise, only possible to count sessions per game."}], "system": "You are an SQL statement expert. Given the table structure 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": "Which users have sent messages in private conversations? Please show their usernames and the conversation IDs."}, {"role": "assistant", "content": "SELECT DISTINCT u.username, m.conversation_id\nFROM social_media.messages m\nJOIN social_media.users u ON m.sender_user_id = u.user_id\nJOIN social_media.conversations c ON m.conversation_id = c.conversation_id\nWHERE c.is_group_chat = false;"}, {"role": "user", "content": "Include the time of the first message they sent in each conversation."}, {"role": "assistant", "content": "SELECT u.username, m.conversation_id, MIN(m.sent_at) AS first_message_time\nFROM social_media.messages m\nJOIN social_media.users u ON m.sender_user_id = u.user_id\nJOIN social_media.conversations c ON m.conversation_id = c.conversation_id\nWHERE c.is_group_chat = false\nGROUP BY u.username, m.conversation_id;"}, {"role": "user", "content": "Can you also show the total number of messages each user has sent in each private conversation?"}, {"role": "assistant", "content": "SELECT u.username, m.conversation_id, COUNT(*) AS message_count, MIN(m.sent_at) AS first_message_time\nFROM social_media.messages m\nJOIN social_media.users u ON m.sender_user_id = u.user_id\nJOIN social_media.conversations c ON m.conversation_id = c.conversation_id\nWHERE c.is_group_chat = false\nGROUP BY u.username, m.conversation_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.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.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.follows ( follow_id character varying(64) NOT NULL, follower_user_id character varying(64) NOT NULL, following_user_id character varying(64) NOT NULL, created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, PRIMARY KEY (follow_id), CONSTRAINT unique_follow UNIQUE (follower_user_id, following_user_id) )\nCREATE TABLE social_media.hashtags ( hashtag_id character varying(64) NOT NULL, tag_name character varying(100) NOT NULL UNIQUE, created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, PRIMARY KEY (hashtag_id) )\nCREATE TABLE social_media.post_hashtags ( post_hashtag_id 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.messages (\n message_id character varying(64) NOT NULL, -- unique identifier for the message\n conversation_id character varying(64) NOT NULL, -- identifier for the conversation thread (FK to conversations.conversation_id)\n sender_user_id character varying(64) NOT NULL, -- identifier of the sender (FK to users.user_id)\n content text, -- textual content of the message\n media_url text, -- URL to attached media (image/video)\n media_type character varying(20), -- type of media ('image', 'video', null)\n sent_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp when message was sent\n read_at timestamp, -- timestamp when message was read by recipient(s)\n PRIMARY KEY (message_id)\n)\nCREATE TABLE social_media.conversations ( conversation_id text PRIMARY KEY, created_at timestamp, last_message_at timestamp, is_group_chat bool, group_name text )\nCREATE TABLE social_media.conversation_participants (\n participant_id character varying(64) NOT NULL, -- unique identifier for the participant entry\n conversation_id character varying(64) NOT NULL, -- identifier of the conversation (FK to conversations.conversation_id)\n user_id character varying(64) NOT NULL, -- identifier of the user in the conversation (FK to users.user_id)\n joined_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp when user joined the conversation\n last_read_at timestamp, -- timestamp indicating up to when the user has read messages\n PRIMARY KEY (participant_id),\n CONSTRAINT unique_user_conversation UNIQUE (conversation_id, user_id) -- prevent user being added multiple times\n)\nCREATE TABLE social_media.notifications ( 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 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": "Show me wallet addresses that hold more than 1000 of any ERC20 token, along with the token symbol and amount, sorted by amount in descending order."}, {"role": "assistant", "content": "SELECT b.wallet_address, t.symbol, b.amount FROM erc20_balances b JOIN sui_coins_metadata t ON b.contract_address = t.coin_type WHERE CAST(b.amount AS decimal) > 1000 ORDER BY CAST(b.amount AS decimal) DESC;"}, {"role": "user", "content": "Can you also include the current price of each token from the token_prices_latest table?"}, {"role": "assistant", "content": "SELECT b.wallet_address, t.symbol, b.amount, p.price FROM erc20_balances b JOIN sui_coins_metadata t ON b.contract_address = t.coin_type JOIN token_prices_latest p ON b.contract_address = p.address WHERE CAST(b.amount AS decimal) > 1000 ORDER BY CAST(b.amount AS decimal) DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE erc1155_approval_for_all (\n block_number bigint NOT NULL, -- Block number containing the transaction\n block_timestamp timestamp(3) NOT NULL, -- Timestamp of the block containing the transaction\n transaction_index integer NOT NULL, -- Index of the transaction within the block\n transaction_hash varchar(66) NOT NULL, -- Transaction hash\n log_index integer NOT NULL, -- Log index\n contract_address varchar(42) NOT NULL -- Event contract address\n)\nCREATE TABLE erc20_balances ( block_number.bigint, contract_address.text, wallet_address.text, amount.text, pk.text )\nCREATE TABLE erc20_balances_historical ( block_number bigint NOT NULL, contract_address varchar NOT NULL, wallet_address varchar NOT NULL, amount varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE nft_holders ( block_number bigint, contract_address varchar, wallet_address varchar, token_id varchar, contract_type varchar, amount varchar, pk varchar )\nCREATE TABLE sui_coins_metadata ( object_id varchar, coin_type varchar, status varchar, decimals bigint, description varchar, icon_url varchar, symbol varchar, name varchar )\nCREATE TABLE nft_metadata (\n blockchain varchar NOT NULL, -- blockchain fields for the functionType in contract\n contract_address varchar NOT NULL, -- Contract address(with bloom filter)\n token_id varchar NOT NULL, -- The number of the token\n contract_name varchar NOT NULL, -- contract_name fields for the functionType in contract\n erc_type varchar NOT NULL, -- The type of token\n amount bigint NOT NULL, -- amount fields for the functionType in contract\n minter varchar NOT NULL, -- minter fields for the functionType in contract\n owner varchar NOT NULL, -- owner fields for the functionType in contract\n mint_block_number bigint NOT NULL, -- mint_block_number fields for the functionType in contract\n mint_time bigint NOT NULL, -- mint_time fields for the functionType in contract\n mint_transaction_hash varchar NOT NULL, -- mint_transaction_hash fields for the functionType in contract\n mint_price varchar NOT NULL, -- mint_price fields for the functionType in contract\n token_uri varchar NOT NULL, -- token_uri fields for the functionType in contract\n metadata varchar NOT NULL, -- metadata fields for the functionType in contract\n name varchar NOT NULL, -- name fields for the functionType in contract\n image_uri varchar NOT NULL, -- image_uri fields for the functionType in contract\n traits varchar NOT NULL, -- traits fields for the functionType in contract\n updated_at bigint NOT NULL, -- updated_at fields for the functionType in contract\n status varchar NOT NULL, -- status fields for the functionType in contract\n rarity_score real NOT NULL, -- rarity_score fields for the functionType in contract\n rarity_rank integer NOT NULL, -- rarity_rank fields for the functionType in contract\n unique_attribute_count integer NOT NULL, -- unique_attribute_count fields for the functionType in contract\n pk integer NOT NULL -- Partition key for the table(floor(mint_time / 1000 / 86400 / 30))\n)\nCREATE TABLE token_prices_latest ( blockchain varchar, address varchar, decimals bigint, symbol varchar, price real, timestamp timestamp )\nCREATE TABLE token_info ( block_timestamp timestamp(3) NOT NULL, block_number bigint NOT NULL, tx_index integer NOT NULL, tx_hash varchar(66) NOT NULL, tick varchar NOT NULL, max_supply decimal(38,0) NOT NULL, lim decimal(38,0) NOT NULL, wlim decimal(38,0) NOT NULL, dec integer NOT NULL, creator varchar(42) NOT NULL )\nCREATE TABLE mud_holesky_redstone (\n address varchar NOT NULL, -- address fields for the functionType in contract\n table_id varchar NOT NULL, -- table_id fields for the functionType in contract\n key_bytes varchar NOT NULL, -- key_bytes fields for the functionType in contract\n key0 varchar NOT NULL, -- key0 fields for the functionType in contract\n key1 varchar NOT NULL, -- key1 fields for the functionType in contract\n static_data varchar NOT NULL, -- static_data fields for the functionType in contract\n encoded_lengths varchar NOT NULL, -- encoded_lengths fields for the functionType in contract\n dynamic_data varchar NOT NULL, -- dynamic_data fields for the functionType in contract\n is_deleted boolean NOT NULL, -- is_deleted fields for the functionType in contract\n block_number bigint NOT NULL, -- Block number uniquely identifying the block\n log_index bigint NOT NULL -- Index of the log within the transaction\n)\nCREATE TABLE token_activities_bitcoin ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash varchar, log_index integer, type varchar, tick varchar, id varchar, amt decimal, from_address varchar, to_address varchar )\nCREATE TABLE token_balances_avalanche (\n block_number bigint NOT NULL, -- Block number containing the transaction\n block_timestamp timestamp(3) NOT NULL, -- Block timestamp containing the transaction\n tick varchar(20) NOT NULL, -- Ticker: Identifier of the inscription\n wallet_address varchar(42) NOT NULL, -- Address of owner\n total_supply decimal(38,0) NOT NULL, -- Max supply: Set max supply of the inscription\n amount decimal(38,0) NOT NULL -- The balance of wallet balance at the corresponding block height\n)\nCREATE TABLE token_info_avalanche ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash text, tick text, max_supply decimal, lim decimal, wlim decimal, dec integer, creator text, minted decimal, holders decimal, txs decimal, updated_timestamp timestamp, completed_timestamp timestamp, id text )\n"} {"conversations": [{"role": "user", "content": "For each ERC20 token, how many unique wallets currently hold them? Show the contract address and unique wallet count."}, {"role": "assistant", "content": "SELECT contract_address, COUNT(DISTINCT wallet_address) AS unique_wallet_count FROM erc20_balances GROUP BY contract_address;"}, {"role": "user", "content": "Add the token symbol and name for each contract by joining to the token_prices_latest table."}, {"role": "assistant", "content": "SELECT e.contract_address, COUNT(DISTINCT e.wallet_address) AS unique_wallet_count, t.symbol, t.address AS token_name FROM erc20_balances e LEFT JOIN token_prices_latest t ON e.contract_address = t.address GROUP BY e.contract_address, t.symbol, t.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 erc1155_approval_for_all (\n block_number bigint NOT NULL, -- Block number containing the transaction\n block_timestamp timestamp(3) NOT NULL, -- Timestamp of the block containing the transaction\n transaction_index integer NOT NULL, -- Index of the transaction within the block\n transaction_hash varchar(66) NOT NULL, -- Transaction hash\n log_index integer NOT NULL, -- Log index\n contract_address varchar(42) NOT NULL -- Event contract address\n)\nCREATE TABLE erc20_balances ( block_number bigint, contract_address text, wallet_address text, amount text, pk text )\nCREATE TABLE erc20_balances_historical (\n block_number bigint NOT NULL, -- Block number containing the transaction\n contract_address varchar NOT NULL, -- Event contract address\n wallet_address varchar NOT NULL, -- The wallet address for the contract\n amount varchar NOT NULL, -- Wallet's on-chain balance at the corresponding block height\n pk integer NOT NULL -- Partition key for the table(floor(block_number / 7200))\n)\nCREATE TABLE nft_holders ( block_number bigint, contract_address varchar, wallet_address varchar, token_id varchar, contract_type varchar, amount varchar, pk varchar )\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.text, coin_type.text, status.text, decimals.bigint, description.text, icon_url.text, symbol.text, name.text )\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 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 (\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_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_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": "List all NFT collections from the sui_nfts table where the owner is not null, including their name and collection_type."}, {"role": "assistant", "content": "SELECT name, collection_type FROM sui_nfts WHERE owner IS NOT NULL;"}, {"role": "user", "content": "Can you also include the display field and filter to only show collections with a package_id starting with '0x'?"}, {"role": "assistant", "content": "SELECT name, collection_type, display FROM sui_nfts WHERE owner IS NOT NULL AND package_id LIKE '0x%';"}, {"role": "user", "content": "Now sort these results by name in ascending order."