Are vectors generated by text-embedding-3-small always the same for the same text input?

[_j]

The embeddings models should not be used to verify identical contents or avoid duplication - you can use a hash algorithm for that for free.

Splitting text into chunks versus reducing the text

Determinism means you always get the same output from the same input. The way you expect computer code to work, basically. The current embeddings models are not deterministic. They do not produce the same output for the same input. I performed 10 embeddings runs, on 3-small model, of the same 600 tokens of text, and got three unique results with tensor comparisons: np.unique(em_ndarray, axis=0) array([[ 0.01526077, 0.01427238, 0.06942467, ..., 0.00670789, -0.01064828, -0.0110238…

Results are close enough between successive runs that it would be effective to almost always return the same top results, and embeddings quality is kind of subjective anyway..