On: Do we think about vector storage wrong?

[osigurdson]

An OpenAI embeddings vector is 1536 4 byte floats. 1 TiB is roughly 174K such embeddings vectors.

[brigadier132 → osigurdson]

Your math is wrong. 100k 32 bit vectors is 600mb

I think your point is right though. Searching through these is requires an index of some sort at any reasonable scale (not google scale).

[osigurdson → brigadier132]

Hmmm, yeah, I used 2^30 instead of 2^40. Should not comment before caffeinating.