gemini-code-assist[bot] commented on PR #37337: URL: https://github.com/apache/beam/pull/37337#issuecomment-3761755611
## Summary of Changes Hello @damccorm, I'm Gemini Code Assist[^1]! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed! This pull request rectifies a prior decision by re-adopting `setuptools` for the JuliaSet example's dependency and packaging needs, moving away from a `requirements.txt` based approach. The change ensures that the example properly utilizes `setup.py` for building and distributing its components to Dataflow workers, which is a more robust and feature-rich method for managing Python project dependencies and installation within the Apache Beam ecosystem. This update streamlines the deployment process and aligns with best practices for Python Dataflow workflows. ### Highlights * **Dependency Management Migration**: The JuliaSet example has been migrated from using a `requirements.txt` file for dependency management to a `setup.py` file, leveraging `setuptools` for packaging and distribution. * **Reversal of Previous Change**: This pull request explicitly undoes a previous change (PR #35962) that moved the example away from `setuptools`, acknowledging that the initial problem should have been fixed within the `distutils` context rather than abandoning `setuptools`. * **Updated Example Configuration**: The integration test (`juliaset_test_it.py`) and the main execution script (`juliaset_main.py`) have been updated to use the `--setup_file` option instead of `--requirements_file` when running the Dataflow pipeline, pointing to the newly introduced `setup.py`. * **Introduction of setup.py with Custom Commands**: A new `setup.py` file has been added for the JuliaSet example, which defines the package using `setuptools`. It also includes an example of custom build commands that can be executed during package installation on worker machines. 🧠**New Feature in Public Preview:** You can now enable **Memory** to help **Gemini Code Assist** learn from your team's feedback. This makes future code reviews more consistent and personalized to your project's style. **Click [here](https://codeassist.google/code-review/login) to enable Memory in your admin console.** <details> <summary><b>Using Gemini Code Assist</b></summary> <br> The full guide for Gemini Code Assist can be found on our [documentation page](https://developers.google.com/gemini-code-assist/docs/review-github-code), here are some quick tips. <b>Invoking Gemini</b> You can request assistance from Gemini at any point by creating a comment using either `/gemini <command>` or `@gemini-code-assist <command>`. Below is a summary of the supported commands on the current page. Feature | Command | Description --- | --- | --- Code Review | `/gemini review` | Performs a code review for the current pull request in its current state. Pull Request Summary | `/gemini summary` | Provides a summary of the current pull request in its current state. Comment | @gemini-code-assist | Responds in comments when explicitly tagged, both in pull request comments and review comments. Help | `/gemini help` | Displays a list of available commands. <b>Customization</b> To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a `.gemini/` folder in the base of the repository. Detailed instructions can be found [here](https://developers.google.com/gemini-code-assist/docs/customize-gemini-behavior-github). <b>Limitations & Feedback</b> Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with :thumbsup: and :thumbsdown: on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up [here](https://google.qualtrics.com/jfe/form/SV_2cyuGuTWsEw84yG). <b>You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the [Gemini Code Assist IDE Extension](https://cloud.google.com/products/gemini/code-assist).</b> </details> [^1]: Review the [Privacy Notices](https://policies.google.com/privacy), [Generative AI Prohibited Use Policy](https://policies.google.com/terms/generative-ai/use-policy), [Terms of Service](https://policies.google.com/terms), and learn how to configure Gemini Code Assist in GitHub [here](https://developers.google.com/gemini-code-assist/docs/customize-gemini-behavior-github). Gemini can make mistakes, so double check it and [use code with caution](https://support.google.com/legal/answer/13505487). -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected]
