test(agents): skip OpenAI-dependent embedding functional test

[kevinmessiaen]

The real embedding functional test requires an OPENAI API key.

Also refresh uv.lock .

[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 addresses a potential issue where a functional test for embedding models could fail due to the absence of an OpenAI API key. By marking this specific test to be skipped, the PR ensures that the test suite remains stable and passes in environments lacking the necessary external credentials. Additionally, it includes an update to the dependency lock file, reflecting any changes in the project's package requirements.

Highlights

• Test Skipping: A functional test for embedding models that relies on an OpenAI API key has been marked to be skipped. This prevents test failures in environments where the API key is not available.
• Dependency Update: The uv.lock file has been refreshed, indicating an update to the project's dependencies.

🧠 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.

Changelog

• libs/giskard-agents/tests/test_embedding_model.py
  • Added a @pytest.mark.skip decorator to test_embedding_model_real_embedding.

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 skips a functional test that depends on an OpenAI API key. My feedback suggests an improvement to conditionally skip the test using pytest.mark.skipif. This will allow the test to run in environments where the API key is present, providing better test coverage for developers who can run it locally.

[gemini-code-assist]

Instead of unconditionally skipping this test, it's better to skip it only when the OPENAI_API_KEY is not available. This allows developers and CI environments with the key to still run this important functional test. You can achieve this using pytest.mark.skipif.

You will need to add import os at the top of the file for this change.

Suggested change

	@pytest.mark.skip(reason="Requires OPENAI API key")
	@pytest.mark.skipif(os.environ.get("OPENAI_API_KEY") is None, reason="Requires OPENAI_API_KEY environment variable")