Dataset Viewer
Auto-converted to Parquet Duplicate
system
stringlengths
315
8.06k
conversations
listlengths
2
48
You are an expert in writing database language. You can write a corresponding database language query to answer the user's question based on the table structure described by the table creation statement. ##Table Structure CREATE TABLE legal_services.cases ( case_id character varying(64) NOT NULL, -- unique identifier for the case/matter case_number character varying(100) UNIQUE, -- official case number (court or internal) case_name text NOT NULL, -- descriptive name or title for the case client_id character varying(64) NOT NULL, -- FK to clients table lead_lawyer_id character varying(64) NOT NULL, -- FK to lawyers table (primary lawyer responsible) case_type character varying(100) NOT NULL, -- e.g., Litigation, Corporate, Family Law, IP status character varying(50) NOT NULL, -- e.g., Open, Closed, Pending, On Hold, Appealed date_opened timestamp NOT NULL, -- date the case was formally opened date_closed timestamp, -- date the case was closed (nullable) description text, -- detailed description of the case court_jurisdiction character varying(128), -- court or jurisdiction if applicable PRIMARY KEY (case_id) ) CREATE 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 ) CREATE 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 )
[ { "role": "user", "content": "Show me the total hours spent by each lawyer for each case, along with the case number and lawyer ID.", "sql": null }, { "role": "assistant", "content": "SELECT t.case_id, c.case_number, t.lawyer_id, SUM(t.hours_spent) AS total_hours\nFROM legal_services.time_en...
You are an expert in writing database language. You can write a corresponding database language query to answer the user's question based on the table structure described by the table creation statement. ##Table Structure CREATE TABLE insurance.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) ) CREATE 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) ) CREATE TABLE insurance.insurance_products ( product_id character varying(64) NOT NULL, product_name character varying(150) NOT NULL, product_type character varying(50) NOT NULL, description text, base_premium numeric(10, 2) NOT NULL, coverage_details text, underwriting_rules text, is_active boolean NOT NULL DEFAULT true, created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, updated_at timestamp, PRIMARY KEY (product_id) ) CREATE 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) )
[ { "role": "user", "content": "Show me the incident date, estimated loss, and the associated product name for all claims with an estimated loss greater than 20000.", "sql": null }, { "role": "assistant", "content": "SELECT c.incident_date, c.estimated_loss, p.product_name\nFROM insurance.clai...
You are an expert in writing database language. You can write a corresponding database language query to answer the user's question based on the table structure described by the table creation statement. ##Table Structure CREATE TABLE legal_services.clients ( client_id character varying(64) NOT NULL, -- unique identifier for the client first_name character varying(100) NOT NULL, -- client's first name last_name character varying(100) NOT NULL, -- client's last name company_name character varying(200), -- company name if applicable email character varying(128) UNIQUE NOT NULL, -- client's primary email phone character varying(32), -- client's contact phone number address text, -- client's full address date_registered timestamp NOT NULL, -- when the client was first registered status character varying(32) NOT NULL, -- client status (e.g., active, inactive, prospect) PRIMARY KEY (client_id) ) CREATE TABLE legal_services.lawyers ( lawyer_id character varying(64) NOT NULL, -- unique identifier for the lawyer first_name character varying(100) NOT NULL, -- lawyer's first name last_name character varying(100) NOT NULL, -- lawyer's last name bar_number character varying(64) UNIQUE NOT NULL, -- lawyer's bar association number firm_id character varying(64), -- FK to law_firms table email character varying(128) UNIQUE NOT NULL, -- lawyer's professional email phone character varying(32), -- lawyer's contact phone number specialization text, -- areas of legal expertise hire_date timestamp NOT NULL, -- date the lawyer was hired or joined is_partner boolean DEFAULT false, -- flag indicating if the lawyer is a partner PRIMARY KEY (lawyer_id) ) CREATE TABLE legal_services.law_firms ( firm_id character varying(64) NOT NULL, -- unique identifier for the law firm firm_name character varying(200) NOT NULL, -- official name of the law firm address text NOT NULL, -- primary address of the firm phone character varying(32), -- firm's main phone number website character varying(255), -- firm's website URL founded_date date, -- date the firm was established managing_partner_id character varying(64), -- FK to lawyers table (optional) PRIMARY KEY (firm_id) ) CREATE TABLE legal_services.cases ( case_id character varying(64) NOT NULL, -- unique identifier for the case/matter case_number character varying(100) UNIQUE, -- official case number (court or internal) case_name text NOT NULL, -- descriptive name or title for the case client_id character varying(64) NOT NULL, -- FK to clients table lead_lawyer_id character varying(64) NOT NULL, -- FK to lawyers table (primary lawyer responsible) case_type character varying(100) NOT NULL, -- e.g., Litigation, Corporate, Family Law, IP status character varying(50) NOT NULL, -- e.g., Open, Closed, Pending, On Hold, Appealed date_opened timestamp NOT NULL, -- date the case was formally opened date_closed timestamp, -- date the case was closed (nullable) description text, -- detailed description of the case court_jurisdiction character varying(128), -- court or jurisdiction if applicable PRIMARY KEY (case_id) ) CREATE TABLE legal_services.appointments ( appointment_id character varying(64) NOT NULL, -- unique identifier for the appointment client_id character varying(64) NOT NULL, -- FK to clients table lawyer_id character varying(64) NOT NULL, -- FK to lawyers table case_id character varying(64), -- FK to cases table (optional, if related to a specific case) start_time timestamp NOT NULL, -- scheduled start date and time end_time timestamp NOT NULL, -- scheduled end date and time location text, -- location of the meeting (address or virtual link) subject character varying(255), -- subject or purpose of the appointment notes text, -- additional notes for the appointment status character varying(50) NOT NULL, -- e.g., Scheduled, Completed, Canceled, Rescheduled created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, PRIMARY KEY (appointment_id) )
[ { "role": "user", "content": "Show all law firms with more than one partner assigned. Display the law firm name and the number of partners.", "sql": null }, { "role": "assistant", "content": "SELECT lf.firm_name, COUNT(l.lawyer_id) AS partner_count\nFROM legal_services.law_firms lf\nJOIN leg...
