Opper

SQL

Natural language to SQL query generation evaluates text-to-query fidelity and schema reasoning. This task is particularly relevant for analytics chat assistants and simplified database interfaces where users need to query data using natural language. Models must understand both the intent behind the question and the structure of the underlying database schema.

SQL – openai/gpt-4o Task | Opper AI

Input Tokens

0

Output Tokens

0

Duration

0

Cost

0

Context

Input

Insert a new course version for course_id = 1 and version_number = 3, with title = 'SQL Basics v3', description = 'Added advanced topics',if that (course_id, version_number) already exists, update the title, description, and set created_at to NOW(). Care with unique constraints, if you need to provide a version_id use the next available.

Expected output

INSERT INTO course_versions (version_id, course_id, version_number, title, description, created_at) SELECT (SELECT COALESCE(MAX(version_id), 0) + 1 FROM course_versions), 1, 3, 'SQL Basics v3', 'Added advanced topics', NOW() ON CONFLICT (course_id, version_number) DO UPDATE SET title = EXCLUDED.title, description = EXCLUDED.description, created_at = NOW() RETURNING *;

Model output

INSERT INTO course_versions (course_id, version_number, title, description, created_at) VALUES (1, 3, 'SQL Basics v3', 'Added advanced topics', NOW()) ON CONFLICT (course_id, version_number) DO UPDATE SET title = EXCLUDED.title, description = EXCLUDED.description, created_at = EXCLUDED.created_at;