[ML] Add rerank task type to internal service #108452
Merged
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Outdated suggestions cannot be applied.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.
Implements the rerank task using cross encoder models uploaded to Elasticsearch using Eland and the _ml/trained_models APIs. The cross encoder model should be configured for
text_similarity
.This example installs the BAAI/bge-reranker-base model:
The rerank endpoint is created in the inference API with:
There is one task setting
return_documents
which defaults to true. Return documents controls whether or not the response contains the input text.Then to rerank:
The response is ordered by relevance, index links back to the original document position
With
return_documents: false
the response does not contain the input text