Skip to main content

AI-powered documentation generation and maintenance tool

Project description

autodoc_ai 🚀

PyPI License Tests

autodoc_ai is an AI-powered tool designed to automatically generate meaningful commit messages and keep documentation up-to-date. It integrates seamlessly into any repository, ensuring that your README and Wiki documentation remain current and useful.

Features

  • Smart Commits: Automatically generate meaningful commit messages derived from git diffs.
  • Auto Documentation: Effortlessly update README and Wiki documentation based on code changes.
  • Quality Checks: Utilize CrewAI agents to evaluate and enhance documentation quality.
  • Streamlined Integration: Execute simple commands for all workflows with ease.

New Commands Overview

  • cmp: Commit changes using AI-generated messages.
  • just cm: Enriches documentation, commits, and pushes.
  • just enrich-days <days>: Update documentation based on the last <days> of commits.
  • just enrich-release: Update documentation based on commits since the last tag.

Quick Start

Integrate autodoc_ai into your repository to keep documentation synchronized:

# Install globally
pip install autodoc_ai

# Or install from source
git clone https://github.com/auraz/autodoc_ai.git
cd autodoc_ai
just install

# Set your OpenAI API key
export OPENAI_API_KEY="your-key-here"

# Optional: Configure logging and debug mode
export AUTODOC_LOG_LEVEL="DEBUG"  # Enable debug logging
export AUTODOC_DISABLE_CALLBACKS="true"  # Disable CrewAI callbacks if needed

# In your project directory
cd your-project
autodoc_ai  # Automatically enriches your README and Wiki based on staged changes

Additional Configuration Options

  • BASH_COMMIT_COMMAND: Customize the commit command for your environment.
  • BASH_COMMIT_SHORTCUT: Set a shortcut for quick access to the commit command.

Documentation Commands

Evaluate Documentation Quality

  • just eval README.md # Auto-detects as README type
  • just eval wiki/Usage.md # Auto-detects wiki page type
  • just eval-all wiki/ # Evaluate all documentation in the directory

Evaluate with Custom Criteria

  • just eval-with-prompt README.md "Check for clear installation instructions and examples"

Deploy Wiki to GitHub

  • just deploy-wiki # Push wiki files to GitHub wiki

Changelog

Stay informed about recent modifications and new features. Refer to the Changelog for updates.

Documentation

For comprehensive guidance, visit the GitHub Wiki:

License

MIT License - see LICENSE file for details.


This README has been enhanced for clarity and improved navigation, ensuring users can easily locate essential information and commands. The addition of a Changelog section allows users to stay updated on recent changes and new features.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

autodoc_ai-2.0.2.tar.gz (216.8 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

autodoc_ai-2.0.2-py3-none-any.whl (40.2 kB view details)

Uploaded Python 3

File details

Details for the file autodoc_ai-2.0.2.tar.gz.

File metadata

  • Download URL: autodoc_ai-2.0.2.tar.gz
  • Upload date:
  • Size: 216.8 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.7.6

File hashes

Hashes for autodoc_ai-2.0.2.tar.gz
Algorithm Hash digest
SHA256 b121dc5b18b0dae3759995a7b9b830727dfcc4c8030dd80de5f6abe230d1bc72
MD5 3acc210ae93b1b43bb1d8a97e18e5376
BLAKE2b-256 6c6288ec82b89d08f242b227deee2a61efa6e6e034113207746bebc6ba22d144

See more details on using hashes here.

File details

Details for the file autodoc_ai-2.0.2-py3-none-any.whl.

File metadata

  • Download URL: autodoc_ai-2.0.2-py3-none-any.whl
  • Upload date:
  • Size: 40.2 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.7.6

File hashes

Hashes for autodoc_ai-2.0.2-py3-none-any.whl
Algorithm Hash digest
SHA256 8e12d67154550ab153e4c7f632e96e52103068a19a5191a61d3600f4bb5c7b64
MD5 f60ae750054efbcaa8abd4ce98dce23e
BLAKE2b-256 ff05bdcb5652a35bbb9ecbc2066cfae59d8e178de0e33b01fbc8b1b4be458ea9

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page