autofaiss
autofaiss copied to clipboard
try to use memory mapping instead of holding all training vectors in memory
might also be done for the index itself
would unlock training with more points and building larger indices with a lower memory
https://stackoverflow.com/a/16867494 adding a memory mapping option to read local embeddings could do it (that option would need to be propagated up to the cli, so things stay fast for high ram availability)
https://github.com/facebookresearch/faiss/issues/2047 should work probably worth a try
this could probably significantly improve the performance of indices, but makes sense to do it only after #5 in order to know the performance