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 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 )
CREATE TABLE social_media.likes ( like_id.text, user_id.text, post_id.text, comment_id.text, created_at.timestamp )
CREATE TABLE social_media.hashtags ( hashtag_id text, tag_name text, created_at timestamp )
CREATE TABLE social_media.post_hashtags ( post_hashtag_id text, post_id text, hashtag_id text )
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, -- 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)
)
| [
{
"role": "user",
"content": "List all post IDs and the corresponding hashtag names where posts were created near latitude 40.0 and longitude -74.0.",
"sql": null
},
{
"role": "assistant",
"content": "SELECT p.post_id, h.tag_name\nFROM social_media.posts p\nJOIN social_media.post_hashtags ph... |
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.lawyers ( lawyer_id text PRIMARY KEY, first_name text, last_name text, bar_number text UNIQUE, firm_id text, email text UNIQUE, phone text, specialization text, hire_date timestamp, is_partner bool )
| [
{
"role": "user",
"content": "List the full name, email, and phone number of all partners together with the full name of a non-partner lawyer in the same law firm.",
"sql": null
},
{
"role": "assistant",
"content": "SELECT p.first_name AS partner_first_name, p.last_name AS partner_last_name,... |
You are an expert in writing database language. You can write a corresponding database language query to answer the user's question based on the table structure described by the table creation statement.
##Table Structure
CREATE TABLE healthcare.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 )
| [
{
"role": "user",
"content": "For each location, what is the average appointment duration? Show location_id and the average duration.",
"sql": null
},
{
"role": "assistant",
"content": "SELECT location_id, AVG(duration_minutes) FROM healthcare.appointments GROUP BY location_id;",
"sql": ... |
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 character varying(64) NOT NULL, -- unique identifier for the service
agency_id character varying(64) NOT NULL, -- FK to agencies table
service_name character varying(255) NOT NULL, -- name of the service (e.g., Driver's License Renewal)
description text,
category character varying(100), -- e.g., Licensing, Benefits, Taxation, Permits
eligibility_criteria text, -- description of who is eligible
standard_fee numeric(10, 2) DEFAULT 0.00, -- typical fee for the service
average_processing_time_days integer, -- estimated processing time
is_active boolean DEFAULT true, -- whether the service is currently offered
online_application_url character varying(255),
PRIMARY KEY (service_id)
)
CREATE 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 )
CREATE TABLE government_services.service_locations (
location_id character varying(64) NOT NULL, -- unique identifier for the physical location
agency_id character varying(64) NOT NULL, -- FK to agencies table
location_name character varying(200), -- e.g., Downtown DMV Office
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, -- description of opening times
contact_phone character varying(32),
is_accessible boolean, -- accessibility information (e.g., wheelchair access)
PRIMARY KEY (location_id)
)
| [
{
"role": "user",
"content": "List the names of service locations and categories of active services offered by the same agency.",
"sql": null
},
{
"role": "assistant",
"content": "SELECT sl.location_name, s.category\nFROM government_services.service_locations AS sl\nJOIN government_services.... |
You are an expert in writing database language. You can write a corresponding database language query to answer the user's question based on the table structure described by the table creation statement.
##Table Structure
CREATE TABLE healthcare.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 )
| [
{
"role": "user",
"content": "Count the total number of distinct specialties listed in the doctors table.",
"sql": null
},
{
"role": "assistant",
"content": "SELECT count(DISTINCT specialty) FROM healthcare.doctors;",
"sql": null
},
{
"role": "user",
"content": "Show the lice... |
You are an expert in writing database language. You can write a corresponding database language query to answer the user's question based on the table structure described by the table creation statement.
##Table Structure
CREATE TABLE healthcare.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) )
CREATE 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) )
CREATE 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) )
CREATE 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) )
| [
{
"role": "user",
"content": "Show all prescriptions with prescription_id, patient_id, medication_id, quantity_dispensed, and refills_allowed.",
"sql": null
},
{
"role": "assistant",
"content": "SELECT prescription_id, patient_id, medication_id, quantity_dispensed, refills_allowed FROM healt... |
You are an expert in writing database language. You can write a corresponding database language query to answer the user's question based on the table structure described by the table creation statement.
