🚀 𝗖𝗼̂́𝗰 𝗖𝗼̂́𝗰 𝗽𝗼𝘄𝗲𝗿𝘀 𝗩𝗶𝗲𝘁𝗻𝗮𝗺’𝘀 𝗻𝗮𝘁𝗶𝗼𝗻𝗮𝗹-𝘀𝗰𝗮𝗹𝗲 𝗔𝗜 𝘀𝗲𝗮𝗿𝗰𝗵 ...

TL;DR · AI 摘要
Cốc Cốc采用Milvus实现越南国家级AI搜索,处理6亿向量,延迟低至19.8ms。
核心要点
- Milvus支持6亿向量生产,计划扩展至15亿规模
- 语义搜索延迟达19.8ms,混合搜索32.1ms
- 在线召回率99%-100%,离线召回率100%
结构提纲
按章节快速跳转。
思维导图
用一张图看清主题之间的关系。
查看大纲文本(无障碍 / 无 JS 友好)
- Milvus助力越南AI搜索
- 技术挑战
- FAISS/USearch局限性
- 解决方案
- Milvus向量数据库
- 性能指标
- 6亿向量处理能力
- 19.8ms语义搜索延迟
金句 / Highlights
值得收藏与分享的关键句。
FAISS和USearch无法分布式处理数亿级向量
Milvus实现6亿向量生产,计划扩展至15亿
语义搜索延迟达19.8ms,混合搜索32.1ms
Milvus on X: "🚀 𝗖𝗼̂́𝗰 𝗖𝗼̂́𝗰 𝗽𝗼𝘄𝗲𝗿𝘀 𝗩𝗶𝗲𝘁𝗻𝗮𝗺’𝘀 𝗻𝗮𝘁𝗶𝗼𝗻𝗮𝗹-𝘀𝗰𝗮𝗹𝗲 𝗔𝗜 𝘀𝗲𝗮𝗿𝗰𝗵 𝘄𝗶𝘁𝗵 𝗠𝗶𝗹𝘃𝘂𝘀 @coccoc_official is Vietnam’s leading homegrown search engine and browser. More than 30 million people use it, generating over 600 million searches each month." / X
Milvus
@milvusio
🚀 𝗖𝗼̂́𝗰 𝗖𝗼̂́𝗰 𝗽𝗼𝘄𝗲𝗿𝘀 𝗩𝗶𝗲𝘁𝗻𝗮𝗺’𝘀 𝗻𝗮𝘁𝗶𝗼𝗻𝗮𝗹-𝘀𝗰𝗮𝗹𝗲 𝗔𝗜 𝘀𝗲𝗮𝗿𝗰𝗵 𝘄𝗶𝘁𝗵 𝗠𝗶𝗹𝘃𝘂𝘀
@
coccoc_official
is Vietnam’s leading homegrown search engine and browser. More than 30 million people use it, generating over 600 million searches each month. As Cốc Cốc expanded semantic retrieval across search, advertising, recommendations, targeting, and internal RAG, its existing vector libraries reached their limits. FAISS and USearch worked for smaller projects but could not distribute hundreds of millions of vectors across machines or support continuous production updates. After validating 𝗠𝗶𝗹𝘃𝘂𝘀 with roughly 30 million query embeddings, Cốc Cốc adopted it as a self-hosted retrieval foundation for five production systems. 🚀 𝗪𝗶𝘁𝗵 𝗠𝗶𝗹𝘃𝘂𝘀, 𝗖𝗼̂́𝗰 𝗖𝗼̂́𝗰 𝗻𝗼𝘄 𝗮𝗰𝗵𝗶𝗲𝘃𝗲𝘀: 🔷 𝟳𝟬𝟬 𝗺𝗶𝗹𝗹𝗶𝗼𝗻 𝘃𝗲𝗰𝘁𝗼𝗿𝘀 in production, with capacity planned for approximately 1.5 billion 🔷 𝟭𝟵.𝟴 𝗺𝘀 𝗣𝟵𝟬 semantic-search latency at peak traffic 🔷 𝟯𝟮.𝟭 𝗺𝘀 𝗣𝟵𝟬 hybrid-search latency at peak traffic 🔷 𝟵𝟵%–𝟭𝟬𝟬% 𝗼𝗻𝗹𝗶𝗻𝗲 𝗿𝗲𝗰𝗮𝗹𝗹 with HNSW and 100% offline recall with FLAT 🔗 Full story:
zilliz.com/customers/cocc…
👉 Try Milvus now:
milvus.io
#BuiltWithMilvus
#VectorDatabase
#AISearch
--- 👉 Follow Milvus, created by Zilliz, for everything related to unstructured data
3:50 PM · Aug 26, 2026
197
Views
1