Skip to content

Saturday, October 10, 2026

Live
Loading the latest AI news…

Glossary · How models work

Embedding

Also called Vector embedding

An embedding is a list of numbers that represents the meaning of a word, sentence, image or document, so that similar things get similar numbers. It lets software find related content by meaning rather than by exact words.

In one line, for a 12-year-old

An embedding is a secret number-address for an idea, so ideas that mean the same thing live close together.

An example

Searching a help centre for "can't log in" finds the article titled "Password reset", because their embeddings are close.

Why it matters to people

Embeddings make search and recommendations smarter, but they can also encode stereotypes found in the text they were built from.