|
|
|
|
|
|
by janalsncm
618 days ago
|
|
|
You technically could use other distance metrics but embeddings are generated from models trained to maximize similarity under specific metrics. Usually that is cosine similarity. A trivial example of how it matters is the vectors (0,1) and (0,2) which have cosine distance 0 but euclidean distance 1. Finally, it’s notable that the author is testing via JavaScript. I am not sure if you’ll be able to take advantage of vectorized (SIMD/BLAS) optimizations. |
|
|