[ENH] Add google genai embedding function

[jairad26]

Description of changes

Summarize the changes made by this PR.

• Improvements & Bug fixes
  • this pr adds google genai embedding function since the other packages are deprecated now
    fixes [Bug]: Gemini wrapper in Python relies on deprecated library #5177
• New functionality
  • ...

Test plan

How are these changes tested?

• Tests pass locally with pytest for python, yarn test for js, cargo test for rust

Migration plan

Are there any migrations, or any forwards/backwards compatibility changes needed in order to make sure this change deploys reliably?

Observability plan

What is the plan to instrument and monitor this change?

Documentation Changes

Are all docstrings for user-facing APIs updated if required? Do we need to make documentation changes in the docs section?

[github-actions]

Reviewer Checklist

Please leverage this checklist to ensure your code review is thorough before approving

Testing, Bugs, Errors, Logs, Documentation

• Can you think of any use case in which the code does not behave as intended? Have they been tested?
• Can you think of any inputs or external events that could break the code? Is user input validated and safe? Have they been tested?
• If appropriate, are there adequate property based tests?
• If appropriate, are there adequate unit tests?
• Should any logging, debugging, tracing information be added or removed?
• Are error messages user-friendly?
• Have all documentation changes needed been made?
• Have all non-obvious changes been commented?

System Compatibility

• Are there any potential impacts on other parts of the system or backward compatibility?
• Does this change intersect with any items on our roadmap, and if so, is there a plan for fitting them together?

Quality

• Is this code of a unexpectedly high quality (Readability, Modularity, Intuitiveness)

[jairad26]

• [ENH] Add google genai embedding function #5836 👈 (View in Graphite)
• main

This stack of pull requests is managed by Graphite. Learn more about stacking.

[propel-code-bot]

Introduce GoogleGenaiEmbeddingFunction and supporting artifacts

Adds first-class support for Google GenAI text embeddings by implementing GoogleGenaiEmbeddingFunction, supplying a JSON-schema for config validation, wiring it into the embedding-function registry, and extending the builtin test set. The change replaces soon-to-be-deprecated PaLM endpoints and keeps API surface consistent with existing embedding providers while enforcing config-schema validation and runtime input checks.

Key Changes

• Implemented new class GoogleGenaiEmbeddingFunction in chromadb/utils/embedding_functions/google_embedding_function.py (≈150 LoC) with constructor, __call__, schema driven config helpers, and safety checks
• Created config schema file schemas/embedding_functions/google_genai.json for JSON-schema validation of GenAI parameters (model_name, vertexai, project, location)
• Registered the new provider in chromadb/utils/embedding_functions/__init__.py (known_embedding_functions, __all__, built-ins set, test expectations)
• Updated unit test chromadb/test/ef/test_ef.py to assert presence of GoogleGenaiEmbeddingFunction in built-ins

Affected Areas

• chromadb/utils/embedding_functions/google_embedding_function.py
• chromadb/utils/embedding_functions/__init__.py
• schemas/embedding_functions/google_genai.json
• chromadb/test/ef/test_ef.py

This summary was automatically generated by @propel-code-bot

[propel-code-bot]

[BestPractice]

Generic exception handling swallows all errors: Catching Exception on line 70 masks important error types like authentication failures, network issues, or API quota exceeded. This makes debugging difficult and hides actionable error information from users.

Suggested Change

Suggested change

	try:
	response = self.client.models.embed_content(
	model=self.model_name, contents=input
	)
	except Exception as e:
	raise ValueError(f"Failed to generate embeddings: {str(e)}") from e
	try:
	response = self.client.models.embed_content(
	model=self.model_name, contents=input
	)
	except ImportError as e:
	raise ValueError(f"Missing dependency: {str(e)}") from e
	except ConnectionError as e:
	raise ValueError(f"Network connection failed: {str(e)}") from e
	except Exception as e:
	raise ValueError(f"Failed to generate embeddings: {str(e)}") from e

⚡ Committable suggestion

Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation.

Context for Agents

[**BestPractice**]

Generic exception handling swallows all errors: Catching `Exception` on line 70 masks important error types like authentication failures, network issues, or API quota exceeded. This makes debugging difficult and hides actionable error information from users.

<details>
<summary>Suggested Change</summary>

```suggestion
        try:
            response = self.client.models.embed_content(
                model=self.model_name, contents=input
            )
        except ImportError as e:
            raise ValueError(f"Missing dependency: {str(e)}") from e
        except ConnectionError as e:
            raise ValueError(f"Network connection failed: {str(e)}") from e
        except Exception as e:
            raise ValueError(f"Failed to generate embeddings: {str(e)}") from e
```

⚡ **Committable suggestion**

Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation.

</details>

File: chromadb/utils/embedding_functions/google_embedding_function.py
Line: 71