Brute-force search over millions of vectors takes seconds per query. I tried IndexIVFFlat and got an error about istrained.
Loading page content…

Find answers to your programming questions.
Brute-force search over millions of vectors takes seconds per query. I tried IndexIVFFlat and got an error about istrained.
index.search returns some IDs of -1, and I don't know how to get from the returned numbers back to my original documents.
FAISS only has IndexFlatL2 and IndexFlatIP. My model's docs say to use cosine similarity. Which index should I use?
I saved a FAISS index with savelocal and loaded it with FAISS.loadlocal. Now similaritysearch fails with an AssertionError (or I get a ValueError about allowdan
My embeddings come from NumPy or PyTorch, and FAISS rejects them with a cryptic TypeError.
I built a FAISS index and it worked, but now index.search(query, k) (or index.add(...)) fails with an AssertionError pointing at assert d == self.d.