A RAG assistant to allow you to chat with any github repo. Learn fast. The default repo is AdalFlow github repo.

Watch the video Click the image above to watch the demo video

.
├── frontend/ # React frontend application
├── src/ # Python backend code
├── api.py # FastAPI server
├── app.py # Streamlit application
└── pyproject.toml # Python dependencies

1. Install dependencies:

poetry install

2. Set up OpenAI API key:

Create a .streamlit/secrets.toml file in your project root:

mkdir -p .streamlit
touch .streamlit/secrets.toml

Add your OpenAI API key to .streamlit/secrets.toml:

OPENAI_API_KEY = "your-openai-api-key-here"

Run the streamlit app:

poetry run streamlit run app.py

Run the API server:

poetry run uvicorn api:app --reload

The API will be available at http://localhost:8000

1. Navigate to the frontend directory:

cd frontend

2. Install Node.js dependencies:

pnpm install

3. Start the development server:

pnpm run dev

The frontend will be available at http://localhost:3000

Analyzes a GitHub repository based on a query.

// Request
{
 "repo_url": "https://github.com/username/repo",
 "query": "What does this repository do?"
}
// Response
{
 "rationale": "Analysis rationale...",
 "answer": "Detailed answer...",
 "contexts": [...]
}

• Clearly structured RAG that can prepare a repo, persit from reloading, and answer questions.
  • DatabaseManager in src/data_pipeline.py to manage the database.
  • RAG class in src/rag.py to manage the whole RAG lifecycle.

• Conditional retrieval. Sometimes users just want to clarify a past conversation, no extra context needed.
• Create an evaluation dataset
• Evaluate the RAG performance on the dataset
• Auto-optimize the RAG model

• Support the display of the whole conversation history instead of just the last message.
• Support the management of multiple conversations.