Fix flaky MMR diversification YAML tests#143706
Merged
mayya-sharipova merged 2 commits intoelastic:mainfrom Mar 6, 2026
Merged
Fix flaky MMR diversification YAML tests#143706mayya-sharipova merged 2 commits intoelastic:mainfrom
mayya-sharipova merged 2 commits 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
Collaborator
|
Pinging @elastic/es-search-relevance (Team:Search Relevance) |
szybia
added a commit
to szybia/elasticsearch
that referenced
this pull request
Mar 6, 2026
…locations * upstream/main: (153 commits) ES|QL: Update docs for TOP_SNIPPETS and DECAY (elastic#143739) Correctly include endpoint id in log msg in AuthorizationPoller (elastic#143743) Bar searching or sorting on _seq_no when disabled (elastic#143600) Generalize `testClientCancellation` test (elastic#143586) JSON_EXTRACT: zero-copy byte slicing for object, array, and number extraction (elastic#143702) Track recycler pages in circuit breaker (elastic#143738) [ESQL] Enable distributed pipeline breakers for external sources via FragmentExec (elastic#143696) Adding 'mode' and 'codec' fields to ES monitoring template (elastic#143673) [ESQL] Columnar I/O and vectorized block conversion for external sources (elastic#143703) Fix flaky MMR diversification YAML tests (elastic#143706) ES|QL codegen: check builder arguments for vector support (elastic#143724) Add Views Security Model (elastic#141050) ESQL: Prevent pushdown of unmapped fields in filters and sorts (elastic#143460) Don't run seq_no pruning tests in release CI (elastic#143725) ESQL: Support intra-row field references in ROW command (elastic#140217) ES|QL: Remove implicit limit in FORK branches in CSV tests (elastic#143601) IndexRoutingTests with and without synthetic id (elastic#143566) Synthetic id upgrade test in serverless (elastic#142471) Disable "Review skipped" comments for PRs without specified labels (elastic#143728) Cleanup ES|QL T-Digest code duplication, add memory accounting (elastic#143662) ...
sidosera
pushed a commit
to sidosera/elasticsearch
that referenced
this pull request
Mar 6, 2026
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
This was referenced Mar 11, 2026
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
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