[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"article-why-amazon-s3-vectors-matters-storage-search-zh":3,"article-related-why-amazon-s3-vectors-matters-storage-search-zh":31,"series-tools-0cc9fd02-9a30-4b10-bd8c-d8ecc52aa370":82},{"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":23,"views":27,"created_at":28,"published_at":29,"topic_cluster_id":30},"0cc9fd02-9a30-4b10-bd8c-d8ecc52aa370","why-amazon-s3-vectors-matters-storage-search-zh","為什麼 Amazon S3 Vectors 更重要的是儲存，不是搜尋","\u003Cp data-speakable=\"summary\">Amazon S3 Vectors 是儲存層的成本勝利，不是搜尋層的\u003Ca href=\"\u002Fnews\u002Fopenclaw-alternatives-install-cleanly-zh\">替代品\u003C\u002Fa>。\u003C\u002Fp>\u003Cp>Amazon 這次把 S3 Vectors 定位成便宜、可持久保存的向量儲存層，而不是拿來取代嚴肅的向量資料庫，方向是對的。它的價值不在於把所有向量都變成即時搜尋，而在於把數十億 embeddings 放進 S3，再把最熱的資料送去 OpenSearch 或其他低延遲系統。\u003Ca href=\"\u002Ftag\u002Faws\">AWS\u003C\u002Fa> 公布的數字很直接：向量儲存、上傳與查詢成本最高可降 90%，單一索引可支援最多 20 億個 vectors，暖查詢延遲約 100 ms。這些指標說明，向量系統真正的瓶頸常常不是算法，而是把所有 embeddings 都養在昂貴記憶體層的成本。\u003C\u002Fp>\u003Ch2>第一個論點：多數團隊花錯錢的地方在儲存，不在搜尋\u003C\u002Fh2>\u003Cp>大多數組織並不需要每\u003Ca href=\"\u002Fnews\u002Fwhy-geminigen-ai-is-just-another-wrapper-zh\">一個\u003C\u002Fa> vector 都住在高價、永遠在線的搜尋引擎裡。它們真正需要的是一個可靠、便宜的地方存放龐大的 embedding 語料，再把高價值、被頻繁查詢的部分升級到熱層。S3 Vectors 解決的正是這個問題：把冷資料留在 S3，讓長尾資料不必因為成本被刪掉、壓縮掉，或乾脆從未被索引。對 \u003Ca href=\"\u002Ftag\u002Frag\">RAG\u003C\u002Fa>、語意搜尋、\u003Ca href=\"\u002Ftag\u002Fagent\">agent\u003C\u002Fa> memory 來說，這等於把可保留的知識量直接拉高。\u003C\u002Fp>\n\u003Cfigure class=\"my-6\">\u003Cimg src=\"https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1780420673702-gq7g.png\" alt=\"為什麼 Amazon S3 Vectors 更重要的是儲存，不是搜尋\" class=\"rounded-xl w-full\" loading=\"lazy\" \u002F>\u003C\u002Ffigure>\n\u003Cp>AWS 自己給的架構示範也很有說服力：OpenSearch 負責高 QPS、低延遲搜尋，S3 Vectors 則承接那些仍需可查詢、但不必永遠熱著的資料。這不是折衷，而是分層。很多團隊會把向量系統做成單一大搜尋叢集，假設所有 embeddings 都值得同樣的服務路徑；實務上根本不是這樣。影片檔案庫、文件湖、歷史互動紀錄，優先順序永遠是便宜持久，再來才是快速啟動。\u003C\u002Fp>\u003Ch2>第二個論點：分層向量基礎設施才是 AI 的預設解\u003C\u002Fh2>\u003Cp>AI 工作負載本來就不均一，向量基礎設施卻常被設計得像所有請求都一樣急。即時聊天的檢索、商品目錄的語意搜尋、以及 agent 的長期記憶，對延遲與新鮮度的要求完全不同。AWS 把 S3 Vectors、Amazon OpenSearch Service 和 Bedrock Knowledge Bases 放在一起，反而更像是把正確的三層架構講\u003Ca href=\"\u002Fnews\u002Fwikipedias-tony-gonzales-page-into-a-clean-brief-zh\">清楚\u003C\u002Fa>：冷儲存、一般檢索、高效服務。這種設計讓團隊只在需要高強度的地方付高強度的錢。\u003C\u002Fp>\u003Cp>更重要的是整合本身。AWS 說 S3 Vectors 可接到 Bedrock Knowledge Bases、SageMaker Unified Studio 與 OpenSearch Service，代表它不是想孤立地贏，而是想成為向量資料的預設後端，再把熱資料升級到更快的索引。這比要求每個 AI 團隊在「昂貴的完整向量資料庫」和「脆弱的自建管線」之間二選一要合理得多。生產環境本來就是這樣演化：先用便宜儲存把資料留住，再把最有價值的切片推進熱層。\u003C\u002Fp>\u003Ch2>反方可能怎麼說\u003C\u002Fh2>\u003Cp>最強的反對意見是：S3 Vectors 不是為最熱路徑設計的。如果應用需要低於 10 ms 的檢索、高 QPS，或複雜過濾與排序，那麼專用向量資料庫或 OpenSearch 仍然更合適。這點沒有錯。S3 Vectors 並不是要消滅向量搜尋引擎，AWS 也沒有這樣宣稱；它的定位本來就明確指向長期、低頻存取的向量資料，而高效能層留給 OpenSearch。