SimFG
SimFG
I think this is not a very good idea, because in this caching process, the scalar data will generally be very large, that is, the data size of the questions...
For this case, you can try using sqlite.
@shanghaikid Is this so strange? I'll verify it later.
Some minor issues were found for this problem: 1. If the password is composed entirely of numbers, it needs to be wrapped in double quotes, mainly to allow YAML to...
@juanandreas I checked and there should be an error in usage. You can refer to the following example: ``` import time import numpy as np from pymilvus import ( MilvusClient,...
Which package is milvus used here? Is it pymilvus.utility? in `milvus.do_bulk_insert`
@tvvignesh i will develop this feature asap
@tvvignesh got it. I'm very sorry that I haven't finished this feature for so long, because I'm currently developing other features of milvus and encountered some tricky problems.
This is a great research, and I appreciate the interest in the gptcache project. Looking forward to the final paper.
It seems that you did not experiment with changing x,y to y,x. It seems that you should use `print (get_score(a, b)), print (get_score(b, a))` for comparison.