##Table Structure
CREATE TABLE healthcare.medical_records (
record_id character varying(64) NOT NULL, -- unique identifier for the medical record entry
patient_id character varying(64) NOT NULL, -- FK to patients table
appointment_id character varying(64) UNIQUE, -- FK to appointments table (can be null if record not tied to specific appt)
doctor_id character varying(64) NOT NULL, -- FK to doctors table (doctor creating the record)
record_date timestamp with time zone NOT NULL, -- date the record/observation was made
chief_complaint text, -- patient's primary reason for visit
present_illness_history text, -- detailed history of the current issue
past_medical_history text, -- relevant past conditions/surgeries
physical_examination_notes text, -- findings from the physical exam
assessment text, -- doctor's assessment/diagnosis summary
treatment_plan text, -- planned course of action
vitals jsonb, -- store vitals like BP, HR, Temp as structured JSON
created_at timestamp with time zone NOT NULL DEFAULT current_timestamp,
PRIMARY KEY (record_id)
)
| [
{
"role": "user",
"content": "List each patient's first and last medical record entries, showing patient_id, earliest_record_id, earliest_record_date, latest_record_id, and latest_record_date.",
"sql": null
},
{
"role": "assistant",
"content": "SELECT\n fl.patient_id,\n fr.record_id AS... |
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.aircraft_models ( model_id text PRIMARY KEY, model_name text, manufacturer text, passenger_capacity int, max_range_km int, engine_type text, wingspan_m numeric, status text, first_flight_date date )
| [
{
"role": "user",
"content": "What are the environmental impact assessments for the production of the Airbus A350 model?",
"sql": null
},
{
"role": "assistant",
"content": "I'm sorry, but I don't have access to data regarding the environmental impact assessments for the production of specifi... |
You are an expert in writing database language. You can write a corresponding database language query to answer the user's question based on the table structure described by the table creation statement.
##Table Structure
CREATE TABLE web3.wallets ( wallet_id text, user_id text, address text, private_key text, created_at timestamp )
| [
{
"role": "user",
"content": "List all pairs of wallets that use the same private_key. Display w1.wallet_id, w1.user_id, w2.wallet_id, w2.user_id, and the shared private_key.",
"sql": null
},
{
"role": "assistant",
"content": "SELECT w1.wallet_id AS wallet1_id,\n w1.user_id AS user1_... |
You are an expert in writing database language. You can write a corresponding database language query to answer the user's question based on the table structure described by the table creation statement.
##Table Structure
CREATE TABLE web3.contracts ( contract_id character varying(64) NOT NULL, address character varying(128) NOT NULL, abi text NOT NULL, bytecode text NOT NULL, deployer_address character varying(128) NOT NULL, deployed_at timestamp NOT NULL, network_id character varying(64) NOT NULL, status character varying(32) NOT NULL, PRIMARY KEY (contract_id) )
CREATE TABLE web3.events ( event_id.text, contract_id.text, event_name.text, data.text, emitted_at.timestamp, transaction_id.text, log_index.integer )
CREATE TABLE web3.tokens (
token_id character varying(64) NOT NULL, -- unique identifier for the token
contract_address character varying(128) NOT NULL, -- address of the token contract
token_name character varying(128) NOT NULL, -- name of the token
token_symbol character varying(32) NOT NULL, -- symbol of the token
decimals integer NOT NULL, -- number of decimals for the token
total_supply numeric(38,14) NOT NULL, -- total supply of the token
PRIMARY KEY (token_id)
)
CREATE TABLE web3.token_transfers ( transfer_id text PRIMARY KEY, token_id text, from_address text, to_address text, value numeric, transaction_id text, log_index int )
CREATE TABLE web3.users ( user_id text, username text, email text, password_hash text, created_at timestamp )
| [
{
"role": "user",
"content": "List all events and any token transfers that occurred in the same transaction, showing event_id, event_name, transfer_id, and token_symbol.",
"sql": null
},
{
"role": "assistant",
"content": "SELECT\n e.event_id,\n e.event_name,\n tt.transfer_id,\n tk.token_... |
You are an expert in writing database language. You can write a corresponding database language query to answer the user's question based on the table structure described by the table creation statement.
