RepoRAGX requires Python 3.12 and several dependencies for RAG functionality, including LangChain, ChromaDB, and Sentence Transformers.
Python version requirement
RepoRAGX requires Python 3.12 specifically. Using other Python versions may cause compatibility issues with dependencies.
python --version
# Should output: Python 3.12.x
Environment manager options
You can use either Conda (recommended) or Python’s built-in venv for environment management.
Using Conda (recommended)
Conda provides better dependency isolation and is the officially recommended approach.
Create environment
Create a new Conda environment with Python 3.12:conda create -p venv python==3.12
venv/ directory in your project folder. Activate environment
Activate the environment:Your terminal prompt should change to show (venv) at the beginning. Using -p venv creates the environment in your project directory, making it easy to manage project-specific dependencies.
Using venv (alternative)
If you prefer Python’s built-in virtual environment manager:
Ensure Python 3.12
Confirm you have Python 3.12 installed: Create virtual environment
Create a new virtual environment: Activate environment
Activate based on your operating system:Linux/macOS:Windows (Command Prompt):venv\Scripts\activate.bat
venv\Scripts\Activate.ps1
Installing dependencies
After activating your environment, install all required packages:
pip install -r requirements.txt
Core dependencies
RepoRAGX uses the following major dependencies (from requirements.txt):
| Package | Version | Purpose |
|---|
langchain | 1.2.10 | Core RAG framework and orchestration |
langchain-community | 0.4.1 | GitHub file loader and community integrations |
langchain-core | 1.2.14 | LangChain core abstractions |
langchain_groq | 1.1.2 | Groq LLM integration |
sentence-transformers | 5.2.3 | Text embeddings using all-MiniLM-L6-v2 |
chromadb | 1.5.1 | Vector database for storing embeddings |
python-dotenv | 1.2.1 | Environment variable management |
The first run may take several minutes as Sentence Transformers downloads the all-MiniLM-L6-v2 model (~80MB).
Environment variables
RepoRAGX uses environment variables for configuration. The application automatically loads these from a .env file using python-dotenv (src/main.py:11).
Required variables
Create a .env file in the project root:
GITHUB_PERSONAL_ACCESS_TOKEN=your_github_token
GROQ_API_KEY=your_groq_key
Using .env.example
The repository includes a .env.example template:
Then edit .env with your actual credentials.
Never commit your .env file to version control. Ensure .env is listed in .gitignore.
Vector store persistence
RepoRAGX stores vector embeddings in a persistent ChromaDB database to avoid re-indexing repositories on each run.
Storage location
Embeddings are stored in:
~/.RepoRAGX/vector_store/
persist_directory = Path.home()/".RepoRAGX"/"vector_store"
os.makedirs(persist_directory, exist_ok=True)
Collection naming
Each repository gets a unique collection name based on the repo identifier:
collection_name = repo.replace("/", "_")
# Example: "AnmolTutejaGitHub/RepoRAGX" → "AnmolTutejaGitHub_RepoRAGX"
To re-index a repository, delete its collection folder from ~/.RepoRAGX/vector_store/ and run the application again.
Verifying your setup
Test your environment configuration:
Activate environment
Ensure your virtual environment is activated
Check output
You should see the RepoRAGX ASCII banner and prompts for API keys:/**
* __________ __________ _____ ____________ ___
* \______ \ ____ ______ ____\______ \ / _ \ / _____/\ \/ /
* | _// __ \\____ \ / _ \| _/ / /_\ \/ \ ___ \ /
* | | \ ___/| |_> > <_> ) | \/ | \ \_\ \/ \
* |____|_ /\___ > __/ \____/|____|_ /\____|__ /\______ /___/\ \
* \/ \/|__| \/ \/ \/ \_/
*/
Chat with your github repository
Troubleshooting
Import errors
If you encounter import errors:
# Verify all packages are installed
pip list | grep -E "langchain|chromadb|sentence-transformers"
# Reinstall dependencies
pip install -r requirements.txt --force-reinstall
Python version mismatch
If you’re using the wrong Python version:
# Check which Python is active
which python
python --version
# Recreate environment with correct version
conda deactivate
conda remove -p venv --all
conda create -p venv python==3.12
conda activate venv/
ChromaDB errors
If ChromaDB fails to initialize:
# Clear the vector store
rm -rf ~/.RepoRAGX/vector_store/
# Reinstall ChromaDB
pip uninstall chromadb
pip install chromadb==1.5.1