Blogs›Milvus›Partition Management for Vector Operations
Milvus 1.1.0 introduces the ability to specify partitions for `get_entity_by_id()` and `delete_entity_by_id()` operations, significantly improving performance for large datasets by allowing targeted data retrieval and deletion. A new `release_collection()` method was added to manually unload collections from memory, enhancing runtime memory management. Performance improvements were also made to `get_entity_by_id()`, Hnswlib index building, and IVF index training.
5/20/2021
Introduced partition specification for `get_entity_by_id()` and `delete_entity_by_id()` methods, enhancing performance by allowing operations to target specific partitions. Added `release_collection()` method for manual unloading of collections from memory. Improved `get_entity_by_id()` performance, upgraded Hnswlib to v0.5.0, and enhanced IVF index training performance.