🤖 AI Educational Chatbot with RAG

An AI chatbot that allows users to upload documents and ask questions using Retrieval-Augmented Generation (RAG) powered by Google Gemini Pro. Features user authentication, document processing, and intelligent query suggestions.

🌟 Features

• Document Support: PDF, TXT, DOCX, PPTX, Markdown, HTML files (up to 16MB)
• Vector Search: FAISS-powered similarity search for content retrieval
• AI Responses: Google Gemini Pro generates contextual answers
• Chat History: Persistent conversation storage
• User Authentication: Secure registration/login with JWT tokens
• Query Suggestions: AI-generated question suggestions
• Analytics: Usage statistics and insights
• Modern UI: Responsive interface with drag-and-drop

🛠️ Tech Stack

• Frontend: HTML5, CSS3, JavaScript
• Backend: Flask (Python)
• Database: SQLite
• Vector DB: FAISS with Sentence Transformers
• LLM: Google Gemini Pro API
• Embeddings: all-MiniLM-L6-v2

📁 Project Structure

RAG/
├── frontend/               # Web interface
├── backend/               # Core logic and APIs
├── data/                  # SQLite database
├── uploads/               # User files
├── vectorstore/           # FAISS index
├── app.py                 # Main Flask app
├── run.py                 # App runner
└── requirements.txt       # Dependencies

🚀 Quick Start

1. Prerequisites

• Python 3.8+
• Google AI Studio API key (Get it here)

2. Setup

# Install dependencies
pip install -r requirements.txt

# Configure environment
cp .env.example .env
# Edit .env and add your GOOGLE_API_KEY

# Run application
python app.py

Visit: http://localhost:5000

📖 Usage

1. Upload: Drag & drop documents (PDF, TXT, DOCX, etc.)
2. Ask: Type questions about your documents
3. Get Answers: AI responses with source attribution

🔧 Key API Endpoints

• POST /upload - Upload documents
• POST /ask - Ask questions
• POST /auth/register - User registration
• POST /auth/login - User login
• GET /chat/history - Chat history
• GET /analytics - Usage analytics

🔒 Security Features

• JWT-based authentication
• bcrypt password hashing
• Input validation and sanitization
• User data isolation
• Guest mode support

🔧 Configuration

Create .env file with:

GOOGLE_API_KEY=your_api_key_here
SECRET_KEY=your_secret_key
FLASK_ENV=development

🐛 Troubleshooting

• API Key Error: Check .env file has valid GOOGLE_API_KEY
• Module Errors: Run pip install -r requirements.txt
• Upload Fails: Check file size (max 16MB) and format support
• Auth Issues: Verify SECRET_KEY in .env

📝 License

MIT License

🙏 Acknowledgments

• Google Gemini flash for AI capabilities
• Sentence Transformers for embeddings
• FAISS for vector search
• Flask for web framework

---

Happy Learning! 🎓