\u003C\u002Fp>\n\u003Cfigure class=\"my-6\">\u003Cimg src=\"https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1780420678240-xxrn.png\" alt=\"為什麼 Amazon S3 Vectors 更重要的是儲存，不是搜尋\" class=\"rounded-xl w-full\" loading=\"lazy\" \u002F>\u003C\u002Ffigure>\n\u003Cp>但這個限制正是它重要的原因。多數團隊不該為了最熱的 20% 流量，去優化最冷的 80% embeddings。真正的反駁不是說 S3 Vectors 在原始速度上打贏所有向量資料庫，而是它消除了把所有 vectors 當成同樣熱資料的昂貴錯誤。如果架構分層做對，最熱的資料仍然會進到最快的系統。S3 Vectors 的價值在於，它讓這個搬遷更便宜、更簡單，也更可持續。\u003C\u002Fp>\u003Ch2>你能做什麼\u003C\u002Fh2>\u003Cp>如果你是工程師或 PM，把 S3 Vectors 當成向量產品的預設冷層，架構上以「升級」而不是「永久常駐」為原則。先把完整 embedding 語料放進 S3，再量測存取頻率，只把活躍切片搬到 OpenSearch 或其他低延遲引擎。如果你是創辦人，這可以直接降低早期單位經濟：先為保留而建，而不只是為搜尋而建，你就能在不背上過大的基礎設施帳單下，做出更完整的 RAG、更好的語意搜尋，以及更穩定的 agent 記憶。","Amazon S3 Vectors 是儲存層的成本勝利，不是搜尋層的替代品；AWS 這樣定位是對的。","aws.amazon.com","https:\u002F\u002Faws.amazon.com\u002Fs3\u002Ffeatures\u002Fvectors\u002F",null,"https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1780420673702-gq7g.png","tools","zh","68cf393d-fb46-4002-9142-9d28e882c794",[17,18,19,20,21,22],"Amazon S3 Vectors","S3","OpenSearch","向量儲存","分層架構","成本優化",[24,25,26],"S3 Vectors 的核心價值是把向量資料的成本壓低，而不是取代高效能搜尋引擎。","向量系統應該分層：冷儲存放在 S3，熱資料升級到 OpenSearch 或其他低延遲層。","對工程、PM 與創辦人來說，重點是先保留完整語料，再按使用率把資料推進熱層。",5,"2026-06-02T17:17:27.081665+00:00","2026-06-02T17:17:27.063+00:00","c3c88dd2-a940-438a-b359-0e5a24562273",{"tags":32,"relatedLang":41,"relatedPosts":45},[33,35,36,38,39],{"name":17,"slug":34},"amazon-s3-vectors",{"name":21,"slug":21},{"name":19,"slug":37},"opensearch",{"name":20,"slug":20},{"name":18,"slug":40},"s3",{"id":15,"slug":42,"title":43,"language":44},"why-amazon-s3-vectors-matters-storage-search-en","Why Amazon S3 Vectors matters more as storage than search","en",[46,52,58,64,70,76],{"id":47,"slug":48,"title":49,"cover_image":50,"image_url":50,"created_at":51,"category":13},"63d8b456-ad6b-475e-86e9-d4677ca226aa","magenta-realtime-2-score-inside-daw-zh","Magenta RealTime 2 讓你在 DAW 裡即時改曲","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1781046204038-8tox.png","2026-06-09T23:02:55.9651+00:00",{"id":53,"slug":54,"title":55,"cover_image":56,"image_url":56,"created_at":57,"category":13},"f60261ff-a42e-4cfb-9f90-97785e633289","open-source-ai-tools-beat-claude-paid-tiers-zh","開源 AI 工具在價值上已經贏過 Claude 付費方案","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1781045266035-on7t.png","2026-06-09T22:47:20.195939+00:00",{"id":59,"slug":60,"title":61,"cover_image":62,"image_url":62,"created_at":63,"category":13},"8520cd4f-2531-4808-a95d-26f590239d7a","500-ai-agent-projects-show-where-agents-work-now-zh","500 個 AI agent 專案，現在能做什麼","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1781033591132-c0nh.png","2026-06-09T19:32:37.03924+00:00",{"id":65,"slug":66,"title":67,"cover_image":68,"image_url":68,"created_at":69,"category":13},"c557ef1c-7fde-4c86-918e-4fb9680ee9df","chocolatey-go-package-policy-installs-zh","Chocolatey 