[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"article-pgvector-100k-vectors-not-default-zh":3,"article-related-pgvector-100k-vectors-not-default-zh":29,"series-industry-8511b941-baf5-48d4-b941-675fa415e66d":77},{"id":4,"slug":5,"title":6,"content":7,"summary":8,"source":9,"source_url":10,"author":11,"image_url":12,"cover_image":12,"category":13,"language":14,"translated_content":11,"related_article_id":15,"keywords":16,"key_takeaways":22,"views":26,"created_at":27,"published_at":28,"topic_cluster_id":11},"8511b941-baf5-48d4-b941-675fa415e66d","pgvector-100k-vectors-not-default-zh","100K 向量以下，pgvector 就夠了，不該當預設","\u003Cp data-speakable=\"summary\">100K 向量以下，pgvector 通常就夠用；當延遲、規模與檢索複雜度上升時，才該換專用\u003Ca href=\"\u002Fnews\u002Fvdbbench-cost-benchmark-vector-databases-zh\">向量資料\u003C\u002Fa>庫。\u003C\u002Fp>\u003Cp>把 pgvector 當預設，不是保守，而是務實：在 100K 向量以下，PostgreSQL 已能處理多數內部搜尋、早期 \u003Ca href=\"\u002Ftag\u002Frag\">RAG\u003C\u002Fa> 與小型語意檢索，沒必要先把架構做重。\u003C\u002Fp>\u003Ch2>第一個論點\u003C\u002Fh2>\u003Cp>100K 這條線很重要，因為它對應的是大多數團隊的真實起點。內部知識庫、產品目錄語意搜尋、客服文件檢索，常常只有數萬到十多萬筆向量。這種量級下，pgvector 直接掛在既有 PostgreSQL 上，通常就能把召回、過濾與權限控制一起做完。\u003C\u002Fp>\n\u003Cfigure class=\"my-6\">\u003Cimg src=\"https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1786656763977-1sw8.png\" alt=\"100K 向量以下，pgvector 就夠了，不該當預設\" class=\"rounded-xl w-full\" loading=\"lazy\" \u002F>\u003C\u002Ffigure>\n\u003Cp>更關鍵的是，PostgreSQL 已經自帶交易、備份、存取控制與 SQL join。若你的團隊本來就有一套成熟的 Postgres 維運流程，新增 pgvector 幾乎不增加心智負擔。相比之下，為了還沒證明會成長的向量檢索，先引入另一套資料庫，反而是在替未來的複雜度提前付費。\u003C\u002Fp>\u003Ch2>第二個論點\u003C\u002Fh2>\u003Cp>專用向量資料庫的優勢，主要出現在規模和延遲開始成為產品指標之後。像 Milvus、Qdrant、Weaviate 這類系統，之所以在 1bench 類型的排名裡靠前，不是因為名字新，而是因為它們就是為 ANN、索引結構與相似度查詢設計的。\u003C\u002Fp>\u003Cp>\u003Ca href=\"\u002Ftag\u002Fgithub\">GitHub\u003C\u002Fa> star 也能側面說明成熟度：Milvus 約 45.2k、Qdrant 約 33.3k、Weaviate 約 16.6k。這代表社群、文件與實戰案例都已累積到一定程度。當資料量進到百萬級、查詢延遲要壓到嚴格 SLO，專用引擎在記憶體布局、索引更新與 top-k 搜尋上的優勢，會直接反映在產品體感上。\u003C\u002Fp>\u003Ch2>反方可能怎麼說\u003C\u002Fh2>\u003Cp>最強的反對意見是：pgvector 只是「先能用」，不是「最終解」。如果團隊明知資料會快速膨脹、查詢量會暴增，先上專用向量資料庫可以少一次遷移，也能提早拿到混合檢索、向量過濾與水平擴展的能力。\u003C\u002Fp>\n\u003Cfigure class=\"my-6\">\u003Cimg src=\"https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1786656758168-ap67.png\" alt=\"100K 向量以下，pgvector 就夠了，不該當預設\" class=\"rounded-xl w-full\" loading=\"lazy\" \u002F>\u003C\u002Ffigure>\n\u003Cp>另一個合理批評是，AI 團隊想要的是語意檢索原生體驗。專用向量資料庫把 embedding、similarity search、RAG 這些概念包成同一個產品語言，整合\u003Ca href=\"\u002Fnews\u002Fzilliz-cost-aware-vdbbench-benchmark-zh\">成本\u003C\u002Fa>較低，對人少、節奏快的新團隊尤其有吸引力。\u003C\u002Fp>\u003Cp>但這些理由只在規模與複雜度已經可見時成立。