What is an embedding?

Published 14 November 2026. Updated 14 November 2026.

Embedding: A list of numbers that represents the meaning of a piece of text, so that texts with similar meanings get numbers that sit close together.

OpenAI's documentation describes an embedding as a vector of numbers where a smaller distance means two texts are more related, and lists search, clustering and recommendations as uses. Retrieval systems compare the embedding of a question with the embeddings of stored passages to find the closest matches.

That is why a page can be retrieved for a query that shares none of its words. Fan-out queries vs keywords looks at what that means for keyword research.

Read next

• What is retrieval-augmented generation (RAG)?
• Fan-out queries vs keywords: what is the difference?
• What is query expansion?

Sources

• Vector embeddings, OpenAI API documentation
• Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks (Lewis et al., arXiv, 2020)