[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"tag-rag":3},{"tag":4,"articles":11},{"id":5,"name":6,"slug":7,"article_count":8,"description_zh":9,"description_en":10},"2286390e-c09c-48fd-8f28-8dc871fb9603","RAG","rag",19,"RAG（Retrieval-Augmented Generation）把檢索與生成接在一起，讓模型先找資料再回答，常見於企業知識庫、語意搜尋、客服與研究助理。這裡聚焦向量資料庫、混合搜尋、索引與召回評估等實作議題。","RAG, or retrieval-augmented generation, combines search with model output so answers can be grounded in source data. This tag covers vector databases, hybrid search, indexing, recall, and evaluation for knowledge bases, semantic search, and enterprise assistants.",[12,21,29,37,44,51,58,66,73,80,87,94,101,108,115,122,129,136,143,150,157,164],{"id":13,"slug":14,"title":15,"summary":16,"category":17,"image_url":18,"cover_image":18,"language":19,"created_at":20},"322ec8bc-61d3-4c80-bb9e-a19941e137c6","how-to-add-temporal-rag-in-production-en","How to Add Temporal RAG in Production","Add a temporal reranking layer to RAG so fresh, valid, and versioned facts rank correctly.","ai-agent","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1778667085221-0mox.png","en","2026-05-13T10:10:31.619892+00:00",{"id":22,"slug":23,"title":24,"summary":25,"category":26,"image_url":27,"cover_image":27,"language":19,"created_at":28},"2834efcd-6c3d-424b-8436-68dbfade265b","ragflow-open-source-rag-agent-engine-en","RAGFlow adds agents to open-source RAG","RAGFlow pairs retrieval-augmented generation with agent features, Docker self-hosting, and support for newer models like GPT-5 and Gemini 3 Pro.","tools","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1778526659080-t2is.png","2026-05-11T19:10:36.388185+00:00",{"id":30,"slug":31,"title":32,"summary":33,"category":34,"image_url":35,"cover_image":35,"language":19,"created_at":36},"7f641864-c532-4bca-908d-fd576ca8772f","why-rag-in-microsoft-foundry-needs-better-indexes-en","Why RAG in Microsoft Foundry needs better indexes, not bigger prompts","RAG in Microsoft Foundry succeeds when retrieval is indexed well, not when prompts get longer.","industry","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1778300468356-mz2x.png","2026-05-09T04:20:24.312147+00:00",{"id":38,"slug":39,"title":40,"summary":41,"category":34,"image_url":42,"cover_image":42,"language":19,"created_at":43},"6f7e369d-ec1e-4945-979d-13fa86fddb90","chatgpt-goblin-bug-closed-models-fragile-en","Why ChatGPT’s Goblin Bug Proves Closed Models Are Fragile","ChatGPT’s goblin bug shows why closed LLMs are too opaque for serious production use.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1778289045403-buxu.png","2026-05-09T01:10:23.459545+00:00",{"id":45,"slug":46,"title":47,"summary":48,"category":17,"image_url":49,"cover_image":49,"language":19,"created_at":50},"bd5df14f-0712-4a15-bc92-ce811968f1e7","how-to-build-advanced-rag-in-n8n-en","How to Build Advanced RAG in n8n","Build a production RAG pipeline in n8n with chunking, hybrid retrieval, reranking, and compression.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1778209851895-vo8n.png","2026-05-08T03:10:30.217289+00:00",{"id":52,"slug":53,"title":54,"summary":55,"category":17,"image_url":56,"cover_image":56,"language":19,"created_at":57},"71f9b52e-54c0-4df7-acbc-3edf5628a0b7","why-rag-is-ending-for-agentic-ai-en","Why RAG is ending for agentic AI","RAG is the wrong layer for agentic AI, and compilation-stage knowledge systems will replace it.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1778105461209-unjv.png","2026-05-06T22:10:29.863227+00:00",{"id":59,"slug":60,"title":61,"summary":62,"category":63,"image_url":64,"cover_image":64,"language":19,"created_at":65},"5bac1973-cbb8-479b-91b9-517454db62d3","why-rag-needs-self-healing-layer-en","Why RAG Needs a Self-Healing Layer, Not Just Better Prompts","RAG should be treated as a failure-prone system that needs real-time self-healing, not prompt tuning.","research","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1778098237814-9wiq.png","2026-05-06T20:10:24.566716+00:00",{"id":67,"slug":68,"title":69,"summary":70,"category":63,"image_url":71,"cover_image":71,"language":19,"created_at":72},"13519d21-7023-407c-8974-7c633ebede9f","why-open-source-llms-should-be-judged-by-workload-not-hype-en","Why Open-Source LLMs Must Be Judged by Workload, Not Hype","Open-source LLMs in 2026 should be chosen by workload fit, not benchmark hype.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1778095240831-b3wm.png","2026-05-06T19:20:22.800006+00:00",{"id":74,"slug":75,"title":76,"summary":77,"category":63,"image_url":78,"cover_image":78,"language":19,"created_at":79},"fcba2ffc-9687-40b6-b58c-a36dc8b4926b","retrieval-augmented-generation-explained-en","Retrieval-Augmented Generation, Explained Simply","RAG lets large language models pull fresh facts from documents before answering, which cuts hallucinations and adds citations.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1778083860476-4o28.png","2026-05-06T16:10:34.177377+00:00",{"id":81,"slug":82,"title":83,"summary":84,"category":63,"image_url":85,"cover_image":85,"language":19,"created_at":86},"ea29007f-e989-470f-8968-68b7111caa88","rag-precision-tuning-hurts-retrieval-accuracy-en","RAG precision tuning can hurt retrieval accuracy","Redis research says tuning RAG embeddings for precision can cut retrieval accuracy by up to 40% and weaken agentic pipelines.