Skip to content
Large language models

Embedding

LLMsIntermediateAlso called embeddings, vector embedding, embedding vector

Definition

A list of numbers that represents the meaning of a piece of data, so that similar things end up with similar numbers.

In plain English

An embedding turns words, sentences, images, or other data into coordinates in a space with hundreds of dimensions. Things with similar meaning land near each other.

That makes it possible to search by meaning rather than by exact words, which is how RAG systems find relevant passages.

Example

The sentences “How do I reset my password?” and “I forgot my login” get embeddings that sit close together, even though they share almost no words.

Sources

Draft, not yet reviewed by a person · Updated Nov 2026