Set the name of a customized llm grader.

[weizhang25]

Set the name of a customized llm grader when it is created in the llm grader generator.

[gemini-code-assist]

Summary of Changes

Hello @weizhang25, 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 introduces a minor but significant enhancement by enabling the assignment of a custom name to an LLM grader during its creation. This change facilitates better identification and management of different grader instances, particularly when dealing with multiple customized configurations.

Highlights

• LLM Grader Naming: The LLMGrader constructor now accepts a name parameter, allowing customized LLM graders to be initialized with a specific name derived from self.config.grader_name.

🧠 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 adds the grader_name from the configuration when creating an LLMGrader instance. The change is straightforward and aligns with the goal of setting a name for customized LLM graders. I've added one comment regarding pre-existing typing issues in the surrounding code that would be beneficial to address for improved code quality and robustness.

[gemini-code-assist]

While adding the name parameter is correct, the surrounding type: ignore comments are concerning as they can hide potential runtime bugs. For instance, self.config.model can be None, but LLMGrader requires a model and will raise an error. The type: ignore comments are likely necessary because the type of self.config is not being correctly inferred as LLMGraderGeneratorConfig.

To improve type safety and make the code more robust, this block could be refactored. Since this is a pre-existing issue, it could be addressed in a follow-up, but here is an example of how it could be improved:

from typing import cast

...
async def generate(self, dataset: List[dict], **kwargs) -> LLMGrader:
    config = cast(LLMGraderGeneratorConfig, self.config)

    if not config.model:
        raise ValueError("LLMGraderGenerator requires a model to be configured.")
    if not config.custom_evaluation_prompt:
        raise ValueError("LLMGraderGenerator requires a custom_evaluation_prompt to be configured.")

    rubrics = await self._generate_rubrics(dataset, **kwargs)
    return LLMGrader(
        model=config.model,
        name=config.grader_name,
        mode=config.grader_mode,
        template=config.custom_evaluation_prompt,
        rubrics=rubrics,
    )

This change would provide proper type inference, allow for the removal of the type: ignore comments, and add necessary guards against None values.