[HeatrayEnjoyer]

What are embeddings and why are they expensive?

[Euphorbium]

Embeddings are vectors of chunks of documents, lists of 1024 (depending on a model) float numbers that represent that short snippet of text. This kind of search works by finding the most similar vectors, calculating them cost fractions of the cent, but when you need to do it billions to trillions of times, it adds up.

[orf]

You could likely calculate them all on a modern MacBook easily enough.

Searching the embeddings is a different problem, but there are lots of specialised databases that can make it efficient.

[Euphorbium]

You can, but it is a scale problem. Doing that would take an unreasonable amount of time at this scale.