}, {"role": "assistant", "content": "SELECT name, collection_type, display FROM sui_nfts WHERE owner IS NOT NULL AND package_id LIKE '0x%' ORDER BY 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 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": "Show me all contracts deployed on the 'ethereum' network along with their deployer addresses and deployment timestamps, sorted by the most recent deployments first."}, {"role": "assistant", "content": "SELECT address, deployer_address, deployed_at FROM web3.contracts WHERE network_id = 'ethereum' ORDER BY deployed_at DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE web3.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": "How many employees work in each department? List the department name and the count."}, {"role": "assistant", "content": "SELECT department, COUNT(*) FROM government_services.employees GROUP BY department"}, {"role": "user", "content": "Only show departments with more than 5 employees."}, {"role": "assistant", "content": "SELECT department, COUNT(*) FROM government_services.employees GROUP BY department HAVING COUNT(*) > 5"}, {"role": "user", "content": "For these departments, also list the job titles present."}, {"role": "assistant", "content": "SELECT department, COUNT(*), STRING_AGG(DISTINCT job_title, ', ') FROM government_services.employees GROUP BY department HAVING COUNT(*) > 5"}, {"role": "user", "content": "Add the total number of employees hired in 2023 for each of these departments."}, {"role": "assistant", "content": "SELECT department, COUNT(*), STRING_AGG(DISTINCT job_title, ', '), SUM(CASE WHEN EXTRACT(YEAR FROM hire_date) = 2023 THEN 1 ELSE 0 END) AS employees_hired_in_2023 FROM government_services.employees GROUP BY department HAVING COUNT(*) > 5"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.citizens ( citizen_id text, national_id_number text, first_name text, last_name text, date_of_birth date, gender text, primary_address text, contact_email text, contact_phone text, registration_date timestamp, is_verified boolean )\nCREATE TABLE government_services.agencies ( agency_id text, agency_name text, jurisdiction_level text, primary_contact_email text, main_phone_number text, website_url text, established_date date, parent_agency_id text )\nCREATE TABLE government_services.services (\n service_id character varying(64) NOT NULL, -- unique identifier for the service\n agency_id character varying(64) NOT NULL, -- FK to agencies table\n service_name character varying(255) NOT NULL, -- name of the service (e.g., Driver's License Renewal)\n description text,\n category character varying(100), -- e.g., Licensing, Benefits, Taxation, Permits\n eligibility_criteria text, -- description of who is eligible\n standard_fee numeric(10, 2) DEFAULT 0.00, -- typical fee for the service\n average_processing_time_days integer, -- estimated processing time\n is_active boolean DEFAULT true, -- whether the service is currently offered\n online_application_url character varying(255),\n PRIMARY KEY (service_id)\n)\nCREATE TABLE government_services.employees ( employee_id text, agency_id text, first_name text, last_name text, job_title text, department text, work_email text, work_phone text, hire_date date, termination_date date, access_level text, manager_employee_id text )\nCREATE TABLE government_services.service_locations ( location_id character varying(64) NOT NULL, agency_id character varying(64) NOT NULL, location_name character varying(200), address text NOT NULL, city character varying(100), state character varying(50), postal_code character varying(20), latitude numeric(9, 6), longitude numeric(9, 6), operating_hours text, contact_phone character varying(32), is_accessible boolean, PRIMARY KEY (location_id) )\nCREATE TABLE government_services.appointments ( appointment_id.text, citizen_id.text, employee_id.text, location_id.text, service_id.text, scheduled_start_time.timestamp, scheduled_end_time.timestamp, purpose.text, status.text, booking_method.text, created_at.timestamp, notes.text )\n"} {"conversations": [{"role": "user", "content": "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 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": "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": "Retrieve all prescriptions linked to chronic diagnoses. Show prescription_id, diagnosis_id, diagnosis_code, and prescription_date."}, {"role": "assistant", "content": "SELECT pr.prescription_id,\n d.diagnosis_id,\n d.diagnosis_code,\n pr.prescription_date\nFROM healthcare.prescriptions pr\nJOIN healthcare.diagnoses d\n ON pr.record_id = d.record_id\nWHERE d.is_chronic = true;"}, {"role": "user", "content": "Include the patient's full name and the prescribing doctor's last name, and sort by prescription_date ascending."}, {"role": "assistant", "content": "SELECT pr.prescription_id,\n d.diagnosis_id,\n d.diagnosis_code,\n pr.prescription_date,\n p.first_name || ' ' || p.last_name AS patient_name,\n doc.last_name AS doctor_last_name\nFROM healthcare.prescriptions pr\nJOIN healthcare.diagnoses d\n ON pr.record_id = d.record_id\nJOIN healthcare.patients p\n ON pr.patient_id = p.patient_id\nJOIN healthcare.doctors doc\n ON pr.doctor_id = doc.doctor_id\nWHERE d.is_chronic = true\nORDER BY pr.prescription_date ASC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.patients ( patient_id.text, first_name.text, last_name.text, date_of_birth.date, gender.text, address.text, phone_number.text, email.text, emergency_contact_name.text, emergency_contact_phone.text, created_at.timestamp, updated_at.timestamp )\nCREATE TABLE healthcare.doctors (\n doctor_id character varying(64) NOT NULL, -- unique identifier for the doctor\n first_name character varying(100) NOT NULL, -- doctor's first name\n last_name character varying(100) NOT NULL, -- doctor's last name\n specialty character varying(100) NOT NULL, -- doctor's medical specialty\n license_number character varying(50) UNIQUE NOT NULL, -- doctor's medical license number\n phone_number character varying(20), -- doctor's contact phone\n email character varying(128) UNIQUE, -- doctor's contact email\n hospital_affiliation_id character varying(64), -- FK to hospitals table (optional)\n created_at timestamp with time zone NOT NULL DEFAULT current_timestamp,\n updated_at timestamp with time zone NOT NULL DEFAULT current_timestamp,\n PRIMARY KEY (doctor_id)\n)\nCREATE TABLE healthcare.appointments ( appointment_id.text, patient_id.text, doctor_id.text, appointment_time.timestamp, duration_minutes.integer, reason.text, status.text, location_id.text, notes.text, created_at.timestamp )\nCREATE TABLE healthcare.medical_records (\n record_id character varying(64) NOT NULL, -- unique identifier for the medical record entry\n patient_id character varying(64) NOT NULL, -- FK to patients table\n appointment_id character varying(64) UNIQUE, -- FK to appointments table (can be null if record not tied to specific appt)\n doctor_id character varying(64) NOT NULL, -- FK to doctors table (doctor creating the record)\n record_date timestamp with time zone NOT NULL, -- date the record/observation was made\n chief_complaint text, -- patient's primary reason for visit\n present_illness_history text, -- detailed history of the current issue\n past_medical_history text, -- relevant past conditions/surgeries\n physical_examination_notes text, -- findings from the physical exam\n assessment text, -- doctor's assessment/diagnosis summary\n treatment_plan text, -- planned course of action\n vitals jsonb, -- store vitals like BP, HR, Temp as structured JSON\n created_at timestamp with time zone NOT NULL DEFAULT current_timestamp,\n PRIMARY KEY (record_id)\n)\nCREATE TABLE healthcare.diagnoses (\n diagnosis_id character varying(64) NOT NULL, -- unique identifier for the diagnosis entry\n record_id character varying(64) NOT NULL, -- FK linking to the specific medical record entry\n patient_id character varying(64) NOT NULL, -- FK to patients table\n doctor_id character varying(64) NOT NULL, -- FK to doctors table (diagnosing doctor)\n diagnosis_code character varying(20) NOT NULL, -- standard code (e.g., ICD-10)\n code_type character varying(10) NOT NULL DEFAULT 'ICD-10', -- type of code used\n description text, -- textual description of the diagnosis\n diagnosis_date date NOT NULL, -- date the diagnosis was made\n status character varying(32) NOT NULL, -- e.g., Active, Resolved, Ruled Out\n is_chronic boolean DEFAULT false, -- flag for chronic conditions\n PRIMARY KEY (diagnosis_id)\n)\nCREATE TABLE healthcare.medications ( medication_id text, medication_name text, generic_name text, manufacturer text, ndc_code text, description text )\nCREATE TABLE healthcare.prescriptions ( prescription_id text, record_id text, patient_id text, doctor_id text, medication_id text, dosage text, frequency text, route text, start_date date, end_date date, quantity_dispensed numeric, refills_allowed integer, prescription_date timestamp )\nCREATE TABLE healthcare.insurance_plans ( plan_id text, plan_name text, insurance_provider text, plan_type text, contact_phone text, website text )\n"} {"conversations": [{"role": "user", "content": "For each event recorded, list its ID, name, and the status and value of the transaction in which it occurred."}, {"role": "assistant", "content": "SELECT E.event_id, E.event_name, E.transaction_id, T.status, T.value FROM web3.events AS E JOIN web3.transactions AS T ON E.transaction_id = T.transaction_id;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE web3.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 ( transaction_id character varying(64) NOT NULL, from_address character varying(128) NOT NULL, to_address character varying(128), value numeric(38,14) NOT NULL, gas_used integer NOT NULL, gas_price numeric(38,14) NOT NULL, block_number integer NOT NULL, timestamp timestamp NOT NULL, input_data text, status character varying(32) NOT NULL, nonce integer NOT NULL, PRIMARY KEY (transaction_id) )\nCREATE TABLE web3.tokens ( token_id text PRIMARY KEY, contract_address text, token_name text, token_symbol text, decimals int, total_supply numeric )\nCREATE TABLE web3.wallets ( wallet_id text, user_id text, address text, private_key text, created_at timestamp )\nCREATE TABLE web3.users ( user_id text, username text, email text, password_hash text, created_at timestamp )\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": "Show me the total number of items acquired per player for each item type, along with the player's username."}, {"role": "assistant", "content": "SELECT p.player_id, p.username, igi.item_type, SUM(pi.quantity) AS total_acquired\nFROM gaming_technology.player_inventory pi\nJOIN gaming_technology.players p ON pi.player_id = p.player_id\nJOIN gaming_technology.in_game_items igi ON pi.item_id = igi.item_id\nGROUP BY p.player_id, p.username, igi.item_type;"}, {"role": "user", "content": "Can you filter this to only include item types 'Weapon' and 'Armor'?"}, {"role": "assistant", "content": "SELECT p.player_id, p.username, igi.item_type, SUM(pi.quantity) AS total_acquired\nFROM gaming_technology.player_inventory pi\nJOIN gaming_technology.players p ON pi.player_id = p.player_id\nJOIN gaming_technology.in_game_items igi ON pi.item_id = igi.item_id\nWHERE igi.item_type IN ('Weapon', 'Armor')\nGROUP BY p.player_id, p.username, igi.item_type;"}, {"role": "user", "content": "Actually, I want to see only those players who have acquired more than 5 of either item type."}, {"role": "assistant", "content": "SELECT p.player_id, p.username, igi.item_type, SUM(pi.quantity) AS total_acquired\nFROM gaming_technology.player_inventory pi\nJOIN gaming_technology.players p ON pi.player_id = p.player_id\nJOIN gaming_technology.in_game_items igi ON pi.item_id = igi.item_id\nWHERE igi.item_type IN ('Weapon', 'Armor')\nGROUP BY p.player_id, p.username, igi.item_type\nHAVING SUM(pi.quantity) > 5;"}, {"role": "user", "content": "Please also include the player's registration_date in the result."}, {"role": "assistant", "content": "SELECT p.player_id, p.username, p.registration_date, igi.item_type, SUM(pi.quantity) AS total_acquired\nFROM gaming_technology.player_inventory pi\nJOIN gaming_technology.players p ON pi.player_id = p.player_id\nJOIN gaming_technology.in_game_items igi ON pi.item_id = igi.item_id\nWHERE igi.item_type IN ('Weapon', 'Armor')\nGROUP BY p.player_id, p.username, p.registration_date, igi.item_type\nHAVING SUM(pi.quantity) > 5;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE gaming_technology.players ( player_id uuid NOT NULL DEFAULT gen_random_uuid(), username character varying(100) NOT NULL UNIQUE, email character varying(255) NOT NULL UNIQUE, password_hash text NOT NULL, registration_date timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP, last_login timestamp with time zone, country_code character(2), status character varying(20) NOT NULL DEFAULT 'active', profile_data jsonb, PRIMARY KEY (player_id) )\nCREATE TABLE gaming_technology.developers ( developer_id.uuid, name.text, country.text, founded_year.integer, website.text, created_at.timestamptz )\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, 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.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 ( inventory_id uuid NOT NULL DEFAULT gen_random_uuid(), player_id uuid NOT NULL, item_id uuid NOT NULL, quantity integer NOT NULL DEFAULT 1, acquired_at timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP, instance_data jsonb, PRIMARY KEY (inventory_id) )\n"} {"conversations": [{"role": "user", "content": "List 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": "What is the history of incidents or accidents that occurred on platform 5 at station GHI?"