Fix flaky MMR diversification YAML tests#143706
Open
mayya-sharipova wants to merge 1 commit intoelastic:mainfrom
Open
Fix flaky MMR diversification YAML tests#143706mayya-sharipova wants to merge 1 commit intoelastic:mainfrom
mayya-sharipova wants to merge 1 commit intoelastic:mainfrom
Conversation
The default int8_hnsw index type quantizes float32 vectors to int8, introducing enough scoring error to non-deterministically reorder documents with close cosine similarities. With only 4 dimensions the quantization is particularly coarse. Use explicit hnsw index type on test dense_vector mappings to get exact float scoring and deterministic KNN result ordering. Update expected results to reflect exact cosine ordering. Closes elastic#143430 Closes elastic#143609
mayya-sharipova
added
>test
elasticsearchmachine
added
the
Team:Search Relevance
Collaborator
|
Pinging @elastic/es-search-relevance (Team:Search Relevance) |
This file contains hidden or 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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
The default int8_hnsw index type quantizes float32 vectors to
int8, introducing enough scoring error to non-deterministically
reorder documents with close cosine similarities. With only 4
dimensions the quantization is particularly coarse.
Use explicit hnsw index type on test dense_vector mappings to
get exact float scoring and deterministic KNN result ordering.
Update expected results to reflect exact cosine ordering.
Closes #143430
Closes #143609