##Table Structure
CREATE TABLE 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 )
CREATE 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 )
CREATE 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) )
CREATE 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 )
CREATE 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) )
CREATE 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) )
CREATE TABLE healthcare.patient_insurance (
patient_insurance_id character varying(64) NOT NULL, -- unique identifier for this patient-plan link
patient_id character varying(64) NOT NULL, -- FK to patients table
plan_id character varying(64) NOT NULL, -- FK to insurance_plans table
policy_number character varying(100) NOT NULL, -- patient's policy number
group_number character varying(100), -- group number, if applicable
subscriber_name character varying(200), -- name of the primary policy holder
effective_date date NOT NULL, -- date the coverage begins
expiration_date date, -- date the coverage ends (if known)
is_primary boolean NOT NULL DEFAULT true, -- indicates if this is the primary insurance
PRIMARY KEY (patient_insurance_id),
UNIQUE (patient_id, plan_id, policy_number) -- ensure a patient doesn't have the same policy twice
)
| [
{
"role": "user",
"content": "Show me all male patients who have received more than one prescription, including their full name, date of birth, and the total number of prescriptions.",
"sql": null
},
{
"role": "assistant",
"content": "SELECT p.patient_id, p.first_name, p.last_name, p.date_of... |
You are an expert in writing database language. You can write a corresponding database language query to answer the user's question based on the table structure described by the table creation statement.
##Table Structure
CREATE TABLE insurance.claims ( claim_id.text, policy_id.text, customer_id.text, incident_date.timestamp, reported_date.timestamp, description.text, estimated_loss.numeric, status.text, settlement_amount.numeric, settlement_date.date, claim_handler_id.text, police_report_number.text )
| [
{
"role": "user",
"content": "List the claim ID, incident date, estimated loss, and the first and last name of the customer for all claims with an estimated loss greater than 5000.",
"sql": null
},
{
"role": "assistant",
"content": "SELECT T1.claim_id, T1.incident_date, T1.estimated_loss, T2... |
You are an expert in writing database language. You can write a corresponding database language query to answer the user's question based on the table structure described by the table creation statement.
##Table Structure
CREATE TABLE 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 )
CREATE TABLE erc1155_approval_for_all ( block_number bigint, block_timestamp timestamp, transaction_index integer, transaction_hash text, log_index integer, contract_address text )
CREATE TABLE erc20_balances ( block_number bigint, contract_address text, wallet_address text, amount text, pk text )
CREATE TABLE erc20_balances_historical ( block_number bigint, contract_address text, wallet_address text, amount text, pk integer )
CREATE TABLE nft_holders ( block_number bigint, contract_address text, wallet_address text, token_id text, contract_type text, amount text, pk text )
CREATE TABLE nft_holder_historical ( block_number bigint, contract_address text, wallet_address text, token_id text, contract_type text, amount text, pk integer )
CREATE TABLE sui_coins ( object_id text, status text, coin_type text, balance text, owner text )
CREATE TABLE sui_coins_metadata ( object_id text, coin_type text, status text, decimals bigint, description text, icon_url text, symbol text, name text )
CREATE TABLE sui_nfts ( object_id text, status text, collection_type text, package_id text, previous_transaction text, display text, owner text, name text )
CREATE 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 )
CREATE 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 )
CREATE TABLE token_prices ( uuid text, blockchain text, address text, decimals bigint, symbol text, price real, timestamp timestamp )
CREATE TABLE token_prices_latest ( blockchain text, address text, decimals bigint, symbol text, price real, timestamp timestamp )
CREATE TABLE erc20_approval ( block_number bigint, block_timestamp timestamp, transaction_index integer, transaction_hash text, log_index integer, contract_address text, pk integer )
CREATE TABLE token_balances ( block_number bigint, block_timestamp timestamp, tick text, wallet_address text, total_supply decimal, amount decimal )
CREATE 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 )
CREATE 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 )
CREATE 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 )
CREATE TABLE token_balances_bitcoin ( block_number bigint, block_timestamp timestamp, tick text, wallet_address text, total_supply text, amount text )
CREATE 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 )
CREATE 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 )
CREATE 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 )
CREATE TABLE token_balances_avalanche ( block_number bigint, block_timestamp timestamp, tick text, wallet_address text, total_supply decimal, amount decimal )
| [
{
"role": "user",
"content": "Find all ERC20 tokens (from token_metas) currently held by wallet '0xfoo...' with a balance over 1000. Show the contract address and amount.",
"sql": null
},
{
"role": "assistant",
"content": "SELECT contract_address, amount\nFROM erc20_balances\nWHERE wallet_ad... |
You are an expert in writing database language. You can write a corresponding database language query to answer the user's question based on the table structure described by the table creation statement.
