feat(py): add sample test with simple flow and implement programmati…

[MengqinShen]

…c evaluation support

Description here... Help the reviewer by:

• linking to an issue that includes more details
• if it's a new feature include samples of how to use the new feature
• (optional if issue link is provided) if you fixed a bug include basic bug details

Checklist (if applicable):

• PR title is following https://www.conventionalcommits.org/en/v1.0.0/
• Tested (manually, unit tested, etc.)
• Docs updated (updated docs or a docs bug required)

[gemini-code-assist]

Summary of Changes

Hello @MengqinShen, 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 significantly enhances the Genkit Python library by integrating programmatic evaluation capabilities. It provides a new API for defining and executing evaluators against datasets, which is crucial for automated testing and quality assurance of AI models. The changes also include a practical demonstration of this feature and improvements to the robustness of the evaluation process's tracing mechanisms.

Highlights

• Programmatic Evaluation API: Introduced a new evaluate async method in genkit.ai._aio.py which allows users to programmatically run evaluators against datasets, providing a streamlined way to assess model performance directly within code.
• Evaluator Reference System: Added EvaluatorRef and evaluator_ref in genkit.blocks.evaluator.py to provide a structured way to reference and configure evaluators, enhancing modularity and reusability.
• New Evaluator Demo: Included a new sample evaluator-demo under py/samples/ that showcases how to define a custom evaluator (substring_match) and run it programmatically using the new ai.evaluate() API.
• Robust Tracing for Evaluation: Improved the eval_stepper_fn in genkit.ai._registry.py with a fallback mechanism to handle tracing infrastructure failures (e.g., in environments with NonRecordingSpans), ensuring evaluations can proceed even if tracing is not fully functional.

🧠 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 introduces programmatic evaluation support by adding a new ai.evaluate() method and an evaluator-demo sample. The changes look good overall, providing a solid foundation for evaluations. I've identified a potential bug in the error handling of the evaluation stepper function, where failures in non-tracing environments might be silently ignored. I've also left a few comments regarding type consistency and code cleanup. Once these points are addressed, this will be a great addition.