You are an expert in writing database language. You can write a corresponding database language query to answer the user's question based on the table structure described by the table creation statement. ##Table Structure CREATE TABLE social_media.users ( user_id character varying(64) NOT NULL, username character varying(50) NOT NULL UNIQUE, email character varying(128) NOT NULL UNIQUE, password_hash text NOT NULL, full_name character varying(100), profile_picture_url text, bio text, location character varying(100), created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, updated_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, is_verified boolean NOT NULL DEFAULT false, PRIMARY KEY (user_id) ) CREATE 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) ) CREATE 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) ) CREATE 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) ) CREATE 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) ) CREATE TABLE social_media.messages ( message_id character varying(64) NOT NULL, conversation_id character varying(64) NOT NULL, sender_user_id character varying(64) NOT NULL, content text, media_url text, media_type character varying(20), sent_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, read_at timestamp, PRIMARY KEY (message_id) ) CREATE TABLE social_media.conversation_participants ( participant_id character varying(64) NOT NULL, conversation_id character varying(64) NOT NULL, user_id character varying(64) NOT NULL, joined_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, last_read_at timestamp, PRIMARY KEY (participant_id), CONSTRAINT unique_user_conversation UNIQUE (conversation_id, user_id) ) CREATE 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) ) CREATE 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) )
[ { "role": "user", "content": "List all users who commented on posts tagged with hashtag 'spring', showing user_id, comment_id, content, and tag_name.", "sql": null }, { "role": "assistant", "content": "SELECT c.user_id, c.comment_id, c.content, h.tag_name\nFROM social_media.comments c\nJOIN ...
You are an expert in writing database language. You can write a corresponding database language query to answer the user's question based on the table structure described by the table creation statement. ##Table Structure CREATE TABLE gaming_technology.players ( player_id uuid PRIMARY KEY, username text, email text, password_hash text, registration_date timestamptz, last_login timestamptz, country_code text, status text, profile_data jsonb ) CREATE TABLE gaming_technology.games ( game_id uuid NOT NULL DEFAULT gen_random_uuid(), title character varying(200) NOT NULL, developer_id uuid NOT NULL, publisher_id uuid, genre character varying(100), release_date date, description text, platform character varying(50) NOT NULL, engine character varying(100), website character varying(255), PRIMARY KEY (game_id) ) CREATE TABLE gaming_technology.developers ( developer_id uuid PRIMARY KEY, name text, country text, founded_year int, website text, created_at timestamptz ) CREATE TABLE gaming_technology.game_sessions ( session_id uuid PRIMARY KEY, player_id uuid, game_id uuid, server_id uuid, start_time timestamptz, end_time timestamptz, duration_seconds int, score int, session_data jsonb ) CREATE TABLE gaming_technology.servers ( server_id.uuid, game_id.uuid, server_name.text, region.text, ip_address.text, port.integer, current_players.integer, max_players.integer, status.text, last_heartbeat.timestamptz ) CREATE TABLE gaming_technology.player_achievements ( player_achievement_id uuid NOT NULL DEFAULT gen_random_uuid(), player_id uuid NOT NULL, achievement_id uuid NOT NULL, unlocked_at timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP, PRIMARY KEY (player_achievement_id), UNIQUE (player_id, achievement_id) ) CREATE TABLE gaming_technology.in_game_items ( item_id uuid NOT NULL DEFAULT gen_random_uuid(), game_id uuid NOT NULL, item_name character varying(150) NOT NULL, item_type character varying(50) NOT NULL, description text, rarity character varying(30), cost_currency character varying(10), cost_amount numeric(12, 2), attributes jsonb, PRIMARY KEY (item_id) ) CREATE TABLE gaming_technology.player_inventory ( inventory_id uuid NOT NULL DEFAULT gen_random_uuid(), player_id uuid NOT NULL, item_id uuid NOT NULL, quantity integer NOT NULL DEFAULT 1, acquired_at timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP, instance_data jsonb, PRIMARY KEY (inventory_id) )
[ { "role": "user", "content": "Show me a list of players and, for each, list all the different games where they have acquired items. Also include the number of unique item types they've acquired per game.", "sql": null }, { "role": "assistant", "content": "SELECT p.player_id, p.username, g.ti...
