SQL Chat

SQL Chat is a chat-based SQL client to ask database questions and query databases using natural language.

As we enter the Developer Tools 2.0 era, there is a massive opportunity to rebuild the existing tools using the chat-based interface. SQL Client is no exception. Instead of navigating across many UI controls, a chat-based interface is much more intuitive. Of course, only if that works, and our goal is to deliver that experience.

SQL Chat is built by Next.js, it supports the following databases and will add more over time:

• MySQL
• PostgreSQL
• MSSQL

• All database connection configs are stored locally in your browser. You can also visit settings to clear the data.

• Only the database schema will be sent to the OpenAI API. No table data will be sent there.

• If you use sqlchat.ai, it will record the anonymised conversations.

If you use sqlchat.ai to connect to your database, you need to add 0.0.0.0 (allow all connections) to the database whitelist IP. Because sqlchat.ai is hosted on Vercel which uses dynamic IP. If this is a concern, please consider the self-host option below.

docker run --name sqlchat --platform linux/amd64 -p 3000:3000 sqlchat/sqlchat

You can set the following environment variables to customize the deployment:

• OPENAI_API_KEY: OpenAI API key. You can get one from here.
• OPENAI_API_ENDPOINT: OpenAI API endpoint. Defaults to https://api.openai.com.

docker run --name sqlchat --platform linux/amd64 --env OPENAI_API_KEY=xxx --env OPENAI_API_ENDPOINT=yyy -p 3000:3000 sqlchat/sqlchat

1. Make a copy of the example environment variables file;

   cp .env.example .env

2. Add your API key and OpenAI API Endpoint(optional) to the newly created .env file;

3. Install dependencies and start the dev server;

   pnpm i && pnpm dev

1. Install dependencies

   pnpm i

2. Generate prisma client from the model

   pnpm prisma generate

3. Seed data

   pnpm prisma db seed

This project is under the BSL License. See the LICENSE file for the full license text.