Skip to main content

​
Installation

RepoRAGX requires Python 3.12 and a few dependencies. This guide will walk you through setting up your environment.
Prerequisites: You’ll need Git installed on your system to clone the repository.

​
System requirements

  • Python: 3.12 (required)
  • Operating system: Linux, macOS, or Windows
  • Disk space: ~2GB for dependencies and model weights
  • Memory: 4GB RAM minimum (8GB recommended for large repositories)

​
Step 1: Clone the repository

First, clone the RepoRAGX repository from GitHub: 
git clone https://github.com/AnmolTutejaGitHub/RepoRAGX.git
cd RepoRAGX

​
Step 2: Set up a virtual environment

RepoRAGX works best in an isolated Python environment. Choose one of the following methods:

​
Step 3: Install dependencies

With your virtual environment activated, install all required packages: 
pip install -r requirements.txt
This will install the following dependencies: 
langchain==1.2.10
langchain-community==0.4.1
langchain-core==1.2.14
python-dotenv==1.2.1
sentence-transformers==5.2.3
chromadb==1.5.1
langchain_groq==1.1.2

​
What gets installed

  • langchain: Core framework for building LLM applications
  • langchain-community: Community integrations including GithubFileLoader
  • langchain-core: Shared abstractions and base classes
  • langchain_groq: Groq LLM integration for llama-3.3-70b-versatile
  • sentence-transformers: Provides the all-MiniLM-L6-v2 embedding model
  • chromadb: Local vector database for storing and querying embeddings
  • python-dotenv: Loads environment variables from .env files
The first time you run RepoRAGX, Sentence Transformers will download the all-MiniLM-L6-v2 model (~90MB). This happens automatically and only needs to be done once.

​
Step 4: Verify installation

Verify that RepoRAGX is installed correctly: 
python -m src.main --help
You should see the RepoRAGX ASCII art banner: 
/**
 *    __________                    __________    _____    ____________  ___
 *    \______   \ ____ ______   ____\______   \  /  _  \  /  _____/\   \/  /
 *     |       _// __ \\____ \ /  _ \|       _/ /  /_\  \/   \  ___ \     / 
 *     |    |   \  ___/|  |_> >  <_> )    |   \/    |    \    \_\  \/     \ 
 *     |____|_  /\___  >   __/ \____/|____|_  /\____|__  /\______  /___/\  \
 *            \/     \/|__|                 \/         \/        \/      \_/
 */

Chat with your github repository
Press Ctrl+C to exit if it starts prompting for credentials.

​
Project structure

After installation, your project structure should look like this: 
RepoRAGX/
├── venv/                          # Virtual environment (ignored by git)
├── src/
│   ├── main.py                    # CLI entry point
│   └── rag/
│       ├── __init__.py
│       ├── github_codebase_loader.py  # Fetches files from GitHub
│       ├── text_splitter.py           # Language-aware chunking
│       ├── embedding_manager.py       # Sentence Transformer embeddings
│       ├── vector_store.py            # ChromaDB vector storage
│       ├── rag_retriever.py           # Similarity search & retrieval
│       └── groq_llm.py               # LLM integration
├── requirements.txt
├── .env.example
└── README.md

​
Troubleshooting

If you don’t have Python 3.12, install it using:macOS (Homebrew):
brew install [email protected]
Ubuntu/Debian:
sudo add-apt-repository ppa:deadsnakes/ppa
sudo apt update
sudo apt install python3.12 python3.12-venv
Windows: Download from python.org
If you encounter errors during pip install, try:
# Upgrade pip first
pip install --upgrade pip

# Then install dependencies
pip install -r requirements.txt
If you’re on macOS with Apple Silicon, you may need to install Rust:
curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh
If ChromaDB fails to initialize, ensure you have write permissions:
# The vector store is created at:
ls -la ~/.RepoRAGX/vector_store

# If it doesn't exist, it will be created automatically
Make sure your virtual environment is activated:
# Check which Python you're using
which python

# Should show path to venv/bin/python
# If not, activate the environment again:
conda activate venv/  # or source venv/bin/activate

​
Next steps

Quick start guide

Learn how to get your API keys and run your first query

Build docs developers (and LLMs) love

Get started for freeTalk to us