Gergely Szilvasy

Given that the solver is trying to resolve faiss-cpu dependencies while installing faiss-gpu, I presume faiss-cpu was installed in the env.

I suggest forcing pytorch-cuda and cudatoolkit to 11.8: `conda install faiss-gpu=1.7.4 mkl=2021 pytorch pytorch-cuda=11.8 cudatoolkit=11.8 numpy -c pytorch -c nvidia` Let me know if this works.

Faiss does not L2 normalize either the query, not the database vectors. Have you done this normalization on the vectors yourself before adding them to the index and querying?

How about not constructing an IndexFlat, but use `faiss.knn()` directly on the memory mapped data? https://github.com/facebookresearch/faiss/blob/main/faiss/python/extra_wrappers.py#L333

M1 is supported in conda since v1.7.4

https://github.com/facebookresearch/faiss/wiki/Guidelines-to-choose-an-index

libfaiss_gpu.a is supposed to be linked into libfaiss via the WHOLE_ARCHIVE directive in its entirety. Maybe this doesn't work when libfaiss is compiled as a static lib. > In FAISS...