How AI Search Works
Also: embeddings, vector embedding
A vector embedding is a numerical representation of text (or images, audio) that captures its meaning as a point in high-dimensional space. Pieces of content with similar meaning sit close together, which lets AI systems retrieve relevant passages by similarity. Embeddings power semantic search and RAG.
Updated
Embeddings are why an engine can tell that "lower cart abandonment" and "fewer checkout drop-offs" are about the same thing. Retrieval ranks candidates by how close their embeddings are to the query.
For content, the implication is to make each passage clearly about one idea, so its embedding is distinct and easy to match to the right question.
Go deeper
How Does AI Search Work?