Duplicate Vectors and HNSW Memory Usage

I was wondering what if anything changes when multiple documents reference the same vector (i.e. doc_1 = { vector : [1, 2]} and doc_2 = { vector : [1, 2]})? Specifically, does the memory footprint of the HNSW graph still follow the estimate model listed in the docs.

Hi @dnock, no nothing changes. Docs are independent so duplicates will exist.