[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"tag-vector-database":3},{"tag":4,"articles":11},{"id":5,"name":6,"slug":7,"article_count":8,"description_zh":9,"description_en":10},"cb44bdbf-9d02-43d7-96a4-eaed664a9a06","vector database","vector-database",6,"向量資料庫是 RAG、語意搜尋與 AI agent 記憶的核心基礎，負責把嵌入向量做高效檢索與相似度比對。這個主題會涵蓋 Qdrant、Milvus、Weaviate 等選型，以及延遲、規模、混合搜尋、成本與部署取捨。","Vector databases power RAG, semantic search, and agent memory by storing embeddings and retrieving nearest neighbors at speed. This tag covers trade-offs in latency, scale, hybrid search, cost, and operational fit across tools like Qdrant, Milvus, and Weaviate.",[12,21,28,35,43,50,58,65,72,79,86,93,100],{"id":13,"slug":14,"title":15,"summary":16,"category":17,"image_url":18,"cover_image":18,"language":19,"created_at":20},"4130de62-a037-464c-883d-5fbf8dd75789","open-source-rag-stack-build-plan-zh","開源 RAG 堆疊把混亂變計畫","拆開七層開源 RAG 堆疊，從 ingestion 到 frontend，直接拿去做自己的 build plan。","tools","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1780872500382-6ang.png","zh","2026-06-07T22:47:55.345265+00:00",{"id":22,"slug":23,"title":24,"summary":25,"category":17,"image_url":26,"cover_image":26,"language":19,"created_at":27},"3ead09ec-5656-4165-9bb0-f602add3c409","qdrant-filter-first-rag-design-decoded-zh","Qdrant 讓 RAG 先過濾再找相似","我拆 Raunaq 的向量資料庫比較，整理出 filter-first RAG 的選型邏輯與可直接貼上的設計模板。","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1780566519640-bdds.png","2026-06-04T09:47:59.450347+00:00",{"id":29,"slug":30,"title":31,"summary":32,"category":17,"image_url":33,"cover_image":33,"language":19,"created_at":34},"fcd9e0a1-085a-48e5-97e2-6d9757ac06f7","2026-system-design-interview-cheat-sheet-page-zh","2026 系統設計面試一頁模板","一頁版 2026 系統設計面試速查表，整理核心概念、取捨、常見模式，外加可直接套用的回答模板。","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1780248830713-47l1.png","2026-05-31T17:33:14.094251+00:00",{"id":36,"slug":37,"title":38,"summary":39,"category":40,"image_url":41,"cover_image":41,"language":19,"created_at":42},"bdf595fb-c181-4a3a-a2ec-e1243ba51c2d","vector-database-market-iot-time-series-zh","向量資料庫盯上 IoT 時序市場","The Business Research Company 透過 openPR 發布快訊，將向量資料庫市場對準 IoT 時序工作負載，但原文未提供規模、成長率或廠商細節。","industry","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1779510354087-0klm.png","2026-05-23T04:25:23.657196+00:00",{"id":44,"slug":45,"title":46,"summary":47,"category":17,"image_url":48,"cover_image":48,"language":19,"created_at":49},"4a78a285-c9ab-400d-a4ea-ada7303fd327","how-to-choose-a-vector-database-in-2026-zh","2026 向量資料庫怎麼選","這篇教你用規模、價格和架構三步篩選 2026 年的向量資料庫，做出可落地的 shortlist。","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1778972632684-qdj2.png","2026-05-16T23:03:29.482997+00:00",{"id":51,"slug":52,"title":53,"summary":54,"category":55,"image_url":56,"cover_image":56,"language":19,"created_at":57},"7095f05c-34f5-469f-a044-2525d2010ce9","how-to-add-temporal-rag-in-production-zh","如何在正式環境加入 Temporal RAG","這篇教你在既有 RAG 中加入時間感知重排層，讓新版本、有效期間內的事件與最新資料優先被 LLM 