AIReview

AIReview is a command-line tool that leverages LLM to provide code reviews for your Git changes.

Features

• Automatic detection of Git changes
• AI-powered code review using OpenAI's GPT models
• Customizable review prompts and project context
• Markdown-formatted review output
• Support for multiple file reviews in a single run

Installation

Install this tool using pip:

pip install aireview

Configuration

Create a configuration file named aireview.config with the following structure in your project root:

[ai]
model = gpt-4
api_key = your_openai_api_key
base_url = https://api.openai.com/v1  # Optional: for custom OpenAI-compatible endpoints

[review]
output = ai-review.md # Output file for the review comments

[context]
project_context = Your project context description... # Example, I am working on Nodejs, typescript project

[prompt]
prompt_template = Your custom review prompt... # Example, Review the changes and provide feedback on the code quality and best practices

Usage

1. Make some changes in your Git repository
2. Add changes to the staging area:

git add  the/changed/files

3. Run AIReview:

aireview --config path/to/aireview.config # you can skip --config if the config file is in the project root

The tool will:

1. Detect your Git changes
2. Send them to the LLM for review
3. Generate a markdown file with the review comments

Development

1. Clone the repository:

git clone https://github.com/setkyar/aireview.git
cd aireview

2. Create and activate a virtual environment:

python -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate

3. Install the package:

pip install -e .

Running Tests

# Install test dependencies
pip install -e ".[test]"

# Run tests
pytest

# Run tests with coverage
coverage run -m pytest
coverage report

Contributing

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