Can these databases do fast averaging of nearest neighbors for regression or do you have to retrieve the neighbors and manually compute a mean across them?
They are primarily for storing wmbeddings for similarity search - not general purpose nearest neighbor algorithms.
You'll have to manually compute the mean after retrieving the nearest neighbors. Automatic fast averaging could be an interesting use case for clustering or using a vector database to generate training though.
Interesting. What systems or algorithms are you referring to by “clustering”?