You are an expert in writing database language. You can write a corresponding database language query to answer the user's question based on the table structure described by the table creation statement. ##Table Structure CREATE TABLE 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 ) CREATE 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 ) CREATE TABLE government_services.documents ( document_id character varying(64) NOT NULL, -- unique identifier for the document instance application_id character varying(64), -- FK to applications table (optional, could be linked to citizen directly) citizen_id character varying(64) NOT NULL, -- FK to citizens table document_type character varying(100) NOT NULL, -- e.g., Passport Scan, Proof of Address, Birth Certificate file_reference text NOT NULL, -- reference to the stored file (e.g., S3 URL, internal path) upload_timestamp timestamp NOT NULL, expiry_date date, verification_status character varying(30) DEFAULT 'Pending', -- e.g., Pending, Verified, Rejected verified_by_employee_id character varying(64), -- FK to employees table verification_timestamp timestamp, PRIMARY KEY (document_id) ) CREATE 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) ) CREATE TABLE government_services.appointments ( appointment_id character varying(64) NOT NULL, -- unique identifier for the appointment citizen_id character varying(64) NOT NULL, -- FK to citizens table employee_id character varying(64), -- FK to employees table (optional, if assigned) location_id character varying(64), -- FK to service_locations table (if physical) service_id character varying(64), -- FK to services table (optional, if related to specific service) scheduled_start_time timestamp NOT NULL, scheduled_end_time timestamp, purpose text NOT NULL, -- reason for the appointment status character varying(30) NOT NULL, -- e.g., Scheduled, Completed, Cancelled, No-Show booking_method character varying(50), -- e.g., Online, Phone, In-Person created_at timestamp NOT NULL, -- when the appointment was booked notes text, PRIMARY KEY (appointment_id) ) CREATE 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 )
[ { "role": "user", "content": "For each service category, show the category and the number of distinct citizens who have scheduled at least one appointment for a service in that category. Order the results by the number of citizens in descending order.", "sql": null }, { "role": "assistant", ...
You are an expert in writing database language. You can write a corresponding database language query to answer the user's question based on the table structure described by the table creation statement. ##Table Structure CREATE TABLE legal_services.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 )
[ { "role": "user", "content": "Find all pairs of appointments that are scheduled for the same case and overlap in time. Show the IDs of the two overlapping appointments and the shared case ID.", "sql": null }, { "role": "assistant", "content": "SELECT t1.appointment_id AS appointment1_id, t2....
You are an expert in writing database language. You can write a corresponding database language query to answer the user's question based on the table structure described by the table creation statement. ##Table Structure CREATE TABLE 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 )
[ { "role": "user", "content": "Show a count of drivers per status.", "sql": null }, { "role": "assistant", "content": "SELECT status, COUNT(*) AS driver_count\nFROM transportation.drivers\nGROUP BY status;", "sql": null }, { "role": "user", "content": "Can you also list the ea...
You are an expert in writing database language. You can write a corresponding database language query to answer the user's question based on the table structure described by the table creation statement. ##Table Structure CREATE TABLE insurance.customers ( customer_id text PRIMARY KEY, first_name text, last_name text, date_of_birth date, ssn_hash text, address_line1 text, address_line2 text, city text, state text, zip_code text, country text, phone_number text, email text, created_at timestamp, updated_at timestamp, status text ) CREATE TABLE insurance.policies ( policy_id text PRIMARY KEY, customer_id text, product_id text, agent_id text, policy_number text, start_date date, end_date date, premium_amount numeric, coverage_limit numeric, deductible numeric, status text, issued_at timestamp, cancellation_date date, cancellation_reason text ) CREATE TABLE insurance.claims ( claim_id text PRIMARY KEY, policy_id text, customer_id text, incident_date timestamp, reported_date timestamp, description text, estimated_loss numeric, status text, settlement_amount numeric, settlement_date date, claim_handler_id text, police_report_number text ) CREATE 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 ) CREATE 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 ) CREATE TABLE insurance.claim_documents ( document_id text PRIMARY KEY, claim_id text, document_type text, file_name text, file_path text, file_size_bytes int, mime_type text, uploaded_by text, uploaded_at timestamp, description text ) CREATE 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 )
[ { "role": "user", "content": "Find the average settlement_amount of closed claims for each claim handler. Return claim_handler_id and avg_settlement_amount.", "sql": null }, { "role": "assistant", "content": "SELECT c.claim_handler_id, AVG(c.settlement_amount) AS avg_settlement_amount\nFROM ...
