Milvus 3.0 发布：湖原生架构与更强检索引擎
🎉 We're so excited to announce that Milvus 3.0 is available today! This is the biggest architectura...
Milvus 3.0 今天上线了，不用再为向量数据库单独备份数据，直接查湖里的文件，检索性能还更强。
Milvus 3.0 今日发布，是该项目历史上最大的架构更新。新版本引入湖原生基础设施，支持直接索引 Parquet、Lance、Iceberg 等格式的数据，无需 ETL。新的 Loon 存储引擎将 ANN 搜索后的点读 I/O 从 9.4 MB 降至 0.07 MB。检索引擎新增服务端 ORDER BY、聚合和分面搜索，支持 StructArray 以原生容纳 ColBERT 和 ColPali 模型。SINDI + BM25 压缩使稀疏索引缩小约 3 倍，QPS 提升约 10 倍。
🎉 We're so excited to announce that Milvus 3.0 is available today! This is the biggest architectura...
🎉 We're so excited to announce that Milvus 3.0 is available today! This is the biggest architectural release in the project's history, with two big shifts. 🌊 𝗦𝗛𝗜𝗙𝗧 𝟭 — 𝗟𝗮𝗸𝗲-𝗻𝗮𝘁𝗶𝘃𝗲 𝗶𝗻𝗳𝗿𝗮𝘀𝘁𝗿𝘂𝗰𝘁𝘂𝗿𝗲 The problem: your vectors already live in the lake, but your search engine needs its own copy. So you build an ETL pipeline — and then maintain it forever. With Milvus 3.0, you get: 1. External Collections → index and serve data that stays in Parquet, Lance, Iceberg, or Vortex. No second copy, no sync job. 2. Loon (Storage v3) → a columnar engine built for the point reads that follow an ANN search. I/O per read went from 9.4 MB to 0.07 MB in our benchmarks. 3. Snapshots + Spark + live schema changes → dedupe, re-embed, and evaluate your data while the live collection keeps serving. ⚡ 𝗦𝗛𝗜𝗙𝗧 𝟮 — 𝗔 𝗺𝗼𝗿𝗲 𝗽𝗼𝘄𝗲𝗿𝗳𝘂𝗹 𝗿𝗲𝘁𝗿𝗶𝗲𝘃𝗮𝗹 𝗲𝗻𝗴𝗶𝗻𝗲 The problem: too much of your retrieval pipeline lives in application code. You over-fetch candidates, then sort, count, and reassemble them yourself. With Milvus 3.0, you get: 1. Server-side ORDER BY, aggregation, and faceted search → sort by price or freshness, count by category, all inside the engine. 2. StructArray → one row per document, many vectors inside. ColBERT and ColPali finally have a native home. 3. SINDI + BM25 compression → a sparse index ~3× smaller, with up to ~10× the QPS on learned sparse embeddings. Put together: one system, one copy of your data, and a lot less glue code. That matters most if you're building: 🤖 AI agents whose data changes constantly 🔍 Multimodal retrieval with late-interaction models 🔒 Governed systems where the data has to stay where it is 📚 RAG and knowledge bases over long documents 🛍️ Search that mixes relevance with price, rating, or inventory 🙏 Huge thanks to the Milvus community — you filed the issues, tested the release candidates, and told us what was actually painful. This relea github.com/milvus-io/milv… wipe through for the milvus.io/blog/announcin… r #Milvus t #VectorDatabase U #AIInfrastructure c #RAG o #OpenSource t.co/hq4qqZASuX #Milvus #VectorDatabase #AIInfrastructure #RAG #OpenSource 💬 1 🔄 0 ❤️ 1 👀 48 📊 1 ⚡
