This release introduces a Python package designed to transform GitHub repositories into structured markdown files. The primary aim of repo2file4gpt is to facilitate the conversion of repository content into a format that is easily interpretable by Language Models, thereby enriching their knowledge base.
Key Features:
- Extracts essential files such as code, markdown, and notebooks from public GitHub repositories.
- Consolidates the content into a single, structured markdown file for each repository, preserving the full hierarchy.
- Offers high configurability, allowing users to specify the GitHub token, list of repositories, file types, and output directory.