SQL Chat is a Docker-deployed chat interface that translates natural language questions into SQL queries and executes them against connected databases. It uses a large language model to generate SQL from plain English instructions, supporting both querying and record modification through INSERT, UPDATE, and DELETE statements within the chat conversation flow.
The application connects to MySQL, PostgreSQL, MSSQL, TiDB Cloud, and OceanBase databases through a unified driver abstraction layer, allowing users to interact with multiple database types from a single chat interface. Users provide their own OpenAI API key for authentication, or can configure a custom API endpoint to use self-hosted or third-party AI models like Ollama. An optional database-backed account system tracks per-user usage, enforces spending limits, and processes payments.
The project is packaged as a Docker container with environment variable configuration for authentication and AI service settings, enabling straightforward self-hosted deployment.