←back to thread

Meilisearch – search engine API bringing AI-powered hybrid search

(github.com)
151 points modinfo | 2 comments | 14 Apr 25 12:46 UTC | HN request time: 0s | source
Show context
softwaredoug ◴[14 Apr 25 22:11 UTC] No.43686848[source]▶
One thing to _always_ dig into is how your hybrid search solution filters the vector search index. This is not at all standardized, often overlooked, but when you want "top X most similar to query by embedding, but also in Y category/match Z search terms" its the core operation your hybrid search is doing

Here's a rollup of algorithms... https://bsky.app/profile/softwaredoug.bsky.social/post/3lmrm...

replies(1): >>43689586 #
1. Kerollmops ◴[15 Apr 25 06:24 UTC] No.43689586[source]▶
Meilisearch is faster when you reduce the dataset by filtering it. I wrote an article on this subject [1].

[1]: https://blog.kerollmops.com/meilisearch-vs-qdrant-tradeoffs-...

replies(1): >>43690473 #
2. andre-z ◴[15 Apr 25 08:51 UTC] No.43690473[source]▶
"Slowness can arise from a misconfigured index or if filterable attributes aren't listed." ;)