You are viewing a plain text version of this content. The canonical link for it is here.
Posted to github@beam.apache.org by "weifonghsia (via GitHub)" <gi...@apache.org> on 2025/03/10 17:59:18 UTC
[I] [Feature Request]: VertexAIImageEmbeddings adding the ability to send in contextual text too [beam]
weifonghsia opened a new issue, #34236:
URL: https://github.com/apache/beam/issues/34236
### What would you like to happen?
The function: VertexAIImageEmbeddings suggests using the `embedding_model_name = 'multimodalembedding@001'`.
The multimodal embedding generator can have both image and contextual text embeddings generated at the same time.
However, if you try to submit with contextual_text
```
mm_embedding_transform = VertexAIImageEmbeddings(
model_name=text_embedding_model_name,
columns=['image','contextual_text'],
# columns=['image'],
dimension=1408,
project=project_id)
```
It will error out `AttributeError: 'str' object has no attribute '_gcs_uri' [while running 'Embedding/RunInference/BeamML_RunInference']` because it's looking for the image.
The FR is to add the functionality so it can handle both.
### Issue Priority
Priority: 2 (default / most feature requests should be filed as P2)
### Issue Components
- [x] Component: Python SDK
- [ ] Component: Java SDK
- [ ] Component: Go SDK
- [ ] Component: Typescript SDK
- [ ] Component: IO connector
- [ ] Component: Beam YAML
- [ ] Component: Beam examples
- [ ] Component: Beam playground
- [ ] Component: Beam katas
- [ ] Component: Website
- [ ] Component: Infrastructure
- [ ] Component: Spark Runner
- [ ] Component: Flink Runner
- [ ] Component: Samza Runner
- [ ] Component: Twister2 Runner
- [ ] Component: Hazelcast Jet Runner
- [ ] Component: Google Cloud Dataflow Runner
--
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.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
Re: [I] [Feature Request]: VertexAIImageEmbeddings adding the ability to send in contextual text too [beam]
Posted by "weifonghsia (via GitHub)" <gi...@apache.org>.
weifonghsia commented on issue #34236:
URL: https://github.com/apache/beam/issues/34236#issuecomment-2711405093
@damccorm
--
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
Re: [I] [Feature Request]: VertexAIImageEmbeddings adding the ability to send in contextual text too [beam]
Posted by "liferoad (via GitHub)" <gi...@apache.org>.
liferoad commented on issue #34236:
URL: https://github.com/apache/beam/issues/34236#issuecomment-2817306142
This will need a new MultiModal Embedding Handler.
--
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
Re: [I] [Feature Request]: VertexAIImageEmbeddings adding the ability to send in contextual text too [beam]
Posted by "jrmccluskey (via GitHub)" <gi...@apache.org>.
jrmccluskey closed issue #34236: [Feature Request]: VertexAIImageEmbeddings adding the ability to send in contextual text too
URL: https://github.com/apache/beam/issues/34236
--
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