fraction

The passage around this formula

The conventional similarity metric is the cosine of the angle between two vectors: $\operatorname{sim}(u, v) = \frac{\langle u, v \rangle}{\lVert u \rVert \, \lVert v \rVert}$. Cosine became conventional for reasons that are mostly good. It is scale-invariant, which matters when vector norms correlate with nuisance properties like token frequency or document length. It reduces to an inner product on normalised vectors, which is cheap and which most approximate indexes support natively. And it is what several influential embedding models were explicitly trained to make meaningful: Sentence-BERT fine-tuned siamese networks precisely so that sentence embeddings could be compared with cosine similarity, cutting a pairwise-comparison workload from roughly 65 hours to…

Read this part in the article →