This project provides an LLM-powered tool for automatically generating code documentation comments, targeting developers who want to streamline the documentation process. It supports various documentation formats (Javadoc, Docstring, etc.) and offers both cloud-based (OpenAI, Azure OpenAI) and local LLM integration for privacy-conscious users.

How It Works

The tool leverages langchain for LLM orchestration and treesitter for accurate code parsing across multiple languages. It generates documentation blocks for entire files or inline comments within methods. The approach prioritizes developer workflow by integrating directly into the terminal and ensuring no unstaged changes are overwritten.

Quick Start & Requirements

• Install via pipx install doc-comments-ai.
• Requires Python >= 3.9.
• OpenAI API key or Azure OpenAI credentials for cloud models.
• For local LLMs, requires models in .gguf format (e.g., via huggingface-cli) and potentially a Rust compiler for llama-cpp-python installation.

Highlighted Details

• Supports 10+ programming languages including Python, TypeScript, Java, Rust, and C++.
• Offers guided mode for interactive confirmation of generated comments.
• Integrates with OpenAI, Azure OpenAI, and local LLMs via llama.cpp and ollama.
• Generates both file-level documentation blocks and inline comments.

Maintenance & Community

The project is actively maintained with CI/CD pipelines for build and publish. Contributions are welcomed via issues and pull requests.

Licensing & Compatibility

The project appears to be under the MIT license, allowing for commercial use and integration with closed-source projects.

Limitations & Caveats

Local LLM performance and quality are highly dependent on the model size and hardware, with larger models requiring significant resources. Installation issues may arise if a Rust compiler is not present for llama-cpp-python.