使用。","ai-agent","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1778667053844-osvs.png","2026-05-13T10:10:30.930982+00:00",{"id":59,"slug":60,"title":61,"summary":62,"category":55,"image_url":63,"cover_image":63,"language":19,"created_at":64},"e63f8dd8-b563-4db4-987e-2118469bc8a7","why-pinecone-compiled-vector-artifacts-ai-agents-zh","為什麼 Pinecone 的編譯式向量工件才是 AI agents 的正解","Pinecone 的方向是對的：AI agents 需要先編譯好的知識工件，而不是每次即時翻找原始向量。","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1778328644209-kopr.png","2026-05-09T12:10:22.152878+00:00",{"id":66,"slug":67,"title":68,"summary":69,"category":55,"image_url":70,"cover_image":70,"language":19,"created_at":71},"a8e2e21f-b0d2-4f4f-89bb-1936d5fe8fd5","how-to-build-agentic-rag-with-langgraph-zh","如何用 LangGraph 打造 Agentic RAG","這篇教你用 LangGraph 建立一個會路由、檢索、驗證並回答問題的 Agentic RAG 工作流。","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1778120450823-zxhl.png","2026-05-07T02:20:28.380469+00:00",{"id":73,"slug":74,"title":75,"summary":76,"category":55,"image_url":77,"cover_image":77,"language":19,"created_at":78},"261fa342-f7bb-4330-a97a-a95f10ae3f94","why-rag-is-ending-for-agentic-ai-zh","為什麼 RAG 正在結束，agentic AI 需要的是編譯式知識層","RAG 不再適合作為 agentic AI 的預設架構，因為代理需要可重用、可驗證的編譯式知識層，而不是每一步都重新檢索原始文本。","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1778105450961-s3p1.png","2026-05-06T22:10:28.570639+00:00",{"id":80,"slug":81,"title":82,"summary":83,"category":55,"image_url":84,"cover_image":84,"language":19,"created_at":85},"e133ed69-fb56-495d-96f6-1e14d7ac3242","how-to-build-a-rag-pipeline-in-5-steps-zh","5 步完成 RAG 管線","這篇教你用 5 個步驟做出 RAG 管線，讓模型先檢索你的文件，再根據內容產生有依據的答案。","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1777959047822-j4yr.png","2026-05-05T05:30:30.368078+00:00",{"id":87,"slug":88,"title":89,"summary":90,"category":17,"image_url":91,"cover_image":91,"language":19,"created_at":92},"fbd1528b-5af1-4e8c-ab31-1af9ac25fc5c","why-qdrant-cloud-enterprise-push-matters-ai-retrieval-zh","為什麼 Qdrant Cloud 的企業化推進，對 AI 檢索很重要","Qdrant Cloud 把向量檢索做成企業級基礎設施，因為 AI 檢索真正需要的是速度、可用性與可稽核性，而不是只會跑 demo。","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1777859592356-14tq.png","2026-05-04T01:52:57.160921+00:00",{"id":94,"slug":95,"title":96,"summary":97,"category":17,"image_url":98,"cover_image":98,"language":19,"created_at":99},"0ad0e45d-cb40-4267-bab8-d05ed973896a","qdrant-milvus-weaviate-rag-2026-comparison-zh","2026 RAG 向量資料庫三選一","2026 年做 RAG，Qdrant、Milvus、Weaviate 各有強項。這篇用延遲、規模、混合搜尋、成本與開發體驗，直接比較三者差異。","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1776126302600-xxf9.png","2026-04-14T00:24:39.218956+00:00",{"id":101,"slug":102,"title":103,"summary":104,"category":55,"image_url":105,"cover_image":105,"language":19,"created_at":106},"367128a2-5c5f-4d39-a51f-9cedd4d538a5","agent-memory-framework-analysis-zh","AI Agent 記憶怎麼設計","AI agent 要能跨任務保持狀態，記憶設計就很重要。本文拆解短期、長期與外部記憶，並比較框架、資料庫與向量檢索的取捨。","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1775058021870-r6l5.png","2026-04-01T10:21:33.242276+00:00"]