README.md

metadata

title: MANIT Chat RAG
emoji: 🎓
colorFrom: blue
colorTo: indigo
sdk: docker
app_port: 7860
pinned: false

MANIT Chat RAG

An AI-powered academic assistant for Maulana Azad National Institute of Technology (MANIT), Bhopal, built with a Retrieval-Augmented Generation (RAG) pipeline. It uses FastAPI for the API backend and serves a minimalist, modern, static HTML/JS/CSS web interface.

This project is configured for single-container Docker deployment, making it ready to be hosted directly on Hugging Face Spaces as a Docker Space.

🚀 How to Run Locally with Docker

1. Ensure your Groq API key is set in server/.env:

   groq_api_key=your_groq_api_key_here
   

2. Build the unified Docker image:

   docker build -t manit-chat .
   

3. Run the container, mounting the data volume and passing the environment file:

   docker run -p 7860:7860 --env-file server/.env -v "$(pwd)/server/data:/app/server/data" manit-chat
   

4. Open your web browser and navigate to http://localhost:7860.

---

☁️ How to Deploy to Hugging Face Spaces

1. Create a new Space on Hugging Face.
2. Give it a name and select Docker as the SDK.
3. Choose Blank (default template) as the starting point.
4. Clone your Space repository locally, or add it as a Git remote in this project folder:

   git init
   git add .
   git commit -m "Configure for Hugging Face Spaces"
   git remote add origin https://huggingface.co/spaces/YOUR_USERNAME/YOUR_SPACE_NAME
   git push -u origin main --force
   

5. Once pushed, go to the Settings tab of your Hugging Face Space page:
   • Scroll down to Variables and secrets.
   • Click New secret.
   • Set the Name to groq_api_key.
   • Set the Value to your Groq API key (gsk_...).
6. Hugging Face will automatically detect the root Dockerfile and build it. Once complete, your Space will be active and running online!