音乐流媒体平台用 Milvus 构建海量向量检索系统
𝟭𝟬𝟬𝗠+ 𝘁𝗿𝗮𝗰𝗸𝘀. 𝗕𝗶𝗹𝗹𝗶𝗼𝗻𝘀 𝗼𝗳 𝘃𝗲𝗰𝘁𝗼𝗿𝘀. ~𝟭𝟬 𝗺𝘀 𝗣𝟵𝟵 𝗱𝗮𝘁𝗮𝗯𝗮𝘀𝗲 ...
朋友A推荐，音乐流媒体平台用Milvus做了个超厉害的向量检索系统，能快速找到歌曲、歌词，还查版权，比传统方法快多了。
音乐流媒体平台通过 Milvus 构建自托管检索层，将每首歌转化为多个短音频向量，实现超过十亿个向量检索，支持歌曲识别、歌词搜索和版权匹配，数据库搜索延迟约十毫秒，同时处理数百次搜索请求。
𝟭𝟬𝟬𝗠+ 𝘁𝗿𝗮𝗰𝗸𝘀. 𝗕𝗶𝗹𝗹𝗶𝗼𝗻𝘀 𝗼𝗳 𝘃𝗲𝗰𝘁𝗼𝗿𝘀. ~𝟭𝟬 𝗺𝘀 𝗣𝟵𝟵 𝗱𝗮𝘁𝗮𝗯𝗮𝘀𝗲 ...
𝟭𝟬𝟬𝗠+ 𝘁𝗿𝗮𝗰𝗸𝘀. 𝗕𝗶𝗹𝗹𝗶𝗼𝗻𝘀 𝗼𝗳 𝘃𝗲𝗰𝘁𝗼𝗿𝘀. ~𝟭𝟬 𝗺𝘀 𝗣𝟵𝟵 𝗱𝗮𝘁𝗮𝗯𝗮𝘀𝗲 𝘀𝗲𝗮𝗿𝗰𝗵. That’s the retrieval scale behind one of the world’s largest music streaming platforms, serving hundreds of millions of listeners across 100+ countries. Search goes beyond song titles: listeners can 𝗽𝗹𝗮𝘆 𝗮 𝘀𝗵𝗼𝗿𝘁 𝗰𝗹𝗶𝗽, 𝗵𝘂𝗺 𝗮 𝘁𝘂𝗻𝗲, 𝗼𝗿 𝘁𝘆𝗽𝗲 𝗮 𝗵𝗮𝗹𝗳-𝗿𝗲𝗺𝗲𝗺𝗯𝗲𝗿𝗲𝗱 𝗹𝘆𝗿𝗶𝗰. The platform also checks uploaded audio for copyright matches against the full catalog. To power these experiences, the team built a 𝘀𝗲𝗹𝗳-𝗵𝗼𝘀𝘁𝗲𝗱 𝗠𝗶𝗹𝘃𝘂𝘀 𝗿𝗲𝘁𝗿𝗶𝗲𝘃𝗮𝗹 𝗹𝗮𝘆𝗲𝗿 spanning audio and lyrics. Each song becomes multiple short audio vectors, pushing the system to billions of vectors across the catalog. Lyrics combine semantic and full-text search, with filters for territory and rights. The result: -> 𝟭𝟬𝟬𝗠+ 𝘁𝗿𝗮𝗰𝗸𝘀 searchable across the full catalog -> ~𝟭𝟬 𝗺𝘀 𝗣𝟵𝟵 database search latency at hundreds of searches per second -> One infrastructure serves for 𝘀𝗼𝗻𝗴 𝗿𝗲𝗰𝗼𝗴𝗻𝗶𝘁𝗶𝗼𝗻, 𝗹𝘆𝗿𝗶𝗰 𝘀𝗲𝗮𝗿𝗰𝗵, 𝗿𝗲𝗰𝗼𝗺𝗺𝗲𝗻𝗱𝗮𝘁𝗶 zilliz.com/customers/musi… 𝗿𝗶𝗴𝗵𝘁 𝗺𝗮𝘁𝗰𝗵𝗶𝗻𝗴 𝗔𝘁 𝘁𝗵𝗶𝘀 𝘀𝗰𝗮𝗹𝗲, 𝘃𝗲𝗰𝘁𝗼𝗿 𝘀𝗲𝗮𝗿𝗰𝗵 𝗶𝘀𝗻’𝘁 𝗷𝘂𝘀𝘁 𝗮 𝗳𝗲𝗮𝘁𝘂𝗿𝗲 𝗯𝗲𝗵𝗶𝗻𝗱 𝗺𝘂𝘀𝗶𝗰 𝗱𝗶𝘀𝗰𝗼𝘃𝗲𝗿𝘆 — 𝗶𝘁’𝘀 𝗰𝗼𝗿𝗲 𝘀𝗲𝗮𝗿𝗰𝗵 𝗶𝗻𝗳𝗿𝗮𝘀𝘁𝗿𝘂𝗰𝘁𝘂𝗿𝗲. See how the platform built it with Milvus: https://t.co/f9vsUJWHcE 💬 1 🔄 0 ❤️ 0 👀 41 📊 1 ⚡