Embedding
임베딩
The meaning of text or an image turned into a list of numbers. Similar meanings get similar numbers.
Overview
A computer cannot grasp what a word means directly. An embedding turns text into hundreds or thousands of numbers, so that text with close meanings gets close numbers. "Puppy" and "doggy" are close, while "puppy" and "tax" are far apart.
With this in place, you can find documents with similar meaning even when the words differ. This is called vector search, and it is mainly used to find related material in RAG.
An everyday example
It is like a library putting books on similar topics on nearby shelves. Even if the titles differ, a book next to the others is easy to find.
Why it matters
It is the base for features like search, recommendations and grouping similar texts. LastAI uses this kind of method too when it groups articles about the same news.
Also calledvector