• Overview
• Features
• Supported Languages
• Installation
• Configuration
• Usage
• How It Works
• Customization
• Contributing
• License
• Contact

The AI-Driven Code Documentation Generator automates the creation of structured documentation for codebases. Utilizing OpenAI's GPT-4 (or Azure OpenAI) and advanced parsing techniques, it extracts code structures and generates insightful docstrings. This tool enhances maintainability and collaboration for projects of any size.

• Multi-Language Support: Automatically generates documentation for Python, JavaScript, TypeScript, Go, C++, Java, HTML, and CSS.

• Structured Documentation: Produces JSON-based documentation conforming to a predefined schema for consistency and ease of use.

• Google-Style Docstrings: Inserts detailed, Google-style docstrings into your codebase.

• Asynchronous Processing: Efficiently handles large codebases with asynchronous file processing.

• Customizable Prompts: Tailor AI prompts to fit your project's specific documentation needs.

• Comprehensive Logging: Detailed logs with log rotation to monitor the documentation process.

• Configuration Flexibility: Customize settings via config.json and environment variables.

• Documentation Report: Generates a Markdown report with all generated documentation and a dynamically generated Table of Contents.

• Unified Badge Function: Generates badges for Cyclomatic Complexity, Halstead Metrics (Volume, Difficulty, Effort), and Maintainability Index.

• Compact Badge Style: Uses flat-square style for badges.

• Dynamic Thresholds: Customizable thresholds for different metrics.

• Enhanced generate_documentation_report: Integrates badge generation into the report.

• Markdown Structure: Uses tables for readability.

• Environment-Based Thresholds: Fetches thresholds from environment variables.

• Asynchronous File Writing: Uses aiofiles for non-blocking operations.

• Comprehensive Scoring: Calculates maximum complexity across functions and methods.

• Robust Error Management: Handles missing Halstead metrics and logs errors.

• Flexibility and Customization: Dynamic thresholds and compact badge styles.

• Python
• JavaScript
• TypeScript
• Go
• C++
• Java
• HTML
• CSS

• Python 3.9+
• Node.js (for JavaScript/TypeScript handlers)
• OpenAI API Key or Azure OpenAI Credentials
• Git (for cloning the repository)

git clone https://github.com/yourusername/yourrepo.git
cd yourrepo

python3 -m venv venv
source venv/bin/activate

pip install -r requirements.txt

Navigate to the scripts directory and install dependencies:

cd scripts
npm install
cd ..

Create a .env file in the root directory:

# OpenAI Configuration
OPENAI_API_KEY=your_openai_api_key
AZURE_OPENAI_API_KEY=your_azure_openai_api_key
ENDPOINT_URL=your_azure_endpoint_url
DEPLOYMENT_NAME=your_azure_deployment_name

# Other Configurations
MODEL_NAME=gpt-4

Create a config.json file:

{
  "project_info": "This project is an AI-driven documentation generator.",
  "style_guidelines": "Follow Google Python Style Guide.",
  "excluded_dirs": ["tests", "docs"],
  "excluded_files": ["setup.py", "manage.py"],
  "skip_types": [".json", ".md", ".txt", ".csv", ".lock"]
}

python3 main.py /path/to/your/project -c config.json --use-azure --concurrency 3 -o documentation_report.md

• /path/to/your/project: Path to the codebase.
• -c config.json: Path to the configuration file.
• --use-azure: Use Azure OpenAI.
• --concurrency 3: Number of concurrent API requests.
• -o documentation_report.md: Output file for the report.

python3 main.py ./my_project -c config.json --use-azure --concurrency 5 -o docs_output.md

1. Configuration: Reads from config.json and environment variables.
2. File Collection: Traverses the project directory.
3. Code Structure Extraction: Extracts structures using handlers.
4. Documentation Generation: Uses AI to generate documentation.
5. Docstring Insertion: Inserts docstrings into source code.
6. Validation: Validates code with syntax checks.
7. Reporting: Compiles Markdown report with badges.

Modify function_schema.json to fit your needs.

Modify format_function_docstring in utils.py.

1. Create a Language Handler: Inherit from BaseHandler.
2. Implement Methods: extract_structure and insert_docstrings.
3. Update LANGUAGE_MAPPING: Add file extensions in utils.py.

1. Fork the Repository

2. Create a Feature Branch

   git checkout -b feature/YourFeature

3. Commit Your Changes

   git commit -m "Add YourFeature"

4. Push to the Branch

   git push origin feature/YourFeature

5. Open a Pull Request

This project is licensed under the MIT License.

For questions or support, contact [email protected].

You can also reach out through:

• GitHub Issues
• Discussion Forum

Enhance your codebase documentation effortlessly with AI-driven precision.