PDF Question-Answering System with CAG

A Python application that uses Groq LLM, LangChain, and Cache-Augmented Generation (CAG) to process PDFs and answer questions about their content.

Features

• PDF Processing: Extract and process text from PDF documents
• Vector Embeddings: Create semantic embeddings for efficient document retrieval
• Cache-Augmented Generation: Intelligent caching system for improved performance
• Groq Integration: Fast LLM inference using Groq's API
• Interactive Q&A: Ask natural language questions about your PDF content

Setup

1. Install dependencies:

   pip install -r requirements.txt

2. Set up environment variables: Create a .env file with your Groq API key:

   GROQ_API_KEY=your_groq_api_key_here
   

3. Place your PDF file in the project directory and name it mypdf.pdf

Usage

Run the main application:

python main.py

Then ask questions about your PDF content interactively.

Project Structure

• main.py - Main application entry point
• pdf_processor.py - PDF text extraction and processing
• cag_system.py - Cache-Augmented Generation implementation
• vector_store.py - Vector database management
• config.py - Configuration settings
• requirements.txt - Python dependencies

How it Works

1. Document Ingestion: The PDF is processed and split into chunks
2. Embedding Creation: Text chunks are converted to vector embeddings
3. Vector Storage: Embeddings are stored in ChromaDB for fast retrieval
4. Caching Layer: CAG system caches frequently accessed information
5. Question Processing: User questions are embedded and matched against the document
6. Answer Generation: Relevant context is sent to Groq LLM for answer generation