[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"tag-向量資料庫":3},{"tag":4,"articles":10,"peer_article_count":107},{"id":5,"name":6,"slug":6,"article_count":7,"description_zh":8,"description_en":9},"f0e1a1d6-eaff-4b63-8dda-9e2a4d9b777c","向量資料庫",3,"向量資料庫用來儲存與檢索高維嵌入，常見於 RAG、語意搜尋與推薦系統。這個主題會關注索引結構、混合搜尋、延遲、召回率、擴充性與成本，也會比較 Qdrant、Milvus、Weaviate、Rust 系方案等實作差異。","Vector databases store and search high-dimensional embeddings for RAG, semantic search, and recommendation systems. This topic covers indexing, hybrid search, latency, recall, scaling, and cost, along with implementation tradeoffs across systems like Qdrant, Milvus, Weaviate, and Rust-based designs.",[11,20,28,35,42,49,57,64,71,78,86,93,100],{"id":12,"slug":13,"title":14,"summary":15,"category":16,"image_url":17,"cover_image":17,"language":18,"created_at":19},"304a413f-48b5-4e03-ae02-805b048d6023","2026-xiang-liang-zi-liao-ku-dui-bi-10-kuan-zen-me-xuan-zh","2026 向量資料庫對比：10 款怎麼選","這篇比較 Pinecone、Weaviate、Qdrant、Milvus、pgvector、Vespa、Redis、Elasticsearch 與 LanceDB，幫你依照成本、規模、延遲與維運難度選出適合 2026 的向量資料庫。","industry","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1782649107089-ppzf.png","zh","2026-06-28T12:17:57.21576+00:00",{"id":21,"slug":22,"title":23,"summary":24,"category":25,"image_url":26,"cover_image":26,"language":18,"created_at":27},"f87f416c-0f08-4137-b070-714cace25274","zvec-turns-local-vector-search-into-a-library-zh","Zvec 把本地向量搜尋變成函式庫","我把 Zvec 拆成一套可直接抄的本地向量搜尋做法：把檢索塞回應用程式、把混合搜尋和全文檢索放進同一個引擎。","tools","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1781714028472-gvbb.png","2026-06-17T16:33:23.906632+00:00",{"id":29,"slug":30,"title":31,"summary":32,"category":16,"image_url":33,"cover_image":33,"language":18,"created_at":34},"ef090e43-8215-497b-9bdd-c43d3d611927","vector-lakebase-milvus-ai-data-platform-zh","Vector Lakebase 把 Milvus 變成 AI 資料平台","5 種能力看 Zilliz Vector Lakebase 如何把即時服務、探索與批次分析整合到同一個 AI 資料底座。","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1781410666114-09nr.png","2026-06-14T04:17:19.97915+00:00",{"id":36,"slug":37,"title":38,"summary":39,"category":25,"image_url":40,"cover_image":40,"language":18,"created_at":41},"4f0b90ab-f554-474e-9efd-ecec55257302","github-rag-production-list-battle-tested-tools-zh","GitHub 49 星 RAG 生產清單","GitHub 上一份 49 星的 RAG 生產清單，把工具、評測、可觀測性與部署選項整理成實戰地圖，方便團隊選型。","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1780870666920-t0hc.png","2026-06-07T22:17:20.22268+00:00",{"id":43,"slug":44,"title":45,"summary":46,"category":25,"image_url":47,"cover_image":47,"language":18,"created_at":48},"62c1b88c-e1b8-49a8-8e92-8ad6670afef2","why-rag-beats-prompting-private-data-zh","為什麼 RAG 比 Prompting 更適合私有資料","RAG 才是回答私有、常變資料的正確架構，因為它把知識放在檢索層，而不是賭模型記得住。","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1780179470536-d3jj.png","2026-05-30T22:17:19.844265+00:00",{"id":50,"slug":51,"title":52,"summary":53,"category":54,"image_url":55,"cover_image":55,"language":18,"created_at":56},"37a5e429-4235-439c-9b05-bb377085462c","8-steps-build-production-rag-with-langchain-zh","8 