RAG Document Q&A System

A Retrieval-Augmented Generation (RAG) system that uses OpenAI embeddings and ChromaDB for document question-answering.

Features

• Document processing and chunking
• OpenAI embeddings for semantic search
• ChromaDB for vector storage
• Caching system for embeddings
• Question answering with context

Setup

1. Clone the repository:

git clone <your-repo-url>
cd <repo-name>

2. Create and activate virtual environment:

python -m venv venv
source venv/bin/activate  # On macOS/Linux

3. Install dependencies:

pip install -r requirements.txt

4. Create a .env file with your OpenAI API key:

OPENAI_API_KEY=your_api_key_here

5. Place your text documents in the news_articles directory

6. Run the application:

python app.py

Project Structure

• app.py: Main application code
• requirements.txt: Python dependencies
• news_articles/: Directory for text documents
• chroma_db/: ChromaDB storage (gitignored)
• embedding_cache.json: Embedding cache (gitignored)

Usage

1. Add your text documents to the news_articles directory
2. Run the application
3. The system will:
   • Process and chunk documents
   • Generate embeddings
   • Store in ChromaDB
   • Allow question answering

Dependencies

• Python 3.10+
• OpenAI API
• ChromaDB
• Other requirements in requirements.txt