I ran a very quick benchmark, and https://github.com/viterin/vek appears to be ~10x faster for cosine similarity than plain Go on an AVX2 machine.
Given this from the README:
At 1536 dimensions (OpenAI default), 70% of the query process under default parameters is spent in the distance function.
It seems like using vek could have a pretty big impact.
I ran a very quick benchmark, and https://github.com/viterin/vek appears to be ~10x faster for cosine similarity than plain Go on an AVX2 machine.
Given this from the README:
It seems like using vek could have a pretty big impact.