🚀 RAG Document Analyzer

A production-ready Retrieval-Augmented Generation (RAG) system for intelligent document question-answering, powered by Groq’s ultra-fast LLM inference.

🎥 Live Demo: https://rag-document-analyzer.vercel.app
📖 API Docs (Swagger): https://rag-document-analyzer.onrender.com/docs
🐛 Report Bug: https://github.com/Emart29/rag-document-analyzer/issues

✨ Overview

RAG Document Analyzer allows users to upload PDF documents and ask natural-language questions while receiving accurate, source-cited answers.
It combines semantic search + LLM reasoning for fast, reliable document intelligence.

Built with:

React + Vite (Frontend)
FastAPI (Backend)
Groq (Llama 3.1 70B) for lightning-fast inference
ChromaDB for vector similarity search

✨ Features

🎯 Core Capabilities

📄 PDF Document Processing: Upload and process PDFs with intelligent text chunking
🧠 AI-Powered Q&A: Ask natural language questions and get accurate answers
🔍 Semantic Search: Vector-based similarity search using ChromaDB
📚 Source Citations: Every answer includes relevant document excerpts with page numbers
💬 Conversation History: Maintains context across multiple questions
⚡ Lightning Fast: Powered by Groq's ultra-fast LLM inference (500+ tokens/sec)

🎨 Modern UI/UX

Beautiful React Interface: Built with Vite, TailwindCSS, and shadcn/ui
Responsive Design: Works seamlessly across devices
Real-time Updates: Live upload progress and query processing
Dark Mode Support: Eye-friendly interface (if implemented)
Drag & Drop: Intuitive document upload experience

🛠️ Technical Excellence

Production-Ready: Comprehensive error handling and validation
Scalable Architecture: Modular, maintainable codebase
API Documentation: Auto-generated Swagger/OpenAPI docs
Type Safety: Pydantic models for request/response validation
Performance Optimized: Efficient chunking, batching, and caching

🏗️ Architecture

┌─────────────────────────────────────────────────────────────┐
│                     React Frontend (Vite)                    │
│  ┌──────────────┐  ┌──────────────┐  ┌──────────────┐      │
│  │  Document    │  │     Chat     │  │   Source     │      │
│  │   Upload     │  │  Interface   │  │  Citations   │      │
│  └──────────────┘  └──────────────┘  └──────────────┘      │
└────────────────────────┬────────────────────────────────────┘
                         │ REST API (Axios)
┌────────────────────────▼────────────────────────────────────┐
│                    FastAPI Backend                           │
│  ┌──────────────────────────────────────────────────────┐   │
│  │              RAG Engine (Orchestrator)                │   │
│  └──┬────────────┬────────────┬────────────┬───────────┘   │
│     │            │            │            │                │
│  ┌──▼───┐   ┌───▼───┐   ┌───▼────┐   ┌───▼─────┐         │
│  │ PDF  │   │ Groq  │   │Sentence│   │ Chroma  │         │
│  │Proces│   │ API   │   │Transform│   │   DB    │         │
│  │sor   │   │(LLM)  │   │ (Embed)│   │(Vector) │         │
│  └──────┘   └───────┘   └────────┘   └─────────┘         │
└─────────────────────────────────────────────────────────────┘

🚀 Quick Start

Prerequisites

Python 3.8+
Node.js 18+
Groq API Key (Get free key)
8GB RAM minimum
2GB free disk space

Installation

1️⃣ Clone Repository

git clone https://github.com/Emart29/rag-document-analyzer.git
cd rag-document-analyzer

2️⃣ Setup Backend

# Navigate to backend
cd backend

# Create virtual environment
python -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate

# Install dependencies
pip install -r requirements.txt

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

# Start backend server
uvicorn app.main:app --reload --host 0.0.0.0 --port 8000

Backend will start on: http://localhost:8000

API Documentation: http://localhost:8000/docs

3️⃣ Setup Frontend

# Open new terminal, navigate to frontend
cd frontend

# Install dependencies
npm install

# Start development server
npm run dev

Frontend will start on: http://localhost:5173

📖 Usage

Upload Documents

Click the Upload tab in the sidebar
Drag & drop a PDF or click Browse
Wait for processing (10-30 seconds)
Document appears in the Documents list

Ask Questions

Select documents (optional - searches all if none selected)
Type your question in the chat input
Press Enter or click Send
Get AI-generated answer with source citations in 2-3 seconds

Example Questions

"What are the main findings of this research?"
"Summarize the key points from page 5"
"Compare the methodologies discussed in the documents"
"What does the author say about machine learning?"

