jargon

Applied AI·Embeddings and retrieval

you rank results by the angle between two vectors, which is a dot product over two magnitudes and one line of code.

Cosine similarity

Draft summary, pending review

The standard similarity measure between two embeddings: the cosine of the angle between them, ranging from -1 to 1, higher meaning more similar. One line of code: dot product divided by the product of magnitudes.

Commonly confused with