步驟打造可上線的 LangChain RAG","這篇教你用 LangChain、向量資料庫、LangSmith 與 FastAPI，從文件匯入一路做到可部署、可追蹤、可維運的生產級 RAG。","ai-agent","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1780178597493-4hz7.png","2026-05-30T22:02:48.14022+00:00",{"id":58,"slug":59,"title":60,"summary":61,"category":25,"image_url":62,"cover_image":62,"language":18,"created_at":63},"a9e7614e-8885-4017-a7a0-a27078f7e347","qdrant-vector-database-ai-search-zh","Qdrant 為 AI 應用加上向量搜尋","Qdrant 是用 Rust 寫的向量資料庫，主打語意搜尋、混合檢索、雲端與邊緣部署，適合 AI 應用做資料查找。","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1779512164975-hjhl.png","2026-05-23T04:55:31.578607+00:00",{"id":65,"slug":66,"title":67,"summary":68,"category":25,"image_url":69,"cover_image":69,"language":18,"created_at":70},"6ca36c73-d147-4134-913d-7e1df080899f","vector-databases-aws-explained-zh","AWS 怎麼看向量資料庫","AWS 這篇在講向量資料庫怎麼存 embeddings、怎麼做相似度搜尋，以及為什麼 Bedrock 常搭配 OpenSearch Service。","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1778973842531-shap.png","2026-05-16T23:23:31.940718+00:00",{"id":72,"slug":73,"title":74,"summary":75,"category":16,"image_url":76,"cover_image":76,"language":18,"created_at":77},"ba13eda6-dc79-45df-a32e-c6a4e26785c1","oracle-ai-doesnt-need-another-database-zh","Oracle：AI 不必再加一個資料庫","InfoWorld 指出，多數企業 AI 應直接在既有資料庫做向量檢索，而不是再建一套向量庫。","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1778973229687-upd6.png","2026-05-16T23:13:28.716862+00:00",{"id":79,"slug":80,"title":81,"summary":82,"category":83,"image_url":84,"cover_image":84,"language":18,"created_at":85},"92b08177-95c6-4743-89a9-f0314e6359c9","retrieval-augmented-generation-explained-zh","RAG 是什麼？白話看懂","RAG 讓 LLM 先查文件再回答，能減少幻覺、補上引用，也更適合企業知識庫與即時資料。","research","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1778083864937-hhfs.png","2026-05-06T16:10:33.474941+00:00",{"id":87,"slug":88,"title":89,"summary":90,"category":25,"image_url":91,"cover_image":91,"language":18,"created_at":92},"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":94,"slug":95,"title":96,"summary":97,"category":83,"image_url":98,"cover_image":98,"language":18,"created_at":99},"6510a804-74fd-4073-9c73-a1b4d3dc491c","ibm-100b-vector-database-single-server-zh","IBM 單機塞進 1000 億向量","IBM 宣稱 CAS 原型在單一伺服器上索引 1000 億向量，平均延遲 694 毫秒、召回率超過 90%。這篇拆解它怎麼做、跟一般向量資料庫差在哪、以及對企業 RAG 架構的影響。","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1776125936277-ct7n.png","2026-04-14T00:18:35.333469+00:00",{"id":101,"slug":102,"title":103,"summary":104,"category":25,"image_url":105,"cover_image":105,"language":18,"created_at":106},"af6bd5c1-b58a-4c4c-adff-9dd6a2bf7cbe","ferresdb-production-rust-vector-db-updates-zh","FerresDB 走向正式上線的 Rust 搜尋","FerresDB 新增 PolarQuant、HNSW 自動調參、PITR、reranking 與 Raft 分散式儲存，開始像一套可上線的 Rust 向量資料庫。","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1775168156597-iqqe.png","2026-04-02T22:15:41.697535+00:00",0]