[ML] Missing chunkers for AzureOpenAIService, AzureAIStudioService and HuggingFace embeddings #109875
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
Pinging @elastic/ml-core (Team:ML) |
|
@elasticmachine update branch |
|
@elasticmachine update branch |
maxhniebergall
approved these changes
Jun 18, 2024
| return List.of(new ErrorChunkedInferenceResults(error.getException())); | ||
| if (model instanceof AzureAiStudioModel baseAzureAiStudioModel) { | ||
| var actionCreator = new AzureAiStudioActionCreator(getSender(), getServiceComponents()); | ||
| var batchedRequests = new EmbeddingRequestChunker(input, EMBEDDING_MAX_BATCH_SIZE, EmbeddingRequestChunker.EmbeddingType.FLOAT) |
There was a problem hiding this comment.
how do we know that the AzureAiStudioModel only uses FLOAT types?
There was a problem hiding this comment.
Looks like the response format is the same as openai which I believe supports float and base64. Elasticsearch only supports float and byte at the moment though.
| * For HuggingFace use a conservatively small max batch size as it is | ||
| * unknown how the model is deployed | ||
| */ | ||
| static final int EMBEDDING_MAX_BATCH_SIZE = 20; |
There was a problem hiding this comment.
If the optimal batch size depends on the hardware, then I think we should make this user configurable. I think we can do that in a future PR if you want to get this one out now.
jonathan-buttner
approved these changes
Jun 18, 2024
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Adds chunking for AzureOpenAIService, AzureAIStudioService and the HuggingFace text embedding service. HuggingFace ELSER is not chunked.