A Basic LLM chatbot featuring a React frontend and FastAPI backend, providing a unified interface for multiple LLM providers (Gemini, OpenAI, Anthropic).

• Implemented through the AIProvider abstract base class
• Allows switching between different LLM providers seamlessly
• Each provider implements the same interface for consistency

• AIProviderFactory creates appropriate provider instances
• Providers can be switched via environment variables
• Simplifies adding new providers

1. Install dependencies:

cd backend
pip install -r requirements.txt

2. Set up environment variables:

# Create .env file
cp .env.example .env

# Add your API keys
GEMINI_API_KEY=your_key_here
OPENAI_API_KEY=your_key_here
ANTHROPIC_API_KEY=your_key_here

3. Run the development server:

uvicorn app.main:app --reload --host 0.0.0.0 --port 8000

1. Install dependencies:

cd frontend
npm install

2. Run the development server:

npm run dev

The frontend will be available at http://localhost:3000

Build and run both services using Docker Compose:

docker-compose up

This will:

• Build and start both frontend and backend services
• Mount code directories for live reloading
• Start the frontend on port 3000 and backend on port 8000

POST /api/chat

Request body:

{
    "message": "Your message here"
}

Response:

{
    "response": "AI generated response",
    "timestamp": "2024-02-10T12:00:00Z",
    "provider": "gemini"
}

To implement a new AI provider:

1. Create a new service class inheriting from AIProvider:

from .base import AIProvider

class NewProvider(AIProvider):
    async def generate_response(self, message: str) -> str:
        # Implementation here
        pass

    async def get_model_info(self) -> Dict[str, Any]:
        # Implementation here
        pass

2. Add the provider to the factory:

class AIProviderFactory:
    _providers = {
        "new_provider": NewProvider,
        # ... other providers
    }

# General settings
DEBUG=1
ENVIRONMENT=development

# Provider selection
AI_PROVIDER=gemini  # Options: gemini, openai, anthropic

# API Keys
GEMINI_API_KEY=your_key
OPENAI_API_KEY=your_key
ANTHROPIC_API_KEY=your_key

The service implements comprehensive error handling:

• API-specific errors (rate limits, quotas)
• Network errors
• Invalid input validation
• Service unavailability

Example error response:

{
    "detail": "Error message here",
    "error_code": "PROVIDER_ERROR",
    "timestamp": "2024-02-10T12:00:00Z"
}

Built by @abdelilah.khossan@gmail.com