}, {"role": "assistant", "content": "I'm sorry, but I can't provide information about the history of incidents or accidents on platform 5 at station GHI. My data is limited to the structural and operational details of the platforms, such as platform ID, station ID, and status. For incident history, you may need to consult a different database or contact the relevant authorities."}], "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": "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": "List all clients along with their case_number and case_type for cases that are currently 'Open'."}, {"role": "assistant", "content": "SELECT c.first_name, c.last_name, c.email, cs.case_number, cs.case_type\nFROM legal_services.clients AS c\nJOIN legal_services.cases AS cs\n ON c.client_id = cs.client_id\nWHERE cs.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.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.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) )\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.documents ( document_id character varying(64) NOT NULL, case_id character varying(64) NOT NULL, document_name character varying(255) NOT NULL, document_type character varying(100), storage_path text NOT NULL, uploaded_by_lawyer_id character varying(64), upload_timestamp timestamp NOT NULL, version integer DEFAULT 1, description text, PRIMARY KEY (document_id) )\nCREATE TABLE legal_services.time_entries ( entry_id character varying(64) NOT NULL, case_id character varying(64) NOT NULL, lawyer_id character varying(64) NOT NULL, date_worked date NOT NULL, hours_spent numeric(5, 2) NOT NULL CHECK (hours_spent > 0), billing_rate numeric(10, 2) NOT NULL, description text NOT NULL, is_billable boolean DEFAULT true, is_billed boolean DEFAULT false, invoice_id character varying(64), created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, PRIMARY KEY (entry_id) )\nCREATE TABLE legal_services.appointments ( appointment_id character varying(64) NOT NULL, client_id character varying(64) NOT NULL, lawyer_id character varying(64) NOT NULL, case_id character varying(64), start_time timestamp NOT NULL, end_time timestamp NOT NULL, location text, subject character varying(255), notes text, status character varying(50) NOT NULL, created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, PRIMARY KEY (appointment_id) )\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": "List all diagnoses made in the last month including diagnosis_date, patient full name, doctor's full name, and description."}, {"role": "assistant", "content": "SELECT d.diagnosis_date,\n p.first_name || ' ' || p.last_name AS patient_name,\n doc.first_name || ' ' || doc.last_name AS doctor_name,\n d.description\nFROM healthcare.diagnoses AS d\nJOIN healthcare.patients AS p\n ON d.patient_id = p.patient_id\nJOIN healthcare.doctors AS doc\n ON d.doctor_id = doc.doctor_id\nWHERE d.diagnosis_date >= CURRENT_DATE - INTERVAL '1 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 healthcare.patients ( patient_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, date_of_birth date NOT NULL, gender character varying(10), address text, phone_number character varying(20), email character varying(128) UNIQUE, emergency_contact_name character varying(200), emergency_contact_phone character varying(20), created_at timestamp with time zone NOT NULL DEFAULT current_timestamp, updated_at timestamp with time zone NOT NULL DEFAULT current_timestamp, PRIMARY KEY (patient_id) )\nCREATE TABLE healthcare.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.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 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) )\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 ( 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": "For each vehicle, list its vehicle_id, license_plate, and any older vehicle of the same type (showing older_vehicle_id and older year)."}, {"role": "assistant", "content": "SELECT cur.vehicle_id,\n cur.license_plate,\n old.vehicle_id AS older_vehicle_id,\n old.year AS older_vehicle_year\nFROM transportation.vehicles cur\nJOIN transportation.vehicles old\n ON cur.type = old.type\n AND old.year < cur.year\nORDER BY cur.vehicle_id, old.year DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.vehicles (\n vehicle_id character varying(64) NOT NULL, -- unique identifier for the vehicle\n license_plate character varying(32) NOT NULL UNIQUE, -- vehicle license plate\n vin character varying(17) UNIQUE, -- vehicle identification number\n make character varying(64) NOT NULL, -- manufacturer of the vehicle\n model character varying(64) NOT NULL, -- model of the vehicle\n year integer NOT NULL, -- manufacturing year\n type character varying(32) NOT NULL, -- type of vehicle (e.g., Bus, Train, Truck, Car, Van)\n capacity integer, -- passenger or cargo capacity\n fuel_type character varying(32) NOT NULL, -- e.g., Diesel, Gasoline, Electric, Hydrogen\n status character varying(32) NOT NULL, -- e.g., Active, Maintenance, Decommissioned\n depot_id character varying(64), -- identifier of the home depot/base\n acquisition_date date, -- date the vehicle was acquired\n PRIMARY KEY (vehicle_id)\n)\n"} {"conversations": [{"role": "user", "content": "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": "Retrieve each prescription's id, patient's full name, medication_name, and prescription_date for prescriptions where dosage contains 'tablet'."}, {"role": "assistant", "content": "SELECT pr.prescription_id, CONCAT(p.first_name, ' ', p.last_name) AS patient_name, m.medication_name, pr.prescription_date\nFROM healthcare.prescriptions pr\nJOIN healthcare.patients p\n ON pr.patient_id = p.patient_id\nJOIN healthcare.medications m\n ON pr.medication_id = m.medication_id\nWHERE pr.dosage ILIKE '%tablet%';"}, {"role": "user", "content": "Also include the prescribing doctor's first and last name, and only show prescriptions after January 1st, 2024."}, {"role": "assistant", "content": "SELECT pr.prescription_id, CONCAT(p.first_name, ' ', p.last_name) AS patient_name, m.medication_name, CONCAT(d.first_name, ' ', d.last_name) AS doctor_name, pr.prescription_date\nFROM healthcare.prescriptions pr\nJOIN healthcare.patients p ON pr.patient_id = p.patient_id\nJOIN healthcare.medications m ON pr.medication_id = m.medication_id\nJOIN healthcare.doctors d ON pr.doctor_id = d.doctor_id\nWHERE pr.dosage ILIKE '%tablet%' AND pr.prescription_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 healthcare.patients ( patient_id.text, first_name.text, last_name.text, date_of_birth.date, gender.text, address.text, phone_number.text, email.text, emergency_contact_name.text, emergency_contact_phone.text, created_at.timestamp, updated_at.timestamp )\nCREATE TABLE healthcare.doctors (\n doctor_id character varying(64) NOT NULL, -- unique identifier for the doctor\n first_name character varying(100) NOT NULL, -- doctor's first name\n last_name character varying(100) NOT NULL, -- doctor's last name\n specialty character varying(100) NOT NULL, -- doctor's medical specialty\n license_number character varying(50) UNIQUE NOT NULL, -- doctor's medical license number\n phone_number character varying(20), -- doctor's contact phone\n email character varying(128) UNIQUE, -- doctor's contact email\n hospital_affiliation_id character varying(64), -- FK to hospitals table (optional)\n created_at timestamp with time zone NOT NULL DEFAULT current_timestamp,\n updated_at timestamp with time zone NOT NULL DEFAULT current_timestamp,\n PRIMARY KEY (doctor_id)\n)\nCREATE TABLE healthcare.appointments ( appointment_id.text, patient_id.text, doctor_id.text, appointment_time.timestamp, duration_minutes.integer, reason.text, status.text, location_id.text, notes.text, created_at.timestamp )\nCREATE TABLE healthcare.medical_records (\n record_id character varying(64) NOT NULL, -- unique identifier for the medical record entry\n patient_id character varying(64) NOT NULL, -- FK to patients table\n appointment_id character varying(64) UNIQUE, -- FK to appointments table (can be null if record not tied to specific appt)\n doctor_id character varying(64) NOT NULL, -- FK to doctors table (doctor creating the record)\n record_date timestamp with time zone NOT NULL, -- date the record/observation was made\n chief_complaint text, -- patient's primary reason for visit\n present_illness_history text, -- detailed history of the current issue\n past_medical_history text, -- relevant past conditions/surgeries\n physical_examination_notes text, -- findings from the physical exam\n assessment text, -- doctor's assessment/diagnosis summary\n treatment_plan text, -- planned course of action\n vitals jsonb, -- store vitals like BP, HR, Temp as structured JSON\n created_at timestamp with time zone NOT NULL DEFAULT current_timestamp,\n PRIMARY KEY (record_id)\n)\nCREATE TABLE healthcare.diagnoses (\n diagnosis_id character varying(64) NOT NULL, -- unique identifier for the diagnosis entry\n record_id character varying(64) NOT NULL, -- FK linking to the specific medical record entry\n patient_id character varying(64) NOT NULL, -- FK to patients table\n doctor_id character varying(64) NOT NULL, -- FK to doctors table (diagnosing doctor)\n diagnosis_code character varying(20) NOT NULL, -- standard code (e.g., ICD-10)\n code_type character varying(10) NOT NULL DEFAULT 'ICD-10', -- type of code used\n description text, -- textual description of the diagnosis\n diagnosis_date date NOT NULL, -- date the diagnosis was made\n status character varying(32) NOT NULL, -- e.g., Active, Resolved, Ruled Out\n is_chronic boolean DEFAULT false, -- flag for chronic conditions\n PRIMARY KEY (diagnosis_id)\n)\nCREATE TABLE healthcare.medications ( medication_id text, medication_name text, generic_name text, manufacturer text, ndc_code text, description text )\nCREATE TABLE healthcare.prescriptions ( prescription_id text, record_id text, patient_id text, doctor_id text, medication_id text, dosage text, frequency text, route text, start_date date, end_date date, quantity_dispensed numeric, refills_allowed integer, prescription_date timestamp )\n"} {"conversations": [{"role": "user", "content": "List all pairs of cases that share the same court jurisdiction, including both case names and their common jurisdiction."}, {"role": "assistant", "content": "SELECT c1.case_name AS case_name_1, c2.case_name AS case_name_2, c1.court_jurisdiction\nFROM legal_services.cases c1\nJOIN legal_services.cases c2\n ON c1.court_jurisdiction = c2.court_jurisdiction\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": "How many wallets has each user created since '2024-07-01'?"}, {"role": "assistant", "content": "SELECT user_id,\n COUNT(*) AS wallet_count\nFROM trading_platform.wallets\nWHERE created_at >= '2024-07-01'\nGROUP BY user_id;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE trading_platform.wallets ( wallet_id text, user_id text, address text, private_key text, created_at timestamp )\n"} {"conversations": [{"role": "user", "content": "Show the number of trips operated by each driver along with the earliest and latest scheduled departure dates for them."}, {"role": "assistant", "content": "SELECT driver_id, COUNT(*) AS trip_count, MIN(scheduled_departure) AS first_departure, MAX(scheduled_departure) AS last_departure FROM transportation.trips GROUP BY driver_id;"}, {"role": "user", "content": "Can you limit this to only include drivers who have operated more than 5 trips?"}, {"role": "assistant", "content": "SELECT driver_id, COUNT(*) AS trip_count, MIN(scheduled_departure) AS first_departure, MAX(scheduled_departure) AS last_departure FROM transportation.trips GROUP BY driver_id HAVING COUNT(*) > 5;"}, {"role": "user", "content": "Add the total number of passengers transported by each driver."}, {"role": "assistant", "content": "SELECT driver_id, COUNT(*) AS trip_count, SUM(passenger_count) AS total_passengers, MIN(scheduled_departure) AS first_departure, MAX(scheduled_departure) AS last_departure FROM transportation.trips GROUP BY driver_id HAVING COUNT(*) > 5;"}, {"role": "user", "content": "Also, sort the result by total_passengers in descending order."}, {"role": "assistant", "content": "SELECT driver_id, COUNT(*) AS trip_count, SUM(passenger_count) AS total_passengers, MIN(scheduled_departure) AS first_departure, MAX(scheduled_departure) AS last_departure FROM transportation.trips GROUP BY driver_id HAVING COUNT(*) > 5 ORDER BY total_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.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 )\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": "List all beneficiaries who do not have any contact information provided. Show beneficiary_id, first_name, and last_name."}, {"role": "assistant", "content": "SELECT beneficiary_id, first_name, last_name FROM insurance.policy_beneficiaries WHERE contact_info IS NULL OR contact_info = ''"}], "system": "You are an SQL statement expert. Given the table structure 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.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": "Count the total number of invoices issued in each calendar year and month. Show the year, month, and the count, ordered chronologically."