My binary vector search is better than your FP32 vectors

My binary vector search is better than your FP32 vectors

I'm still trying to get my head around this, but here's what I understand so far.

Embedding vectors as calculated by models such as OpenAI text-embedding-3-small are arrays of floating point values, which look something like this:

[0.0051681744, 0.017187592, -0.018685209, -0.01855924, -0.04725188...] - 1356 elements long

Different embedding models have different lengths, but they tend to be hundreds up to low thousands of numbers. If each float is 32 bits …

arrays binary embedding embeddings floating point head look openai search small something text text-embedding-3 values vector vectors vector search