Automatically generate comprehensive documentation for your Python projects using OpenAI's GPT models. This tool analyzes your codebase and creates detailed, well-structured documentation that helps developers understand and use your code effectively.

• 🔍 Intelligent Code Analysis: Uses AST parsing to understand your code structure
• 📝 Comprehensive Documentation: Generates detailed docs for modules, classes, functions, and more
• 🚀 Incremental Updates: Only regenerates docs for files that have changed
• 🔧 Git Integration: Tracks changes through git history
• 💰 Cost-Effective: Minimal API usage through smart caching and incremental updates
• 🎨 Beautiful Output: Generates well-structured Markdown documentation
• ⚙️ Highly Configurable: Customize what gets documented and how
• 🖥️ CLI & API: Use as a command-line tool or integrate into your Python projects

pip install ai-doc-generator

Or install from source:

git clone https://github.com/haseebrj17/ai-doc-generator.git
cd ai-doc-generator
pip install -e .

1. Set your OpenAI API key:

export OPENAI_API_KEY="your-api-key-here"

2. Generate documentation for your project:

ai-doc-gen /path/to/your/project

That's it! Your documentation will be generated in docs/generated/.

# Generate docs for current directory
ai-doc-gen

# Generate docs for specific path
ai-doc-gen /path/to/project

# Force full regeneration (ignore cache)
ai-doc-gen --full

# Use a specific model
ai-doc-gen --model gpt-4o-mini

# Custom output directory
ai-doc-gen --output docs/api

# Include test files
ai-doc-gen --include-tests

# Dry run to see what would be documented
ai-doc-gen --dry-run

from ai_doc_generator import Config, DocumentationGenerator

# Create configuration
config = Config(
    project_root="./my_project",
    output_dir="./docs",
    include_tests=False,
    model="gpt-4o"
)

# Generate documentation
generator = DocumentationGenerator(config)
generator.generate_documentation()

Create a ai-doc-config.json file in your project root:

{
  "model": "gpt-4o",
  "output_dir": "docs/generated",
  "include_patterns": ["*.py"],
  "exclude_dirs": ["tests", "__pycache__", ".venv"],
  "exclude_files": ["setup.py"],
  "max_file_size": 100000,
  "include_tests": false
}

For a typical Python project:

• Small project (10k lines): ~$2-3
• Medium project (50k lines): ~$8-12
• Large project (100k lines): ~$15-25

After initial generation, incremental updates cost 90% less!

docs/generated/
├── README.md                 # Main documentation index
├── project-overview.md       # High-level project analysis
├── api-reference.md         # Complete API reference
├── modules/                 # Module-specific documentation
│   ├── core/
│   ├── utils/
│   └── ...
└── documentation.json       # Raw documentation data

Only regenerate documentation for files that have changed:

# First run - documents everything
ai-doc-gen

# Subsequent runs - only changed files
ai-doc-gen

Customize the documentation style:

config = Config(
    system_prompt="Generate concise API documentation focusing on usage examples..."
)

Use different models for different purposes:

• gpt-4o: Best quality, detailed documentation
• gpt-4o-mini: Faster and cheaper, good for most projects
• gpt-4-turbo-preview: Balance of quality and cost

# Clone the repository
git clone https://github.com/haseebrj17/ai-doc-generator.git
cd ai-doc-generator

# Install development dependencies
pip install -e ".[dev]"

# Run tests
pytest

# Run linting
black .
flake8 .
mypy .

# Run tests with coverage
pytest --cov=ai_doc_generator

The project documentation is available at: https://haseebrj17.github.io/ai-doc-generator/

1. Go to Settings → Pages in your GitHub repository
2. Under "Build and deployment", select "Deploy from a branch"
3. Choose gh-pages branch and / (root) folder
4. Click Save

This project has automated publishing workflows:

When you push changes to main with an updated version in pyproject.toml, the package will automatically be published to PyPI if all tests pass.

1. Create a new tag: git tag v1.0.1 && git push origin v1.0.1
2. The workflow will automatically publish to PyPI

1. Create an account on PyPI
2. Generate an API token from your account settings
3. Add the token as PYPI_API_TOKEN in your repository secrets (Settings → Secrets → Actions)
4. Optionally, add TEST_PYPI_API_TOKEN for test releases

Contributions are welcome! Please feel free to submit a Pull Request. For major changes, please open an issue first to discuss what you would like to change.

1. Fork the repository
2. Create your feature branch (git checkout -b feature/AmazingFeature)
3. Commit your changes (git commit -m 'Add some AmazingFeature')
4. Push to the branch (git push origin feature/AmazingFeature)
5. Open a Pull Request

This project is licensed under the MIT License - see the LICENSE file for details.

• OpenAI for providing the GPT models
• The Python AST module for code analysis
• All contributors and users of this project

• 📧 Email: muhamadhaseeb2001@gmail.com
• 🐛 Issues: GitHub Issues
• 💬 Discussions: GitHub Discussions

Made with ❤️ by Muhammad Haseeb