←back to thread

276 points Fendy | 9 comments | | HN request time: 0.204s | source | bottom
Show context
Fendy ◴[] No.45169625[source]
what do you think?
replies(1): >>45169755 #
1. sharemywin ◴[] No.45169755[source]
it's annoying to me that there's not a doc store with vectors. seems like the vector dbs just store the vectors I think.
replies(6): >>45170029 #>>45170099 #>>45170435 #>>45170622 #>>45170624 #>>45171855 #
2. jeffchuber ◴[] No.45170029[source]
chroma stores both
replies(1): >>45170076 #
3. nkozyra ◴[] No.45170076[source]
As does Azure's AI search.
4. intalentive ◴[] No.45170099[source]
I just use sqlite
5. storus ◴[] No.45170435[source]
Pinecone allows 40k of metadata with each vector which is often enough.
6. whakim ◴[] No.45170622[source]
Elasticsearch and Vespa both fit the bill for this, if your scale grows beyond the purpose-built vector stores.
7. simonw ◴[] No.45170624[source]
Elasticsearch and MongoDB Atlas and PostgreSQL and SQLite all have vector indexes these days.
replies(1): >>45171055 #
8. KaoruAoiShiho ◴[] No.45171055[source]
> MongoDB Atlas

It took a while but eventually opensource dies.

9. CuriouslyC ◴[] No.45171855[source]
My search service Lens returns exact spans from search, while having the best performance both in terms of latency and precision/recall within a budget. I'm just working on release cleanup and final benchmark validation so hopefully I can get it in your hands soon.