---
title: Jarvis Space
emoji: 📚
colorFrom: yellow
colorTo: purple
sdk: docker
pinned: false
---

Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

# Jarvis AI Assistant

A voice-enabled AI assistant with WebSocket communication, LLM integration, and MCP tools.

## Deployment to Hugging Face Spaces

### Directory Structure

The application follows this structure:
```
jarvis-space/
├── Dockerfile
├── backend/
│   ├── app.py
│   ├── config.yaml
│   ├── requirements.txt
│   └── pretrained_models/
├── frontend/
│   ├── index.html
│   ├── script.js
│   ├── style.css
│   └── static/
```

### Deploying to Hugging Face Spaces

1. Create a new Space on Hugging Face with Docker template
2. Add the following secrets in the Space settings:
   - `HF_TOKEN`: Your Hugging Face token
   - `GOOGLE_MAPS_API_KEY`: (Optional) For Google Maps integration
   - `BRAVE_API_KEY`: (Optional) For Brave Search integration
   - `ACCUWEATHER_API_KEY`: (Optional) For weather information

3. Push your code to the Space repository
4. The Dockerfile will build and deploy your application

### Testing the WebSocket

You can test the WebSocket connection by accessing:
```
https://your-space-name.hf.space/test_websocket.html
```

### Troubleshooting

If you encounter a 404 error:
- Check the Space logs to ensure all services are running
- Verify that static files are being served correctly
- Make sure the frontend directory is properly copied in the Docker image

## Development

### Local Setup

1. Install dependencies:
```bash
pip install -r backend/requirements.txt
```

2. Run the application:
```bash
uvicorn backend.app:app --host 0.0.0.0 --port 7860 --reload
```

### Directory Structure

- `backend/`: Contains the FastAPI application, LLM integration, and MCP tools
- `frontend/`: Contains the web interface with WebSocket client
- `Dockerfile`: Defines the container for deployment