Milvus 3.0把向量检索直接做到数据所在的湖上，不用来回搬数据，搞RAG和Agent的可以试试。
向量数据库Milvus 3.0正式发布，主打湖原生向量检索。新版本通过External Collections支持直接查询对象存储中的Parquet、Vortex格式数据，以及Lance、Iceberg等开放表格式。Loon Storage v3优化了S3对象存储上的点读取性能，快照与Spark DataSource V2让批处理和回填更稳定。检索引擎新增ORDER BY、聚合和分面搜索，StructArray与SINDI增强了多向量和稀疏混合检索能力。
🎉 𝗠𝗶𝗹𝘃𝘂𝘀 𝟯.𝟬 𝗶𝘀 𝗻𝗼𝘄 𝗮𝘃𝗮𝗶𝗹𝗮𝗯𝗹𝗲, 𝗮𝗻𝗱 𝗶𝘁’𝘀 𝗮 𝗺𝗮𝗷𝗼𝗿 𝘀𝘁𝗲𝗽 ...
🎉 𝗠𝗶𝗹𝘃𝘂𝘀 𝟯.𝟬 𝗶𝘀 𝗻𝗼𝘄 𝗮𝘃𝗮𝗶𝗹𝗮𝗯𝗹𝗲, 𝗮𝗻𝗱 𝗶𝘁’𝘀 𝗮 𝗺𝗮𝗷𝗼𝗿 𝘀𝘁𝗲𝗽 𝘁𝗼𝘄𝗮𝗿𝗱 𝗹𝗮𝗸𝗲-𝗻𝗮𝘁𝗶𝘃𝗲 𝘃𝗲𝗰𝘁𝗼𝗿 𝘀𝗲𝗮𝗿𝗰𝗵. 🔥 Key highlights: • External Collections let teams build retrieval directly where their data already lives: in object storage, open data formats like Parquet and Vortex, and open table formats like Lance and Iceberg. • Loon Storage v3 improves point reads for lake-native retrieval on S3-style object storage. • Snapshots, Spark DataSource V2, and live schema changes bring stable collection views into batch workflows, recovery, backfill, and schema evolution. • ORDER BY, aggregation, and faceted search move more result processing into the retrieval engine. • StructArray and SINDI strengthen multi-vector, sparse, and hybrid retrieval workloads. For builders working on RAG, agents, multimodal search, and AI data pipelines, Milvus 3.0 reduces duplicate data movement and pushes more retrieval logic into the engine itself. It is a big step toward a cleaner architecture: lake-native storage, offline data improvement, online serving, and retrieval-time processi github.com/milvus-io/milv… one open-source vector milvus.io/blog/announcin… https://t.co/3ckzkUVicH 📖 Full launch blog: https://t.co/hq4qqZASuX 💬 1 🔄 0 ❤️ 1 👀 50 📊 1 ⚡