##Table Structure
CREATE TABLE transportation.locations ( location_id 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) )
| [
{
"role": "user",
"content": "Get all pairs of locations in the same city, showing both location IDs, names, and the shared city.",
"sql": null
},
{
"role": "assistant",
"content": "SELECT l1.location_id AS location1_id, l1.name AS location1_name,\n l2.location_id AS location2_id, l2.n... |
You are an expert in writing database language. You can write a corresponding database language query to answer the user's question based on the table structure described by the table creation statement.
##Table Structure
CREATE TABLE 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 )
| [
{
"role": "user",
"content": "How many cases are associated with each unique lead lawyer ID? Show the lead lawyer ID and the count of cases, but only for lawyers who lead at least 5 cases. Sort the results by the case count in descending order.",
"sql": null
},
{
"role": "assistant",
"conten... |
You are an expert in writing database language. You can write a corresponding database language query to answer the user's question based on the table structure described by the table creation statement.
##Table Structure
CREATE TABLE blockchain.addresses ( address_id text PRIMARY KEY, public_key text, balance numeric )
CREATE TABLE blockchain.wallets (
wallet_id character varying(64) NOT NULL, -- unique identifier for the wallet
user_id character varying(64) NOT NULL, -- identifier of the user owning the wallet
address_id character varying(128) NOT NULL, -- identifier of the address associated with the wallet
private_key text NOT NULL, -- private key of the wallet
PRIMARY KEY (wallet_id)
)
CREATE TABLE blockchain.users (
user_id character varying(64) NOT NULL, -- unique identifier for the user
username character varying(128) NOT NULL, -- username of the user
email character varying(128) NOT NULL, -- email address of the user
password_hash text NOT NULL, -- hashed password of the user
PRIMARY KEY (user_id)
)
CREATE TABLE blockchain.smart_contracts ( contract_id text PRIMARY KEY, creator_address text, code text, timestamp timestamp )
| [
{
"role": "user",
"content": "Find users whose username contains 'admin'.",
"sql": null
},
{
"role": "assistant",
"content": "SELECT user_id, username, email FROM blockchain.users WHERE username LIKE '%admin%';",
"sql": null
},
{
"role": "user",
"content": "For these users, l... |
You are an expert in writing database language. You can write a corresponding database language query to answer the user's question based on the table structure described by the table creation statement.
