damccorm commented on code in PR #35677:
URL: https://github.com/apache/beam/pull/35677#discussion_r2285609463
##########
sdks/python/apache_beam/ml/transforms/embeddings/vertex_ai.py:
##########
@@ -281,3 +294,194 @@ def get_ptransform_for_processing(self, **kwargs) ->
beam.PTransform:
return RunInference(
model_handler=_ImageEmbeddingHandler(self),
inference_args=self.inference_args)
+
+
+@dataclass
+class VertexAIMultiModalInput:
+ image: Optional[Image] = None
+ video: Optional[Video] = None
+ contextual_text: Optional[str] = None
Review Comment:
From
https://www.google.com/url?q=https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/multimodal-embeddings-api%23request_body&sa=D&source=docs&ust=1755616714498799&usg=AOvVaw3yaLxsXOYCo9hUA32-GbqB
it looks like image at least could have an associated mimeType now or
eventually (to represent if it is e.g. a jpg, png, etc...).
> should this change, we can always update things on our end.
Could we update this in a backwards compatible way?
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
