- ๐ Table of Contents
- ๐ Overview
- ๐ Demos
- ๐ค Features
- ๐ฉโ๐ป Usage
- ๐ฃ Roadmap
- ๐ Changelog
- ๐ค Contributing
- ๐ License
- ๐ Acknowledgments
README-AI is a command-line tool that generates robust README.md files for your software and data projects. By simply providing a remote repository URL or path to your codebase, this tool auto-generates documentation for your entire project, leveraging the capabilities OpenAI's GPT language model APIs.
๐ฏ Motivation
Simplifies the process of writing and maintaining high-quality project documentation, enhancing developer productivity and workflow. The ultimate goal of readme-ai is to improve the adoption and usability of open-source software, enabling all skill levels to better understand complex codebases and easily use open-source tools.
This project is currently under development and has an opinionated configuration. While readme-ai provides an excellent starting point for documentation, its important to review all text generated by the OpenAI API to ensure it accurately represents your codebase.
Command-Line Interface
โฃ Run readme-ai in your terminal via PyPI, Docker, and more!
cli-demo.mov
Streamlit Community Cloud
โฃ Use readme-ai directly in your browser! Zero installation, zero code!
streamlit-demo.mov
โถ Project Badges
โฃ A slogan to highlight your poject is generated by prompting OpenAI's GPT engine. โฃ Codebase dependencies and metadata are visualized using Shields.io badges. |
![]() |
โฃ CLI option --badges
lets you choose between two styles currently: square and shields. Contributions for new ideas and styling options are welcome!
![]() |
![]() |
โธ Overview and Features Table
โฃ An overview paragraph and features table are generated using detailed prompts, embedded with project metadata. |
![]() |
โน Dynamic Usage Instructions
โฃ Generates instructions for installing, running, and testing your project. Instructions are created by identifying the codebase's top language and referring to our language_setup.toml configuration file. |
![]() |
โป Templates Coming Soon
โฃ Developing CLI option letting users select from a variety of README styles โฃ Templates for use-cases such as data, machine learning, web development, and more! |
|
โผ Example README Files
Output File | Repository | Languages | |
---|---|---|---|
1๏ธโฃ | readme-python.md | readme-ai | Python |
2๏ธโฃ | readme-typescript.md | chatgpt-app-react-typescript | TypeScript, React |
3๏ธโฃ | readme-javascript.md | assistant-chat-gpt-javascript | JavaScript, React |
4๏ธโฃ | readme-kotlin.md | file.io-android-client | Kotlin, Java, Android |
5๏ธโฃ | readme-rust-c.md | rust-c-app | C, Rust |
6๏ธโฃ | readme-go.md | go-docker-app | Go |
7๏ธโฃ | readme-java.md | java-minimal-todo | Java |
8๏ธโฃ | readme-fastapi-redis.md | async-ml-inference | Python, FastAPI, Redis |
9๏ธโฃ | readme-mlops.md | mlops-course | Python, Jupyter |
๐ | readme-pyflink.md | flink-flow | PyFlink |
Dependencies
Please ensure you have the following dependencies installed on your system:
- Python version 3.9 or higher
- Package manager (i.e. pip, conda, poetry) or Docker
- OpenAI API paid account and API key
Repository
A remote repository URL or path to your local project's directory is needed to use readme-ai. The following repository types are currently supported:
- GitHub
- GitLab
- Bitbucket
- File System
OpenAI API
An OpenAI API account and API key are needed to use readme-ai. The steps below outline this process:
๐ OpenAI API - Setup Instructions
- Go to the OpenAI website.
- Click the "Sign up for free" button.
- Fill out the registration form with your information and agree to the terms of service.
- Once logged in, click on the "API" tab.
- Follow the instructions to create a new API key.
- Copy the API key and keep it in a secure place.
โ ๏ธ OpenAI API - Cautionary Guidelines
-
Review Sensitive Information: Before running the application, ensure that all content in your repository is free of sensitive information. Please note that readme-ai does not filter out sensitive data from the README file, and it does not modify any files in your repository.
-
API Usage Costs: The OpenAI API is not free, and you will be charged for each request made. Costs can accumulate rapidly, so it's essential to be aware of your usage. You can monitor your API usage and associated costs by visiting the OpenAI API Usage Dashboard.
-
Paid Account Recommended: Setting up a paid account with OpenAI is highly recommended to avoid potential issues. Without a payment method on file, your API usage will be restricted to base GPT-3 models. This limitation can result in less accurate README file generation and may lead to API errors due to request limits.
