Closed generall closed 1 year ago
Awesome. Thanks a lot for the contribution!
I think this is a bit too late for me to include in the benchmarks I'm publishing in #399 – I have to draw a line somewhere. But I'm planning to re-run everything in just a few weeks anyway. I don't intend to promote the results much until then.
Hi @erikbern, is there any ETA for the next run?
Hi!
Sorry for late updates, just noticed that qdrant is included into the latest run. In general I would say that comparing client-server vector DBs with pure embedded implementations of algorithms might be misleading, but since other DBs are participating, we kinda have to as well.
In this PR I tried to do changes with the following goals:
Hope you could re-run the latest iteration with those changes included.
Expected RPS increase with those changes: 2-3x