The Evolution of Semantic Search in a Vector Database

Sasha: It's really interesting and we're seeing a lot of as folks are moving from this sort of keyword, lexical search to semantic search in a vector database. But can you explain to folks a little bit about how a vector database works and how you might set up an embedding through, for example, like do it and a cloud vendor? Yeah. So you take a text, you take the embedding model and you get a representation of what the model learned based on what it was trained on. You get a vector representation of the information represented in this large embedding space. And it's stored in a vector databases and you get some nice algorithms to properly get the data