}, {"role": "assistant", "content": "SELECT EXTRACT(YEAR FROM issue_date) AS issue_year, EXTRACT(MONTH FROM issue_date) AS issue_month, COUNT(*) AS invoice_count FROM legal_services.invoices GROUP BY issue_year, issue_month ORDER BY issue_year, issue_month;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.invoices ( invoice_id.text, invoice_number.text, client_id.text, case_id.text, issue_date.date, due_date.date, total_amount.numeric, amount_paid.numeric, status.text, payment_date.timestamp, notes.text, created_at.timestamp )\n"} {"conversations": [{"role": "user", "content": "Show me all trips along with the vehicle make and the route distance in km."}, {"role": "assistant", "content": "SELECT t.trip_id, v.make, r.distance_km\nFROM transportation.trips t\nJOIN transportation.vehicles v ON t.vehicle_id = v.vehicle_id\nJOIN transportation.routes r ON t.route_id = r.route_id;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.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.routes ( route_id.text, route_number.text, description.text, origin_location_id.text, destination_location_id.text, distance_km.numeric, estimated_duration_minutes.integer, type.text )\nCREATE TABLE transportation.trips ( trip_id text 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.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 patients who have been prescribed medications with dosage greater than 50mg, along with their medication details and prescribing doctor's name."}, {"role": "assistant", "content": "SELECT p.patient_id, p.first_name, p.last_name, pr.dosage, pr.medication_id, pr.start_date, doc.first_name AS doctor_first_name, doc.last_name AS doctor_last_name FROM healthcare.patients p JOIN healthcare.prescriptions pr ON p.patient_id = pr.patient_id JOIN healthcare.doctors doc ON pr.doctor_id = doc.doctor_id WHERE CAST(SUBSTRING_INDEX(pr.dosage, 'mg', 1) AS UNSIGNED) > 50;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE healthcare.patients ( patient_id.text, first_name.text, last_name.text, date_of_birth.date, gender.text, address.text, phone_number.text, email.text, emergency_contact_name.text, emergency_contact_phone.text, created_at.timestamp, updated_at.timestamp )\nCREATE TABLE healthcare.appointments ( appointment_id.text, patient_id.text, doctor_id.text, appointment_time.timestamp, duration_minutes.integer, reason.text, status.text, location_id.text, notes.text, created_at.timestamp )\nCREATE TABLE healthcare.diagnoses ( diagnosis_id.text, record_id.text, patient_id.text, doctor_id.text, diagnosis_code.text, code_type.text, description.text, diagnosis_date.date, status.text, is_chronic.boolean )\nCREATE TABLE healthcare.prescriptions ( prescription_id.text, record_id.text, patient_id.text, doctor_id.text, medication_id.text, dosage.text, frequency.text, route.text, start_date.date, end_date.date, quantity_dispensed.numeric, refills_allowed.integer, prescription_date.timestamp )\nCREATE TABLE healthcare.insurance_plans ( plan_id.text, plan_name.text, insurance_provider.text, plan_type.text, contact_phone.text, website.text )\n"} {"conversations": [{"role": "user", "content": "Can you list the names of agencies that do not have a parent agency assigned, ordered by their established date?"}, {"role": "assistant", "content": "SELECT agency_id, agency_name, established_date\nFROM government_services.agencies\nWHERE parent_agency_id IS NULL\nORDER BY established_date;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.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 )\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": "Show me the top 5 NFT collections with the highest floor price on Ethereum, along with their names and contract addresses."}, {"role": "assistant", "content": "SELECT name, contract_address, floor_price FROM nft_collections WHERE blockchain = 'ethereum' ORDER BY CAST(floor_price AS decimal) DESC LIMIT 5;"}, {"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, floor_price, banner_image_url FROM nft_collections WHERE blockchain = 'ethereum' AND erc_type = 'ERC721' ORDER BY CAST(floor_price AS decimal) DESC LIMIT 5;"}, {"role": "user", "content": "I think there's a typo in your query - it should be 'nft_collections' not 'nft_collections'. Also, can you join this with the nft_metadata table to include the average rarity score for these collections?"}, {"role": "assistant", "content": "SELECT nc.name, nc.contract_address, nc.floor_price, nc.banner_image_url, AVG(nm.rarity_score) as avg_rarity_score FROM nft_collections nc JOIN nft_metadata nm ON nc.contract_address = nm.contract_address WHERE nc.blockchain = 'ethereum' AND nc.erc_type = 'ERC721' GROUP BY nc.name, nc.contract_address, nc.floor_price, nc.banner_image_url ORDER BY CAST(nc.floor_price AS decimal) DESC LIMIT 5;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE erc1155_approval_for_all (\n block_number bigint NOT NULL, -- Block number containing the transaction\n block_timestamp timestamp(3) NOT NULL, -- Timestamp of the block containing the transaction\n transaction_index integer NOT NULL, -- Index of the transaction within the block\n transaction_hash varchar(66) NOT NULL, -- Transaction hash\n log_index integer NOT NULL, -- Log index\n contract_address varchar(42) NOT NULL -- Event contract address\n)\nCREATE TABLE erc20_balances ( block_number.bigint, contract_address.text, wallet_address.text, amount.text, pk.text )\nCREATE TABLE erc20_balances_historical ( block_number bigint NOT NULL, contract_address varchar NOT NULL, wallet_address varchar NOT NULL, amount varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE nft_metadata (\n blockchain varchar NOT NULL, -- blockchain fields for the functionType in contract\n contract_address varchar NOT NULL, -- Contract address(with bloom filter)\n token_id varchar NOT NULL, -- The number of the token\n contract_name varchar NOT NULL, -- contract_name fields for the functionType in contract\n erc_type varchar NOT NULL, -- The type of token\n amount bigint NOT NULL, -- amount fields for the functionType in contract\n minter varchar NOT NULL, -- minter fields for the functionType in contract\n owner varchar NOT NULL, -- owner fields for the functionType in contract\n mint_block_number bigint NOT NULL, -- mint_block_number fields for the functionType in contract\n mint_time bigint NOT NULL, -- mint_time fields for the functionType in contract\n mint_transaction_hash varchar NOT NULL, -- mint_transaction_hash fields for the functionType in contract\n mint_price varchar NOT NULL, -- mint_price fields for the functionType in contract\n token_uri varchar NOT NULL, -- token_uri fields for the functionType in contract\n metadata varchar NOT NULL, -- metadata fields for the functionType in contract\n name varchar NOT NULL, -- name fields for the functionType in contract\n image_uri varchar NOT NULL, -- image_uri fields for the functionType in contract\n traits varchar NOT NULL, -- traits fields for the functionType in contract\n updated_at bigint NOT NULL, -- updated_at fields for the functionType in contract\n status varchar NOT NULL, -- status fields for the functionType in contract\n rarity_score real NOT NULL, -- rarity_score fields for the functionType in contract\n rarity_rank integer NOT NULL, -- rarity_rank fields for the functionType in contract\n unique_attribute_count integer NOT NULL, -- unique_attribute_count fields for the functionType in contract\n pk integer NOT NULL -- Partition key for the table(floor(mint_time / 1000 / 86400 / 30))\n)\nCREATE TABLE nft_collections ( blockchain.text, contract_address.text, name.text, symbol.text, deploy_block_number.bigint, deploy_block_time.bigint, erc_type.text, owner.text, traits.text, description.text, slug.text, media_info.text, image_url.text, banner_image_url.text, updated_at.bigint, banner.text, token_count.bigint, floor_price.text, floor_price_symbol.text, floor_price_contract.text, pk.integer )\nCREATE TABLE token_prices ( uuid varchar(36) NOT NULL, blockchain varchar(36) NOT NULL, address varchar(42) NOT NULL, decimals bigint NOT NULL, symbol varchar(36) NOT NULL, price real NOT NULL, timestamp timestamp(6) NOT NULL )\nCREATE TABLE erc20_approval ( block_number bigint NOT NULL, block_timestamp timestamp(6) NOT NULL, transaction_index integer NOT NULL, transaction_hash varchar NOT NULL, log_index integer NOT NULL, contract_address varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE token_info ( block_timestamp timestamp(3) NOT NULL, block_number bigint NOT NULL, tx_index integer NOT NULL, tx_hash varchar(66) NOT NULL, tick varchar NOT NULL, max_supply decimal(38,0) NOT NULL, lim decimal(38,0) NOT NULL, wlim decimal(38,0) NOT NULL, dec integer NOT NULL, creator varchar(42) NOT NULL )\nCREATE TABLE mud_holesky_redstone (\n address varchar NOT NULL, -- address fields for the functionType in contract\n table_id varchar NOT NULL, -- table_id fields for the functionType in contract\n key_bytes varchar NOT NULL, -- key_bytes fields for the functionType in contract\n key0 varchar NOT NULL, -- key0 fields for the functionType in contract\n key1 varchar NOT NULL, -- key1 fields for the functionType in contract\n static_data varchar NOT NULL, -- static_data fields for the functionType in contract\n encoded_lengths varchar NOT NULL, -- encoded_lengths fields for the functionType in contract\n dynamic_data varchar NOT NULL, -- dynamic_data fields for the functionType in contract\n is_deleted boolean NOT NULL, -- is_deleted fields for the functionType in contract\n block_number bigint NOT NULL, -- Block number uniquely identifying the block\n log_index bigint NOT NULL -- Index of the log within the transaction\n)\nCREATE TABLE token_info_bitcoin ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash varchar, tick varchar, max_supply decimal, lim decimal, wlim decimal, dec integer, creator varchar )\nCREATE TABLE token_info_avalanche ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash text, tick text, max_supply decimal, lim decimal, wlim decimal, dec integer, creator text, minted decimal, holders decimal, txs decimal, updated_timestamp timestamp, completed_timestamp timestamp, id text )\n"} {"conversations": [{"role": "user", "content": "How many tokens had a net positive flow according to smart_money_token_performance, and what is their average ROI?"}, {"role": "assistant", "content": "SELECT COUNT(*) AS token_count, AVG(roi) AS avg_roi\nFROM smart_money_token_performance\nWHERE net_flow > 0;"}, {"role": "user", "content": "Now, break this down by chain, and order the results by avg_roi descending."}, {"role": "assistant", "content": "SELECT chain, COUNT(*) AS token_count, AVG(roi) AS avg_roi\nFROM smart_money_token_performance\nWHERE net_flow > 0\nGROUP BY chain\nORDER BY avg_roi DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\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": "For wallet '0x...', list the token IDs of the NFTs currently held, the name of their collection, and that collection's floor price."}, {"role": "assistant", "content": "SELECT T1.token_id, T2.name, T2.floor_price FROM nft_holders AS T1 INNER JOIN nft_collections AS T2 ON T1.contract_address = T2.contract_address WHERE T1.wallet_address = '0x...';"}], "system": "You are an expert in writing database language. You can write a corresponding database language query to answer the user's question based on the table structure described by the table creation statement. \n##Table Structure\nCREATE TABLE token_metas ( block_timestamp timestamp, block_number bigint, transaction_hash text, transaction_index bigint, from_address text, contract_address text, symbol text, total_supply text, name text, decimals bigint, is_erc20 integer, is_erc721 integer, is_erc1155 integer, is_proxy integer, extra_info text, pk integer )\nCREATE TABLE erc1155_approval_for_all ( block_number bigint, block_timestamp timestamp, transaction_index integer, transaction_hash text, log_index integer, contract_address text )\nCREATE TABLE erc20_balances ( block_number bigint, contract_address text, wallet_address text, amount text, pk text )\nCREATE TABLE erc20_balances_historical ( block_number bigint, contract_address text, wallet_address text, amount text, pk integer )\nCREATE TABLE nft_holders ( block_number bigint, contract_address text, wallet_address text, token_id text, contract_type text, amount text, pk text )\nCREATE TABLE nft_holder_historical ( block_number bigint, contract_address text, wallet_address text, token_id text, contract_type text, amount text, pk integer )\nCREATE TABLE sui_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 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_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_balances_bitcoin ( block_number bigint, block_timestamp timestamp, tick text, wallet_address text, total_supply text, amount text )\nCREATE TABLE token_info_bitcoin ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash text, tick text, max_supply decimal, lim decimal, wlim decimal, dec integer, creator text )\nCREATE TABLE token_activities_bitcoin ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash text, log_index integer, type text, tick text, id text, amt decimal, from_address text, to_address text )\nCREATE TABLE token_activities_avalanche ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash text, log_index integer, type text, tick text, id text, amt decimal, from_address text, to_address text )\nCREATE TABLE token_balances_avalanche ( block_number bigint, block_timestamp timestamp, tick text, wallet_address text, total_supply decimal, amount decimal )\nCREATE TABLE token_info_avalanche ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash text, tick text, max_supply decimal, lim decimal, wlim decimal, dec integer, creator text, minted decimal, holders decimal, txs decimal, updated_timestamp timestamp, completed_timestamp timestamp, id text )\n"} {"conversations": [{"role": "user", "content": "List all 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": "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": "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": "Can you provide the total number of fuel refueling events and the sum of total_cost at each fueling location, including the location name and city?"