##Table Structure
CREATE TABLE financial_services.customers ( customer_id character varying(64) NOT NULL, first_name character varying(100) NOT NULL, last_name character varying(100) NOT NULL, date_of_birth date NOT NULL, ssn_hash character varying(128), address text NOT NULL, city character varying(100) NOT NULL, state character varying(50) NOT NULL, zip_code character varying(20) NOT NULL, country character varying(50) NOT NULL, email character varying(128) UNIQUE, phone_number character varying(32), created_at timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, status character varying(32) NOT NULL, risk_profile character varying(50), PRIMARY KEY (customer_id) )
CREATE 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) )
CREATE TABLE financial_services.securities ( security_id character varying(64) NOT NULL, ticker_symbol character varying(20) NOT NULL UNIQUE, isin_code character varying(12) UNIQUE, cusip_code character varying(9) UNIQUE, security_name text NOT NULL, security_type character varying(50) NOT NULL, exchange character varying(50), currency character varying(3) NOT NULL, issuer_name character varying(255), sector character varying(100), last_updated timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP, PRIMARY KEY (security_id) )
CREATE TABLE financial_services.trades ( trade_id character varying(64) NOT NULL, account_id character varying(64) NOT NULL, security_id character varying(64) NOT NULL, order_id character varying(64), trade_type character varying(10) NOT NULL, quantity numeric(19, 8) NOT NULL, price_per_unit numeric(19, 8) NOT NULL, total_amount numeric(19, 4) NOT NULL, commission numeric(10, 4), trade_timestamp timestamp NOT NULL, settlement_date date, status character varying(32) NOT NULL, execution_venue character varying(100), PRIMARY KEY (trade_id), FOREIGN KEY (account_id) REFERENCES financial_services.accounts(account_id), FOREIGN KEY (security_id) REFERENCES financial_services.securities(security_id) )
CREATE 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) )
| [
{
"role": "user",
"content": "List all customers and the total amount they have traded, showing their full name, email, and the total across all their trades. Join customers to their accounts, then to trades.",
"sql": null
},
{
"role": "assistant",
"content": "SELECT c.customer_id, c.first_n... |
You are an expert in writing database language. You can write a corresponding database language query to answer the user's question based on the table structure described by the table creation statement.
##Table Structure
CREATE TABLE 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 )
CREATE 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 )
CREATE 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 )
CREATE 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 )
CREATE 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 )
| [
{
"role": "user",
"content": "For each account type, show the average balance and the number of completed trades associated with accounts of that type.",
"sql": null
},
{
"role": "assistant",
"content": "SELECT a.account_type, AVG(a.balance) AS average_balance, COUNT(t.trade_id) AS completed... |
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.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 )
| [
{
"role": "user",
"content": "Can you show me the number of lawyers grouped by specialization?",
"sql": null
},
{
"role": "assistant",
"content": "SELECT specialization, COUNT(*) AS lawyer_count FROM lawyers GROUP BY specialization;",
"sql": null
},
{
"role": "user",
"content... |
You are an expert in writing database language. You can write a corresponding database language query to answer the user's question based on the table structure described by the table creation statement.
##Table Structure
CREATE TABLE 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 )
| [
{
"role": "user",
"content": "Can you show me all user IDs that have both email and push notifications disabled, along with whether their profile is set to private?",
"sql": null
},
{
"role": "assistant",
"content": "SELECT user_id, private_profile FROM social_media.user_settings WHERE email... |
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 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) )
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 )
| [
{
"role": "user",
"content": "Which services have 'Eligibility' mentioned in their eligibility_criteria field?",
"sql": null
},
{
"role": "assistant",
"content": "SELECT service_name, eligibility_criteria\nFROM government_services.services\nWHERE eligibility_criteria ILIKE '%Eligibility%';",... |
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.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 )
| [
{
"role": "user",
"content": "Find documents that have the same document_name but are associated with different cases. Show the document name and the two different case IDs.",
"sql": null
},
{
"role": "assistant",
"content": "SELECT d1.document_name, d1.case_id AS case_id_1, d2.case_id AS ca... |
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
Node Label ':AircraftModel'. Properties: { model_id: String (Constraint: UNIQUE), model_name: String, manufacturer: String, passenger_capacity: Integer, max_range_km: Integer, engine_type: String, wingspan_m: Float, status: String, first_flight_date: Date }. Index on model_id.
Node Label ':Component'. Properties: { component_id: String (Constraint: UNIQUE), part_number: String (Constraint: UNIQUE), component_name: String, description: String, weight_kg: Float, cost_usd: Float, criticality_level: String }. Relationships: (:Component)-[:MADE_OF]->(:Material {material_id}), (:Component)-[:SUPPLIED_BY]->(:Supplier {supplier_id}). Index on component_id, part_number.
Node Label ':Material'. Properties: { material_id: String (Constraint: UNIQUE), material_name: String, specification: String, description: String, density_kg_m3: Float, tensile_strength_mpa: Integer }. Index on material_id.
Node Label ':AssemblyLine'. Properties: { line_id: String (Constraint: UNIQUE), line_name: String, location_building: String, location_area: String, capacity_units_per_month: Integer, status: String }. Relationship: (:AssemblyLine)-[:BUILDS_MODEL]->(:AircraftModel {model_id}). Index on line_id.
Node Label ':AssemblyStep'. Properties: { step_id: String (Constraint: UNIQUE), step_number: Integer, step_name: String, description: String, standard_duration_hours: Float, required_skill_level: String, workstation: String }. Relationship: (:AssemblyLine {line_id})-[:HAS_STEP {sequence: <step_number>}]->(:AssemblyStep). Index on step_id.
Node Label ':AircraftBuild'. Properties: { build_id: String (Constraint: UNIQUE), serial_number: String (Constraint: UNIQUE), build_start_date: Datetime, estimated_completion_date: Date, actual_completion_date: Datetime, current_status: String, customer_order_id: String }. Relationships: (:AircraftBuild)-[:IS_MODEL]->(:AircraftModel {model_id}), (:AircraftBuild)-[:ASSEMBLED_ON]->(:AssemblyLine {line_id}). Index on build_id, serial_number, current_status.
Node Label ':Inspection'. Properties: { inspection_id: String (Constraint: UNIQUE), inspection_type: String, inspection_timestamp: Datetime, result: String, remarks: String }. Relationships: (:AircraftBuild {build_id})-[:UNDERWENT]->(:Inspection), (:Inspection)-[:PERFORMED_BY]->(:Employee {employee_id}), (:Inspection)-[:INSPECTED_COMPONENT]->(:Component {component_id}) (optional), (:Inspection)-[:FOLLOWED_STEP]->(:AssemblyStep {step_id}) (optional). Index on inspection_id.
| [
{
"role": "user",
"content": "我想获取某个组件的详细信息，包括组件名称、描述、重量以及成本。",
"sql": null
},
{
"role": "assistant",
"content": "MATCH (c:Component)\nWHERE c.component_id = 'specific_component_id'\nRETURN c.component_name, c.description, c.weight_kg, c.cost_usd",
"sql": null
},
{
"role": "user"... |
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.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 )
| [
{
"role": "user",
"content": "Can you list all appointments along with the scheduled start time, purpose, and booking method, as well as the employee ID and location ID for each appointment?",
"sql": null
},
{
"role": "assistant",
"content": "SELECT appointment_id, scheduled_start_time, purp... |
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.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 )
| [
{
"role": "user",
"content": "Show each vehicle's ID along with another vehicle's ID where they share the same make but have different models. Sort by the first vehicle_id.",
"sql": null
},
{
"role": "assistant",
"content": "SELECT v1.vehicle_id AS vehicle_a, v2.vehicle_id AS vehicle_b\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 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 )
| [
{
"role": "user",
"content": "I want to retrieve the agent ID, first and last name, along with their manager's contact email and phone number.",
"sql": null
},
{
"role": "assistant",
"content": "SELECT a.agent_id,\n a.first_name || ' ' || a.last_name AS agent_name,\n m.contact_em... |
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 for platform details. Key format: platform:<platform_id>
// 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
// To link platforms to stations (optional):
// SADD station:station_xyz:platforms platform:plat_123 platform:plat_456
// Use Hashes for train details. Key format: train:<train_id>
// HSET train:train_789 train_id "train_789" train_number "Acela 2151" model "Siemens Velaro" ... status "Active" ...
// To find train by train_number (optional index):
// SET train_number:"Acela 2151" train:train_789
// Use Hashes for car details. Key format: car:<car_id>
// 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"
// To link cars to trains (optional):
// SADD train:train_789:cars car:car_abc car:car_def
// Use Hashes for details. Key format: route_station:<route_station_id>
// HSET route_station:rs_ne_1 route_station_id "rs_ne_1" route_id "route_ne_corr" station_id "station_bos" sequence_order 1 ...
// To find stops for a route, use a Sorted Set (score by sequence_order):
// ZADD route:route_ne_corr:stops 1 route_station:rs_ne_1
// ZADD route:route_ne_corr:stops 2 route_station:rs_ne_2
// Use Hashes for schedule details. Key format: schedule:<schedule_id>
// 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"
// Use Hashes for details. Key format: schedule_stop:<stop_id>
// HSET schedule_stop:stop_sched1122_1 stop_id "stop_sched1122_1" schedule_id "sched_1122" station_id "station_bos" ...
