Opensearch's team fix for reducing search latency #278
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Outdated suggestions cannot be applied.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.
What kind of change does this PR introduce? (Bug fix, feature, docs update, ...)
Opensearch's 2.4 release led to serious speed latency issues because of new segmentation strategy of the Lucene 9.4 Decrease Marqo-os latencies via index settings[ENHANCEMENT] #265
This pr adds new index setting that would prevent further issues and in total leads to:
What is the current behavior? (You can also link to an open issue here)
Decrease Marqo-os latencies via index settings[ENHANCEMENT] #265
"took" field from executing single vector search on a 10mil vector index:
What is the new behavior (if this is a feature change)?
After fix "took" field from executing single vector search on a 10mil vector index:
Have unit tests been run against this PR? (Has there also been any additional testing?)
All the tensor_search passed while some model testing failed, probably this is related to M1 architecture.
As well tested index creation and verified that settings are applied and indeed affect index performance
Please check if the PR fulfills these requirements