}, {"role": "assistant", "content": "SELECT l.location_id, l.name, l.city, COUNT(fl.fuel_log_id) AS num_refuels, SUM(fl.total_cost) AS total_cost\nFROM transportation.fuel_logs fl\nJOIN transportation.locations l ON fl.location_id = l.location_id\nGROUP BY l.location_id, l.name, l.city;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE transportation.vehicles ( vehicle_id.text, license_plate.text, vin.text, make.text, model.text, year.integer, type.text, capacity.integer, fuel_type.text, status.text, depot_id.text, acquisition_date.date )\nCREATE TABLE transportation.drivers ( driver_id.text, employee_id.text, first_name.text, last_name.text, license_number.text, license_expiry_date.date, contact_number.text, email.text, hire_date.date, status.text )\nCREATE TABLE transportation.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": "Show me all home loans (loan_id, principal_amount, interest_rate) where the current principal balance is more than 75% of the original principal amount, along with the account_id and employee details (first_name, last_name) of the employee who processed the loan application."}, {"role": "assistant", "content": "SELECT l.loan_id, l.principal_amount, l.interest_rate, l.account_id, e.first_name, e.last_name FROM financial_services.loans l JOIN financial_services.employees e ON l.account_id = e.employee_id WHERE l.loan_type = 'Home' AND l.current_principal_balance > (l.principal_amount * 0.75)"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE financial_services.transactions ( transaction_id.text, account_id.text, related_account_id.text, transaction_type.text, amount.numeric, currency.text, transaction_date.timestamp, effective_date.date, description.text, status.text, reference_number.text )\nCREATE TABLE financial_services.securities ( security_id.text, ticker_symbol.text, isin_code.text, cusip_code.text, security_name.text, security_type.text, exchange.text, currency.text, issuer_name.text, sector.text, last_updated.timestamp )\nCREATE TABLE financial_services.market_data ( data_point_id.bigint, security_id.text, data_timestamp.timestamp, open_price.numeric, high_price.numeric, low_price.numeric, close_price.numeric, adjusted_close_price.numeric, volume.bigint, source.text )\nCREATE TABLE financial_services.employees ( employee_id.text, first_name.text, last_name.text, job_title.text, department.text, branch_id.text, email.text, phone_extension.text, hire_date.date, termination_date.date, manager_id.text, status.text )\nCREATE TABLE financial_services.loans ( loan_id.text, account_id.text, loan_type.text, principal_amount.numeric, current_principal_balance.numeric, interest_rate.numeric, term_months.integer, origination_date.date, maturity_date.date, monthly_payment.numeric, collateral_description.text, status.text )\n"} {"conversations": [{"role": "user", "content": "List all distinct job titles present in the organization."}, {"role": "assistant", "content": "SELECT DISTINCT job_title FROM government_services.employees;"}], "system": "You are an SQL statement expert. Given the table structure 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": "List each service_type and the number of maintenance logs performed for that type, only including service_types with more than 10 records."}, {"role": "assistant", "content": "SELECT service_type,\n COUNT(*) AS log_count\nFROM transportation.maintenance_logs\nGROUP BY service_type\nHAVING COUNT(*) > 10;"}, {"role": "user", "content": "Now include the average cost of each service_type and order the results by average cost descending."}, {"role": "assistant", "content": "SELECT service_type,\n COUNT(*) AS log_count,\n AVG(cost) AS avg_cost\nFROM transportation.maintenance_logs\nGROUP BY service_type\nHAVING COUNT(*) > 10\nORDER BY avg_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.vehicles ( vehicle_id.text, license_plate.text, vin.text, make.text, model.text, year.integer, type.text, capacity.integer, fuel_type.text, status.text, depot_id.text, acquisition_date.date )\nCREATE TABLE transportation.trips ( trip_id.text, route_id.text, vehicle_id.text, driver_id.text, scheduled_departure.timestamp, actual_departure.timestamp, scheduled_arrival.timestamp, actual_arrival.timestamp, origin_location_id.text, destination_location_id.text, status.text, passenger_count.integer, cargo_manifest_id.text )\nCREATE TABLE transportation.locations ( location_id.text, name.text, type.text, address_line1.text, city.text, state_province.text, postal_code.text, country.text, latitude.numeric, longitude.numeric, timezone.text )\nCREATE TABLE transportation.maintenance_logs ( log_id.text, vehicle_id.text, service_date.date, odometer_reading.integer, service_type.text, description.text, cost.numeric, mechanic_name.text, next_service_due_date.date )\nCREATE TABLE transportation.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": "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": "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": "List pairs of smoking and non-smoking rooms on the same floor for each property, showing the property_id, floor, smoking room_number, and non_smoking room_number."}, {"role": "assistant", "content": "SELECT r1.property_id,\n r1.floor,\n r1.room_number AS smoking_room,\n r2.room_number AS non_smoking_room\nFROM hospitality_technology.rooms r1\nJOIN hospitality_technology.rooms r2\n ON r1.property_id = r2.property_id\n AND r1.floor = r2.floor\n AND r1.is_smoking = TRUE\n AND r2.is_smoking = FALSE;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE hospitality_technology.rooms ( room_id.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 )\n"} {"conversations": [{"role": "user", "content": "Show me all maintenance logs for vehicles of make 'Toyota' performed after January 1, 2024. Include the log ID, vehicle ID, service date, and service type."}, {"role": "assistant", "content": "SELECT ml.log_id, ml.vehicle_id, ml.service_date, ml.service_type\nFROM transportation.maintenance_logs ml\nJOIN transportation.vehicles v ON ml.vehicle_id = v.vehicle_id\nWHERE v.make = 'Toyota' AND ml.service_date > '2024-01-01';"}, {"role": "user", "content": "Can you add the maintenance cost and mechanic name to each entry and sort the results by service date descending?"}, {"role": "assistant", "content": "SELECT ml.log_id, ml.vehicle_id, ml.service_date, ml.service_type, ml.cost, ml.mechanic_name\nFROM transportation.maintenance_logs ml\nJOIN transportation.vehicles v ON ml.vehicle_id = v.vehicle_id\nWHERE v.make = 'Toyota' AND ml.service_date > '2024-01-01'\nORDER BY ml.service_date DESC;"}, {"role": "user", "content": "Actually, only show logs where the maintenance cost is greater than 1000."}, {"role": "assistant", "content": "SELECT ml.log_id, ml.vehicle_id, ml.service_date, ml.service_type, ml.cost, ml.mechanic_name\nFROM transportation.maintenance_logs ml\nJOIN transportation.vehicles v ON ml.vehicle_id = v.vehicle_id\nWHERE v.make = 'Toyota' AND ml.service_date > '2024-01-01' AND ml.cost > 1000\nORDER BY ml.service_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 transportation.vehicles ( vehicle_id text, license_plate text, vin text, make text, model text, year integer, type text, capacity integer, fuel_type text, status text, depot_id text, acquisition_date date )\nCREATE TABLE transportation.drivers (\n driver_id character varying(64) NOT NULL, -- unique identifier for the driver\n employee_id character varying(64) NOT NULL UNIQUE, -- employee reference number\n first_name character varying(128) NOT NULL, -- driver's first name\n last_name character varying(128) NOT NULL, -- driver's last name\n license_number character varying(64) NOT NULL UNIQUE, -- driving license number\n license_expiry_date date NOT NULL, -- expiry date of the license\n contact_number character varying(32), -- phone number\n email character varying(128) UNIQUE, -- email address\n hire_date date NOT NULL, -- date the driver was hired\n status character varying(32) NOT NULL, -- e.g., Active, On Leave, Terminated\n PRIMARY KEY (driver_id)\n)\nCREATE TABLE transportation.routes ( route_id text PRIMARY KEY, route_number text, description text, origin_location_id text, destination_location_id text, distance_km numeric, estimated_duration_minutes int, type text )\nCREATE TABLE transportation.maintenance_logs ( log_id.text, vehicle_id.text, service_date.date, odometer_reading.integer, service_type.text, description.text, cost.numeric, mechanic_name.text, next_service_due_date.date )\nCREATE TABLE transportation.fuel_logs ( fuel_log_id text, vehicle_id text, trip_id text, log_timestamp timestamp, fuel_type text, quantity numeric, unit text, cost_per_unit numeric, total_cost numeric, odometer_reading integer, location_id text )\n"} {"conversations": [{"role": "user", "content": "For each asset, I want to know how many orders have the status 'filled', showing the asset symbol."}, {"role": "assistant", "content": "SELECT m.value AS asset_symbol,\n COUNT(*) AS filled_order_count\nFROM trading_platform.orders o\nJOIN trading_platform.metadata m\n ON o.asset_id = m.asset_id\n AND m.key = 'symbol'\nWHERE o.status = 'filled'\nGROUP BY m.value;"}, {"role": "user", "content": "Include assets that have zero filled orders, showing filled_order_count as 0."}, {"role": "assistant", "content": "WITH asset_symbols AS (\n SELECT DISTINCT asset_id,\n value AS asset_symbol\n FROM trading_platform.metadata\n WHERE key = 'symbol'\n)\nSELECT a.asset_symbol,\n COALESCE(f.filled_order_count, 0) AS filled_order_count\nFROM asset_symbols a\nLEFT JOIN (\n SELECT asset_id,\n COUNT(*) AS filled_order_count\n FROM trading_platform.orders\n WHERE status = 'filled'\n GROUP BY asset_id\n) f\n ON a.asset_id = f.asset_id;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE trading_platform.users (\n user_id character varying(64) NOT NULL, -- unique identifier for the user\n username character varying(128) NOT NULL, -- username of the user\n email character varying(128) NOT NULL, -- email address of the user\n password_hash text NOT NULL, -- hashed password of the user\n created_at timestamp NOT NULL, -- time when the user account was created\n PRIMARY KEY (user_id)\n)\nCREATE TABLE trading_platform.orders (\n order_id character varying(64) NOT NULL, -- unique identifier for the order\n user_id character varying(64) NOT NULL, -- identifier of the user placing the order\n wallet_id character varying(64) NOT NULL, -- identifier of the wallet used for the order\n asset_id character varying(64) NOT NULL, -- identifier of the asset being traded\n order_type character varying(32) NOT NULL, -- type of the order (e.g., buy, sell)\n quantity numeric(38,14) NOT NULL, -- quantity of the asset in the order\n price numeric(38,14) NOT NULL, -- price per unit of the asset\n status character varying(32) NOT NULL, -- status of the order (e.g., open, filled, canceled)\n created_at timestamp NOT NULL, -- time when the order was created\n PRIMARY KEY (order_id)\n)\nCREATE TABLE trading_platform.dapps (\n dapp_id character varying(64) NOT NULL, -- unique identifier for the DApp\n name character varying(128) NOT NULL, -- name of the DApp\n description text NOT NULL, -- description of the DApp\n url character varying(256) NOT NULL, -- URL of the DApp\n PRIMARY KEY (dapp_id)\n)\nCREATE TABLE trading_platform.peers (\n peer_id character varying(64) NOT NULL, -- unique identifier for the peer\n ip_address character varying(15) NOT NULL, -- IP address of the peer\n port integer NOT NULL, -- port number of the peer\n last_seen timestamp NOT NULL, -- last time the peer was active\n PRIMARY KEY (peer_id)\n)\nCREATE TABLE trading_platform.metadata (\n metadata_id character varying(64) NOT NULL, -- unique identifier for the metadata\n asset_id character varying(64) NOT NULL, -- identifier of the asset the metadata is associated with\n key character varying(128) NOT NULL, -- key of the metadata\n value text NOT NULL, -- value of the metadata\n PRIMARY KEY (metadata_id)\n)\nCREATE TABLE trading_platform.logs (\n log_id character varying(64) NOT NULL, -- unique identifier for the log entry\n user_id character varying(64), -- identifier of the user associated with the log entry\n action character varying(128) NOT NULL, -- action performed\n details text NOT NULL, -- details of the action\n logged_at timestamp NOT NULL, -- time when the log entry was created\n PRIMARY KEY (log_id)\n)\n"} {"conversations": [{"role": "user", "content": "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": "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": "Which route numbers connect locations with a distance less than 80 km and more than 5 words in their description? Include the route type in the results."