AI Glossary
Embedding
vector embedding, feature vector, embeddings
An embedding is a numerical representation of text (or an image) as a vector, where closeness between vectors signals similarity in meaning — the foundation of semantic search and RAG systems.
- Turns meaning into numbers.
- Close vectors = similar meaning.
- The basis of semantic search and RAG.
An embedding lets you compare texts by meaning rather than by exact words. The model turns a passage into a vector; two passages with similar meaning get vectors that sit close together.
That is why semantic search can find a relevant document even when it contains not a single word from the query.
Related terms
In guides
Related articles