AI agent glossary
Embeddings
Lists of numbers that represent the meaning of text, so that pieces of text with similar meanings end up close together and can be found by similarity.
An embedding model turns a sentence, paragraph, or document into a vector, a long list of numbers. The useful property is that texts with similar meaning produce vectors that are close to each other, even if they use different words.
This enables semantic search. You embed your documents once and store the vectors. When a question comes in, you embed it too and find the stored vectors nearest to it. Those are the passages most likely to be relevant.
Embeddings are the foundation of most retrieval-augmented generation systems. They are not magic, though. Keyword search often beats them for exact names, codes, and identifiers, and many good systems combine both.
A search for 'how do I get my money back' finds a help article titled 'Refund policy' even though they share no words, because their embeddings are close.
Learn more in the course
Related terms
Go from definitions to doing
Learn to use and build AI agents in 65 practical lessons.