feat: change default fuzziness from AUTO to 0 in OpenSearch retrievers#3198
Open
SyedShahmeerAli12 wants to merge 1 commit intodeepset-ai:mainfrom
Open
feat: change default fuzziness from AUTO to 0 in OpenSearch retrievers#3198SyedShahmeerAli12 wants to merge 1 commit intodeepset-ai:mainfrom
SyedShahmeerAli12 wants to merge 1 commit intodeepset-ai:mainfrom
Conversation
SyedShahmeerAli12
requested review from
julian-risch
and removed request for
a team
github-actions
Bot
added
integration:opensearch
integration:amazon-bedrock
type:documentation
Contributor
Coverage report (amazon_bedrock)
Click to see where and how coverage changed
This report was generated by python-coverage-comment-action |
||||||||||||||||||||||||
Contributor
Coverage report (opensearch)
This PR does not seem to contain any modification to coverable code. |
Contributor
|
Hey @SyedShahmeerAli12 you also touched amazon bedrock files which are unrelated to your PR, please remove them. |
fuzziness="AUTO" was causing severe performance regressions (30s → 6s search times) for large indexes. Switching the default to 0 (exact matching) avoids the clause explosion that AUTO triggers on big corpora. Users who need fuzzy matching can still pass fuzziness="AUTO" explicitly. Closes deepset-ai#3187
SyedShahmeerAli12
force-pushed
the
fix/opensearch-fuzziness-default-off
branch
from
5d72bf0 to
5c62c73
Compare
Contributor
Author
|
@sjrl removed the Amazon Bedrock files, the PR now only contains the OpenSearch fuzziness changes. |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Closes #3187
fuzziness="AUTO"was causing severe performance regressions on large indexes — search times going from 30s → 6s when turned off"AUTO"to0(exact matching) in:OpenSearchBM25RetrieverOpenSearchHybridRetrieverOpenSearchDocumentStore._bm25_retrieval/_bm25_retrieval_asyncfuzziness="AUTO"explicitly — no functionality removed, just the default changesTest plan
to_dictserialization tests to reflect new defaultrun()call assertion tests to reflect new defaultfrom_dicttests that explicitly pass"AUTO"are unchanged (backward compat with old serialized configs)