README.md

---
title: RNGPIT AI Assistant
emoji: 🎓
colorFrom: blue
colorTo: indigo
sdk: docker
app_port: 7860
app_file: app.py
pinned: false
---

# RNGAI-WEB Chatbot

This is an AI-powered chatbot for RNG Patel Institute of Technology (RNGPIT) that uses RAG (Retrieval Augmented Generation) to answer questions about courses, admissions, facilities, placements, and campus life.

## Features

- 🎓 Comprehensive information about RNGPIT
- 🤖 Powered by NVIDIA API (Llama 3.1 70B)
- 📚 RAG-based knowledge retrieval
- 🎨 Beautiful, modern UI with dark/light theme
- 📊 Admin dashboard with analytics
- 🐳 Docker support for easy deployment

## Setup

### 1. Clone and Install

```bash
cd RNGAI-WEB
pip install -r requirements.txt
```

### 2. Configure Environment Variables

Copy the example environment file:

```bash
copy .env.example .env
```

Then edit `.env` and add your credentials:

```env
NVIDIA_API_KEY=your_nvidia_api_key_here
SUPABASE_URL=your_supabase_url_here
SUPABASE_KEY=your_supabase_key_here
```

**Get your credentials:**
- **NVIDIA API**: https://build.nvidia.com
- **Supabase**: https://supabase.com

### 3. Run the Application

**Local Development:**

```bash
python app.py
```

**Using Docker:**

```bash
docker-compose up -d
```

The application will be available at: `http://localhost:7860` (or the port specified in docker-compose)

## Project Structure

```
RNGAI-WEB/
├── app.py                 # Main Flask application
├── requirements.txt       # Python dependencies
├── .env                   # Environment variables (not in git)
├── .env.example          # Environment template
├── Dockerfile            # Docker configuration
├── docker-compose.yml    # Docker Compose config
├── templates/
├── static/
└── data/
```

## Environment Variables

| Variable | Description | Required |
|----------|-------------|----------|
| `NVIDIA_API_KEY` | API key from NVIDIA | Yes |
| `SUPABASE_URL` | Your Supabase project URL | Yes |
| `SUPABASE_KEY` | Your Supabase API key | Yes |

## Tech Stack

- **Backend**: Flask, Python 3.11
- **AI**: NVIDIA API (Llama 3.1), Sentence Transformers
- **Vector DB**: ChromaDB
- **Database**: Supabase
- **Frontend**: HTML, CSS, JavaScript