Hacker News Reader

I guess that at a big enough scale it starts making sense. But not sure what “big” really is.

Pgvector seems to perform very poorly compared to Qdrant: https://nirantk.com/writing/pgvector-vs-qdrant/

I absolutely believe that at the moment - Qdrant is clearly a fantastic piece of technology.

But if I was using Qdrant myself I'd treat it like ElasticSearch - I'd denormalize some of my data into it, but I'd still do most of my work in the relational database and treat Qdrant as effectively an external index for my stuff.

Maybe I'm getting hung up on the world "database" here as indicating that you use that instead of an RDBMS, when actually everyone selling a vector database expects you to use it as effectively an external indexing mechanism instead.

I personally read it as “vector cache”, because you can use it to, eg, store a phrasing to repeat later.

i wish nirantk would add an addendum noting the pgvector issue was fixed or people like me will have to put up the counter response every single time https://youtu.be/MDxEXKkxf2Q?si=eUhNtghbiLRJ7yHB

Very interesting. I didn’t know about it. Thanks!

Reply on news.ycombinator.com