Query-Chatbot🤖

An intelligent chatbot that allows users to query product and supplier data using natural language. Built with React (frontend), FastAPI (backend), and integrated with OpenAI for data summarization.

Features

• Natural Language Queries: Ask questions like:
  • "Show me all products under brand X"
  • "Which suppliers provide laptops?"
• Supplier Data Summarization: Enhanced responses using LLM (OpenAI GPT-3.5/4).
• Product & Supplier Search: Query structured data from MySQL/PostgreSQL.
• Responsive UI: Modern chat interface with query history panel.
• REST API: Fully documented endpoints with Swagger UI.

Tech Stack

Backend

Frontend

Installation

Backend Setup

# Clone the repository
git clone https://github.com/yourusername/ai-chatbot.git
cd ai-chatbot/chatbot-backend

# Create and activate virtual environment
python -m venv venv
source venv/bin/activate  # Windows: venv\Scripts\activate

# Install dependencies
pip install -r requirements.txt

# Set up environment variables
cp .env.example .env  # Update values in .env

Frontend Setup

cd ../chatbot-frontend
npm install

Configuration

1. Database: Update .env with your MySQL/PostgreSQL credentials:

   DATABASE_URL=mysql+pymysql://user:password@localhost:3306/chatbot_db

2. OpenAI: Add your API key for LLM features:

   OPENAI_API_KEY=your_api_key_here

3. Initialize Database:

   -- Run via MySQL Workbench or CLI
   CREATE DATABASE chatbot_db;
   USE chatbot_db;
   SOURCE database/init.sql;

Usage

1. Start Backend:

   cd chatbot-backend
   uvicorn app.main:app --reload

2. Start Frontend:

   cd chatbot-frontend
   npm run dev

3. Access the chatbot at http://localhost:5173.

API Documentation

Interactive documentation available at http://localhost:8000/docs:

Endpoint	Method	Description
/api/v1/products/{brand}	GET	Get products by brand
/api/v1/suppliers/{category}	GET	Get suppliers by product category
/api/v1/suppliers/{id}/summary	GET	Get LLM-summarized supplier info

Example Response:

{
  "summary": "Supplier A specializes in Electronics and Laptops. Contact: contact@supplierA.com"
}

Deployment

1. Frontend:
   

2. Backend:
   Deploy to Render or AWS EC2 with:

   docker build -t chatbot-backend .

3. Database: Use PlanetScale or AWS RDS.

Contributing

1. Fork the repository
2. Create a feature branch (git checkout -b feature/your-feature)
3. Commit changes (git commit -m 'Add amazing feature')
4. Push to branch (git push origin feature/your-feature)
5. Open a Pull Request

License

MIT License - see LICENSE

---

Need Help?
Open an issue or contact krdevanshu06@rediffmail.com

---

Key Features

• Clear installation instructions
• Badges for tech stack visibility
• API documentation table
• One-click deployment buttons
• Mobile-responsive formatting
• License and contribution guidelines