If you need to store vector, surely the easiest solution is to run `CREATE EXTENSION vector`. When, or if, you need more, then look at alternatives, but I'm sure most people will have a much easier time just adding it to their existing database.

Pgvector is definitely the easiest way to get started. I did not really get the problem the article was trying to sell.

Setting up an ingestion pipeline to your existing db, vs ingesting into yet another db seems to not solve a problem I have.

If there was one thing I wish pgvector was better at, it would be to allow composite indexes (ie find vector where category). But it's a minor point.

I was genuinely surprised just how easy it was to get a fully working RAG set up with Postgres. It was a few hours over a weekend to get something "working" and then probably a bit less time a following weekend to have a nicer database structure and rebuild it learning from the mistakes during the first attempt. The harder part comes next, because that involves multiple tables of user provided data, multi tenancy with a shared core vector schema, and all the actual business logic, so I've put it all on hold for a real breakdown now, but I wouldn't expect it to be much of a problem with what I've found so far with pgvector, and Postgres in general.

the article was aimed more at teams that don't have an existing postgres setup and are evaluating standalone vector databases from scratch. if you're already running postgres with pgvector, you're in a good spot

I was asking myself the whole article “what does this mysterious semantic search api actually do?” and was a bit underwhelmed when the result came out to be - managed vector database.

When they generated this post, they set their LLM to “long and obfuscated” instead of “concise and clear.”

you're completely wrong. we also added "make no mistakes" in the end

If this were on Mad Men:

"You don't need a hamburger... you need McDonald's".

fair point on the framing. we do use vector search internally, so calling it "not a vector database" is a stretch. the argument i was trying to make is more narrow: most teams evaluating pinecone or qdrant don't need to operate the vector layer themselves. they need search results from an api call. whether that api uses vectors, BM25, or hamsters under the hood shouldn't matter to them. i could have been clearer about that

So the classic build vs buy question