AI Glossary

Embeddings

Also called vector embeddings

What does “Embeddings” mean?

Embeddings: Lists of numbers that represent the meaning of a piece of text, image or other data, produced by an embedding model. Items with similar meanings end up with similar numbers, so software can compare meaning mathematically. They power semantic search, recommendations, clustering and RAG.

Embeddings visual guide: Lists of numbers that represent the meaning of a piece of text, image or other data, produced by an embedding model. Items with similar meanings end up with similar numbers, so software can compare meaning mathematically. They power semantic search, recommendations, clustering and RAG.
Visual guide Open full size (new tab)

What is an example of “Embeddings”?

"How do I reset my password?" and "I forgot my login" produce close embeddings even though they share few words.

Keep learning

See also

Embedding modelTermSemantic searchTermVector databaseTermRetrieval-augmented generationTerm

Same topic

ChunkingTermLatent spaceTermFew-shot promptingTermContext windowTermFrequency and presence penaltiesTerm