gemini-code-assist[bot] commented on PR #37458: URL: https://github.com/apache/beam/pull/37458#issuecomment-3825336647
## Summary of Changes Hello @PDGGK, 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 significantly enhances the Apache Beam Python SDK's Kafka integration by adding native support for Kafka record headers. This feature allows users to attach metadata to their Kafka messages, providing greater flexibility and richer context for data processing workflows. The implementation involves a new cross-language transform in Java to handle the conversion of structured Beam Row elements into Kafka ProducerRecords with headers, alongside updates to the Python `WriteToKafka` API and necessary validation. ### Highlights * **Kafka Headers Support in Python SDK**: The Python `WriteToKafka` transform now includes a `with_headers` parameter, enabling users to write Kafka records with custom headers. * **New Cross-Language Transform for Headers**: A new Java class, `WriteWithHeaders`, has been introduced. This class acts as a cross-language transform, converting `beam.Row` elements (which can include key, value, and headers) into Kafka `ProducerRecord` objects. * **URN Registration**: A new URN, `beam:transform:org.apache.beam:kafka_write_with_headers:v1`, has been registered to identify the new `WriteWithHeaders` external transform. * **Input Schema for Headers**: When `with_headers=True`, input elements must be `beam.Row` objects with `key` (bytes), `value` (bytes), and an optional `headers` field (List[Row(key=str, value=bytes)]). Optional `topic`, `partition`, and `timestamp` fields are also supported for per-record overrides. * **Serializer Restriction**: When using `with_headers=True`, only `ByteArraySerializer` is supported for both key and value serializers to ensure compatibility with header handling. 🧠**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]
