Retrieval After RAG: Hybrid Search, Agents, and Database Design — Simon Hørup Eskildsen of Turbopuffer

**Simon Hørup Eskildsen** (0:00)
I don't think I've said this publicly before, but I just called Lockie and was like, Lockey, if this doesn't have PMF by the end of the year, we'll just return all the money to you. But it's just like, I don't really, Justine and I don't want to work on this unless it's really working. So we want to give it the best shot this year, and we're really going to go for it. We're going to hire a bunch of people, and we're just going to be honest with everyone. When I don't know how to play a game, I just play with open cards. Lockie was the only person that didn't freak out. He was like, I've never heard anyone say that before.

**Alessio** (0:31)
Hey everyone, welcome to the Latent Space Podcast. This is Alessio, Pando Colonelat, and I'm joined by Swix, editor of Latent Space.

**Swyx** (0:36)
Hello, we're still recording in the Colonel Studio for the first time. Very excited. And today we're joined by Simon Eskildsen of Turbo Farfer. Welcome.

**Simon Hørup Eskildsen** (0:46)
Thank you so much for having me.

**Swyx** (0:48)
Turbo Farfer has really gone on a huge tear, and I do have to mention that you're not my newest member, you're the Danish Aarhus Mafia, where there's a lot of legendary programmers have come out of it, like Bjorn Stjostrup, Rasmus Lerdov, Anders Halsberg, and the V8 team and Google Maps team. You're mostly Canadian now. But isn't that interesting? There's so much strong Danish presence.

**Simon Hørup Eskildsen** (1:12)
Yeah, I was writing a post not that long ago about the influences. So I grew up in Denmark, right? I left when I was 18 to go to Canada to work at Shopify.
And so I would still say that I feel more Danish than Canadian. This is also the weird accent. I can't say TH because this is like, I don't, you know, my wife is also Canadian. And I think, I think like one of the things in Denmark is just like, there's just such a ruthless pragmatism. And there's also a big focus on just aesthetics. Like they're like very, people really care about like where, what things look like. And Canada has a lot of attributes, US has a lot of attributes. But I think there's been lots of great things to carry. I don't know what's in the water in Augusto. And I don't know that I could be considered part of the Augusto Mafia quite yet, compared to the phenomenal individuals we just mentioned. Barra OV is also Danish Canadian. Yeah, I don't know where he lives now, but he's the PHP.

**Swyx** (2:10)
Yeah, and obviously, Toby German will move to Canada as well. There's this import that is an interesting talent move.

**Alessio** (2:19)
I think I would love to get from you the definition of Turbopuffer because I think you could be a VectorDB, which is maybe a bad word now in some circles. You could be a search engine. It's like, let's just start there and then we'll maybe run through the history of how you got to this point.

**Simon Hørup Eskildsen** (2:33)
For sure. Yeah, so Turbopuffer is, at this point in time, a search engine, right? We do full-text search and we do vector search, and that's really what we're specialized in. If you're trying to do much more than that, then this might not be the right place yet, but Turbopuffer is all about search. The other way that I think about it is that we can take all of the world's knowledge, all of the exabytes and exabytes of data that there is, and we can use those tokens to train a model. But we can't compress all of that into a few terabytes of weights, right? We can compress into a few terabytes of weights, how to reason with the world, how to make sense of the knowledge. But we have to somehow connect it to something external that actually holds that in full fidelity and truth. That's the thing that we intend to become, right? That's like a very holier-than-now kind of phrasing, right? But being the search engine for unstructured data is the focus of Turbopuffer at this point in time.

**Alessio** (3:27)
Let's break down. People may say, well, didn't Elasticsearch already do this? Then some other people may say, is this search on my data? Is this closer to Ragt and to XR, like a public search thing?
How do you segment the different types of search?

**Simon Hørup Eskildsen** (3:43)
The way that I generally think about this is, there's a lot of database companies. I think if you want to build a really big database company, you need a couple of ingredients to be in the air, which only happens roughly every 15 years. You need a new workload. You basically need the ambition that every single company on Earth is going to have data in your database multiple times. You look at a company like Oracle.