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
Is your feature request related to a problem? Please describe.
I want to use SPTAG to do kNN queries on vectors from a TF-IDF vectorizer, usually sparse vectors. Can I use sparse vectors in SPTAG or rather do you have an idea of how it might perform with sparsity?
The text was updated successfully, but these errors were encountered:
Currently, we do not support sparse vectors. One quick solution is to try to compress the sparse vectors to the low-dimensional compacted vectors using some deep learning algorithms. Another solution is that you can try to modify (or add new) Dataset and DistanceUtils to do read, write and distance computation for the sparse vectors.
Is your feature request related to a problem? Please describe.
I want to use SPTAG to do kNN queries on vectors from a TF-IDF vectorizer, usually sparse vectors. Can I use sparse vectors in SPTAG or rather do you have an idea of how it might perform with sparsity?
The text was updated successfully, but these errors were encountered: