Add cookbook for tagging traces with metadata

[SecroLoL]

Carry over Yifan's cookbook for adding tags to traces (enabling metadata).

This was originally taken from Yifan's PR for trace tags but moved because we removed the src/demo/ folder.

There's also a small commit to remove random cursor comments.

[gemini-code-assist]

Summary of Changes

Hello @SecroLoL, 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 new example cookbook showcasing the trace metadata tagging feature, specifically how to associate customer IDs and arbitrary tags with traces. It also includes some minor cleanup in an existing cookbook and updates a project dependency.

Highlights

• New Cookbook: Added a new cookbook demonstrating how to use the judgment.set_metadata() method to add customer IDs and tags to traces.
• Code Cleanup: Removed various commented-out code and extraneous comments from the LangGraph music recommender cookbook.
• Dependency Update: Updated the judgeval dependency in the Pipfile from a local editable path to a standard package reference.

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 in your pull request via creating an issue comment (i.e. comment on the pull request page) using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands.

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 issue 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 is currently in preview and 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 to provide feedback.

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 configureGemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

[SecroLoL]

Let's wait to merge this because we need to hold until Yifan's PR is merged. JudgmentLabs/judgeval#261

[gemini-code-assist]

Code Review

This pull request introduces a new cookbook example (cookbooks/features/tagging.py) demonstrating how to add metadata tags and customer IDs to traces using the judgeval library. The changes also include updating the judgeval dependency in Pipfile from a local path to a general dependency and removing some commented-out code and unnecessary comments in the music_agent.py example for better clarity. The new cookbook is well-structured and clearly demonstrates the tagging feature. My main suggestion is to incorporate type hints in the new Python script to enhance maintainability.

[gemini-code-assist]

Consider adding a return type hint to this function signature. Type hints improve code readability and help static analysis tools catch potential errors, as outlined in PEP 484.¹

Style Guide References

Suggested change

	def get_customer_id():
	def get_customer_id() -> str:

Footnotes

1. PEP 484 introduces type hints for Python. Adding them to function signatures clarifies the expected types of arguments and return values, enhancing code maintainability and enabling static type checking. ↩

[gemini-code-assist]

Adding a return type hint here would improve clarity on what this function is expected to return. This aligns with best practices for maintainable Python code (PEP 484).¹

Additionally, consider adding from typing import List, Dict, Any at the beginning of the file if you plan to add more detailed type hints for variables like tags or trace_data within the function body.

Style Guide References

Suggested change

	def test_metadata():
	def test_metadata() -> str:

Footnotes

1. PEP 484, the type hinting standard for Python, recommends using type hints for function signatures to improve code understanding and allow for static type checking, which can prevent bugs. ↩