Refactor: Remove unused 'responses' argument from Gemma3 generate_preprocess

[jaytiwarihub]

Overview

This PR resolves a TODO in gemma3_causal_lm_preprocessor.py by removing the unused responses argument from the generate_preprocess method.

Changes

• Removed logic in generate_preprocess that handled responses input, as it is unnecessary for generation tasks.
• Simplified the input handling logic to focus solely on prompts and images during inference.
• Updated gemma3_causal_lm_preprocessor_test.py to remove responses from the input data in test_generate_preprocess and test_text_generate_preprocess.

Reasoning

As noted in the codebase TODO, generate_preprocess is intended for inference (generation), where ground-truth responses are not needed. Support for responses should be isolated to call() for training/fine-tuning purposes. This change removes dead code and clarifies the API.

Verification

• Ran the specific test file: pytest keras_hub/src/models/gemma3/gemma3_causal_lm_preprocessor_test.py
• Confirmed all tests passed (including the modified tests).

[gemini-code-assist]

Summary of Changes

Hello @jaytiwarihub, I'm Gemini Code Assist¹! 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 refactors the generate_preprocess method within the Gemma3 causal language model preprocessor. The primary goal is to remove the responses argument, which was identified as unnecessary for generation tasks and only relevant for training or fine-tuning. This change streamlines the inference pipeline, removes dead code, and clarifies the method's intended use, improving overall code maintainability and API clarity.

Highlights

• Code Cleanup: Removed the unused responses argument and its associated logic from the generate_preprocess method in gemma3_causal_lm_preprocessor.py.
• Input Handling Simplification: Simplified the input handling within generate_preprocess to exclusively process prompts and images, aligning with its role in inference tasks.
• Test Updates: Updated gemma3_causal_lm_preprocessor_test.py to reflect the removal of the responses argument from test cases, ensuring consistency.

🧠 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 to enable Memory in your admin console.

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

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.

Customization

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.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 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.

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.

Footnotes

1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

[gemini-code-assist]

Code Review

This pull request correctly removes the unused responses argument from the generate_preprocess method in Gemma3CausalLMPreprocessor, which simplifies the logic for inference. The change is well-reasoned and aligns with the goal of separating training and generation concerns. I've pointed out a minor code duplication issue that can be cleaned up. Overall, this is a good refactoring.