You are an expert in writing database language. You can write a corresponding database language query to answer the user's question based on the table structure described by the table creation statement. ##Table Structure CREATE TABLE 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 ) CREATE 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 ) CREATE 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 ) CREATE 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 ) CREATE 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 ) CREATE TABLE hospitality_technology.payments ( payment_id character varying(64) NOT NULL, -- unique identifier for the payment transaction reservation_id character varying(64), -- FK to reservations (if payment is for a stay) guest_id character varying(64) NOT NULL, -- FK to guests (who paid) bill_id character varying(64), -- FK to bills/invoices this payment applies to amount numeric(12,2) NOT NULL, -- amount of the payment currency_code character varying(3) NOT NULL, -- ISO currency code (e.g., USD, EUR) payment_method character varying(50) NOT NULL, -- e.g., CreditCard, Cash, BankTransfer, Points, Voucher card_type character varying(50), -- e.g., Visa, MasterCard, Amex (if CC) card_last_four character varying(4), -- last 4 digits of CC (if CC) transaction_ref character varying(128), -- reference ID from payment gateway or processor payment_timestamp timestamp with time zone NOT NULL DEFAULT current_timestamp, -- when the payment occurred status character varying(50) NOT NULL, -- e.g., Pending, Succeeded, Failed, Refunded, Disputed staff_id_processed character varying(64), -- FK to staff (who processed the payment) notes text, -- notes about the payment 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) ) CREATE TABLE hospitality_technology.reviews ( review_id character varying(64) NOT NULL, property_id character varying(64) NOT NULL, reservation_id character varying(64) UNIQUE, guest_id character varying(64) NOT NULL, rating_overall integer, rating_cleanliness integer, rating_service integer, rating_location integer, rating_value integer, comment text, review_source character varying(100), review_date timestamp with time zone NOT NULL DEFAULT current_timestamp, is_public boolean DEFAULT true, staff_response text, response_staff_id character varying(64), response_date timestamp with time zone, PRIMARY KEY (review_id), FOREIGN KEY (property_id) REFERENCES hospitality_technology.properties(property_id), FOREIGN KEY (reservation_id) REFERENCES hospitality_technology.reservations(reservation_id), FOREIGN KEY (guest_id) REFERENCES hospitality_technology.guests(guest_id), FOREIGN KEY (response_staff_id) REFERENCES hospitality_technology.staff(staff_id) )
[ { "role": "user", "content": "Show all payments along with the guest's first and last name, and the staff member who processed each payment. Include payment_id, amount, currency_code, payment_timestamp, guest first_name, guest last_name, staff first_name, and staff last_name.", "sql": null }, { ...
You are an expert in writing database language. You can write a corresponding database language query to answer the user's question based on the table structure described by the table creation statement. ##Table Structure CREATE TABLE insurance.agents ( agent_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, agency_name character varying(150), license_number character varying(100) NOT NULL UNIQUE, license_state character varying(50) NOT NULL, contact_email character varying(128) UNIQUE, contact_phone character varying(30), hire_date date, termination_date date, status character varying(20) NOT NULL DEFAULT 'Active', commission_rate numeric(5, 4) NOT NULL DEFAULT 0.05, manager_id character varying(64), PRIMARY KEY (agent_id) )
[ { "role": "user", "content": "Show all active agents along with their respective managers' full names.", "sql": null }, { "role": "assistant", "content": "SELECT a.agent_id, a.first_name || ' ' || a.last_name AS agent_name, m.first_name || ' ' || m.last_name AS manager_name FROM insurance.ag...
You are an expert in writing database language. You can write a corresponding database language query to answer the user's question based on the table structure described by the table creation statement. ##Table Structure CREATE TABLE gaming_technology.players ( player_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for the player username character varying(100) NOT NULL UNIQUE, -- player's chosen display name email character varying(255) NOT NULL UNIQUE, -- player's email address for login/recovery password_hash text NOT NULL, -- securely hashed password registration_date timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP, -- when the player account was created last_login timestamp with time zone, -- timestamp of the last successful login country_code character(2), -- player's country (ISO 3166-1 alpha-2) status character varying(20) NOT NULL DEFAULT 'active', -- account status (e.g., active, banned, suspended) profile_data jsonb, -- flexible field for avatar url, bio, preferences etc. PRIMARY KEY (player_id) ) CREATE TABLE gaming_technology.games ( game_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for the game title character varying(200) NOT NULL, -- official title of the game developer_id uuid NOT NULL, -- FK linking to the developers table publisher_id uuid, -- FK linking to a potential publishers table (optional) genre character varying(100), -- primary genre (e.g., RPG, FPS, Strategy) release_date date, -- official release date description text, -- short description or synopsis of the game platform character varying(50) NOT NULL, -- primary platform (e.g., PC, PlayStation 5, Xbox Series X, Mobile) engine character varying(100), -- game engine used (e.g., Unreal Engine 5, Unity) website character varying(255), -- official website URL PRIMARY KEY (game_id) -- FOREIGN KEY (developer_id) REFERENCES gaming_technology.developers(developer_id) -- Example FK constraint ) CREATE TABLE