}, {"role": "assistant", "content": "SELECT route_number, type FROM transportation.routes WHERE distance_km < 80 AND array_length(regexp_split_to_array(description, '\\s+'), 1) > 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.routes ( route_id text, route_number text, description text, origin_location_id text, destination_location_id text, distance_km numeric, estimated_duration_minutes integer, type text )\n"} {"conversations": [{"role": "user", "content": "Show the first name, last name, and email of customers who have filed a claim, along with the status and estimated loss of each claim."}, {"role": "assistant", "content": "SELECT T1.first_name, T1.last_name, T1.email, T2.status, T2.estimated_loss FROM insurance.customers AS T1 INNER JOIN insurance.claims AS T2 ON T1.customer_id = T2.customer_id;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE insurance.customers ( customer_id text, first_name text, last_name text, date_of_birth date, ssn_hash text, address_line1 text, address_line2 text, city text, state text, zip_code text, country text, phone_number text, email text, created_at timestamp, updated_at timestamp, status text )\nCREATE TABLE insurance.claims ( claim_id 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 character varying(64) NOT NULL, policy_id character varying(64) NOT NULL, customer_id character varying(64) NOT NULL, payment_date timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, amount_paid numeric(12, 2) NOT NULL, payment_method character varying(50), transaction_reference character varying(128) UNIQUE, due_date date, payment_period_start date, payment_period_end date, status character varying(30) NOT NULL DEFAULT 'Completed', PRIMARY KEY (payment_id) )\nCREATE TABLE insurance.claim_documents ( document_id.text, 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 agency that is a parent, how many direct child agencies does it have? Show the parent agency name and the count."}, {"role": "assistant", "content": "SELECT parent.agency_name AS parent_agency_name, COUNT(child.agency_id) AS child_agency_count FROM government_services.agencies AS parent INNER JOIN government_services.agencies AS child ON parent.agency_id = child.parent_agency_id GROUP BY parent.agency_id, parent.agency_name;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.agencies ( agency_id character varying(64) NOT NULL, agency_name character varying(255) NOT NULL, jurisdiction_level character varying(50) NOT NULL, primary_contact_email character varying(128), main_phone_number character varying(32), website_url character varying(255), established_date date, parent_agency_id character varying(64), PRIMARY KEY (agency_id) )\n"} {"conversations": [{"role": "user", "content": "Show me the first name, last name, and email for all clients registered in January 2023."}, {"role": "assistant", "content": "SELECT first_name, last_name, email FROM legal_services.clients WHERE EXTRACT(YEAR FROM date_registered) = 2023 AND EXTRACT(MONTH FROM date_registered) = 1;"}, {"role": "user", "content": "Only show those who have provided a phone number."}, {"role": "assistant", "content": "SELECT first_name, last_name, email FROM legal_services.clients WHERE EXTRACT(YEAR FROM date_registered) = 2023 AND EXTRACT(MONTH FROM date_registered) = 1 AND phone IS NOT NULL;"}, {"role": "user", "content": "Also, exclude any clients whose status is 'inactive'."}, {"role": "assistant", "content": "SELECT first_name, last_name, email FROM legal_services.clients WHERE EXTRACT(YEAR FROM date_registered) = 2023 AND EXTRACT(MONTH FROM date_registered) = 1 AND phone IS NOT NULL AND status != 'inactive';"}, {"role": "user", "content": "Order the results by last name, then first name."}, {"role": "assistant", "content": "SELECT first_name, last_name, email FROM legal_services.clients WHERE EXTRACT(YEAR FROM date_registered) = 2023 AND EXTRACT(MONTH FROM date_registered) = 1 AND phone IS NOT NULL AND status != 'inactive' ORDER BY last_name, first_name;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.clients (\n client_id character varying(64) NOT NULL, -- unique identifier for the client\n first_name character varying(100) NOT NULL, -- client's first name\n last_name character varying(100) NOT NULL, -- client's last name\n company_name character varying(200), -- company name if applicable\n email character varying(128) UNIQUE NOT NULL, -- client's primary email\n phone character varying(32), -- client's contact phone number\n address text, -- client's full address\n date_registered timestamp NOT NULL, -- when the client was first registered\n status character varying(32) NOT NULL, -- client status (e.g., active, inactive, prospect)\n PRIMARY KEY (client_id)\n)\n"} {"conversations": [{"role": "user", "content": "What are the personal contact details of the staff member associated with staff_id 'STAFF789' who worked on a specific maintenance record?"}, {"role": "assistant", "content": "I'm sorry, but I can't provide personal contact details of staff members as this information is not stored in the maintenance_records table and is outside the scope of the available data."}], "system": "You are an SQL statement expert and you can refuse the user's question if the question is not related to the table structure. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE train_station_management.maintenance_records ( record_id text, asset_id text, asset_type text, maintenance_type text, staff_id text, start_datetime timestamp, end_datetime timestamp, description text, cost numeric, status text )\n"} {"conversations": [{"role": "user", "content": "Show 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": "Could you list all pairs of developers that are based in the same country and share the same website domain?"}, {"role": "assistant", "content": "SELECT\n d1.name AS developer1_name,\n d2.name AS developer2_name,\n d1.country,\n d1.website\nFROM\n gaming_technology.developers AS d1\nJOIN\n gaming_technology.developers AS d2 ON d1.country = d2.country\n AND d1.website = d2.website\n AND d1.developer_id < d2.developer_id\nWHERE\n d1.country IS NOT NULL\n AND d1.website IS NOT NULL AND d1.website != '';"}], "system": "You are an SQL statement expert. Given the table structure 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 (\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)\n"} {"conversations": [{"role": "user", "content": "Show me the top 3 smart money addresses by profit across all chains, along with their most profitable token and chain information."}, {"role": "assistant", "content": "SELECT address, profit, most_profit_token, chain\nFROM smart_money_profit\nORDER BY profit DESC\nLIMIT 3;"}, {"role": "user", "content": "Actually, I only want to see addresses from Ethereum chain with ROI over 30%."}, {"role": "assistant", "content": "SELECT address, profit, most_profit_token, roi\nFROM smart_money_profit\nWHERE chain = 'Ethereum' AND roi > 30\nORDER BY profit DESC\nLIMIT 3;"}, {"role": "user", "content": "Can you add their realized profit ratio and filter to only show results with profit over $100,000?"}, {"role": "assistant", "content": "SELECT address, profit, most_profit_token, roi, realized_ratio\nFROM smart_money_profit\nWHERE chain = 'Ethereum' AND roi > 30 AND profit > 100000\nORDER BY profit DESC\nLIMIT 3;"}, {"role": "user", "content": "Now order these results by ROI in descending order instead of profit."}, {"role": "assistant", "content": "SELECT address, profit, most_profit_token, roi, realized_ratio\nFROM smart_money_profit\nWHERE chain = 'Ethereum' AND roi > 30 AND profit > 100000\nORDER BY roi 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, -- fundraising record id project_id character varying(32) NOT NULL, -- the invested project's id project_name character varying(128) NOT NULL, -- name of the invested project rounds_name character varying(32), -- name of the fundraising round investment_value numeric(38,14), -- amount of the fundraising in USD investment_date character varying(128), -- the date of the investment happened introduction character varying(128), -- the introduction of the invested project valuation numeric(38,14), -- the valuation of the project in USD when invested )\nCREATE TABLE narrative_info ( narrative character varying(512) NOT NULL, -- the id of narrative top_3_coins text, -- the top 3 tokens in the narrative price_change_percentage_1h double precision, -- change in value divided by the absolute price value of the original token price in 1 hour in the narrative price_change_percentage_24h double precision, -- change in value divided by the absolute price value of the original token price in 24 hours in the narrative price_change_percentage_7d double precision, -- change in value divided by the absolute price value of the original token price in 7 days in the narrative market_cap double precision, -- the market cap of the narrative volume_24h double precision, -- the trade volume of the narrative trend_rank bigint, -- the trending rank of the narrative, value 1 expresses the most popular narrative token_num bigint, -- total token number in the narrative ,PRIMARY KEY (narrative) )\nCREATE TABLE smart_money_profit ( address character varying(100) NOT NULL, -- the user's address rank INT, -- the rank of the address in trade performance, value 1 expresses the best address. profit numeric(38,6), -- the profit user made in a month roi numeric(38,2), -- the roi of the user in a month realized_ratio numeric(38,2), -- the percentage of the user's realized profit most_profit_token character varying(100), -- the token symbol of the user's most profitable trade last_trade_time character varying(100), -- the last trade time of the user chain character varying(100), -- the chain that the address resides PRIMARY KEY (address, chain) )\n"} {"conversations": [{"role": "user", "content": "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": "Find all users who registered with a Yahoo email address, along with their registration dates."}, {"role": "assistant", "content": "SELECT user_id, username, email, password_hash FROM blockchain.users WHERE email LIKE '%@yahoo.com';"}, {"role": "user", "content": "This query doesn't show registration dates. Can you modify it to include the registration date?"}, {"role": "assistant", "content": "I notice the users table doesn't have a registration date column. Would you like me to show other available information from the users table?"}, {"role": "user", "content": "Then just show me the count of Yahoo email users instead."}, {"role": "assistant", "content": "SELECT COUNT(*) as yahoo_user_count FROM blockchain.users WHERE email LIKE '%@yahoo.com';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE blockchain.blocks ( block_id text, previous_block_id text, timestamp timestamp, nonce integer, merkle_root text, difficulty integer )\nCREATE TABLE blockchain.transactions (\n transaction_id character varying(64) NOT NULL, -- unique identifier for the transaction\n block_id character varying(64) NOT NULL, -- identifier of the block containing the transaction\n sender_address character varying(128) NOT NULL, -- address of the sender\n receiver_address character varying(128) NOT NULL, -- address of the receiver\n amount numeric(38,14) NOT NULL, -- amount transferred\n timestamp timestamp NOT NULL, -- time when the transaction was created\n signature text NOT NULL, -- digital signature of the transaction\n PRIMARY KEY (transaction_id)\n)\nCREATE TABLE blockchain.addresses ( address_id text PRIMARY KEY, public_key text, balance numeric )\nCREATE TABLE blockchain.users ( user_id character varying(64) NOT NULL, username character varying(128) NOT NULL, email character varying(128) NOT NULL, password_hash text NOT NULL, PRIMARY KEY (user_id) )\n"} {"conversations": [{"role": "user", "content": "For each block number, show the highest transaction value and the status of the transaction with the highest value."}, {"role": "assistant", "content": "SELECT t.block_number, t.value AS max_value, t.status\nFROM web3.transactions t\nJOIN (\n SELECT block_number, MAX(value) AS max_value\n FROM web3.transactions\n GROUP BY block_number\n) mv\n ON t.block_number = mv.block_number AND t.value = mv.max_value;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE web3.transactions ( transaction_id.text, from_address.text, to_address.text, value.numeric, gas_used.integer, gas_price.numeric, block_number.integer, timestamp.timestamp, input_data.text, status.text, nonce.integer )\n"} {"conversations": [{"role": "user", "content": "Which active insurance products contain the word 'comprehensive' or 'premium' in their description? List their product IDs, product names, types, and base premiums."}, {"role": "assistant", "content": "SELECT product_id, product_name, product_type, base_premium\nFROM insurance.insurance_products\nWHERE is_active = TRUE\n AND (\n description ILIKE '%comprehensive%' OR\n description ILIKE '%premium%'\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 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": "What is the total amount paid across all premium payments for payments marked as 'Failed'?"