vector-db-benchmark VS vector-search

Qdrant’s benchmark results are strongly in favor of accuracy and efficiency. We recommend that you consider them before deciding that an LLM is enough. Take a look at our open-source benchmark reports and try out the tests yourself.

Qdrant made their own benchmark. It is quite simple and also takes into consideration more options, so it should be better suited for benchmarking for production purposes.

is noWhen it comes to Supabase, it's using pgvector under the hood, so it would make sense to benchmark it with the other Open Source tools. There is an open PR for that, but it's pretty old: https://github.com/qdrant/vector-db-benchmark/pull/50

P.S.: Perhaps you want to add your database to our benchmarks repo?

Do we have any idea why lucene vector search underperforms? As of lucene 9.1 (and elastic 8.4), it runs the same sort of filtered/categorical HNSW that qdrant runs (https://lucene.apache.org/core/9_1_0/core/org/apache/lucene/...). Qdrant's benchmarking code (https://github.com/qdrant/vector-db-benchmark/blob/9263ba/en...) does use the new filtered ann query with elastic 8.4, so it appears to be a fair benchmark. Why is lucene/elastic so much slower? Is it a rust vs. java thing? Or some memory management issues?

There is also an open-source framework for benchmarking https://github.com/qdrant/vector-db-benchmark

i started doing this at http://vectorsearch.dev but it could use some love.

this isn't keyword search it's vector search. learn more here: https://vectorsearch.dev/

series of tutorials and comparisons that aim to teach a foundations about vector search: https://vectorsearch.dev/

sounds like how vector search engines work, you convert a corpus into embeddings then search and the results are ordered by relevance score. i’m building a series of tutorials here: http://vectorsearch.dev

working on a comparison table: https://github.com/esteininger/vector-search/tree/master/fou...