Thank you for your interest in contributing to LLM Vision! All kinds of contributions are welcome, whether you're fixing a bug, adding translations, or adding new features.
Tip
Check beta versions and other branches first, before you start working on a new fix/feature. Your fix or feature might already exist!
- Fork the repository and clone it locally.
- Create a new branch for your changes:
git checkout -b feature/your-feature-name
- Make your changes, test them thoroughly (run the tests in
/tests, and commit with clear, descriptive messages. - Open a Pull Request against the latest
vX.Y.Z-betabranch with a summary of what you've changed and why.
If you're unsure about something, have questions about the codebase, or need guidance on how to approach a contribution, don't hesitate to reach out on Discord. We're always happy to answer questions and provide support.
You can also check the Discussions tab for technical questions or browse the Documentation for context on how things work.
- Follow the existing code style and structure.
- Keep changes focused: one feature or fix per PR where possible.
- Include comments where the intent isn't immediately obvious.
- Use type hints to indicate the variable type.
- Run all tests in
/tests. - Test your changes against a working Home Assistant instance before submitting.
AI tools are acceptable for debugging: using them to understand errors, trace logic, or look up API behavior is fine. However, purely AI-generated or "vibe-coded" pull requests will not be accepted and will be closed by maintainers without review.
All contributed code should reflect genuine understanding of what it does and why.
Please use GitHub Issues for bug reports and feature requests rather than pull requests. Check existing issues before opening a new one, and include debug logs for bug reports (debugging can be enabled on the integration's settings page).
By contributing, you agree that your contributions will be licensed under the Apache-2.0 License.