Re:Solr’s Dense Vector Search for indexing and searching den...
by bratao on Monday September 05, 2022 @12:58PM
(#32726458)
Shameless plug from someone not related to the project. Try https://vespa.ai , fully open-source, very mature hybrid search with dense and approximated vector search. A breeze to deploy and maintain compared to ES and Solr. If I could name a single secret ingredient for my startup, is Vespa.
[ Parent
| on HN ]
Re:Solr’s Dense Vector Search for indexing and searching den...
by forrest2 on Monday September 05, 2022 @03:33PM
(#32728359)
Vespa looks pretty compelling; indexing looks like a dream.
I'd recommend basically anything else over a customized ES / Solr cluster. Some of the least fun clusters to manage. Great for simple use-cases / anything you see in a tutorial. The moment you walk off the beaten path with them, best of luck.
Just an anecdote
Re:Solr’s Dense Vector Search for indexing and searching den...
by binarymax on Monday September 05, 2022 @05:00PM
(#32729420)
Solr has its quirks for sure, but I’ve seen multi-terabyte sized indices running with great relevance and performance. I would call it a mechanics search engine. It is very powerful but you need to get your hands dirty.
Re:Solr’s Dense Vector Search for indexing and searching den...
by lmeyerov on Monday September 05, 2022 @06:00PM
(#32730013)
can vespa index 100M+ vectors on a regular RAM cpu server? any faster w/ a gpu (T4 / A10)?
Re:Solr’s Dense Vector Search for indexing and searching den...
by lmeyerov on Wednesday September 07, 2022 @01:59PM
(#32753905)
Super promising, thanks. Will definitely watch for production readiness - this direction is a big deal as we find most data is cold (logs, docs, ..), not hot, and finally starts becoming more relevant than just doing ES or our own!
Re:Solr’s Dense Vector Search for indexing and searching den...
by mountainriver on Monday September 05, 2022 @03:39PM
(#32728431)
Vespa seemed like a total mess compared to Milvus when I picked them up
Re:Solr’s Dense Vector Search for indexing and searching den...
by peterstjohn on Monday September 05, 2022 @04:08PM
(#32728840)
Two big reasons for Vespa over Milvus 1.x:
* Filtering
* String-based IDs
(a caveat that I haven't used Milvus 2.x recently, which does fix these issues, but brings in a bunch of other dependencies like Kafka or Pulsar)