Changelog Master Feed cover image

Data augmentation with LlamaIndex (Practical AI #224)

Changelog Master Feed

00:00

The Different Types of Embeddings

An embedding is just a vector of numbers, usually like floating point numbers. And so it's a way of like condensing a piece of text into some vector of numbers that has some mathematical properties where you can measure similarity between different pieces of content. So for instance, if you look at the biography of a singer, it's going to be pretty close to biography of another singer versus if it's about, I don't know, like the American Revolution or something like that,. Lama index is sort of not a a vector store. But we're really trying to build this like broader set of like abstractions and tools through our indices, our query interfaces, plus other abstractions that we

Transcript
Play full episode

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!
App store bannerPlay store banner
Get the app