[ML] Include the chunk text offsets in chunked inference response #118659
+610
−1,412
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
davidkyle
added
>refactoring
:ml
|
Pinging @elastic/ml-core (Team:ML) |
💔 Backport failed
You can use sqren/backport to manually backport by running |
davidkyle
added a commit
to davidkyle/elasticsearch
that referenced
this pull request
Dec 16, 2024
…astic#118659) # Conflicts: # x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/services/elastic/ElasticInferenceService.java # x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/services/huggingface/elser/HuggingFaceElserService.java # x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/services/googleaistudio/GoogleAiStudioServiceTests.java
elasticsearchmachine
pushed a commit
that referenced
this pull request
Dec 16, 2024
…18659) (#118775) # Conflicts: # x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/services/elastic/ElasticInferenceService.java # x-pack/plugin/inference/src/main/java/org/elasticsearch/xpack/inference/services/huggingface/elser/HuggingFaceElserService.java # x-pack/plugin/inference/src/test/java/org/elasticsearch/xpack/inference/services/googleaistudio/GoogleAiStudioServiceTests.java
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Outdated suggestions cannot be applied.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.
Creates a new interface
ChunkedInferencefor carrying the chunked inference results to Semantic Text, the response object contains the chunked text and the text offsets in the original source string. In future the text will be removed and just the offsets returned.It was noted that the
InferenceService::chunkedInfermethod is always called on the local node and the result classes are never serialised across nodes, hence these classes do not need to implement toXContent or namedwritable.There is a lot of churn in this PR but almost all of it is due to changing the signature of
InferenceService::chunkedInfer.