AI-Powered UPSC Study Assistant

A comprehensive full-stack application that leverages multi-agent architecture and RAG-based knowledge retrieval to assist UPSC aspirants in their studies.

🚀 Features

• Multi-Agent System: Retriever, Summarizer, Question Generator, and Critic agents
• RAG-Based Knowledge Retrieval: Vector embeddings for semantic search across documents
• Document Ingestion: Support for PDFs, notes, research papers, and bookmarks
• AI-Powered Q&A: Get concise, exam-focused answers with key points
• Practice Questions: Automatically generated MCQs and short-answer questions
• Progress Tracking: Monitor your study progress and topic coverage

🏗️ Architecture

Backend

• FastAPI: High-performance Python web framework
• Multi-Agent System: LangChain-based agent orchestration
• Vector Database: FAISS for efficient similarity search
• LLM Integration: OpenAI/Gemini/LLaMA 2 support
• Document Processing: PyPDF2, langchain for text extraction and chunking

Frontend

• React: Modern, responsive user interface
• Material-UI: Beautiful, accessible components
• Real-time Updates: WebSocket integration for live progress

Data Pipeline

• Document Ingestion: Automated text extraction and processing
• Embedding Generation: OpenAI embeddings for semantic search
• Chunking Strategy: Optimal text splitting for RAG performance

🛠️ Tech Stack

• Backend: Python 3.9+, FastAPI, LangChain, FAISS, PyPDF2
• Frontend: React 18, Material-UI, Axios
• Database: FAISS (vector), SQLite (metadata)
• AI/ML: OpenAI API, LangChain agents
• Deployment: Docker, Docker Compose

📋 Prerequisites

• Python 3.9+
• Node.js 16+
• Docker and Docker Compose
• OpenAI API key (or alternative LLM provider)

🚀 Quick Start

Option 1: Docker (Recommended)

# Clone the repository
git clone <your-repo-url>
cd resume_upsc

# Set environment variables
cp .env.example .env
# Edit .env with your API keys

# Run the entire stack
docker-compose up -d

# Access the application
# Frontend: http://localhost:3000
# Backend: http://localhost:8000
# API Docs: http://localhost:8000/docs

Option 2: Local Development

# Backend setup
cd backend
python -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate
pip install -r requirements.txt
uvicorn main:app --reload

# Frontend setup
cd frontend
npm install
npm start

📁 Project Structure

resume_upsc/
├── backend/                 # FastAPI backend
│   ├── app/
│   │   ├── agents/         # Multi-agent system
│   │   ├── api/            # API endpoints
│   │   ├── core/           # Configuration and utilities
│   │   ├── models/         # Data models
│   │   ├── services/       # Business logic
│   │   └── utils/          # Helper functions
│   ├── data/               # Document storage
│   ├── embeddings/         # Vector embeddings
│   └── main.py            # Application entry point
├── frontend/               # React frontend
│   ├── src/
│   │   ├── components/     # UI components
│   │   ├── pages/          # Page components
│   │   ├── services/       # API services
│   │   └── utils/          # Helper functions
│   └── public/             # Static assets
├── scripts/                # Utility scripts
├── docker-compose.yml      # Docker orchestration
└── README.md              # This file

🔧 Configuration

Environment Variables

Create a .env file in the root directory:

# OpenAI Configuration
OPENAI_API_KEY=your_openai_api_key_here
OPENAI_MODEL=gpt-4

# Alternative LLM Providers
GEMINI_API_KEY=your_gemini_api_key_here
ANTHROPIC_API_KEY=your_anthropic_api_key_here

# Database Configuration
DATABASE_URL=sqlite:///./upsc_assistant.db

# Vector Store Configuration
EMBEDDING_MODEL=text-embedding-ada-002
CHUNK_SIZE=1000
CHUNK_OVERLAP=200

# Server Configuration
HOST=0.0.0.0
PORT=8000
DEBUG=True

📚 Usage

1. Document Upload

• Upload PDFs, notes, and research papers through the web interface
• Documents are automatically processed and indexed
• Support for batch uploads

2. Ask Questions

• Use the search bar to ask UPSC-related questions
• Get AI-generated answers with key points and references
• View source documents for verification

3. Practice Questions

• Generate MCQs and short-answer questions from your documents
• Track your performance and progress
• Focus on weak areas

4. Progress Tracking

• Monitor your study progress
• View topic coverage charts
• Identify knowledge gaps

🤖 Multi-Agent System

Retriever Agent

• Searches uploaded documents using vector embeddings
• Implements semantic search for relevant content
• Returns ranked document chunks

Summarizer Agent

• Generates concise, exam-focused summaries
• Extracts key points and concepts
• Maintains UPSC syllabus alignment

Question Generator Agent

• Creates practice questions from retrieved content
• Generates MCQs with explanations
• Adapts difficulty based on user level

Critic Agent

• Validates factual consistency of answers
• Cross-references multiple sources
• Ensures accuracy and reliability

🔍 API Endpoints

Document Management

• POST /api/documents/upload - Upload documents
• GET /api/documents/ - List all documents
• DELETE /api/documents/{id} - Delete document

Knowledge Query

• POST /api/query/ - Ask questions
• GET /api/query/history - Query history

Practice Questions

• POST /api/questions/generate - Generate questions
• GET /api/questions/ - List questions
• POST /api/questions/submit - Submit answers

Progress Tracking

• GET /api/progress/ - User progress
• GET /api/progress/topics - Topic coverage

🧪 Testing

# Backend tests
cd backend
pytest

# Frontend tests
cd frontend
npm test

🚀 Deployment

Production Deployment

# Build production images
docker-compose -f docker-compose.prod.yml build

# Deploy to production
docker-compose -f docker-compose.prod.yml up -d

Environment-Specific Configs

• docker-compose.yml - Development environment
• docker-compose.prod.yml - Production environment
• docker-compose.test.yml - Testing environment

🤝 Contributing

1. Fork the repository
2. Create a feature branch
3. Make your changes
4. Add tests
5. Submit a pull request

📄 License

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

🆘 Support

• Create an issue for bugs or feature requests
• Check the documentation for detailed guides
• Join our discussion forum

🔮 Roadmap

• Multi-language support
• Mobile app
• Advanced analytics dashboard
• Integration with UPSC exam schedule
• Collaborative study groups
• Offline mode support