gaming_technology.game_sessions ( session_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for the game session player_id uuid NOT NULL, -- FK linking to the players table game_id uuid NOT NULL, -- FK linking to the games table server_id uuid, -- FK linking to the servers table (nullable for single-player) start_time timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP, -- when the session began end_time timestamp with time zone, -- when the session ended (null if ongoing) duration_seconds integer, -- calculated duration of the session in seconds score integer, -- player's score for the session, if applicable session_data jsonb, -- flexible field for session-specific info (e.g., map played, character used) PRIMARY KEY (session_id) -- FOREIGN KEY (player_id) REFERENCES gaming_technology.players(player_id), -- FOREIGN KEY (game_id) REFERENCES gaming_technology.games(game_id), -- FOREIGN KEY (server_id) REFERENCES gaming_technology.servers(server_id) ) CREATE TABLE gaming_technology.servers ( server_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for the game server instance game_id uuid NOT NULL, -- FK linking to the game this server hosts server_name character varying(150), -- display name for the server region character varying(50) NOT NULL, -- geographical region (e.g., us-east-1, eu-west-2) ip_address character varying(45), -- IP address (IPv4 or IPv6) port integer, -- network port number current_players integer NOT NULL DEFAULT 0, -- number of players currently connected max_players integer NOT NULL, -- maximum player capacity status character varying(30) NOT NULL DEFAULT 'offline', -- server status (e.g., online, offline, maintenance) last_heartbeat timestamp with time zone, -- last time the server reported its status PRIMARY KEY (server_id) -- FOREIGN KEY (game_id) REFERENCES gaming_technology.games(game_id) ) CREATE TABLE gaming_technology.achievements ( achievement_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for an achievement definition game_id uuid NOT NULL, -- FK linking to the game the achievement belongs to name character varying(150) NOT NULL, -- name of the achievement description text NOT NULL, -- how to unlock the achievement icon_url character varying(255), -- URL for the achievement's icon points integer DEFAULT 0, -- points awarded for unlocking (optional) hidden boolean DEFAULT false, -- whether the achievement details are hidden until unlocked PRIMARY KEY (achievement_id) -- FOREIGN KEY (game_id) REFERENCES gaming_technology.games(game_id) ) CREATE TABLE gaming_technology.player_achievements ( player_achievement_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for this unlock instance player_id uuid NOT NULL, -- FK linking to the player who unlocked it achievement_id uuid NOT NULL, -- FK linking to the achievement definition unlocked_at timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP, -- when the achievement was unlocked PRIMARY KEY (player_achievement_id), UNIQUE (player_id, achievement_id) -- Ensure a player can only unlock an achievement once -- FOREIGN KEY (player_id) REFERENCES gaming_technology.players(player_id), -- FOREIGN KEY (achievement_id) REFERENCES gaming_technology.achievements(achievement_id) ) CREATE TABLE gaming_technology.in_game_items ( item_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for the item definition game_id uuid NOT NULL, -- FK linking to the game this item belongs to item_name character varying(150) NOT NULL, -- name of the item item_type character varying(50) NOT NULL, -- type (e.g., Cosmetic, Consumable, Weapon, Armor) description text, -- description of the item rarity character varying(30), -- item rarity (e.g., Common, Rare, Epic, Legendary) cost_currency character varying(10), -- currency code if purchasable (e.g., USD, EUR, GOLD) cost_amount numeric(12, 2), -- price if purchasable attributes jsonb, -- flexible field for item stats or properties PRIMARY KEY (item_id) -- FOREIGN KEY (game_id) REFERENCES gaming_technology.games(game_id) ) CREATE TABLE gaming_technology.player_inventory ( inventory_id uuid NOT NULL DEFAULT gen_random_uuid(), -- unique identifier for an inventory entry player_id uuid NOT NULL, -- FK linking to the player owning the item item_id uuid NOT NULL, -- FK linking to the item definition quantity integer NOT NULL DEFAULT 1, -- number of items held (for stackable items) acquired_at timestamp with time zone NOT NULL DEFAULT CURRENT_TIMESTAMP, -- when the item was acquired instance_data jsonb, -- data specific to this instance (e.g., weapon mods, durability) PRIMARY KEY (inventory_id), -- Optional unique constraint if items are non-stackable or unique instances -- UNIQUE (player_id, item_id) -- Use if quantity is always 1 -- FOREIGN KEY (player_id) REFERENCES gaming_technology.players(player_id), -- FOREIGN KEY (item_id) REFERENCES gaming_technology.in_game_items(item_id) )
[ { "role": "user", "content": "Show usernames of players who own items of 'Legendary' rarity.", "sql": null }, { "role": "assistant", "content": "SELECT DISTINCT T1.username FROM players AS T1 JOIN player_inventory AS T2 ON T1.player_id = T2.player_id JOIN in_game_items AS T3 ON T2.item_id = ...
You are an expert in writing database language and you can refuse the user's question if the question is not related to the table structure. You can write a corresponding database language query to answer the user's question based on the table structure described by the table creation statement. ##Table Structure CREATE TABLE manufacturing.employees ( employee_id text PRIMARY KEY, first_name text, last_name text, job_title text, skill_certifications text, hire_date date, assigned_line_id text, employment_status text, supervisor_employee_id text )
[ { "role": "user", "content": "What is the total number of vacation days taken by employee with ID 'EMP101' in the past year?", "sql": null }, { "role": "assistant", "content": "I'm sorry, but I can't provide information on the vacation days taken by an employee as this data is not stored in ...
