Traditional RAG

A Python implementation of Retrieval-Augmented Generation (RAG) using LangChain, ChromaDB, and language models via Groq API. This project demonstrates how to build a system that retrieves relevant documents and generates contextual responses.

Features

• 📄 Multi-format Document Loading: Support for PDF and text files
• 🔍 Vector Search: Efficient similarity search using FAISS and ChromaDB
• 🧠 LLM Integration: Powered by Groq's fast language models
• 📝 Embeddings: Sentence-transformers for high-quality document embeddings
• 🔗 LangChain Integration: Built with LangChain for flexible RAG pipelines
• 📊 Jupyter Notebooks: Ready-to-use notebooks for PDF loading and document querying

Project Structure

traditional-rag/
├── main.py                      # Main application entry point
├── pyproject.toml              # Project metadata and dependencies
├── requirements.txt            # pip dependencies
├── README.md                   # This file
├── CONTRIBUTING.md             # Contribution guidelines
├── LICENSE                     # MIT License
├── .gitignore                  # Git ignore rules
├── .env.example                # Environment variables template
│
├── data/                       # Data directory
│   ├── pdf_files/             # PDF documents for processing
│   ├── text_files/            # Text documents
│   │   ├── sample1.txt
│   │   └── sample2.txt
│   └── vector_store/          # ChromaDB vector store
│
└── notebook/                   # Jupyter notebooks
    ├── pdf_loader.ipynb       # PDF loading examples
    └── document.ipynb         # Document querying examples

Prerequisites

• Python 3.13 or higher
• A valid Groq API key (get one at https://console.groq.com)
• Virtual environment (recommended)

Installation

Using uv (Recommended)

# Clone the repository
git clone https://github.com/yourusername/traditional-rag.git
cd traditional-rag

# Create virtual environment and install dependencies
uv venv
source .venv/bin/activate  # On Windows: .venv\Scripts\activate
uv pip install -e .

Using pip

git clone https://github.com/yourusername/traditional-rag.git
cd traditional-rag

python -m venv .venv
source .venv/bin/activate  # On Windows: .venv\Scripts\activate
pip install -r requirements.txt

Configuration

1. Create environment file:

   cp .env.example .env

2. Add your Groq API key:

   GROQ_API_KEY=your_api_key_here

The .env file will be automatically loaded by python-dotenv.

Usage

Running the Main Application

python main.py

Using Jupyter Notebooks

1. PDF Loader Notebook: Learn how to load and process PDF files

   jupyter notebook notebook/pdf_loader.ipynb

2. Document Query Notebook: Explore RAG querying with your documents

   jupyter notebook notebook/document.ipynb

Basic RAG Pipeline Example

from langchain_community.document_loaders import PyPDFLoader
from langchain_community.vectorstores import Chroma
from langchain_text_splitters import CharacterTextSplitter
from langchain_groq import ChatGroq

# Load documents
loader = PyPDFLoader("path/to/document.pdf")
documents = loader.load()

# Split documents
splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=100)
docs = splitter.split_documents(documents)

# Create vector store
vectorstore = Chroma.from_documents(docs, embedding=embeddings)

# Query with RAG
llm = ChatGroq(model="mixtral-8x7b-32768")
response = llm.invoke("Your question here")

Key Dependencies

• langchain & langchain-community: RAG framework and integrations
• chromadb: Vector database for storing embeddings
• faiss-cpu: Efficient similarity search
• sentence-transformers: Creating embeddings from text
• groq: Fast language model API
• pymupdf & pypdf: PDF document loading
• python-dotenv: Environment variable management

Environment Variables

Create a .env file in the root directory:

GROQ_API_KEY=your_groq_api_key_here

Development

Setting up for development:

# Install in editable mode with dev dependencies
uv pip install -e ".[dev]"

# Run tests
pytest tests/

# Format code
black .

# Lint
pylint src/

Contributing

Contributions are welcome! Please see CONTRIBUTING.md for guidelines.

License

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

Roadmap

• Add more embedding model options
• Implement query result caching
• Add support for more document formats (Word, Excel, etc.)
• Implement document metadata filtering
• Add comprehensive test suite
• Create CLI tool for document ingestion

Troubleshooting

API Key Issues

• Ensure your GROQ_API_KEY is set in .env
• Check that your API key is valid at https://console.groq.com

Vector Store Issues

• Delete the data/vector_store/ directory to reset ChromaDB
• Ensure you have write permissions to the data directory

Dependency Issues

• Update all dependencies: uv pip install --upgrade -r requirements.txt
• Clear cache: rm -rf .venv and reinstall

Resources

• LangChain Documentation
• ChromaDB Documentation
• Groq API Documentation
• RAG Concepts

Support

For issues and questions:

• 🐛 GitHub Issues
• 💬 Discussions

---

Made with ❤️ for the RAG community