Code documentation generation with LLMs

Focus on writing your code, let LLMs write the documentation for you.
Generate comprehensive documentation for your code using OpenAI's powerful language models.

Built with treesitter and OpenAI API

✨ Features

• 📝  Generate documentation comment blocks for all methods in a file
  • e.g. Javadoc, JSDoc, Docstring, Rustdoc etc.
• ✍️   Generate inline documentation comments in method bodies
• 🌳  Treesitter integration for accurate code parsing
• 🔄  Support for various OpenAI models (GPT-3.5, GPT-4, etc.)

Note

Documentation will only be added to files without unstaged changes, so nothing is overwritten.

📋 Requirements

• Python >= 3.9
• OpenAI API Key

📦 Installation

Install in an isolated environment with pipx:

pipx install doc-comments-ai

If you are facing issues using pipx you can also install directly from source through PyPI with:

pip install doc-comments-ai

However, it is recommended to use pipx instead to benefit from isolated environments for the dependencies.

🔧 Configuration

Environment Variables

You can configure the application using environment variables. Create a .env file in your project root directory based on the provided .env.example:

# OpenAI API Key (Required)
OPENAI_API_KEY=your_api_key_here

# OpenAI Model Selection (Optional, defaults to gpt-3.5-turbo)
# Available options: gpt-3.5-turbo, gpt-4, gpt-3.5-turbo-16k, etc.
OPENAI_MODEL=gpt-3.5-turbo

# OpenAI API Base URL (Optional, for proxy or custom endpoints)
# OPENAI_BASE_URL=https://api.openai.com/v1

Or set them directly in your environment:

export OPENAI_API_KEY=your_api_key_here
export OPENAI_MODEL=gpt-4  # Optional
export OPENAI_BASE_URL=your_custom_url  # Optional

🚀 Usage

Generate documentation for methods in a file:

# Basic usage with default model (gpt-3.5-turbo)
aicomment <RELATIVE_FILE_PATH>

# Use a specific model
aicomment <RELATIVE_FILE_PATH> --model gpt-4

# Add inline comments to method bodies
aicomment <RELATIVE_FILE_PATH> --inline

# Confirm documentation generation for each method
aicomment <RELATIVE_FILE_PATH> --guided

Note

For extensive and descriptive documentation, consider using GPT-4 or GPT-3.5-turbo-16k models which have larger context windows.

📚 Supported Languages

• Python
• Typescript
• Javascript
• Java
• Rust
• Kotlin
• Go
• C++
• C
• C#
• Haskell

🛟 Troubleshooting

• During installation with pipx

  pip failed to build package: tiktoken
  
  Some possibly relevant errors from pip install:
    error: subprocess-exited-with-error
    error: can't find Rust compiler
  

  Make sure the rust compiler is installed on your system from here.

🌟 Contributing

If you are missing a feature or facing a bug don't hesitate to open an issue or raise a PR. Any kind of contribution is highly appreciated!