[
https://issues.apache.org/jira/browse/SOLR-17928?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=18034450#comment-18034450
]
Puneet Ahuja commented on SOLR-17928:
-------------------------------------
[~hossman]Increasing the topK to get more accuracy is more of a
work-around/hack. Using efSearch is a cleaner way to increase accuracy by
increasing the number of vectors explored during graph traversal.
I can implement the efSearchFactor as you suggested, and keep the default value
as 1.0, so the existing users will not be affected, and their queries will work
same as before, as efSearch = topK by default.
> Add efSearch parameter to knn query
> -----------------------------------
>
> Key: SOLR-17928
> URL: https://issues.apache.org/jira/browse/SOLR-17928
> Project: Solr
> Issue Type: Improvement
> Components: vector-search
> Reporter: Ishan Chattopadhyaya
> Priority: Major
> Labels: pull-request-available
> Time Spent: 10m
> Remaining Estimate: 0h
>
> Right now, only topK can be requested. efSearch is a standard overfetch
> parameter.
> Proposing that we add it for better recall accuracy.
> (FYI, Elasticsearch calls it num_candidates. Commonly referred to as
> efSearch, similar to efConstruction that we call beamWidth)
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
