feat(genai/embeddings/multimodal): Add multimodal video embedding example

[Kef131]

Description

Fixes #
b/546128007

Add new example for generating multimodal videos embeddings using the Gemini API and corresponding test.

• Added multimodal_embedding_video.py implementing an example of embedding image and text content using the Gemini embedding model (gemini-embedding-2).
• Changed the default GOOGLE_CLOUD_LOCATION for tests from us-central1 to global for broader compatibility.

Checklist

Testing

• I have tested this change on a live environment and verified it works as intended.

Compliance & Style

• I have followed the Sample Guidelines.
• The README is updated with all relevant information (if applicable).
• If this PR adds a new sample directory: I updated the CODEOWNERS file.

---

Post-Approval Actions

• Please merge this PR for me once it is approved

[snippet-bot]

Here is the summary of changes.

You are about to add 1 region tag.

• genai/embeddings/multimodal_embedding_video.py:15, tag aiplatform_genai_multimodal_embedding_video

---

This comment is generated by snippet-bot.
If you find problems with this result, please file an issue at:
https://github.com/googleapis/repo-automation-bots/issues.
To update this comment, add snippet-bot:force-run label or use the checkbox below:

• Refresh this comment

[gemini-code-assist]

Code Review

This pull request introduces a new example and test for multimodal video embedding using the gemini-embedding-2 model. The feedback highlights that changing the global GOOGLE_CLOUD_LOCATION environment variable to global can break other regional tests like model tuning; it is recommended to revert this change and use monkeypatch to set the location locally for the video embedding test. Additionally, the reviewer suggests constructing the Part object directly with file_data and video_metadata instead of mutating it after creation to ensure robustness and idiomatic code.

[angelcaamal]

LGTM!

[XrossFox]

LGTM

[amcolin]

I think we need to pass the Vertex AI flags here. Since we are pointing to a gs:// bucket, the client needs to connect to Google Cloud rather than the default AI Studio backend.

Suggested change

	client = genai.Client()
	client = genai.Client(vertexai=True, project="YOUR_PROJECT_ID", location="us")

Here is the documentation example for reference: https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/embeddings/get-multimodal-embeddings#dimensions