AI

Embedding

A list of numbers that captures the meaning of text (or an image) so machines can compare it.

An embedding turns a piece of content into a vector — a long array of numbers — where similar meanings land close together in mathematical space. 'Dog' and 'puppy' produce nearby vectors; 'dog' and 'tax law' land far apart. This is what lets you search by meaning instead of exact keywords, and it's the foundation of semantic search and RAG. You generate embeddings with an embedding model, then store and compare them.