You are an expert in writing database language. You can write a corresponding database language query to answer the user's question based on the table structure described by the table creation statement. ##Table Structure CREATE TABLE social_media.conversations ( conversation_id text PRIMARY KEY, created_at timestamp, last_message_at timestamp, is_group_chat bool, group_name text )
[ { "role": "user", "content": "Show me all group chats with their names and the time they were last active.", "sql": null }, { "role": "assistant", "content": "SELECT group_name, last_message_at FROM social_media.conversations WHERE is_group_chat = TRUE;", "sql": null }, { "role":...
You are an expert in writing database language. You can write a corresponding database language query to answer the user's question based on the table structure described by the table creation statement. ##Table Structure CREATE TABLE insurance.premium_payments ( payment_id text PRIMARY KEY, policy_id text, customer_id text, payment_date timestamp, amount_paid numeric, payment_method text, transaction_reference text, due_date date, payment_period_start date, payment_period_end date, status text )
[ { "role": "user", "content": "Which customers have made more than three premium payments in 2024? Show the customer_id and the number of payments.", "sql": null }, { "role": "assistant", "content": "SELECT customer_id, COUNT(*) AS payment_count FROM insurance.premium_payments WHERE payment_d...
You are an expert in writing database language. You can write a corresponding database language query to answer the user's question based on the table structure described by the table creation statement. ##Table Structure CREATE TABLE hospitality_technology.services ( service_id text, property_id text, service_name text, description text, category text, price numeric, unit text, is_available boolean, department text )
[ { "role": "user", "content": "List all food and beverage services (category = 'Food & Beverage') with their names, prices, and units, where the price is less than $20.", "sql": null }, { "role": "assistant", "content": "SELECT service_name, price, unit FROM hospitality_technology.services WH...
You are an expert in writing database language. You can write a corresponding database language query to answer the user's question based on the table structure described by the table creation statement. ##Table Structure CREATE TABLE government_services.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 )
[ { "role": "user", "content": "Find all applications that were submitted in 2023 but received a decision ('Approved' or 'Rejected') in 2024. List the application ID, submitted date, decision date, and status.", "sql": null }, { "role": "assistant", "content": "SELECT application_id, submitted...
You are an expert in writing database language. You can write a corresponding database language query to answer the user's question based on the table structure described by the table creation statement. ##Table Structure CREATE TABLE insurance.claims ( claim_id text, policy_id text, customer_id text, incident_date timestamp, reported_date timestamp, description text, estimated_loss numeric, status text, settlement_amount numeric, settlement_date date, claim_handler_id text, police_report_number text ) CREATE 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 ) CREATE 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 ) CREATE 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 )
[ { "role": "user", "content": "Show me all claims with police reports that were handled by agents hired in the last 2 years, along with the agent's full name and agency.", "sql": null }, { "role": "assistant", "content": "SELECT c.claim_id, c.policy_id, c.incident_date, c.police_report_number...
You are an expert in writing database language. You can write a corresponding database language query to answer the user's question based on the table structure described by the table creation statement. ##Table Structure CREATE TABLE hospitality_technology.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 )
[ { "role": "user", "content": "How many reservations have been booked each month in 2023?", "sql": null }, { "role": "assistant", "content": "SELECT DATE_TRUNC('month', created_at) AS month,\n COUNT(*) AS reservation_count\nFROM hospitality_technology.reservations\nWHERE created_at >= '...
You are an expert in writing database language. You can write a corresponding database language query to answer the user's question based on the table structure described by the table creation statement. ##Table Structure CREATE TABLE blockchain.wallets ( wallet_id.text, user_id.text, address_id.text, private_key.text )
[ { "role": "user", "content": "Show me all wallet addresses that belong to user_id 'U12345'.", "sql": null }, { "role": "assistant", "content": "SELECT address_id FROM blockchain.wallets WHERE user_id = 'U12345';", "sql": null }, { "role": "user", "content": "Now join this wit...
You are an expert in writing database language. You can write a corresponding database language query to answer the user's question based on the table structure described by the table creation statement. ##Table Structure CREATE TABLE government_services.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 ) CREATE 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 ) CREATE 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 ) CREATE 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 ) CREATE 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 ) CREATE 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 )
[ { "role": "user", "content": "Show the full names and contact emails of all citizens who have made a payment for an application that is currently in 'Pending' status.", "sql": null }, { "role": "assistant", "content": "SELECT DISTINCT c.first_name || ' ' || c.last_name AS full_name, c.contac...
