What are embeddings?
Also called: embedding, vector embeddings
Embeddings are lists of numbers that represent the meaning of text, images or other data, so that similar things get similar numbers. They let computers measure how close two pieces of text are in meaning, which powers semantic search, recommendations and RAG.
How do embeddings work?
An embedding model turns each piece of text into a vector, for example 768 numbers. Texts about the same idea land near each other in that space, even if they use different words.
Why do embeddings matter?
Embeddings are how AI apps find relevant information by meaning, not just matching keywords.
An example
Example: A search for 'refund for a damaged parcel' finds a help article titled 'Returns for broken items' because their embeddings are close.
Related terms
Learn it properly
Embeddings are covered in AI Builder, with short lessons, practice questions and instant feedback.