Afsheenkhi/chatbot-phase3

Todo Chatbot API - Phase 3

AI-powered conversational todo management system with JWT authentication and MCP integration.

Features

• —🤖 AI-powered natural language todo management
• —🔐 JWT-based authentication
• —💾 PostgreSQL database with file-based fallback
• —🔧 MCP (Model Context Protocol) integration
• —🚀 FastAPI backend
• —📝 Complete CRUD operations for todos
• —🔄 Real-time chat history management

API Endpoints

• —GET / - Root endpoint with API info
• —GET /health - Health check endpoint
• —POST /auth/register - User registration
• —POST /auth/login - User authentication
• —POST /chat - Chat endpoint for todo management
• —GET /history - Get chat history
• —GET /prompts - Get conversation prompts

Configuration

This Space requires the following environment variables (set in Space Settings → Variables):

Required Variables:

• —OPEN_ROUTER_API_KEY - OpenRouter API key for AI model
• —DATABASE_URL - PostgreSQL database connection string
• —BETTER_AUTH_SECRET - Authentication secret key
• —PHASE2_API_URL - Phase 2 backend API URL
• —INTERNAL_SERVICE_TOKEN - Internal service authentication token
• —ENVIRONMENT - Set to production
• —ALLOWED_ORIGINS - Comma-separated list of allowed CORS origins

Optional Variables:

• —MODEL_NAME - AI model name (default: google/gemini-2.0-flash-001)
• —AGENT_TEMPERATURE - AI temperature (default: 0.7)
• —AGENT_MAX_TOKENS - Max tokens (default: 500)
• —LOG_LEVEL - Logging level (default: INFO)
• —RATE_LIMIT_REQUESTS - Rate limit requests (default: 30)
• —RATE_LIMIT_WINDOW - Rate limit window in seconds (default: 60)

Documentation

• —Deployment Guide
• —Environment Variables Template
• —API Documentation: /docs (Swagger UI)

Tech Stack

• —Framework: FastAPI
• —Database: PostgreSQL (Neon)
• —AI Model: Google Gemini 2.0 Flash (via OpenRouter)
• —Authentication: JWT tokens
• —Containerization: Docker

Development

Local development instructions available in the repository.

License

MIT