• 📍 Table of Contents
• 🤖 Overview
• 🔮 Features
• 🚀 Getting Started
  • ✅ Dependencies
    • 📂 Repository
    • 🔐 OpenAI API Setup
  • 💻 Installation
  • 🪄 Using README-AI
  • 🧪 Running Tests
• 🛠 Future Development
• 🤝 Contributing
• 📄 License
• 👏 Acknowledgments

README-AI is a powerful, user-friendly tool that automatically generates high-quality README files for your Git repositories using OpenAI's language model APIs. By simply providing the path or url to your project's codebase, this tool will craft a well-structured and comprehensive README that highlights your project's features, installation steps, usage instructions, and more.

⚠️ Note:

This project is currently under development and has an opinionated configuration and setup. While README-AI provides an excellent starting point for any project that requires documentation, it is important to review all text that is generated by the OpenAI API to ensure that it accurately represents your codebase.

🔝 Return

📍 Repository File Summaries Code summaries of each script in your repository are generated via OpenAI's large language model APIs, such as gpt-3.5-turbo. Your codebase is parsed and file contents are converted to natural language, and displayed in Markdown table format.

↕️

📍 Introduction, Badges, Table of Contents The OpenAI API generates a 1-sentence phrase describing your project. Project dependencies and software visualized using beautiful SVG icon badges. Badges are sorted by hex code, displayed from light to dark hues. A table of contents is also provided for your README.md file.

📍 Project Feature Table These sections are generated using detailed prompts, embedded with your repository metadata. The Overview section describes your project's use case and application. The Features section highlights attributes of your codebase, formatted in a Markdown table. Working on fine-tuning the prompts to improve the accuracy and relevance to your project.

Why not a directory tree as well? Visualize your codebase structure in your README.

Dynamically generates installation and run guides to help others explore and use your code!

📍 Setup Support for: Python Rust Go C Kotlin Java JavaScript TypeScript

Adds additional standard sections to build out a robust README file!

Markdown example files generated by the README-AI app!

Developing a feature that allows the user to select from a variety of README formats and styles.

Example template options include data and ML focused, research, hackathons, minimal, and more!

🔝 Return

Before you begin, ensure that you have the following prerequisites installed:

• Python 3.7 or higher
• Conda package manager (recommended)
• Access to the OpenAI API (see OpenAI API Setup below)

Most user's will run README-AI using the command-line interface, specifying their repository on run-time. However, if you would like to use the default configuration, you will need to update the configuration file with your repository's remote URL (GitHub, GitLab) or local directory pat on your machine.

# Repository Configuration
[git]
repository = "INSERT YOUR REPOSITORY URL / PATH HERE"

To use README-AI, you will need an API key for OpenAI. Follow the steps below to create an API key:

1. Clone the README-AI repository:

git clone https://github.com/eli64s/README-AI.git && cd README-AI

2. Create a Conda environment and install the required dependencies:

# With Bash
bash setup/setup.sh

# With Conda
conda env create -f setup/environment.yaml
conda activate readme_ai
pip install -r requirements.txt

3. Set up the OpenAI API key by creating an environment variable:

export OPENAI_API_KEY=<your-api-key>

Use the command-line to provide the OpenAI API key (if not already set) and specify an output path for your README file, along with the path to your local repository or remote code repository.

Command-Line Arguments:

• --api_key : Provide your OpenAI API key.
• --output : Provide a path where to write the output file.
• --repository : Provide a remote Git URL or a local directory.

python src/main.py --api_key skabc123 --output README_AI.md --repository https://github.com/eli64s/README-AI

Alternatively, run the bash script to run README-AI with the default configuration.

bash scripts/run.sh

To run the unit-tests for README-AI, use the following command.

bash scripts/test.sh

🔝 Return

• Add additional language setup guides for populating the 🚀 Getting Started README section.
• Implement multiple README templates with different formats and styling.
• Add feature to select the language of text written to the README file.
• Add a UI using Textual or another framework to improve the user experience.

Contributions are welcomed and encouraged! Please follow these steps in the Contributing Guidelines, thank you!

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

SVG Icons

• Aveek-Saha/GitHub-Profile-Badges
• Ileriayo/Markdown-Badges

🔝 Return