做智能体开发的团队终于有了一个把对话记忆从黑盒变成可读可搜索的方案，建议试试 memsearch 开源项目。
在伦敦非结构化数据聚会上，Milvus 开发者关系负责人 Jiang Chen 分享了将原始对话日志转化为智能体长期记忆的方法。核心思路是让记忆以 Markdown 文件形式可读可编辑，再通过语义搜索和混合搜索让智能体根据含义检索上下文，即使不记得关键词也能找到。该工作流可通过开源项目 memsearch 实现，适合构建更智能的对话式 AI 应用。
At last month’s Unstructured Data Meetup London, Jiang Chen, our Head of Developer Relations, broke ...
At last month’s Unstructured Data Meetup London, Jiang Chen, our Head of Developer Relations, broke down a question more agent builders are running into: 𝗵𝗼𝘄 𝗱𝗼 𝘆𝗼𝘂 𝘁𝘂𝗿𝗻 𝗿𝗮𝘄 𝗰𝗼𝗻𝘃𝗲𝗿𝘀𝗮𝘁𝗶𝗼𝗻 𝗵𝗶𝘀𝘁𝗼𝗿𝘆 𝗶𝗻𝘁𝗼 𝘂𝘀𝗲𝗳𝘂𝗹 𝗹𝗼𝗻𝗴-𝘁𝗲𝗿𝗺 𝗺𝗲𝗺𝗼𝗿𝘆? Raw conversation logs are a good starting point, but they should not become another black box. The key is to make memory readable and editable as Markdown files, then layer on semantic search and hybrid search so agents can recover the right context by meaning, even when no one remembers the exact keyword. You can explore this workflow with memsearch, an open- youtu.be/3mDFw933wdE?ut… for agent memory. 🎬 github.com/zilliztech/mem… o #AgentMemory � #VectorSearch n #RAG Hub: https://t.co/rbSO5eWu6X #AgentMemory #VectorSearch #RAG Your browser does not support the video tag. 🔗 View on Twitter 💬 0 🔄 0 ❤️ 2 👀 141 📊 1 ⚡