Updated questions and golden queries to prevent accept multiple correct answers and reduce ambiguity

data/questions_gen.csv

@@ -60,8 +60,8 @@ What are the names of all the courses offered by the department of Computer Scie
 "What are the easiness scores for courses in the ""Computer Science"" department?","SELECT {course.name, course.course_id, course.number}, course.easiness_score FROM course WHERE course.department ilike '%Computer Science%';",advising,where
 How many students have taken a course in-person or online?,SELECT count(DISTINCT sr.student_id) AS num_students FROM student_record sr JOIN student s ON sr.student_id = s.student_id WHERE sr.how ilike '%in-person%' OR sr.how ilike '%online%';,advising,where
 Which flight has the shortest duration between departure and arrival times? Convert to minutes.,"SELECT {flight.flight_number, flight.flight_id}, (arrival_time - departure_time) / 60 AS duration_minutes FROM flight ORDER BY duration_minutes LIMIT 1;",atis,date_functions
-What's the average duration between departure and arrival times minus 34 minutes? Convert from UNIX to regular datetime.,SELECT avg(to_timestamp(arrival_time) - to_timestamp(departure_time) - interval '34 minutes') AS average_duration FROM flight;,atis,date_functions
-Count the number of flight departures for each month?,"SELECT month.month_name, count(*) AS departure_count FROM flight JOIN MONTH ON extract(MONTH FROM to_timestamp(flight.departure_time)) = month.month_number GROUP BY month.month_name, month.month_number ORDER BY month.month_number;",atis,date_functions
+What's the average duration between departure and arrival times minus 34 minutes? Convert from UNIX to regular datetime.,"SELECT avg(to_timestamp(arrival_time) - to_timestamp(departure_time) - interval '34 minutes') AS average_duration FROM flight;SELECT AVG(arrival_time - departure_time)/60 - 34 AS average_duration FROM flight;",atis,date_functions
+Count the number of flight departures for each month?,"SELECT month.month_name, count(*) AS departure_count FROM flight JOIN MONTH ON extract(MONTH FROM to_timestamp(flight.departure_time)) = month.month_number GROUP BY month.month_name, month.month_number ORDER BY month.month_number;SELECT date_trunc('month', to_timestamp(flight.departure_time)) AS MONTH, COUNT(*) AS num_departures FROM flight GROUP BY MONTH ORDER BY MONTH;",atis,date_functions
 What's the earliest flight departure time in the day in HH:MM?,"SELECT to_char(to_timestamp(departure_time)::TIME, 'HH24:MI') AS earliest_departure_time FROM flight ORDER BY earliest_departure_time LIMIT 1",atis,date_functions
 What's the difference in time in days between today and the earliest flight departure?,"SELECT date_part('day', CURRENT_DATE - to_timestamp(departure_time)) AS difference_in_days FROM flight ORDER BY departure_time LIMIT 1;",atis,date_functions
 What is the total cost of round-trip fares for each airline code?,"SELECT fare.fare_airline, SUM(fare.round_trip_cost) AS total_round_trip_cost FROM fare GROUP BY fare.fare_airline ORDER BY total_round_trip_cost DESC;",atis,group_by
@@ -70,7 +70,7 @@ What is the total cost of round-trip fares for each airline code?,"SELECT fare.f
 "How many meals are served in each compartment, sorted by the number of meals in descending order?","SELECT food_service.compartment, COUNT(food_service.meal_number) AS number_of_meals FROM food_service GROUP BY food_service.compartment ORDER BY number_of_meals DESC NULLS LAST;",atis,group_by
 "How many flights depart from each airport code, excluding stopovers?","SELECT airport.airport_code, COUNT(flight.from_airport) AS num_departures FROM airport LEFT JOIN flight ON airport.airport_code = flight.from_airport GROUP BY airport.airport_code;SELECT airport.airport_code, COUNT(flight.from_airport) AS num_departures FROM airport JOIN flight ON airport.airport_code = flight.from_airport GROUP BY airport.airport_code;",atis,group_by
 "Which flight ids to Chicago (ORD) have the longest duration from departure to arrival, sorted in ascending order?","SELECT flight.flight_id, (flight.arrival_time - flight.departure_time) AS duration FROM flight WHERE to_airport = 'ORD' ORDER BY duration ASC NULLS LAST;",atis,order_by
-"Which airport(s) have the shortest minimum connect time, sorted in ascending order? Show the minimum connect time.","SELECT {airport.airport_name, airport.airport_code}, airport.minimum_connect_time FROM airport ORDER BY airport.minimum_connect_time ASC NULLS LAST LIMIT 1;",atis,order_by
+"Which airports have the shortest minimum connect time, sorted in ascending order? Show the minimum connect time.","SELECT {airport.airport_name, airport.airport_code}, airport.minimum_connect_time FROM airport ORDER BY airport.minimum_connect_time ASC NULLS LAST;",atis,order_by
 Which aircraft code can carry the highest weight of cargo that any aircraft can carry?,SELECT aircraft.aircraft_code FROM aircraft ORDER BY pay_load DESC NULLS LAST LIMIT 1;,atis,order_by
 What are the top 2 airlines with the most flights?,"SELECT {airline.airline_name, airline.airline_code}, COUNT(flight.flight_id) AS number_of_flights FROM flight JOIN airline ON flight.airline_code = airline.airline_code GROUP BY {} ORDER BY number_of_flights DESC NULLS LAST LIMIT 2;",atis,order_by
