Re: [PR] [#34236] Add Vertex AI Multi-Modal embedding handler [beam]

["jrmccluskey (via GitHub)" <gi...@apache.org>]

jrmccluskey commented on code in PR #35677:
URL: https://github.com/apache/beam/pull/35677#discussion_r2322561859


##########
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:
   Wound up wrapping everything (this wound up being cleaner for both videos and text, for images it's a little overkill as of now but that's fine) and got everything documented. Started messing with the union input type. but given that we're actually interacting with column names in the function signature instead we get some really annoying code paths (and also run into Python's native type hinting limitations) so I dropped that idea for now. Will likely return later. 



-- 
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: github-unsubscribe@beam.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org