You are an expert in writing database language. You can write a corresponding database language query to answer the user's question based on the table structure described by the table creation statement. ##Table Structure CREATE TABLE social_media.users ( user_id character varying(64) NOT NULL, -- unique identifier for the user username character varying(50) NOT NULL UNIQUE, -- user's unique handle email character varying(128) NOT NULL UNIQUE, -- user's email address password_hash text NOT NULL, -- hashed password full_name character varying(100), -- user's full name profile_picture_url text, -- URL to the profile picture bio text, -- short user biography location character varying(100), -- user's location created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of account creation updated_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of last profile update is_verified boolean NOT NULL DEFAULT false, -- verification status PRIMARY KEY (user_id) ) CREATE TABLE social_media.posts ( post_id character varying(64) NOT NULL, -- unique identifier for the post user_id character varying(64) NOT NULL, -- identifier of the user who created the post (FK to users.user_id) content text, -- textual content of the post media_url text, -- URL to attached media (image/video) media_type character varying(20), -- type of media ('image', 'video', null) created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of post creation updated_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of last post edit visibility character varying(20) NOT NULL DEFAULT 'public', -- visibility ('public', 'friends', 'private') location_lat numeric(9,6), -- latitude of post location location_lon numeric(9,6), -- longitude of post location PRIMARY KEY (post_id) ) CREATE TABLE social_media.comments ( comment_id character varying(64) NOT NULL, -- unique identifier for the comment post_id character varying(64) NOT NULL, -- identifier of the post being commented on (FK to posts.post_id) user_id character varying(64) NOT NULL, -- identifier of the user who made the comment (FK to users.user_id) parent_comment_id character varying(64), -- identifier of the parent comment if it's a reply (FK to comments.comment_id) content text NOT NULL, -- textual content of the comment created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of comment creation updated_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of last comment edit PRIMARY KEY (comment_id) ) CREATE TABLE social_media.likes ( like_id character varying(64) NOT NULL, -- unique identifier for the like user_id character varying(64) NOT NULL, -- identifier of the user who liked (FK to users.user_id) post_id character varying(64), -- identifier of the post being liked (FK to posts.post_id, nullable) comment_id character varying(64), -- identifier of the comment being liked (FK to comments.comment_id, nullable) created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of when the like occurred PRIMARY KEY (like_id), CONSTRAINT unique_user_like UNIQUE (user_id, post_id, comment_id), -- prevent duplicate likes CONSTRAINT check_like_target CHECK (post_id IS NOT NULL OR comment_id IS NOT NULL) -- ensure it likes something ) CREATE TABLE social_media.follows ( follow_id character varying(64) NOT NULL, -- unique identifier for the follow relationship follower_user_id character varying(64) NOT NULL, -- identifier of the user who is following (FK to users.user_id) following_user_id character varying(64) NOT NULL, -- identifier of the user being followed (FK to users.user_id) created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of when the follow started PRIMARY KEY (follow_id), CONSTRAINT unique_follow UNIQUE (follower_user_id, following_user_id) -- prevent duplicate follows ) CREATE TABLE social_media.hashtags ( hashtag_id character varying(64) NOT NULL, -- unique identifier for the hashtag tag_name character varying(100) NOT NULL UNIQUE, -- the actual hashtag text (without '#') created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp when the hashtag was first used PRIMARY KEY (hashtag_id) ) CREATE TABLE social_media.messages ( message_id character varying(64) NOT NULL, -- unique identifier for the message conversation_id character varying(64) NOT NULL, -- identifier for the conversation thread (FK to conversations.conversation_id) sender_user_id character varying(64) NOT NULL, -- identifier of the sender (FK to users.user_id) content text, -- textual content of the message media_url text, -- URL to attached media (image/video) media_type character varying(20), -- type of media ('image', 'video', null) sent_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp when message was sent read_at timestamp, -- timestamp when message was read by recipient(s) PRIMARY KEY (message_id) ) CREATE TABLE social_media.conversations ( conversation_id character varying(64) NOT NULL, -- unique identifier for the conversation created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp when conversation was initiated last_message_at timestamp, -- timestamp of the last message in the conversation is_group_chat boolean NOT NULL DEFAULT false, -- indicates if it's a group chat or direct message group_name character varying(100), -- name of the group chat (if applicable) PRIMARY KEY (conversation_id) ) CREATE TABLE social_media.conversation_participants ( participant_id character varying(64) NOT NULL, -- unique identifier for the participant entry conversation_id character varying(64) NOT NULL, -- identifier of the conversation (FK to conversations.conversation_id) user_id character varying(64) NOT NULL, -- identifier of the user in the conversation (FK to users.user_id) joined_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp when user joined the conversation last_read_at timestamp, -- timestamp indicating up to when the user has read messages PRIMARY KEY (participant_id), CONSTRAINT unique_user_conversation UNIQUE (conversation_id, user_id) -- prevent user being added multiple times ) CREATE TABLE social_media.notifications ( notification_id character varying(64) NOT NULL, -- unique identifier for the notification recipient_user_id character varying(64) NOT NULL, -- user receiving the notification (FK to users.user_id) sender_user_id character varying(64), -- user triggering the notification (FK to users.user_id, can be null for system notifications) notification_type character varying(30) NOT NULL, -- type of notification ('like', 'comment', 'follow', 'mention', 'message') target_entity_id character varying(64), -- ID of the related entity (post_id, comment_id, user_id, conversation_id) target_entity_type character varying(20), -- type of the related entity ('post', 'comment', 'user', 'conversation') created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp notification was created read_at timestamp, -- timestamp notification was marked as read PRIMARY KEY (notification_id) ) CREATE TABLE social_media.user_settings ( setting_id character varying(64) NOT NULL, -- unique identifier for the setting entry user_id character varying(64) NOT NULL UNIQUE, -- user the settings belong to (FK to users.user_id) theme character varying(20) DEFAULT 'light', -- UI theme ('light', 'dark') email_notifications_enabled boolean DEFAULT true, -- enable/disable email notifications push_notifications_enabled boolean DEFAULT true, -- enable/disable push notifications private_profile boolean DEFAULT false, -- is the user profile private updated_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, -- timestamp of last setting change PRIMARY KEY (setting_id) )
[ { "role": "user", "content": "List users who commented on posts and the content of the post they commented on. Show commenter username and post content.", "sql": null }, { "role": "assistant", "content": "SELECT T1.username, T2.content FROM social_media.users AS T1 JOIN social_media.comments...
