Hi all, I have 5 copies/replicas of a SOLR collection with SOLR Cloud & Zookeeper (SOLR 9.0)
I'm trying to get to the bottom of a strange issue: Documents that are updated with queries to a single SOLR server/endpoint get replicated across all replicas in the cluster (as you'd expect) and this includes a dense vector field but, strangely, the KNN dense-vector results from each server/replica are different (different topK results when the same query is run against each replica/server). Does this make sense? I don't really understand the "beamwidth" setting documented in the docs (so I've left hnswBeamWidth at the default (40 I think for SOLR 9.0). I'm also wondering: Does SOLR KNN search mean it indexes static values at the point of indexing (like nearest neighbour friends?) and if data changes over time (documents removed, documents added) will this affect the KNN performance? thanks for any info Derek -- Derek Conniffe Harvey Software Systems Ltd T/A HSSL Telephone (IRL): 086 856 3823 Telephone (US): (650) 449 6044 Skype: dconnrt Email: [email protected] *Disclaimer:* This email and any files transmitted with it are confidential and intended solely for the use of the individual or entity to whom they are addressed. If you have received this email in error please delete it (if you are not the intended recipient you are notified that disclosing, copying, distributing or taking any action in reliance on the contents of this information is strictly prohibited). *Warning*: Although HSSL have taken reasonable precautions to ensure no viruses are present in this email, HSSL cannot accept responsibility for any loss or damage arising from the use of this email or attachments. P For the Environment, please only print this email if necessary.
