AI Code Documenter

AI-powered documentation generator for your code that integrates with Git hooks and lint-staged.

Features

• 🤖 Uses AI to automatically generate and update code documentation
• 🔄 Seamlessly integrates with Git hooks via lint-staged
• 🧰 Support for JSDoc, TSDoc, docstrings, and Markdown formats
• ⚡ Command line interface for individual files or batch processing
• 🛠️ Programmable API for custom integrations
• 📝 Preserves your code while enhancing documentation
• 🚀 Parallel processing with configurable concurrency limits

Installation

npm install --save-dev ai-code-documenter
# or
yarn add --dev ai-code-documenter

Setup with lint-staged

1. Install the package
2. Update your lint-staged configuration in package.json:

{
  "lint-staged": {
    "*.{js,jsx,ts,tsx}": [
      "ai-document",
      "prettier --write",
      "eslint --fix"
    ]
  }
}

For improved performance with multiple files, you can set a concurrency limit:

{
  "lint-staged": {
    "*.{js,jsx,ts,tsx}": [
      "ai-document --concurrency 3",
      "prettier --write",
      "eslint --fix"
    ]
  }
}

Command Line Usage

Document individual files:

npx ai-document src/components/Button.tsx

Document multiple files:

npx ai-document src/**/*.ts --verbose

CLI options:

--verbose         Show detailed output
--tsdoc           Use TSDoc style (default is JSDoc)
--docstring       Use docstring style (for Python-like docs)
--markdown        Use Markdown style
--config <path>   Specify config file location
--concurrency <n> Set maximum number of files to process in parallel (default: 5)
--no-colors       Disable colored output

API Usage

import { documentFile, documentFiles } from 'ai-code-documenter';

// Document a single file
const result = await documentFile('src/utils/helper.ts', {
  outputStyle: 'tsdoc',
  verbose: true
});

// Document multiple files with concurrency limit
const results = await documentFiles([
  'src/components/Button.tsx',
  'src/utils/format.ts'
], {
  model: 'gpt-4',
  verbose: true,
  maxConcurrency: 3 // Process up to 3 files at once
});

Configuration

Create a configuration file in one of the following formats:

• .ai-documenter.json
• .ai-documenter.js
• .ai-documenter.ts
• ai-documenter.config.js
• ai-documenter.config.ts

Example JSON configuration:

{
  "apiKey": "your-openai-api-key", // Optional: can also use OPENAI_API_KEY env variable
  "model": "gpt-3.5-turbo", // Default model to use
  "outputStyle": "jsdoc", // jsdoc, tsdoc, docstring, or markdown
  "verbose": false, // Whether to show detailed logs
  "maxConcurrency": 5 // Maximum number of files to process concurrently
}

Example JavaScript/TypeScript configuration:

module.exports = {
  apiKey: process.env.MY_OPENAI_KEY,
  model: 'gpt-4',
  maxConcurrency: 3, // Process up to 3 files simultaneously
  // Other options...
};

Environment Variables

The tool supports loading environment variables from various .env files:

• .env - Default environment variables
• .env.local - Local overrides (not committed to git)
• .env.development - Development environment variables
• .env.development.local - Local overrides for development
• .env.production - Production environment variables
• .env.production.local - Local overrides for production
• .env.test - Test environment variables
• .env.test.local - Local overrides for test

Variables are loaded with the following precedence (highest to lowest):

1. .env.[environment].local
2. .env.local
3. .env.[environment]
4. .env

Required environment variables:

• OPENAI_API_KEY: Your OpenAI API key (unless specified in configuration)

Supported Languages

• JavaScript (.js)
• TypeScript (.ts)
• React (.jsx, .tsx)
• Support for additional languages coming soon!

How It Works

1. The tool extracts code from your files
2. It sends the code to an AI model with specific documentation instructions
3. The AI analyzes the code and generates appropriate documentation
4. The tool updates your files with the enhanced documentation
5. No code logic is changed, only comments are added or improved

License

MIT

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

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