A FastAPI-based backend application for an interactive tutoring system with WebSocket support.

Interactive Tutor Backend powers real-time, AI-assisted learning experiences. It manages users, sessions, courses, dashboards, and orchestrates WebSocket-based tutoring flows. Optional integrations for language and speech services are available via modules in app/resources (OpenAI, ElevenLabs, Deepgram).

Frontend: The companion React frontend lives in the interactive-tutor-v3 codebase.

Watch a short walkthrough of the experience: Loom demo.

• FastAPI web framework
• WebSocket support for real-time communication
• CORS configuration for localhost development
• Modular structure with separate routes and logic folders
• Learning interface WebSocket endpoint

interactive-tutor-be/
├── main.py                    # Main application entry point
├── requirements.txt           # Python dependencies
├── routes/                    # API routes
│   ├── __init__.py
│   └── websocket_routes.py    # WebSocket routes
├── logic/                     # Business logic
│   ├── __init__.py
│   ├── websocket_manager.py   # WebSocket connection management
│   └── learning_interface.py  # Learning interface logic
└── README.md

1. Install dependencies:

pip install -r requirements.txt

2. Run the application:

python main.py

Or using uvicorn directly:

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

• GET / - Root endpoint
• GET /health - Health check endpoint

• WS /learning-interface - Main learning interface WebSocket

The /learning-interface WebSocket endpoint supports the following message types:

1. Ping

{
  "type": "ping"
}

2. Learning Request

{
  "type": "learning_request",
  "topic": "mathematics",
  "difficulty": "beginner"
}

3. User Response

{
  "type": "user_response",
  "content": "user input text",
  "session_id": "session_123"
}

4. Session Start

{
  "type": "session_start",
  "session_id": "session_123",
  "user_name": "John Doe"
}

5. Session End

{
  "type": "session_end",
  "session_id": "session_123"
}

The server responds with appropriate JSON messages based on the request type, including error handling and timestamps.

The application is configured to allow CORS requests from:

• http://localhost:3000
• http://localhost:3001
• http://localhost:8000
• http://127.0.0.1:3000
• http://127.0.0.1:3001
• http://127.0.0.1:8000

To run in development mode with auto-reload:

uvicorn main:app --reload

The application will be available at http://localhost:8000