gemini-code-assist[bot] commented on PR #37491: URL: https://github.com/apache/beam/pull/37491#issuecomment-3842999751
## 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 reintroduces the `use_vertex_flex_api` option for the `GeminiModelHandler` in Apache Beam's ML inference module. This allows users to leverage a more cost-effective Vertex AI Flex API for Gemini models, which is particularly suitable for batch processing workloads where higher latency can be tolerated. The changes involve modifying the `GeminiModelHandler`'s constructor and client creation logic to support this new configuration, along with comprehensive pydoc updates and a dedicated unit test to validate the functionality. ### Highlights * **Reintroduction of Vertex Flex API**: The `use_vertex_flex_api` option is added back to `GeminiModelHandler` for cost-effective Gemini model inference, enabling a more economical approach for certain workloads. * **Enhanced Documentation**: Improved pydoc is provided for the new `use_vertex_flex_api` parameter, detailing its purpose, benefits, and linking to the official Vertex AI Flex Paygo documentation. * **Conditional Client Configuration**: The `genai.Client` creation logic is updated to conditionally use Vertex Flex API specific `HttpOptions` (including `api_version`, `headers`, and an extended `timeout`) when the flex API option is enabled. * **New Test Coverage**: A new unit test `test_create_client_with_flex_api` has been added to ensure the correct behavior of the Flex API client initialization, verifying that `genai.Client` and `HttpOptions` are called with the appropriate parameters. 🧠**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>Changelog</b></summary> * **sdks/python/apache_beam/ml/inference/gemini_inference.py** * Imported `HttpOptions` from `google.genai.types`. * Introduced `use_vertex_flex_api` boolean parameter to `GeminiModelHandler.__init__`. * Updated docstring for `GeminiModelHandler.__init__` to explain `use_vertex_flex_api` and link to relevant Vertex AI documentation. * Stored `use_vertex_flex_api` as an instance attribute. * Modified `create_client` to instantiate `genai.Client` with `HttpOptions` configured for the Vertex Flex API when `use_vertex_flex_api` is true, setting `api_version`, `headers`, and `timeout`. * **sdks/python/apache_beam/ml/inference/gemini_inference_test.py** * Imported the `mock` module from `unittest`. * Added `TestGeminiModelHandler` class with `test_create_client_with_flex_api` to verify that `genai.Client` and `HttpOptions` are called with the correct parameters when `use_vertex_flex_api` is enabled. </details> <details> <summary><b>Activity</b></summary> * This pull request is a re-submission of a previous change (PR #37051) to add the Vertex Flex API option, now that the official documentation for Vertex AI Flex Paygo is publicly available. </details> <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]