}, {"role": "assistant", "content": "SELECT sum(amount_paid) FROM insurance.premium_payments WHERE status = 'Failed';"}], "system": "You are an SQL statement expert. Given the table structure 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.premium_payments ( payment_id text, policy_id text, customer_id text, payment_date timestamp, amount_paid numeric, payment_method text, transaction_reference text, due_date date, payment_period_start date, payment_period_end date, status text )\nCREATE TABLE insurance.claim_documents ( document_id text, claim_id text, document_type text, file_name text, file_path text, file_size_bytes integer, mime_type text, uploaded_by text, uploaded_at timestamp, description text )\nCREATE TABLE insurance.policy_beneficiaries ( beneficiary_id text, policy_id text, customer_id text, first_name text, last_name text, relationship text, percentage_share numeric, contact_info text, added_at timestamp )\n"} {"conversations": [{"role": "user", "content": "List all trades that occurred on '2023-10-26' and have a status of 'PENDING'."}, {"role": "assistant", "content": "SELECT * FROM financial_services.trades WHERE DATE(trade_timestamp) = '2023-10-26' AND status = 'PENDING';"}, {"role": "user", "content": "From that list, only show the trade_id, security_id, and total_amount."}, {"role": "assistant", "content": "SELECT trade_id, security_id, total_amount FROM financial_services.trades WHERE DATE(trade_timestamp) = '2023-10-26' AND status = 'PENDING';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE 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": "List all pairs of hashtags that were created on the same date. Show both tag names and the creation date."}, {"role": "assistant", "content": "SELECT a.tag_name AS tag1, b.tag_name AS tag2, a.created_at::date AS created_date\nFROM social_media.hashtags a\nJOIN social_media.hashtags b\n ON a.created_at::date = b.created_at::date\n AND a.hashtag_id < b.hashtag_id;"}, {"role": "user", "content": "Actually, only include pairs where both tag names start with the letter 'S'."}, {"role": "assistant", "content": "SELECT a.tag_name AS tag1, b.tag_name AS tag2, a.created_at::date AS created_date\nFROM social_media.hashtags a\nJOIN social_media.hashtags b\n ON a.created_at::date = b.created_at::date\n AND a.hashtag_id < b.hashtag_id\nWHERE a.tag_name LIKE 'S%'\n AND b.tag_name LIKE 'S%';"}], "system": "You are an SQL statement expert. Given the table structure 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.hashtags ( hashtag_id character varying(64) NOT NULL, tag_name character varying(100) NOT NULL UNIQUE, created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, PRIMARY KEY (hashtag_id) )\n"} {"conversations": [{"role": "user", "content": "List all pairs of tokens (show token_id for both) that share the same contract address, excluding pairs where the token_id is the same."}, {"role": "assistant", "content": "SELECT t1.token_id AS token_id1, t2.token_id AS token_id2, t1.contract_address FROM web3.tokens AS t1 JOIN web3.tokens AS t2 ON t1.contract_address = t2.contract_address WHERE t1.token_id < t2.token_id;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE web3.tokens ( token_id character varying(64) NOT NULL, contract_address character varying(128) NOT NULL, token_name character varying(128) NOT NULL, token_symbol character varying(32) NOT NULL, decimals integer NOT NULL, total_supply numeric(38,14) NOT NULL, PRIMARY KEY (token_id) )\n"} {"conversations": [{"role": "user", "content": "List the service_id, service_name, and agency_id for all active services that have an online application URL provided."}, {"role": "assistant", "content": "SELECT service_id,\n service_name,\n agency_id\nFROM government_services.services\nWHERE is_active = TRUE\n AND online_application_url IS NOT NULL;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE 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.appointments (\n appointment_id character varying(64) NOT NULL, -- unique identifier for the appointment\n citizen_id character varying(64) NOT NULL, -- FK to citizens table\n employee_id character varying(64), -- FK to employees table (optional, if assigned)\n location_id character varying(64), -- FK to service_locations table (if physical)\n service_id character varying(64), -- FK to services table (optional, if related to specific service)\n scheduled_start_time timestamp NOT NULL,\n scheduled_end_time timestamp,\n purpose text NOT NULL, -- reason for the appointment\n status character varying(30) NOT NULL, -- e.g., Scheduled, Completed, Cancelled, No-Show\n booking_method character varying(50), -- e.g., Online, Phone, In-Person\n created_at timestamp NOT NULL, -- when the appointment was booked\n notes text,\n PRIMARY KEY (appointment_id)\n)\nCREATE TABLE government_services.notifications ( 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 all users who have commented on a post and have also liked any comment on that same post. I want their user IDs and the corresponding post IDs."}, {"role": "assistant", "content": "SELECT DISTINCT c.user_id, c.post_id\nFROM social_media.comments c\nJOIN social_media.likes l ON l.comment_id IS NOT NULL AND l.post_id = c.post_id AND l.user_id = c.user_id"}, {"role": "user", "content": "Can you also include the comment content that was liked and the time the like was created?"}, {"role": "assistant", "content": "SELECT DISTINCT c.user_id, c.post_id, c2.content AS liked_comment_content, l.created_at AS like_created_at\nFROM social_media.comments c\nJOIN social_media.likes l ON l.comment_id IS NOT NULL AND l.post_id = c.post_id AND l.user_id = c.user_id\nJOIN social_media.comments c2 ON c2.comment_id = l.comment_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.comments (\n comment_id character varying(64) NOT NULL, -- unique identifier for the comment\n post_id character varying(64) NOT NULL, -- identifier of the post being commented on (FK to posts.post_id)\n user_id character varying(64) NOT NULL, -- identifier of the user who made the comment (FK to users.user_id)\n parent_comment_id character varying(64), -- identifier of the parent comment if it's a reply (FK to comments.comment_id)\n content text NOT NULL, -- textual content of the comment\n created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of comment creation\n updated_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of last comment edit\n PRIMARY KEY (comment_id)\n)\nCREATE TABLE social_media.likes ( like_id.text, user_id.text, post_id.text, comment_id.text, created_at.timestamp )\nCREATE TABLE social_media.follows ( follow_id text PRIMARY KEY, follower_user_id text, following_user_id text, created_at timestamp )\nCREATE TABLE social_media.hashtags ( hashtag_id character varying(64) NOT NULL, tag_name character varying(100) NOT NULL UNIQUE, created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, PRIMARY KEY (hashtag_id) )\nCREATE TABLE social_media.messages ( message_id text PRIMARY KEY, conversation_id text, sender_user_id text, content text, media_url text, media_type text, sent_at timestamp, read_at timestamp )\n"} {"conversations": [{"role": "user", "content": "For each Bitcoin token tick, show me the creator address from the token_info_bitcoin table and the number of unique wallets currently holding that token."}, {"role": "assistant", "content": "SELECT ti.tick, ti.creator, COUNT(DISTINCT tb.wallet_address) AS unique_wallets FROM token_info_bitcoin ti JOIN token_balances_bitcoin tb ON ti.tick = tb.tick GROUP BY ti.tick, ti.creator;"}, {"role": "user", "content": "Now, only include ticks where there are more than 5 unique wallets, and order the result by the number of unique wallets descending."}, {"role": "assistant", "content": "SELECT ti.tick, ti.creator, COUNT(DISTINCT tb.wallet_address) AS unique_wallets FROM token_info_bitcoin ti JOIN token_balances_bitcoin tb ON ti.tick = tb.tick GROUP BY ti.tick, ti.creator HAVING COUNT(DISTINCT tb.wallet_address) > 5 ORDER BY unique_wallets DESC;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE erc1155_approval_for_all (\n block_number bigint NOT NULL, -- Block number containing the transaction\n block_timestamp timestamp(3) NOT NULL, -- Timestamp of the block containing the transaction\n transaction_index integer NOT NULL, -- Index of the transaction within the block\n transaction_hash varchar(66) NOT NULL, -- Transaction hash\n log_index integer NOT NULL, -- Log index\n contract_address varchar(42) NOT NULL -- Event contract address\n)\nCREATE TABLE erc20_balances ( block_number bigint, contract_address varchar, wallet_address varchar, amount varchar, pk varchar )\nCREATE TABLE erc20_balances_historical ( block_number bigint, contract_address text, wallet_address text, amount text, pk integer )\nCREATE TABLE nft_holders ( block_number.bigint, contract_address.text, wallet_address.text, token_id.text, contract_type.text, amount.text, pk.text )\nCREATE TABLE sui_coins ( object_id varchar NOT NULL, status varchar NOT NULL, coin_type varchar NOT NULL, balance varchar NOT NULL, owner varchar NOT NULL )\nCREATE TABLE sui_coins_metadata (\n object_id varchar NOT NULL, -- object id of the coin metadata object\n coin_type varchar NOT NULL, -- coin type, eg. 0x...66::reap_token::REAP_TOKEN\n status varchar NOT NULL, -- coin status, eg. exists, deleted\n decimals bigint NOT NULL, -- decimals of the coin\n description varchar NOT NULL, -- description of the coin\n icon_url varchar NOT NULL, -- icon url of the coin\n symbol varchar NOT NULL, -- symbol of the coin\n name varchar NOT NULL -- name of the coin\n)\nCREATE TABLE sui_nfts ( object_id.text, status.text, collection_type.text, package_id.text, previous_transaction.text, display.text, owner.text, name.text )\nCREATE TABLE nft_collections ( blockchain varchar NOT NULL, contract_address varchar NOT NULL, name varchar NOT NULL, symbol varchar NOT NULL, deploy_block_number bigint NOT NULL, deploy_block_time bigint NOT NULL, erc_type varchar NOT NULL, owner varchar NOT NULL, traits varchar NOT NULL, description varchar NOT NULL, slug varchar NOT NULL, media_info varchar NOT NULL, image_url varchar NOT NULL, banner_image_url varchar NOT NULL, updated_at bigint NOT NULL, banner varchar NOT NULL, token_count bigint NOT NULL, floor_price varchar NOT NULL, floor_price_symbol varchar NOT NULL, floor_price_contract varchar NOT NULL, pk integer NOT NULL )\nCREATE TABLE token_prices ( uuid.text, blockchain.text, address.text, decimals.bigint, symbol.text, price.real, timestamp.timestamp )\nCREATE TABLE token_prices_latest ( blockchain.text, address.text, decimals.bigint, symbol.text, price.real, timestamp.timestamp )\nCREATE TABLE erc20_approval ( block_number.bigint, block_timestamp.timestamp, transaction_index.integer, transaction_hash.text, log_index.integer, contract_address.text, pk.integer )\nCREATE TABLE token_balances (\n block_number bigint NOT NULL, -- Block number containing the transaction\n block_timestamp timestamp(3) NOT NULL, -- Block timestamp containing the transaction\n tick varchar NOT NULL, -- Token tick\n wallet_address varchar(42) NOT NULL, -- Address of owner\n total_supply decimal(38,0) NOT NULL, -- Max supply\n amount decimal(38,0) NOT NULL -- The balance of wallet balance at the corresponding block height\n)\nCREATE TABLE token_info ( block_timestamp timestamp(3) NOT NULL, block_number bigint NOT NULL, tx_index integer NOT NULL, tx_hash varchar(66) NOT NULL, tick varchar NOT NULL, max_supply decimal(38,0) NOT NULL, lim decimal(38,0) NOT NULL, wlim decimal(38,0) NOT NULL, dec integer NOT NULL, creator varchar(42) NOT NULL )\nCREATE TABLE token_activities ( block_timestamp.timestamp, block_number.bigint, tx_index.integer, tx_hash.text, log_index.integer, type.text, tick.text, id.text, amt.decimal, from_address.text, to_address.text )\nCREATE TABLE mud_holesky_redstone ( address text, table_id text, key_bytes text, key0 text, key1 text, static_data text, encoded_lengths text, dynamic_data text, is_deleted boolean, block_number bigint, log_index bigint )\nCREATE TABLE token_balances_bitcoin (\n block_number bigint NOT NULL, -- Block number containing the transaction\n block_timestamp timestamp(3) NOT NULL, -- Block timestamp containing the transaction\n tick varchar(255) NOT NULL, -- Ticker: Identifier of the inscription\n wallet_address varchar(42) NOT NULL, -- Address of owner\n total_supply varchar NOT NULL, -- Max supply: Set max supply of the inscription\n amount varchar NOT NULL -- The balance of wallet balance at the corresponding block height\n)\nCREATE TABLE token_info_bitcoin ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash text, tick text, max_supply decimal, lim decimal, wlim decimal, dec integer, creator text )\nCREATE TABLE token_activities_bitcoin ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash text, log_index integer, type text, tick text, id text, amt decimal, from_address text, to_address text )\nCREATE TABLE token_activities_avalanche ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash varchar, log_index integer, type varchar, tick varchar, id varchar, amt decimal, from_address varchar, to_address varchar )\nCREATE TABLE token_balances_avalanche (\n block_number bigint NOT NULL, -- Block number containing the transaction\n block_timestamp timestamp(3) NOT NULL, -- Block timestamp containing the transaction\n tick varchar(20) NOT NULL, -- Ticker: Identifier of the inscription\n wallet_address varchar(42) NOT NULL, -- Address of owner\n total_supply decimal(38,0) NOT NULL, -- Max supply: Set max supply of the inscription\n amount decimal(38,0) NOT NULL -- The balance of wallet balance at the corresponding block height\n)\nCREATE TABLE token_info_avalanche ( block_timestamp timestamp, block_number bigint, tx_index integer, tx_hash varchar, tick varchar, max_supply decimal, lim decimal, wlim decimal, dec integer, creator varchar, minted decimal, holders decimal, txs decimal, updated_timestamp timestamp, completed_timestamp timestamp, id varchar )\n"} {"conversations": [{"role": "user", "content": "List the first and last names of employees and the full name of the citizens for whom they have scheduled appointments."