[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"tag-embeddings":3},{"tag":4,"articles":10},{"id":5,"name":6,"slug":6,"article_count":7,"description_zh":8,"description_en":9},"8790c445-ebb0-439b-99fd-b1a2983cc87c","embeddings",4,"Embeddings 是把文字、語音或程式碼轉成可比較的向量表示，讓語意搜尋、RAG、相似度比對與向量資料庫能運作。它常用在 Redis Vector Search、新詞初始化與 ASR 評測等場景，直接影響檢索品質與模型對齊。","Embeddings turn text, speech, or code into vectors that systems can compare for semantic search, retrieval-augmented generation, similarity matching, and vector databases. They also shape tasks like token initialization, ASR evaluation, and context retrieval in tools such as Redis Vector Search.",[11,20,28,36,43,50],{"id":12,"slug":13,"title":14,"summary":15,"category":16,"image_url":17,"cover_image":17,"language":18,"created_at":19},"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。","tools","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1778973842531-shap.png","zh","2026-05-16T23:23:31.940718+00:00",{"id":21,"slug":22,"title":23,"summary":24,"category":25,"image_url":26,"cover_image":26,"language":18,"created_at":27},"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。","ai-agent","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1778120450823-zxhl.png","2026-05-07T02:20:28.380469+00:00",{"id":29,"slug":30,"title":31,"summary":32,"category":33,"image_url":34,"cover_image":34,"language":18,"created_at":35},"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":37,"slug":38,"title":39,"summary":40,"category":25,"image_url":41,"cover_image":41,"language":18,"created_at":42},"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":44,"slug":45,"title":46,"summary":47,"category":33,"image_url":48,"cover_image":48,"language":18,"created_at":49},"b41b3999-fa8c-4e87-8914-4ed027fe8bfe","llms-for-asr-evaluation-beyond-wer-zh","LLM 評測 ASR 不只看 WER","這篇論文把 decoder-based LLM 拿來當 ASR 評測器，結果在人工一致性上明顯贏過 WER；在 HATS 的二選一任務，最佳模型達 92–94%。","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1777010993292-cy1y.png","2026-04-24T06:09:37.70822+00:00",{"id":51,"slug":52,"title":53,"summary":54,"category":16,"image_url":55,"cover_image":55,"language":18,"created_at":56},"663a3bd8-6160-4b37-bf18-e3c54e7541d2","windsurf-flow-context-engine-2026-zh","Windsurf Flow 怎麼讓上下文不斷線","Windsurf Flow 用索引、記憶與規則維持 AI 上下文。本文拆解 Cascade、Tab、RAG 與 .windsurfrules 的運作方式，並比較它和其他 AI 寫碼工具的差異。","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1775272013033-va0v.png","2026-04-04T03:06:35.776413+00:00"]