🛠️ Technology Stack

Frontend

Technology	Purpose
React 18	UI framework
Vite	Build tool & dev server
TailwindCSS	Styling
shadcn/ui	UI components
Tanstack Query	Server state management
Axios	HTTP client
React Markdown	Answer rendering
Lucide React	Icons

Backend

Technology	Purpose
FastAPI	REST API framework
Groq API	LLM inference (Llama 3.1 70B)
ChromaDB	Vector database
Sentence Transformers	Text embeddings
PyPDF2 & pdfplumber	PDF text extraction
Pydantic	Data validation
Uvicorn	ASGI server

📊 Performance Metrics

Tested on: Dell Latitude 5400 (i5-8th gen, 8GB RAM)

Operation	Time	Notes
Document Upload	10-30s	5-page PDF
Question Answering	1-3s	Including retrieval & generation
Semantic Search	<100ms	ChromaDB query
Memory Usage	~600MB	Backend runtime
LLM Inference	500+ tokens/sec	Via Groq

🚢 Deployment

Frontend Deployment (Vercel) - FREE ✅

# Install Vercel CLI
npm i -g vercel

# Navigate to frontend folder
cd frontend

# Deploy
vercel

# Follow prompts, set environment variable:
# VITE_API_URL=https://your-backend-url.onrender.com

Backend Deployment (Render.com) - FREE ✅

Create render.yaml in project root:

services:
  - type: web
    name: rag-backend
    env: python
    region: oregon
    plan: free
    buildCommand: |
      cd backend
      pip install -r requirements.txt
    startCommand: cd backend && uvicorn app.main:app --host 0.0.0.0 --port $PORT
    envVars:
      - key: GROQ_API_KEY
        sync: false
      - key: PYTHON_VERSION
        value: 3.11.0

Push to GitHub
Connect repo to Render.com
Add GROQ_API_KEY environment variable
Deploy!

Your app will be live at:

Frontend: https://your-app.vercel.app
Backend API: https://your-api.onrender.com

📁 Project Structure

rag-document-analyzer/
├── backend/
│   ├── app/
│   │   ├── main.py              # FastAPI application
│   │   ├── models.py            # Pydantic models
│   │   ├── routers/             # API endpoints
│   │   │   ├── documents.py     # Document operations
│   │   │   ├── query.py         # Q&A endpoints
│   │   │   └── system.py        # Health & stats
│   │   ├── services/            # Business logic
│   │   │   ├── rag_engine.py    # RAG orchestration
│   │   │   ├── groq_client.py   # LLM interface
│   │   │   ├── embeddings.py    # Vector generation
│   │   │   └── pdf_processor.py # Document processing
│   │   └── database/
│   │       └── chroma_db.py     # Vector database
│   ├── requirements.txt
│   ├── .env
│   └── README.md
├── frontend/
│   ├── src/
│   │   ├── components/          # React components
│   │   │   ├── Header.jsx
│   │   │   ├── Sidebar.jsx
│   │   │   ├── ChatInterface.jsx
│   │   │   ├── DocumentList.jsx
│   │   │   └── ui/              # shadcn components
│   │   ├── services/
│   │   │   └── api.js           # API client
│   │   ├── App.jsx
│   │   └── main.jsx
│   ├── package.json
│   ├── tailwind.config.js
│   └── README.md
├── README.md                    # This file
└── LICENSE

🧪 Testing

Backend Tests

cd backend

# Test individual components
python app/services/groq_client.py
python app/services/embeddings.py
python app/database/chroma_db.py
python app/services/rag_engine.py

# API documentation
# Visit: http://localhost:8000/docs

Frontend Tests

cd frontend

# Run development server
npm run dev

# Build for production
npm run build

# Preview production build
npm run preview

🔒 Security & Best Practices

✅ Environment variables for sensitive data
✅ Input validation with Pydantic
✅ CORS configuration for frontend
✅ File size and type validation
✅ Error handling and logging
✅ API rate limiting (recommended for production)
⚠️ Add authentication for production use
⚠️ Implement user management for multi-tenant

🐛 Troubleshooting

Backend Issues

Issue: "GROQ_API_KEY not found"

# Solution: Check .env file
cat backend/.env  # Should show GROQ_API_KEY=gsk_...

Issue: ChromaDB errors

# Solution: Clear database and restart
rm -rf backend/chroma_db/
# Restart backend

Issue: PDF processing fails

# Solution: Install additional dependencies
pip install python-magic-bin  # Windows
pip install python-magic       # Mac/Linux

Frontend Issues

Issue: API connection refused

# Solution: Check VITE_API_URL in .env
# Verify backend is running on correct port

Issue: Build errors

# Solution: Clear cache and reinstall
rm -rf node_modules package-lock.json
npm install

🎯 Future Enhancements

🤝 Contributing

Contributions are welcome! Please follow these steps:

Fork the repository
Create a feature branch (git checkout -b feature/AmazingFeature)
Commit your changes (git commit -m 'Add some AmazingFeature')
Push to the branch (git push origin feature/AmazingFeature)
Open a Pull Request

📝 License

This project is licensed under the MIT License - see the LICENSE file for details.

👤 Author

Your Name

LinkedIn: Emmanuel Nwanguma
GitHub: Emart29

🙏 Acknowledgments

Groq - Ultra-fast LLM inference platform
ChromaDB - Open-source embedding database
FastAPI - Modern Python web framework
Sentence Transformers - State-of-the-art text embeddings
shadcn/ui - Beautiful React components
Vercel - Frontend hosting platform
Render - Backend hosting platform

📊 Project Stats

⭐ If this project helped you, please give it a star! ⭐

Made with ❤️ by Emmanuel Nwanguma

⬆ Back to Top

Name		Name	Last commit message	Last commit date
Latest commit History 15 Commits
.vscode		.vscode
backend		backend
frontend		frontend
.python-version		.python-version
README.md		README.md

Emart29/rag-document-analyzer

Folders and files

Latest commit

History

Repository files navigation