Improve on matching speed by a NN search
amartyaamp opened this issue · comments
Amartya Chaudhuri commented
Currently our speed is bound by the dot product of query and the document vectors.
We can use NN algorithm to speed up the process. To find the closest vectors given to the query vectors.
Amartya Chaudhuri commented
We can use Annoy NN to fast up the process
Amartya Chaudhuri commented
Closed with 33fd50b