// To find stops for a schedule, use a Sorted Set (score by sequence_order):
// ZADD schedule:sched_1122:stops 1 schedule_stop:stop_sched1122_1
// ZADD schedule:sched_1122:stops 2 schedule_stop:stop_sched1122_2
// Use Hashes for passenger details. Key format: passenger:<passenger_id>
// HSET passenger:pass_pqr passenger_id "pass_pqr" first_name "Alice" last_name "Smith" email "alice.smith@example.com" ...
// To find passenger by email (optional index):
// SET passenger_email:"alice.smith@example.com" passenger:pass_pqr
// Use Hashes for booking details. Key format: booking:<booking_id>
// HSET booking:book_zyx booking_id "book_zyx" passenger_id "pass_pqr" schedule_id "sched_1122" ... status "Confirmed" ...
// To link bookings to passengers/schedules (optional):
// SADD passenger:pass_pqr:bookings booking:book_zyx
// SADD schedule:sched_1122:bookings booking:book_zyx
// Use Hashes for ticket details. Key format: ticket:<ticket_id>
// HSET ticket:tkt_1a2b ticket_id "tkt_1a2b" booking_id "book_zyx" car_id "car_abc" seat_number "12A" ... is_checked_in 0 ...
// To link tickets to bookings (optional):
// SADD booking:book_zyx:tickets ticket:tkt_1a2b
// Use Hashes for staff details. Key format: staff:<staff_id>
// HSET staff:staff_mno staff_id "staff_mno" first_name "Bob" ... employee_number "E12345" ... is_active 1
// To find staff by employee number (optional index):
// SET staff_employee_number:"E12345" staff:staff_mno
// Use Hashes for maintenance record details. Key format: maintenance_record:<record_id>
// HSET maintenance_record:maint_rec_001 record_id "maint_rec_001" asset_id "train_789" asset_type "Train" ... status "Completed"
// To link records to assets (optional):
// SADD train:train_789:maintenance maintenance_record:maint_rec_001
// SADD platform:plat_123:maintenance maintenance_record:maint_rec_002
| [
{
"role": "user",
"content": "Can you help me retrieve the details of all schedules for a specific train with train_id 'train_789', including the route and stops information?",
"sql": null
},
{
"role": "assistant",
"content": "HGETALL train:train_789\nSMEMBERS schedule:sched_*:train:train_78... |
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
// PUT /schedules
{
"mappings": {
"properties": {
"schedule_id": { "type": "keyword" },
"train_id": { "type": "keyword" }, // References trains index
"route_id": { "type": "keyword" }, // References routes index
"departure_datetime": { "type": "date" }, // ISO 8601 format recommended
"arrival_datetime": { "type": "date" },
"status": { "type": "keyword" },
"notes": { "type": "text" }
}
}
}
// PUT /passengers
{
"mappings": {
"properties": {
"passenger_id": { "type": "keyword" },
"first_name": {
"type": "text",
"fields": { "keyword": { "type": "keyword", "ignore_above": 100 } }
},
"last_name": {
"type": "text",
"fields": { "keyword": { "type": "keyword", "ignore_above": 100 } }
},
"email": { "type": "keyword" }, // Often used for exact matches
"phone_number": { "type": "keyword" },
"date_of_birth": { "type": "date", "format": "yyyy-MM-dd" },
"loyalty_program_id": { "type": "keyword" },
"created_at": { "type": "date" }
}
}
}
| [
{
"role": "user",
"content": "能否帮我查询特定列车行程(schedule_id 为 'sched_001')的详细信息，包括列车出发和到达时间，以及该行程所属路线的ID和相关乘客信息？",
"sql": null
},
{
"role": "assistant",
"content": "SELECT s.schedule_id, s.train_id, s.route_id, s.departure_datetime, s.arrival_datetime, s.status, p.passenger_id, p.first_name, p.la... |
End of preview. Expand
in Data Studio
No dataset card yet
- Downloads last month
- 4