-
Runtime Considerations: README file generation typically takes less than a minute. If the process exceeds a few minutes (e.g., 3 minutes), it's advisable to terminate readme-ai to prevent extended processing times.
Using Pip
Pip is the recommended installation method for most users.
pip install readmeai
Using Docker
Docker is recommended for users wanting to run the application in a containerized environment.
docker pull zeroxeli/readme-ai:latest
Manually Install
1๏ธโฃ Clone the readme-ai repository.
git clone https://github.com/eli64s/readme-ai
2๏ธโฃ Navigate to readme-ai directory.
cd readme-ai
3๏ธโฃ Install dependencies using a method below.
Using Bash
bash setup/setup.sh
Using Conda
conda create -n readmeai python=3.9 -y && \
conda activate readmeai && \
pip install -r requirements.txt
Using Poetry
poetry shell && \
poetry install
Command-Line Arguments
To generate a README.md file, use the readmeai
command in your terminal, along with the arguments below.
Short Flag | Long Flag | Description | Status |
---|---|---|---|
-k |
--api-key |
Your language model API secret key. | Optional |
-b |
--badges |
Select 'shields' or 'square' for badge style. | Optional |
-c |
--encoding |
Encoding used to tokenize text. | Optional |
-f |
--offline-mode |
Run offline without calling the OpenAI API. | Optional |
-m |
--model |
Large language model engine (gpt-3.5-turbo) | Optional |
-o |
--output |
The output path for your README.md file. | Optional |
-r |
--repository |
The URL or path to your code repository. | Required |
-t |
--temperature |
The temperature (randomness) of the model. | Optional |
-l |
--language |
The language of text to write README in. | Coming Soon! |
-s |
--style |
The README template style to build. | Coming Soon! |
Custom Settings
To customize the README file generation process, you can modify the following sections of the configuration file:
- api - OpenAI language model API configuration settings.
- git - Default git repository settings used if no repository is provided.
- paths - Directory paths and files used by the readme-ai application.
- prompts - Large language model prompts used to generate the README file.
- md - Dynamic Markdown section code templates used to build the README file.
Using Pip
# Option 1: Run readmeai command with all required command-line arguments.
readmeai --api-key "YOUR_API_KEY" --output readme-ai.md --repository https://github.com/eli64s/readme-ai
# Option 2: Run readmeai command with OpenAI API key set as environment variable.
export OPENAI_API_KEY="YOUR_API_KEY"
readmeai -o readme-ai.md -r https://github.com/eli64s/readme-ai -b shields
Using Docker
# Option 1: Run Docker container with all required command-line arguments.
docker run -it \
-e OPENAI_API_KEY="YOUR_API_KEY" \
-v "$(pwd)":/app zeroxeli/readme-ai:latest \
readmeai -o readme-ai.md -r https://github.com/eli64s/readme-ai
# Option 2: Run Docker container with OpenAI API key set as environment variable.
export OPENAI_API_KEY="YOUR_API_KEY"
docker run -it \
-e OPENAI_API_KEY=$OPENAI_API_KEY \
-v "$(pwd)":/app zeroxeli/readme-ai:latest \
readmeai -o readme-ai.md -r https://github.com/eli64s/readme-ai
Using Streamlit
Use the app directly in your browser via Streamlit Community Cloud.
Manually Run
Using Conda
conda activate readmeai
export OPENAI_API_KEY="YOUR_API_KEY"
python3 -m readmeai.cli.commands -o readme-ai.md -r https://github.com/eli64s/readme-ai
Using Poetry
poetry shell
export OPENAI_API_KEY="YOUR_API_KEY"
poetry run python3 -m readmeai.cli.commands -o readme-ai.md -r https://github.com/eli64s/readme-ai
Execute the test suite using the command below.
bash scripts/test.sh
- Publish project as a Python library via PyPI and a Docker image on Docker Hub.
- Integrate and deploy app with Streamlit to provide a simple user-interface for using the tool.
- Develop GitHub Actions script to automatically update the README file when new code is pushed.
- Design README output templates for a variety of use-cases (i.e. data, web-dev, minimal, etc.)
- Add support for generating README files in any language (i.e. CN, ES, FR, JA, KO, RU).
Looking to contribute to readme-ai? Here is what you can do to help:
- ๐จ Create new templates for different use-cases (i.e. data, web-dev, minimal, etc.).
- The README is constructed in sections, defined in the [config.toml] file.
- Follow the existing format to get started.
- ๐ Look for opportunities to make the code more efficient and readable, or Pythonic as they say.
- ๐ค Exception handling and bug fixes are always welcome.
Badges