若資料集仍小、流量仍低、而且團隊本來就運行 PostgreSQL，那麼多一套系統帶來的部署、監控、備援與故障排查\u003Ca href=\"\u002Fnews\u002Fzilliz-cost-aware-scoring-vdbbench-zh\">成本\u003C\u002Fa>，通常比 pgvector 的性能上限更早成為問題。先用 pgvector，等延遲或召回真的卡住，再升級，才是把錢和時間花在刀口上。\u003C\u002Fp>\u003Ch2>你能做什麼\u003C\u002Fh2>\u003Cp>如果你是工程師，先用 PostgreSQL + pgvector，並設定明確門檻：資料量、p95 延遲、召回率、以及是否需要混合檢索。若你是 PM 或創辦人，把專用向量資料庫視為一筆和產品指標綁定的基礎設施投資，不要把它當成 AI 形象工程。當向量檢索只是功能之一，pgvector 是更好的預設；當向量檢索就是核心路徑，才輪到 Qdrant、Milvus、Weaviate 這類專用系統上場。\u003C\u002Fp>","我主張 pgvector 應該是 100K 向量以下的預設選擇；只有當規模、延遲與檢索複雜度上來時，才值得上專用向量資料庫。","1bench.dev","https:\u002F\u002F1bench.dev\u002Fdatabases\u002Fvector",null,"https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1786656763977-1sw8.png","industry","zh","fae47509-4ad5-4546-8936-e7e1fe24c0df",[17,18,19,20,21],"pgvector","PostgreSQL","向量資料庫","語意檢索","RAG",[23,24,25],"100K 向量以下，pgvector 通常足夠，且能保留 PostgreSQL 的完整生態。","專用向量資料庫的價值主要在百萬級規模、嚴格延遲與更複雜的檢索需求。","架構選擇應跟產品路徑對齊，不要為了 AI 標籤過早增加系統複雜度。",1,"2026-08-13T21:32:18.3739+00:00","2026-08-13T21:32:18.37+00:00",{"tags":30,"relatedLang":36,"relatedPosts":40},[31,33,35],{"name":21,"slug":32},"rag",{"name":18,"slug":34},"postgresql",{"name":19,"slug":19},{"id":15,"slug":37,"title":38,"language":39},"pgvector-enough-small-datasets-not-default-en","pgvector is enough for small datasets, not your default","en",[41,47,53,59,65,71],{"id":42,"slug":43,"title":44,"cover_image":45,"image_url":45,"created_at":46,"category":13},"1c5f0bb7-ea6e-413d-8e72-b02f20316ef4","astra-fangman-yanfa-5-ge-guan-jian-xin-hao-zh","Astra放慢研发的5个关键信号","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1786647774714-k0m5.png","2026-08-13T19:02:29.945739+00:00",{"id":48,"slug":49,"title":50,"cover_image":51,"image_url":51,"created_at":52,"category":13},"0ffd4803-74bb-43f8-a5be-0a5681ecc049","anthropic-custom-ai-inference-chips-claude-zh","Anthropic 也要自己做 AI 晶片","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1786645974543-pram.png","2026-08-13T18:32:29.543527+00:00",{"id":54,"slug":55,"title":56,"cover_image":57,"image_url":57,"created_at":58,"category":13},"e0d0476a-e3d5-4bf7-995b-e5416f5e392a","moka-ai-hrms-three-layer-architecture-zh","Moka AI 不是锦上添花，HRMS 选型正在转向三层架构","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1786611776096-cy66.png","2026-08-13T09:02:28.103219+00:00",{"id":60,"slug":61,"title":62,"cover_image":63,"image_url":63,"created_at":64,"category":13},"3640e980-0be1-408e-b5fe-a1ad42022b61","ai-hardware-rally-short-sellers-august-2026-zh","AI硬件反攻，8月空頭更難做","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1786584781842-0bny.png","2026-08-13T01:32:36.671063+00:00",{"id":66,"slug":67,"title":68,"cover_image":69,"image_url":69,"created_at":70,"category":13},"f1349fae-7cbd-49a0-9d6a-ceaa65b51c1e","pixel-11-launch-live-google-reveals-zh","Pixel 