[gfourfour]

Ah didn’t realize it was every language. Yes I’m using a light weight open model - but also my use case doesn’t require anything super heavy weight. Wikipedia articles are very feature-dense and differentiable from one another. It doesn’t require a massive feature vector to create meaningful embeddings.

[tjake]

it's 35M 1024 vectors Plus the text

[gfourfour]

Still, $5000 is kind of insane. That makes no sense to me.