Optimal Indexing Configuration for 10 Million with 8400 Dimensions #40483
Unanswered
sctrueew
asked this question in
Q&A and General discussion
Replies: 1 comment
-
If you run with purely memory mode, I would guess 300GB+ memory is required. For your current hardware, if recall is not a strict concern, I would recommend to run with IVFSQ8 or HNSWSQ8. We don't support windows so a docker is required. Unfortunatelhy you don't have SSDs, thus diskANN will not be an option. Running on Zilliz cloud capacity instance is another recommendation I have. |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
Hi, I hope you're doing well.
I have approximately 10 million data points with a dimension of 8400. I would like to know what configuration I should set for indexing them.
Server specifications:
OS: Windows Server
RAM: 64 GB
Storage: 10 TB HDD
Thank you in advance!
Beta Was this translation helpful? Give feedback.
All reactions