You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Hello and thanks a lot for making this open-source !
I was wondering if you had considered the NMSLIB-HNSW approximate nearest neighbor algorithm for use with these embeddings, as according to (here) it is faster than Annoy ?
The text was updated successfully, but these errors were encountered:
There is also Scann that looks even faster, but I haven't tried it. I used NMSLIB-HNSW in the context of searching for neighbours in embeddings space from contrastive learning using the tensorflow-similarity lib, which is similar to this repo's use-case. Tensorflow-similarity doesn't use Scann so maybe there's a subtle blocker !
Hello and thanks a lot for making this open-source !
I was wondering if you had considered the NMSLIB-HNSW approximate nearest neighbor algorithm for use with these embeddings, as according to (here) it is faster than Annoy ?
The text was updated successfully, but these errors were encountered: