What is Embedding?

An embedding is a list of numbers that represents the meaning of a piece of text, so similar texts end up close together — the basis of semantic search and RAG.

An embedding model turns text into a vector (hundreds or thousands of numbers). Texts about the same idea land near each other in that space even when they share no words, which lets you search by meaning: "cancel my plan" finds "how do I end my subscription".

Embeddings power retrieval for RAG, duplicate detection, clustering and recommendations. They don't generate text — a separate language model does that after retrieval.