的 Go 安裝變成政策","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1781029110289-xkbh.png","2026-06-09T18:18:05.078435+00:00",{"id":71,"slug":72,"title":73,"cover_image":74,"image_url":74,"created_at":75,"category":13},"90b2df54-df6e-417d-9e16-91e9ad2f53d7","go-support-policy-turns-releases-into-a-checklist-zh","Go 支援政策把發版變清單","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1781028200122-3m4u.png","2026-06-09T18:02:49.50176+00:00",{"id":77,"slug":78,"title":79,"cover_image":80,"image_url":80,"created_at":81,"category":13},"119c23c6-8ae7-4c4e-820e-1eba0730d702","rustdesk-self-hosting-secure-remote-access-zh","RustDesk 自架遠端存取部署指南","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1781017373324-g7et.png","2026-06-09T15:02:24.118819+00:00",[83,88,93,98,103,108,113,118,123,128],{"id":84,"slug":85,"title":86,"created_at":87},"855cd52f-6fab-46cc-a7c1-42195e8a0de4","surepath-real-time-mcp-policy-controls-zh","SurePath 推出即時 MCP 政策控管","2026-03-26T07:57:40.77233+00:00",{"id":89,"slug":90,"title":91,"created_at":92},"9b19ab54-edef-4dbd-9ce4-a51e4bae4ebb","mcp-in-2026-the-ai-tool-layer-teams-use-zh","2026 年 MCP：團隊真的在用的 AI 工具層","2026-03-26T08:01:46.589694+00:00",{"id":94,"slug":95,"title":96,"created_at":97},"af9c46c3-7a28-410b-9f04-32b3de30a68c","prompting-in-2026-what-actually-works-zh","2026 提示工程，真正有用的是什麼","2026-03-26T08:08:12.453028+00:00",{"id":99,"slug":100,"title":101,"created_at":102},"05553086-6ed0-4758-81fd-6cab24b575e0","garry-tan-open-sources-claude-code-toolkit-zh","Garry Tan 開源 Claude Code 工具包","2026-03-26T08:26:20.068737+00:00",{"id":104,"slug":105,"title":106,"created_at":107},"042a73a2-18a2-433d-9e8f-9802b9559aac","github-ai-projects-to-watch-in-2026-zh","2026 必看 20 個 GitHub AI 專案","2026-03-26T08:28:09.619964+00:00",{"id":109,"slug":110,"title":111,"created_at":112},"a5f94120-ac0d-4483-9a8b-63590071ac6a","claude-code-vs-cursor-2026-zh","Claude Code 與 Cursor 深度對比：202…","2026-03-26T13:27:14.279193+00:00",{"id":114,"slug":115,"title":116,"created_at":117},"0975afa1-e0c7-4130-a20d-d890eaed995e","practical-github-guide-learning-ml-2026-zh","2026 機器學習入門 GitHub 實用指南","2026-03-27T01:16:49.712576+00:00",{"id":119,"slug":120,"title":121,"created_at":122},"bfdb467a-290f-4a80-b3a9-6f081afb6dff","aiml-2026-student-ai-ml-lab-repo-review-zh","AIML-2026：像課綱的學生實驗 Repo","2026-03-27T01:21:51.467798+00:00",{"id":124,"slug":125,"title":126,"created_at":127},"80cabc3e-09fc-4ff5-8f07-b8d68f5ae545","ai-trending-github-repos-and-research-feeds-zh","AI Trending：把 AI 資源收成一張表","2026-03-27T01:31:35.262183+00:00",{"id":129,"slug":130,"title":131,"created_at":132},"3ce6e6e2-bac5-463e-9f8d-45caabcc61f7","awesome-ai-for-science-research-tools-map-zh","AI 科研工具清單，開始像地圖了","2026-03-27T01:46:50.521945+00:00"]