11 發表會重點整理","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1786581163428-ivyj.png","2026-08-13T00:32:20.178966+00:00",{"id":72,"slug":73,"title":74,"cover_image":75,"image_url":75,"created_at":76,"category":13},"07408fa7-809f-49e2-873d-427cb10c0c15","claude-invisible-watermark-right-direction-zh","Claude隱形水印是正確方向，不是暴政","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1786579370713-ic6h.png","2026-08-13T00:02:25.128006+00:00",[78,83,88,93,98,103,108,113,118,123],{"id":79,"slug":80,"title":81,"created_at":82},"ee073da7-28b3-4752-a319-5a501459fb87","ai-in-2026-what-actually-matters-now-zh","2026 AI 真正重要的事","2026-03-26T07:09:12.008134+00:00",{"id":84,"slug":85,"title":86,"created_at":87},"83bd1795-8548-44c9-9a7e-de50a0923f71","trump-ai-framework-power-speech-state-preemption-zh","川普 AI 框架瞄準電力、言論與州權","2026-03-26T07:12:18.695466+00:00",{"id":89,"slug":90,"title":91,"created_at":92},"ea6be18b-c903-4e54-97b7-5f7447a612e0","nvidia-gtc-2026-big-ai-announcements-zh","NVIDIA GTC 2026 重點拆解","2026-03-26T07:14:26.62638+00:00",{"id":94,"slug":95,"title":96,"created_at":97},"4bcec76f-4c36-4daa-909f-54cd702f7c93","claude-users-spreading-out-and-getting-better-zh","Claude 用戶更分散，也更會用","2026-03-26T07:22:52.325888+00:00",{"id":99,"slug":100,"title":101,"created_at":102},"bd903b15-2473-4178-9789-b7557816e535","openclaw-raises-hard-question-for-ai-models-zh","OpenClaw 逼問 AI 模型價值","2026-03-26T07:24:54.707486+00:00",{"id":104,"slug":105,"title":106,"created_at":107},"eeac6b9e-ad9d-4831-8eec-8bba3f9bca6a","gap-google-gemini-checkout-fashion-search-zh","Gap 把結帳搬進 Gemini","2026-03-26T07:28:23.937768+00:00",{"id":109,"slug":110,"title":111,"created_at":112},"0740e53f-605d-4d57-8601-c10beb126f3c","google-pushes-gemini-transition-to-march-2026-zh","Google 把 Gemini 轉換延到 2026 年 3…","2026-03-26T07:30:12.825269+00:00",{"id":114,"slug":115,"title":116,"created_at":117},"e660d801-2421-4529-8fa9-86b82b066990","metas-llama-4-benchmark-scandal-gets-worse-zh","Meta Llama 4 分數風波又擴大","2026-03-26T07:34:21.156421+00:00",{"id":119,"slug":120,"title":121,"created_at":122},"183f9e7c-e143-40bb-a6d5-67ba84a3a8bc","accenture-mistral-ai-sovereign-enterprise-deal-zh","Accenture 攜手 Mistral AI 賣主權 AI","2026-03-26T07:38:14.818906+00:00",{"id":124,"slug":125,"title":126,"created_at":127},"191d9b1b-768a-478c-978c-dd7431a38149","mistral-ai-faces-its-hardest-year-yet-zh","Mistral AI 迎來最硬的一年","2026-03-26T07:40:23.716374+00:00"]