📄 RAG Document Q&A System

Retrieval-Augmented Generation for intelligent document question answering

Overview

A production-ready RAG (Retrieval-Augmented Generation) system that answers questions over document collections using semantic search, intelligent chunking strategies, and context-aware retrieval.

Architecture

Documents → Chunking → Embedding → Vector Store → Retrieval → Context Assembly → Answer Generation

Features

• 📑 Multiple Chunking Strategies — Fixed-size, sentence-based, and paragraph-level chunking
• 🔍 Semantic Search — Embedding-based retrieval with configurable top-k results
• 📊 Streamlit Dashboard — 4-page interactive UI for document management and Q&A
• 🚀 REST API — Full FastAPI backend with health checks and query endpoints
• ✅ Comprehensive Tests — 24 tests covering retrieval, ranking, and API endpoints
• 🧠 Context Window Management — Intelligent context assembly with relevance scoring

Tech Stack

Component	Technology
Backend	Python 3.12, FastAPI, Uvicorn
NLP	Embeddings, TF-IDF, Sentence Transformers
Frontend	Streamlit with Plotly charts
Testing	pytest, httpx
Data	In-memory vector store

Quick Start

# Clone and setup
git clone https://github.com/mohamed-elkholy95/rag-document-qa.git
cd rag-document-qa

# Install dependencies
pip install -r requirements.txt

# Run tests
python -m pytest tests/ -v

# Start API server
python -m src.api.main

# Start Streamlit dashboard
streamlit run streamlit_app/app.py

Project Structure

├── src/                    # Source code
│   ├── api/main.py         # FastAPI endpoints
│   ├── config.py           # Configuration management
│   ├── chunker.py          # Document chunking strategies
│   ├── retriever.py        # Semantic search & ranking
│   └── generator.py        # Answer generation
├── streamlit_app/          # Interactive dashboard
│   ├── app.py              # Main app with navigation
│   └── pages/              # Multi-page dashboard (4 pages)
├── tests/                  # Test suite (24 tests)
│   ├── conftest.py
│   └── test_*.py
├── requirements.txt
└── README.md

API Endpoints

Method	Endpoint	Description
GET	/health	Health check
POST	/query	Submit a question and get an answer

Dashboard Pages

1. 📊 Overview — System status and document statistics
2. 📄 Upload — Upload and manage documents
3. 💬 Ask — Interactive Q&A interface
4. 📈 Analytics — Retrieval metrics and performance

Testing

# Run all tests
python -m pytest tests/ -v

# Run with coverage
python -m pytest tests/ --cov=src --cov-report=term-missing

Author

Mohamed Elkholy — GitHub · melkholy@techmatrix.com

---

_{Built with Python, FastAPI, and Streamlit}