Flask SQL Assistant

This project is a Python-based web application built with Flask that uses AI language models to answer questions related to an SQL database. It can distinguish between general and database-specific queries and respond accordingly.

Features

• SQL Database Integration: Connects to a MySQL database to fetch useful information.
• AI-Powered Queries: Uses language models to interpret and answer both database-related and general queries.
• Flask API: Provides an endpoint to query the assistant.
• Error Handling: Includes basic error handling for incoming requests.

Requirements

• Python 3.7+
• MySQL
• Required Python packages (see Installation)

Installation

1. Clone the Repository

   git clone <repository-url>
   cd <repository-directory>

2. Set Up Environment Variables

   Create a .env file to store your environment variables such as API keys, if required.

3. Install Python Packages

   Install the necessary dependencies using pip:

   pip install -r requirements.txt

4. Configure Database

   Update SQLDatabase.from_uri in your script to match your database connection URI.

Usage

To run the Flask application, execute:

python app.py

The server will start and be available on http://0.0.0.0:5000.

Endpoints

• POST /ask: Accepts a JSON payload containing the user's question.
  • Example request:

    {
      "question": "How many products are in the inventory?"
    }

Response

• If the question is related to the database:

  • Type: database
  • Returns the result of the SQL query.

• If the question is general:

  • Type: general
  • Provides an AI-generated response.

Example response:

{
  "type": "database",
  "response": "There are 15 products in the inventory."
}

Deployment

Use Waitress to serve the application in a production environment:

python -m waitress --call 'your_script:create_app'

Contributing

Please make sure to update tests as appropriate and adhere to the code style guidelines.

License

MIT License. See LICENSE for more details.

Acknowledgements

• Flask
• Langchain
• OpenAI APIs