NLQuery

NLQuery is an AI-powered tool that translates natural language into SQL queries, making database interactions more intuitive and accessible.

• Natural language to SQL query conversion
• Support for multiple database types (PostgreSQL, MySQL)
• AI-powered query generation using Claude or OpenAI
• Interactive chat interface
• Real-time query results display
• Pagination for large result sets
• Configurable database and AI settings

• Docker and Docker Compose
• Database server (PostgreSQL or MySQL)
• AI API key (Claude or OpenAI)

1. Clone the repository:

git clone https://github.com/yourusername/nlquery.git
cd nlquery

2. Create a .env file from the example:

cp .env.example .env

3. Edit the .env file with your database and AI configuration.

4. Build and start the containers:

docker-compose up --build

5. Access the application:

• Frontend: http://localhost:3000
• Backend API: http://localhost:8000

• Provider: Choose between Claude or OpenAI
• API Key: Your AI provider API key
• Model: Specific model to use (e.g., claude-3-opus-20240229 or gpt-4)
• Temperature: AI response randomness (0-1)
• Max Tokens: Maximum response length

1. Create a virtual environment:

cd backend
python -m venv venv
source venv/bin/activate  # On Windows: .\venv\Scripts\activate

2. Install dependencies:

pip install -r requirements.txt

3. Run the development server:

export $(cat ../.env | xargs)
uvicorn app.main:app --reload

1. Install dependencies:

cd frontend-old
npm install

2. Run the development server:

npm run dev

sql-chat/
├── backend/
│   ├── app/
│   │   ├── __init__.py
│   │   ├── main.py
│   │   ├── core/
│   │   │   ├── __init__.py
│   │   │   ├── config.py
│   │   │   └── security.py
│   │   ├── api/
│   │   │   ├── __init__.py
│   │   │   └── routes.py
│   │   └── models/
│   │       ├── __init__.py
│   │       └── schemas.py
│   ├── requirements.txt
│   └── Dockerfile
├── frontend/
│   ├── src/
│   │   ├── components/
│   │   │   ├── Chat.jsx
│   │   │   ├── ConfigForm.jsx
│   │   │   └── QueryResults.jsx
│   │   ├── App.jsx
│   │   └── main.jsx
│   ├── package.json
│   └── Dockerfile
├── docker-compose.yml
└── README.md

Send a natural language query to the system.

Request:

{
  "message": "Show me all orders from last month",
  "conversation_id": "optional-conversation-id"
}

Response:

{
  "message": "Query results...",
  "sql": "SELECT * FROM...",
  "results": [
    {
      "column1": "value1",
      "column2": "value2"
    }
  ]
}

Create a new conversation.

Response:

{
  "conversation_id": "uuid"
}

Get conversation history.

Response:

{
  "messages": [
    {
      "role": "user",
      "content": "message"
    },
    {
      "role": "assistant",
      "content": "response"
    }
  ]
}

• All database credentials and API keys should be stored securely
• Use environment variables for sensitive information
• Enable SSL for database connections in production
• Implement proper authentication and authorization
• Regularly update dependencies for security patches

1. Fork the repository
2. Create a feature branch
3. Commit your changes
4. Push to the branch
5. Create a Pull Request

This project is licensed under the MIT License - see the LICENSE file for details. Database Settings

• Type: PostgreSQL or MySQL
• Host: Database server hostname
• Port: Database server port
• Database: Database name
• Username: Database user
• Password: Database password
• SSL: Enable/disable SSL connection