Please check
https://medium.com/@milvusio/managing-data-in-massive-scale-...
It explains how Milvus managing vectors.
It explains how Milvus managing vectors.
Why are you not quantizing the vectors when you insert them? Bolt [1] and Quicker-ADC [2] make 10-100x compression basically free for approximate search (and also get you ~100x compression roughly 10x faster querying within a partition....)
[1] https://github.com/dblalock/bolt
[2] https://github.com/technicolor-research/faiss-quickeradc
Based on our users experience, SQ8 is the most balanced one at this moment. SQ8 provides 8x compression, higher accuracy and better performance.