 What are the aircraft codes for all aircraft with a cruising speed of over 200 mph? sort the aircraft codes in ascending order.,SELECT aircraft.aircraft_code FROM aircraft WHERE aircraft.cruising_speed > 200 ORDER BY aircraft.aircraft_code ASC NULLS LAST;,atis,order_by
@@ -82,7 +82,7 @@ How does the average ratio of the cruising speed to the payload of an aircraft v
 Which flights serve meals in first class? Give me the flight id and meal description.,"SELECT flight.flight_id, food_service.meal_description FROM flight JOIN food_service ON flight.meal_code = food_service.meal_code WHERE LOWER(food_service.compartment) LIKE '%first class%';",atis,table_join
 Which airlines offer flights with a stopover in Dallas?,"SELECT DISTINCT {airline.airline_name, airline.airline_code} FROM flight_stop JOIN airport ON flight_stop.stop_airport = airport.airport_code JOIN flight ON flight_stop.flight_id = flight.flight_id JOIN airline ON flight.airline_code = airline.airline_code WHERE airport.airport_location ILIKE '%Dallas%';",atis,table_join
 Which airlines offer flights from LAX to ORD?,"SELECT DISTINCT {airline.airline_name, airline.airline_code} FROM flight JOIN airline ON flight.airline_code = airline.airline_code WHERE flight.from_airport = 'LAX' AND flight.to_airport = 'ORD';",atis,table_join
-"Which airlines offer flights from Chicago (ORD) to New York (JFK), and how many stops do they have, sorted by number of stops?","SELECT {airline.airline_name, airline.airline_code}, flight.stops FROM flight JOIN airline ON flight.airline_code = airline.airline_code WHERE flight.from_airport = 'ORD' AND flight.to_airport = 'JFK' GROUP BY {}, flight.stops ORDER BY flight.stops NULLS LAST;",atis,table_join
+"Which airlines offer flights from Chicago (ORD) to New York (JFK), and how many stops do they have, sorted by number of stops in ascending order?","SELECT {airline.airline_name, airline.airline_code}, flight.stops FROM flight JOIN airline ON flight.airline_code = airline.airline_code WHERE flight.from_airport = 'ORD' AND flight.to_airport = 'JFK' GROUP BY {}, flight.stops ORDER BY flight.stops NULLS LAST;",atis,table_join
 "Which airlines do not have flights that depart or arrive at JFK, excluding stopovers?","SELECT DISTINCT {a.airline_name, a.airline_code} FROM public.airline a LEFT JOIN public.flight f ON a.airline_code = f.airline_code AND (f.to_airport = 'JFK' OR f.from_airport = 'JFK') GROUP BY {} HAVING COUNT(f.flight_id) = 0;",atis,table_join
 Which state code is Orlando International Airport in?,SELECT state_code FROM airport WHERE airport_name ILIKE '%Orlando International Airport%';,atis,where
 Which flights operate on Mondays and Wednesdays? Give me the relevant flight numbers,"SELECT {flight.flight_number, flight.flight_id} FROM flight WHERE LOWER(flight.flight_days) LIKE '%mon%' AND LOWER(flight.flight_days) LIKE '%wed%';",atis,where
@@ -146,7 +146,7 @@ Give me the total number of papers published in the first 12 months of 2019.,SEL
 "On average, how many papers per month were published in the whole of 2020?",SELECT cast(count(*) AS float)/ 12 AS average_papers_per_month FROM paper WHERE YEAR = 2020;,scholar,date_functions
 What is the total number of papers published per year?,"SELECT paper.year, COUNT(paper.paperid) AS total_papers FROM paper GROUP BY paper.year ORDER BY paper.year NULLS LAST;",scholar,group_by
 What is the total number of papers published in each year?,"SELECT paper.year, COUNT(paper.paperid) AS total_papers FROM paper GROUP BY paper.year ORDER BY paper.year;",scholar,group_by
-What is the total number of papers associated with each dataset?,"SELECT paperdataset.datasetid, COUNT(DISTINCT paperdataset.paperid) AS total_papers FROM paperdataset GROUP BY paperdataset.datasetid;",scholar,group_by
+What is the total number of papers associated with each dataset?,"SELECT paperdataset.datasetid, COUNT(DISTINCT paperdataset.paperid) AS total_papers FROM paperdataset GROUP BY paperdataset.datasetid;SELECT dataset.datasetname, COUNT(paperdataset.paperid) AS total_papers FROM paperdataset JOIN dataset ON paperdataset.datasetid = dataset.datasetid GROUP BY dataset.datasetname ORDER BY total_papers DESC NULLS LAST;",scholar,group_by
 How many keyphrases are associated with each paper?,"SELECT paperkeyphrase.paperid, COUNT(paperkeyphrase.keyphraseid) AS keyphrase_count FROM paperkeyphrase GROUP BY paperkeyphrase.paperid ORDER BY keyphrase_count DESC NULLS LAST;",scholar,group_by
 How many authors have published more than 2 papers?,SELECT COUNT(*) AS number_of_authors FROM (SELECT writes.authorid FROM writes GROUP BY writes.authorid HAVING COUNT(writes.paperid) > 2) AS subquery;,scholar,group_by
 "Which papers have the highest number of authors, ordered by the number of authors in descending order?","SELECT writes.paperid, COUNT(writes.authorid) AS num_authors FROM writes GROUP BY writes.paperid ORDER BY num_authors DESC NULLS LAST;",scholar,order_by

prompts/prompt_openai.md

@@ -0,0 +1,12 @@
+### Instructions:
+Your task is to convert a text question to a SQL query that runs on Postgres, given a database schema.
+
+### Input:
+Generate a SQL query that answers the question `{user_question}`.
+
+This query will run on a database whose schema is represented in this string:
+{table_metadata_string}
+
+### Response:
+Given the database schema, here is the SQL query that answers `{user_question}`:
+```sql