Bergum: In-database ML like PostgresML is the wrong architectural direction
Jo Kristian Bergum · The Rise and Fall of the Vector DB category: Jo Kristian Bergum (ex-Chief Scientist, Vespa) · Apr 19, 2025 · at 17:24
Former Vespa Chief Scientist Jo Kristian Bergum rejects the trend of running ML model inference and embedding pipelines directly inside transactional SQL databases.
0:00 / 0:41exact quote · 41.7s
▶ Watch the full episode on YouTube → 720p mp4 · rendered on demand · StarZero watermark
“No, I'm not. I'm sorry. I, I'm not. I think this is, yeah, we also seen other players that tries to, you know, move a lot of the logic into the database, agentic embedding inference and whatnot. I think if the right direction is to Keep infrastructure a little bit separate from that because they're like different scaling properties. I think people can stitch those two things together instead of trying to do everything with one single platform. So no, I'm not bullish on that because I don't believe in the developer experience of writing like these huge SQL statements for transforming data from this and then embedding it and then writing it back and expressing this in the database.”
quote is from the automated transcript, cleaned for reading: filler sounds and stutters are removed, nothing is rephrased. names can be misheard (the analysis reads context, assessments check outside sources). how →
More from Jo Kristian Bergum
Bergum: The standalone vector database infrastructure category is dying
“I'm not saying that the companies are dying, right? I'm just saying that the separate infrastructure category is dying, right? Because you have vector search capabilities in almost any DB technology nowadays, right?”
Bergum: Pinecone will not endure like MongoDB because it is too narrow
“So there's always like this convergence, but MongoDB kind of, it sticks, but I don't think that for Pinecoin that was originally leading that movement, it won't like stick in the same way.
It's too narrow.
It's too, too narrow.”
Bergum: pgvector is outpacing some standalone vector DBs in search capabilities
“So actually, what you can see, PJ Vector is doing more in the capabilities of vector search than some of the real vector database players, right?”
Bergum: Building knowledge graphs is the bottleneck in Graph RAG, not databases
“The core issue issue is actually to build the knowledge graph, right? The entities, the relationships. So if you say graph, graph, You know, databases or graph rag is going to kill vector rag and all that discussion. I think the first issue is to actually buil…”
Bergum: Search, not vector storage, is the natural abstraction for RAG
“I think that's a more natural abstraction for connecting AI with knowledge and all the arguments for doing rag. I think the natural concept there is search.”
Bergum: Standalone embedding API startups face a difficult business model
“I think it's a difficult business model to be in, like, because you have to have an API based service and you have to do batching and you have to make up for the compute and then, you know, are people willing to pay for it? And I think maybe that's why Voyage …”