You are an expert in writing database language. You can write a corresponding database language query to answer the user's question based on the table structure described by the table creation statement. ##Table Structure Use Hashes. Key pattern: 'component:<component_id>'. 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:<material_id>' -> Set<component_id>).
[ { "role": "user", "content": "Can you help me get a list of components and their associated materials, including the supplier information for each component?", "sql": null }, { "role": "assistant", "content": "SMEMBERS material_components:<material_id>\nHGETALL component:<component_id>\nHGET...
You are an expert in writing database language. You can write a corresponding database language query to answer the user's question based on the table structure described by the table creation statement. ##Table Structure CREATE TABLE financial_services.securities ( security_id character varying(64) NOT NULL, -- unique identifier for the security ticker_symbol character varying(20) NOT NULL UNIQUE, -- stock ticker or fund symbol isin_code character varying(12) UNIQUE, -- International Securities Identification Number cusip_code character varying(9) UNIQUE, -- CUSIP number security_name text NOT NULL, -- full name of the security security_type character varying(50) NOT NULL, -- e.g., Stock, Bond, ETF, Mutual Fund, Option, Future exchange character varying(50), -- primary exchange where traded (e.g., NYSE, NASDAQ) currency character varying(3) NOT NULL, -- currency the security is denominated in issuer_name character varying(255), -- name of the issuing entity sector character varying(100), -- industry sector last_updated timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, PRIMARY KEY (security_id) )
[ { "role": "user", "content": "For each sector, retrieve the ticker symbol and last_updated timestamp of the earliest and latest updated securities, labeling them as earliest_ticker, earliest_updated, latest_ticker, and latest_updated.", "sql": null }, { "role": "assistant", "content": "WITH ...
You are an expert in writing database language. You can write a corresponding database language query to answer the user's question based on the table structure described by the table creation statement. ##Table Structure CREATE TABLE transportation.fuel_logs ( fuel_log_id character varying(64) NOT NULL, -- unique identifier for the fuel log entry vehicle_id character varying(64) NOT NULL, -- identifier of the vehicle fueled trip_id character varying(64), -- optional: identifier of the trip during which fueling occurred log_timestamp timestamp with time zone NOT NULL, -- time when fueling occurred fuel_type character varying(32) NOT NULL, -- type of fuel added (matches vehicle's fuel type) quantity numeric(10, 3) NOT NULL, -- amount of fuel added (e.g., Liters, Gallons, kWh) unit character varying(16) NOT NULL, -- unit of quantity (e.g., L, gal, kWh) cost_per_unit numeric(8, 4), -- price per unit of fuel total_cost numeric(10, 2) NOT NULL, -- total cost of the fuel purchase odometer_reading integer, -- vehicle mileage at time of fueling location_id character varying(64), -- identifier of the fueling station/location PRIMARY KEY (fuel_log_id) )
[ { "role": "user", "content": "For each trip, provide the trip_id, the total fuel quantity refueled, and the number of refueling events that occurred during the trip.", "sql": null }, { "role": "assistant", "content": "SELECT trip_id, SUM(quantity) AS total_fuel_quantity, COUNT(*) AS refuel_e...
You are an expert in writing database language. You can write a corresponding database language query to answer the user's question based on the table structure described by the table creation statement. ##Table Structure CREATE TABLE trading_platform.dapps ( dapp_id character varying(64) NOT NULL, -- unique identifier for the DApp name character varying(128) NOT NULL, -- name of the DApp description text NOT NULL, -- description of the DApp url character varying(256) NOT NULL, -- URL of the DApp PRIMARY KEY (dapp_id) ) CREATE TABLE trading_platform.kyc_audit ( kyc_audit_id character varying(64) NOT NULL, -- unique identifier for the KYC audit user_id character varying(64) NOT NULL, -- identifier of the user being audited status character varying(32) NOT NULL, -- status of the KYC audit (e.g., pending, approved, rejected) reviewed_at timestamp NOT NULL, -- time when the KYC audit was reviewed PRIMARY KEY (kyc_audit_id) )
[ { "role": "user", "content": "Show me the names and URLs of all DApps, and for each DApp, list the KYC status and last review date for all users who have an audit entry.", "sql": null }, { "role": "assistant", "content": "SELECT d.name AS dapp_name, d.url, k.user_id, k.status, k.reviewed_at\...
End of preview. Expand in Data Studio

No dataset card yet

Downloads last month
4