Chat with Github Repo - A Python project for understanding Github repositories
Chat with Github Repo is an open-source Python project that allows you to chat with any Github repository and quickly understand its codebase. The project was created using Streamlit, OpenAI GPT-3.5-turbo, and Activeloop's Deep Lake.
The project works by scraping a Github repository and embedding its codebase using Langchain, storing the embeddings in Deep Lake. The chatbot then searches the dataset stored in Deep Lake to find relevant information and generates responses based on the user's input.
If you are interested in AI and want to learn more, the creator, Peter W, provides the Github link to the project, where you can try it out and give feedback. He plans to extend the project to support multiple repositories in the future.
According to the project's Github page, there are two Python scripts that demonstrate how to create a chatbot using Streamlit, OpenAI GPT-3.5-turbo, and Activeloop's Deep Lake. One script scrapes the Github repository, and the other script creates a chatbot interface using Streamlit. The chatbot interface allows you to chat with the codebase and ask questions about the repository.
To install and use the project, follow these instructions from the project's Github page:
Installation
pip install -r requirements.txt
Usage
python scrape.py --url {github-repo-url} --save-path {path-to-store-embs}
streamlit run chatbot.py
Note that you will need to have a valid OpenAI API key to use the project.