Milvus 2.2.9: A Highly Anticipated Release with Optimal User Experience
Jun 6, 2023Owen Jiao, Fendy Feng
Summary
Introduced support for JSON data types, allowing storage and querying of JSON alongside vector metadata. Enabled dynamic schema functionality via SDK, automatically filling dynamic fields into a hidden JSON field. Implemented Partition Key feature, allowing user-specific columns as primary keys for partitioning, removing partition limits and the need for explicit partition load/release APIs. Added support for Alibaba Cloud OSS.
More from the AI Data Storage Engine trail
- Milvus Snapshots: Point-in-Time Collection Views Without Copying Data
- Announcing Milvus 3.0: Lake-Native Vector Search and a More Powerful Retrieval Engine
- How to Recover Milvus Data After etcd Corruption Without a Backup
- Open Tag: An Open-Source Claude Tag for Claude Code and Codex
- How Force Merge Compaction Nearly Doubled Milvus Search QPS