fix(tests): Uses gemini-embedding-001 by default

[kevinmessiaen]

Description

Fix skipped tests by using gemini model by default

Related Issue

Fixes #2305

Type of Change

• 🔧 Bug fix (non-breaking change which fixes an issue)

[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 resolves an issue where certain functional tests were being skipped by updating the default embedding model used in the test suite. By switching the default to gemini/gemini-embedding-001, the previously skipped test_embedding_model_real_embedding can now run, enhancing test coverage and ensuring the functionality of embedding models is properly validated.

Highlights

• Default Embedding Model Update: The default embedding model used in tests has been updated from 'text-embedding-3-small' to 'gemini/gemini-embedding-001' to ensure tests can run without specific API keys.
• Test Unskip: A functional test, test_embedding_model_real_embedding, which was previously skipped due to requiring an OpenAI API key, has been unskipped, allowing it to execute with the new default Gemini model.

🧠 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/conftest.py
  • Updated the default embedding model from "text-embedding-3-small" to "gemini/gemini-embedding-001" in the embedding_model fixture.
• libs/giskard-agents/tests/test_embedding_model.py
  • Removed the @pytest.mark.skip decorator from the test_embedding_model_real_embedding function.

Ignored Files

• Ignored by pattern: .github/workflows/** (1)
  • .github/workflows/integration-tests.yml

Activity

• The pull request was created by kevinmessiaen to fix skipped tests.
• Changes were implemented to use the Gemini embedding model by default in the test configuration.
• A functional test was unskipped to allow it to run with the updated default model.

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 updates the default embedding model for tests from OpenAI's text-embedding-3-small to gemini/gemini-embedding-001. This change also enables a previously skipped functional test for real embeddings, which is a good improvement. I've added one suggestion in conftest.py to improve maintainability by avoiding code duplication.

[gemini-code-assist]

To improve maintainability and avoid duplicating the default model name, we can refactor this fixture. The default model gemini/gemini-embedding-001 is already specified in the LitellmEmbeddingModel definition. By conditionally adding the model argument only when the TEST_EMBEDDING_MODEL environment variable is set, we can rely on the default defined in the model class and have a single source of truth for the default model.

Suggested change

	return EmbeddingModel(
	model=os.getenv("TEST_EMBEDDING_MODEL", "text-embedding-3-small"),
	model=os.getenv("TEST_EMBEDDING_MODEL", "gemini/gemini-embedding-001"),
	params=EmbeddingParams(dimensions=1536),
	)
	model_name = os.getenv("TEST_EMBEDDING_MODEL")
	init_kwargs = {"params": EmbeddingParams(dimensions=1536)}
	if model_name:
	init_kwargs["model"] = model_name
	return EmbeddingModel(**init_kwargs)