Glossary
What are embeddings?
A way of turning text into a list of numbers (a vector) that captures its meaning, so text with similar meaning ends up close together. Embeddings are what let retrieval search by meaning instead of exact words.
An embedding turns a word (or a whole sentence, or an image) into a list of numbers — a position in space — chosen so that things with similar meaning land near each other. “King” sits close to “queen”; “cat” close to “dog”; the two groups far apart.
Words placed by meaning (2D projection)
Similar meanings cluster. The real space has hundreds of dimensions — this is a flattened peek at two of them.
Because meaning becomes distance, a computer can finally ask “which of these is most like that?” by finding the nearest points — the engine behind a vector database and RAG.
Related terms
Appears in these lessons
See the space
Watch words become coordinates
RAG & Search turns text into vectors and finds nearest neighbors live — free to try in the app.