}, {"role": "assistant", "content": "SELECT T1.first_name , T1.last_name , T3.first_name , T3.last_name FROM government_services.employees AS T1 JOIN government_services.appointments AS T2 ON T1.employee_id = T2.employee_id JOIN government_services.citizens AS T3 ON T2.citizen_id = T3.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 ( citizen_id text PRIMARY KEY, national_id_number text, first_name text, last_name text, date_of_birth date, gender text, primary_address text, contact_email text, contact_phone text, registration_date timestamp, is_verified boolean )\nCREATE TABLE government_services.agencies ( agency_id text PRIMARY KEY, agency_name text, jurisdiction_level text, primary_contact_email text, main_phone_number text, website_url text, established_date date, parent_agency_id text )\nCREATE TABLE government_services.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 text PRIMARY KEY, citizen_id text, service_id text, submitted_at timestamp, status text, last_updated_at timestamp, assigned_employee_id text, decision_date date, notes text, reference_number text )\nCREATE TABLE government_services.documents ( document_id text PRIMARY KEY, application_id text, citizen_id text, document_type text, file_reference text, upload_timestamp timestamp, expiry_date date, verification_status text, verified_by_employee_id text, verification_timestamp timestamp )\nCREATE TABLE government_services.payments ( payment_id text PRIMARY KEY, application_id text, citizen_id text, service_id text, amount numeric, currency text, payment_method text, payment_provider_reference text, payment_timestamp timestamp, status text, notes text )\nCREATE TABLE government_services.employees ( employee_id text PRIMARY KEY, agency_id text, first_name text, last_name text, job_title text, department text, work_email text, work_phone text, hire_date date, termination_date date, access_level text, manager_employee_id text )\nCREATE TABLE government_services.appointments ( appointment_id text PRIMARY KEY, citizen_id text, employee_id text, location_id text, service_id text, scheduled_start_time timestamp, scheduled_end_time timestamp, purpose text, status text, booking_method text, created_at timestamp, notes text )\nCREATE TABLE government_services.notifications ( notification_id text PRIMARY KEY, citizen_id text, application_id text, message_subject text, message_body text, channel text, sent_at timestamp, status text, related_entity_type text, related_entity_id text )\n"} {"conversations": [{"role": "user", "content": "What is the current number of passengers at station with ID 'ST123' right now?"}, {"role": "assistant", "content": "I'm sorry, but I can't provide information on the current number of passengers at a station. The data I have access to only includes static details about stations such as their name, location, and number of platforms, not real-time passenger counts."}], "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 (\n station_id character varying(64) NOT NULL, -- Unique identifier for the station\n station_name character varying(128) NOT NULL, -- Name of the station\n city character varying(100) NOT NULL, -- City where the station is located\n state_province character varying(100), -- State or province\n country_code character varying(3) NOT NULL, -- ISO country code\n address text, -- Full address of the station\n timezone character varying(64) NOT NULL, -- Timezone ID (e.g., 'America/New_York')\n number_of_platforms integer NOT NULL DEFAULT 0, -- Total number of platforms\n created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- When the station record was created\n last_updated_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- When the station record was last updated\n PRIMARY KEY (station_id)\n)\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": "Can you show me the total number of passengers registered in the database?"}, {"role": "assistant", "content": "db.passengers.countDocuments({})"}], "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// db.createCollection('passengers')\n// Optional: db.passengers.createIndex({ passenger_id: 1 }, { unique: true })\n// Optional: db.passengers.createIndex({ email: 1 }, { unique: true, sparse: true })\n// Optional: db.passengers.createIndex({ phone_number: 1 }, { unique: true, sparse: true })\n{\n _id: ObjectId(),\n passenger_id: \"pass_pqr\", // String (unique)\n first_name: \"Alice\", // String\n last_name: \"Smith\", // String\n email: \"alice.smith@example.com\", // String (unique, sparse)\n phone_number: \"+15551234567\", // String (unique, sparse)\n date_of_birth: ISODate(\"1990-03-20\"), // Date\n loyalty_program_id: \"LOYALTY123\", // String\n created_at: ISODate(\"2023-02-01T11:00:00Z\") // Date\n}\n"} {"conversations": [{"role": "user", "content": "Find the names of service locations where services categorized as 'Licensing' have had appointments scheduled."}, {"role": "assistant", "content": "SELECT DISTINCT T1.location_name FROM service_locations AS T1 JOIN appointments AS T2 ON T1.location_id = T2.location_id JOIN services AS T3 ON T2.service_id = T3.service_id WHERE T3.category = 'Licensing';"}], "system": "You are an SQL statement expert. Given the table structure 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 (\n service_id character varying(64) NOT NULL, -- unique identifier for the service\n agency_id character varying(64) NOT NULL, -- FK to agencies table\n service_name character varying(255) NOT NULL, -- name of the service (e.g., Driver's License Renewal)\n description text,\n category character varying(100), -- e.g., Licensing, Benefits, Taxation, Permits\n eligibility_criteria text, -- description of who is eligible\n standard_fee numeric(10, 2) DEFAULT 0.00, -- typical fee for the service\n average_processing_time_days integer, -- estimated processing time\n is_active boolean DEFAULT true, -- whether the service is currently offered\n online_application_url character varying(255),\n PRIMARY KEY (service_id)\n)\nCREATE TABLE government_services.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.appointments (\n appointment_id character varying(64) NOT NULL, -- unique identifier for the appointment\n citizen_id character varying(64) NOT NULL, -- FK to citizens table\n employee_id character varying(64), -- FK to employees table (optional, if assigned)\n location_id character varying(64), -- FK to service_locations table (if physical)\n service_id character varying(64), -- FK to services table (optional, if related to specific service)\n scheduled_start_time timestamp NOT NULL,\n scheduled_end_time timestamp,\n purpose text NOT NULL, -- reason for the appointment\n status character varying(30) NOT NULL, -- e.g., Scheduled, Completed, Cancelled, No-Show\n booking_method character varying(50), -- e.g., Online, Phone, In-Person\n created_at timestamp NOT NULL, -- when the appointment was booked\n notes text,\n PRIMARY KEY (appointment_id)\n)\n"} {"conversations": [{"role": "user", "content": "Show a list of all DApps together with the total number of unique assets linked to each via the metadata table."}, {"role": "assistant", "content": "SELECT d.dapp_id, d.name, d.url, COUNT(DISTINCT m.asset_id) AS unique_asset_count\nFROM trading_platform.dapps d\nLEFT JOIN trading_platform.metadata m ON m.asset_id IS NOT NULL\nGROUP BY d.dapp_id, d.name, d.url;"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE trading_platform.orders ( order_id text PRIMARY KEY, user_id text, wallet_id text, asset_id text, order_type text, quantity numeric, price numeric, status text, created_at timestamp )\nCREATE TABLE trading_platform.trades ( trade_id text PRIMARY KEY, order_id text, buyer_id text, seller_id text, asset_id text, quantity numeric, price numeric, traded_at timestamp )\nCREATE TABLE trading_platform.utxos ( utxo_id text PRIMARY KEY, transaction_id text, output_index int, address text, amount numeric, spent boolean )\nCREATE TABLE trading_platform.dapps ( dapp_id text PRIMARY KEY, name text, description text, url text )\nCREATE TABLE trading_platform.peers ( peer_id text PRIMARY KEY, ip_address text, port int, last_seen timestamp )\nCREATE TABLE trading_platform.metadata ( metadata_id text PRIMARY KEY, asset_id text, key text, value text )\nCREATE TABLE trading_platform.kyc_audit ( kyc_audit_id text PRIMARY KEY, user_id text, status text, reviewed_at timestamp )\nCREATE TABLE trading_platform.logs ( log_id text PRIMARY KEY, user_id text, action text, details text, logged_at timestamp )\n"} {"conversations": [{"role": "user", "content": "List all agencies that do not have a website URL specified. Return their agency_id, agency_name, and main_phone_number."}, {"role": "assistant", "content": "SELECT agency_id, agency_name, main_phone_number FROM government_services.agencies WHERE website_url IS NULL OR website_url = '';"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE government_services.agencies ( agency_id character varying(64) NOT NULL, agency_name character varying(255) NOT NULL, jurisdiction_level character varying(50) NOT NULL, primary_contact_email character varying(128), main_phone_number character varying(32), website_url character varying(255), established_date date, parent_agency_id character varying(64), PRIMARY KEY (agency_id) )\n"} {"conversations": [{"role": "user", "content": "List all medical records created in the last 7 days, including patient_id, doctor_id, and record_date."}, {"role": "assistant", "content": "SELECT patient_id, doctor_id, record_date FROM healthcare.medical_records WHERE created_at >= CURRENT_DATE - INTERVAL '7 days';"}, {"role": "user", "content": "Actually, I only need records where the treatment_plan is not empty."}, {"role": "assistant", "content": "SELECT patient_id, doctor_id, record_date FROM healthcare.medical_records WHERE created_at >= CURRENT_DATE - INTERVAL '7 days' AND treatment_plan IS NOT NULL AND treatment_plan != '';"}, {"role": "user", "content": "Can you also sort them by record_date in descending order?"}, {"role": "assistant", "content": "SELECT patient_id, doctor_id, record_date FROM healthcare.medical_records WHERE created_at >= CURRENT_DATE - INTERVAL '7 days' AND treatment_plan IS NOT NULL AND treatment_plan != '' ORDER BY record_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 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 )\n"} {"conversations": [{"role": "user", "content": "List all transfers of the token named 'Wrapped Ether', showing the transfer id, token id, value, and the contract address of the token."}, {"role": "assistant", "content": "SELECT tt.transfer_id, tt.token_id, tt.value, t.contract_address\nFROM web3.token_transfers tt\nJOIN web3.tokens t ON tt.token_id = t.token_id\nWHERE t.token_name = 'Wrapped Ether';"}, {"role": "user", "content": "Actually, can you also include the username of the user who owns the sender address, if such a user exists?"}, {"role": "assistant", "content": "SELECT tt.transfer_id, tt.token_id, tt.value, t.contract_address, u.username\nFROM web3.token_transfers tt\nJOIN web3.tokens t ON tt.token_id = t.token_id\nLEFT JOIN web3.users u ON tt.from_address = (\n SELECT w.address FROM web3.wallets w WHERE w.user_id = u.user_id AND w.address = tt.from_address LIMIT 1\n)\nWHERE t.token_name = 'Wrapped Ether';"}], "system": "You are an SQL statement expert. Given the table structure 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.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.token_transfers ( transfer_id character varying(64) NOT NULL, token_id character varying(64) NOT NULL, from_address character varying(128) NOT NULL, to_address character varying(128) NOT NULL, value numeric(38,14) NOT NULL, transaction_id character varying(64) NOT NULL, log_index integer NOT NULL, PRIMARY KEY (transfer_id) )\nCREATE TABLE web3.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) )\n"} {"conversations": [{"role": "user", "content": "How many lawyers who are partners were hired in each year? Show the hire year and the count."}, {"role": "assistant", "content": "SELECT strftime('%Y', hire_date) AS hire_year , count(lawyer_id) FROM legal_services.lawyers WHERE is_partner = true GROUP BY hire_year"}], "system": "You are an SQL statement expert. Given the table structure described by the CREATE TABLE statement, write an SQL query that provides the solution to the user's question.\n##Table Structure\nCREATE TABLE legal_services.lawyers (\n lawyer_id character varying(64) NOT NULL, -- unique identifier for the lawyer\n first_name character varying(100) NOT NULL, -- lawyer's first name\n last_name character varying(100) NOT NULL, -- lawyer's last name\n bar_number character varying(64) UNIQUE NOT NULL, -- lawyer's bar association number\n firm_id character varying(64), -- FK to law_firms table\n email character varying(128) UNIQUE NOT NULL, -- lawyer's professional email\n phone character varying(32), -- lawyer's contact phone number\n specialization text, -- areas of legal expertise\n hire_date timestamp NOT NULL, -- date the lawyer was hired or joined\n is_partner boolean DEFAULT false, -- flag indicating if the lawyer is a partner\n PRIMARY KEY (lawyer_id)\n)\n"}