feat(genai/embeddings): migrate multimodal embeddings to genai - #14515
Conversation
Sorry, something went wrong.
Migrates the sample for generating multimodal (image, video, text) embeddings to the new `google-genai` SDK and adds the corresponding test.
There was a problem hiding this comment.
Code Review
This pull request introduces a new example (multimodal_example.py) for generating multimodal embeddings (combining image, video, and text) using the google-genai SDK, and adds a corresponding test in test_embeddings_examples.py. A critical issue was identified in the test where the get_image_video_text_embeddings function is referenced but not actually called due to missing parentheses, which prevents the test from executing the actual embedding logic.
Sorry, something went wrong.
|
Here is the summary of changes. You are about to add 1 region tag.
This comment is generated by snippet-bot.
|
Sorry, something went wrong.
|
|
||
| # [END aiplatform_genai_multimodal_embedding_image_video_text] | ||
|
|
||
| if __name__ == "__main__": |
There was a problem hiding this comment.
Do we need to remove the main function?
Sorry, something went wrong.
There was a problem hiding this comment.
done
Sorry, something went wrong.
amcolin
left a comment
There was a problem hiding this comment.
LGTM
Sorry, something went wrong.
Description
Migrates the sample for generating multimodal (image, video, text) embeddings to the new google-genai SDK and adds the corresponding test.
Tested locally.
Fixes b/546128628
Checklist
Testing
Compliance & Style
Post-Approval Actions