gemini-code-assist[bot] commented on PR #37428: URL: https://github.com/apache/beam/pull/37428#issuecomment-3802789782
## Summary of Changes Hello @Eliaaazzz, 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 enhances the `RunInference` component by introducing a flexible content-aware dynamic batching mechanism. Previously, batching was strictly count-based, which was inefficient for variable-length inputs common in NLP and LLM workloads. The new feature allows users to define a custom function (`element_size_fn`) to determine the "size" or "weight" of each element (e.g., token count), enabling `RunInference` to create batches that optimize resource utilization and prevent out-of-memory issues. The implementation follows a modular design using a wrapper pattern, ensuring that existing pipelines remain unaffected while providing powerful new capabilities. ### Highlights * **Content-Aware Dynamic Batching**: Introduced the ability to perform dynamic batching based on element size rather than just element count, addressing limitations with variable-length inputs in ML inference workloads like NLP and LLMs. * **`element_size_fn` Integration**: Users can now provide a custom `element_size_fn` to `ModelHandler`, which is then passed to `beam.BatchElements` to define how elements are sized for batching, enabling optimization based on 'weight' (e.g., token count). * **Modular Design**: Implemented using a `_SizingModelHandler` wrapper (decorator pattern) to extend `ModelHandler` functionality without modifying existing classes, ensuring backward compatibility, type safety, and adherence to the Open-Closed Principle. * **Comprehensive Testing**: New unit tests were added to verify correct `element_size_fn` injection into batching arguments, proper delegation of `ModelHandler` methods by the wrapper, and compatibility when chaining multiple `ModelHandler` wrappers. 🧠 **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]
