chore(py): add back evaluator sample

[huangjeff5]

No description provided.

[gemini-code-assist]

Summary of Changes

Hello, 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 reintroduces a comprehensive Python sample for Genkit evaluators, providing practical examples of how to implement custom evaluation logic. It showcases two distinct approaches: a simple regex-based evaluator for pattern matching and a more advanced LLM-as-judge evaluator for subjective scoring. The changes aim to guide users in developing their own evaluation functions within the Genkit framework, complete with updated documentation and necessary data files for immediate testing.

Highlights

• Evaluator Sample Reintroduction: Reintroduced a Python sample demonstrating custom Genkit evaluators, including both a regex-based and an LLM-as-judge implementation.
• Regex Evaluator: Implemented a byo/url evaluator that uses regular expressions to check for the presence of URLs in output, requiring no LLM interaction.
• LLM-as-Judge Evaluator: Developed a byo/deliciousness evaluator that leverages an LLM to score output based on a predefined prompt, acting as an 'LLM-as-judge'.
• Supporting Files: Added necessary dataset JSON files for both evaluators and a prompt definition file for the LLM-as-judge evaluator to facilitate testing and demonstration.
• Documentation Update: Updated the README.md with clear instructions for setting up and running both the regex and LLM-based evaluators using genkit eval:run commands.

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.

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 two new evaluators: a regex-based URL matcher and an LLM-as-judge for 'deliciousness'. It includes the necessary datasets and a prompt definition for the LLM evaluator. The README.md has been updated to provide clear instructions on how to run these new evaluators. The implementation is clean, leverages Pydantic for robust schema validation, and correctly utilizes environment variables for model configuration, which are good practices for maintainability and flexibility. The changes enhance the sample evaluators, providing practical examples of both rule-based and LLM-powered evaluation patterns within the Genkit framework.