Vector Search, the AI Stack and more with Bob van Luijt

Open||Source||Data

This episode features an interview with Bob van Luijt, CEO and Co-Founder of SeMI Technologies and co-creator of Weaviate, an open source vector search engine.

At just 15 years of age, Bob started his own software company in the Netherlands. He went on to study music at ArtEZ University of the Arts and Berklee College of Music, and completed the Harvard Business School Program of Management Excellence. Bob is also a TedX speaker, discussing the relationship between software and language.

In this episode, Sam sits down with Bob to break down vector search, the AI-first ecosystem, and how music and software relate to one another.

-------------------

“I dare to argue that from the two big waves in database technology that we've seen, so first, in the seventies and eighties with SQL. And then the whole NoSQL wave that we have seen and the big winners that are in there, I dare to argue that we see a third wave coming up. And the third wave, I simply call it AI-first. And what I mean with that is that these models play an important role. So we do it from the perspective of the models first. And in that new segment, you see four niches. So the first niche that we see are what I like to call the embedding providers. The Hugging Faces of this world, the OpenAIs of this world, etc. Those who bring us the embeddings that we need to do the vectorization. Then secondly, we have so-called neural search frameworks. So we see frameworks like Haystack and Jina. Then third, we have the feature stores. So the feature stores take care of storing large chunks of features that we later can use to do vectorization on those kinds of things.And then we have the search engines. And Weaviate is an example of such a search engine that takes care of searching through data on a large scale that is vectorized.It might be a bold statement, but I really believe that we see this third wave of database technology happening.” – Bob van Luijt

-------------------

Episode Timestamps:

(01:45): How Bob defines open source data

(04:09): What is a vector database and why do we need them?

(07:55): How data is different before and after vectorization

(13:58): Orders of magnitude faster or personal

(16:09): How music and software relate to each other for Bob

(19:33): Bob’s inspiration behind Weaviate

(25:02): The AI-first ecosystem

(27:38): The distinction between vector search engines, feature stores, neural search frameworks, and embedding

(32:28): Bob’s advice for folks on the OSS startup journey

-------------------

Links:

LinkedIn - Connect with Bob

Twitter - Follow Bob

Twitter - Follow Weaviate

Weaviate

SeMI Technologies

Bob’s TedX Talk

Bob's Forbes Article on the AI-First Database Ecosystem