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1778055669873-dzqb.png","2026-05-06T08:20:37.633155+00:00",{"id":88,"slug":89,"title":90,"summary":91,"category":26,"image_url":92,"cover_image":92,"language":19,"created_at":93},"446b7edd-c5cd-44e0-a791-7d1b7eeff59b","aws-bedrock-knowledge-bases-rag-en","AWS Bedrock Knowledge Bases simplifies RAG","Amazon Bedrock Knowledge Bases helps teams build RAG apps with managed ingestion, retrieval, citations, and structured-data queries.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1777960283790-qbn4.png","2026-05-05T05:51:09.166897+00:00",{"id":95,"slug":96,"title":97,"summary":98,"category":34,"image_url":99,"cover_image":99,"language":19,"created_at":100},"b2450abd-b108-4e4d-b1d7-1b02c17db850","why-databricks-rag-is-platform-play-not-feature-en","Why Databricks RAG Is a Platform Play, Not a Feature","Databricks treats RAG as an end-to-end platform problem, and that is the right way to build it.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1777959651374-avrm.png","2026-05-05T05:40:30.329823+00:00",{"id":102,"slug":103,"title":104,"summary":105,"category":17,"image_url":106,"cover_image":106,"language":19,"created_at":107},"95ec8193-dee3-4ec5-93db-89f285d07612","how-to-build-a-rag-pipeline-in-5-steps-en","How to Build a RAG Pipeline in 5 Steps","Build a retrieval-augmented generation pipeline that grounds AI answers in your own data.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1777959054423-dgs9.png","2026-05-05T05:30:32.335273+00:00",{"id":109,"slug":110,"title":111,"summary":112,"category":26,"image_url":113,"cover_image":113,"language":19,"created_at":114},"7345c59c-d547-4527-9246-80ce69103878","actian-vectorai-db-claims-22x-faster-search-en","Actian’s VectorAI DB Claims 22x Faster Search","Actian says VectorAI DB embeds vector search inside apps and delivers up to 22x faster retrieval than common alternatives.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1777936265007-zpnb.png","2026-05-04T23:10:39.821703+00:00",{"id":116,"slug":117,"title":118,"summary":119,"category":34,"image_url":120,"cover_image":120,"language":19,"created_at":121},"f6394fc8-88a9-47c6-a6e4-06eb469cf589","why-2026-ai-engineer-roadmap-wrong-starting-point-en","Why the 2026 AI engineer roadmap is the wrong starting point","The 2026 AI engineer roadmap is too broad to be the first plan you follow.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1777860663438-awh9.png","2026-05-04T02:10:25.69749+00:00",{"id":123,"slug":124,"title":125,"summary":126,"category":63,"image_url":127,"cover_image":127,"language":19,"created_at":128},"2ff3b7ca-c656-4814-9057-0457055b9263","mathnet-benchmark-math-reasoning-retrieval-en","MathNet: Global Multimodal Math Reasoning & Retrieval","MathNet adds 30,676 Olympiad problems across 47 countries and tests both solving and retrieval for multimodal models.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1776751434139-coi2.png","2026-04-21T06:03:38.96902+00:00",{"id":130,"slug":131,"title":132,"summary":133,"category":26,"image_url":134,"cover_image":134,"language":19,"created_at":135},"e8390502-7cb7-4bfa-878c-0d2685a39c2a","qdrant-milvus-weaviate-rag-2026-comparison-en","Qdrant vs Milvus vs Weaviate for RAG in 2026","Qdrant, Milvus, and Weaviate power different RAG needs in 2026. Here’s how they compare on latency, scale, hybrid search, and cost.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1776126293632-1zod.png","2026-04-14T00:24:39.888894+00:00",{"id":137,"slug":138,"title":139,"summary":140,"category":63,"image_url":141,"cover_image":141,"language":19,"created_at":142},"10619d9e-17e5-426e-8139-5ad963627565","ibm-100b-vector-database-single-server-en","IBM hits 100B vectors on one server","IBM says its CAS prototype indexed 100 billion vectors on one server, with 694 ms latency and 90% recall for RAG.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1776125931570-zfe2.png","2026-04-14T00:18:35.637601+00:00",{"id":144,"slug":145,"title":146,"summary":147,"category":26,"image_url":148,"cover_image":148,"language":19,"created_at":149},"9e741ead-c3f3-4c24-936b-09a29042fe1f","windsurf-flow-context-engine-2026-en","How Windsurf Flow Keeps Context Alive","Windsurf Flow updates AI context as you work. Here’s how RAG, Cascade, Memories, and rules shape every suggestion.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1775272011306-6ocr.png","2026-04-04T03:06:36.235488+00:00",{"id":151,"slug":152,"title":153,"summary":154,"category":26,"image_url":155,"cover_image":155,"language":19,"created_at":156},"08b053e4-b9e4-472d-a5bd-91f504015262","what-openrag-does-for-enterprise-ai-en","What OpenRAG Does for Enterprise AI","IBM’s OpenRAG packages retrieval, indexing, and model orchestration so teams can build grounded AI apps on their own data.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1775164555625-p4wn.png","2026-04-02T21:15:39.349005+00:00",{"id":158,"slug":159,"title":160,"summary":161,"category":26,"image_url":162,"cover_image":162,"language":19,"created_at":163},"66a7cbf8-7e76-41d4-9bbf-eaca9761bf69","github-ai-projects-to-watch-in-2026-en","20 GitHub AI Projects to Watch in 2026","OpenClaw may top GitHub, but 2026’s AI list shows a bigger shift toward agents, workflow systems, RAG, and multimodal tools.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1774520011176-ag2v.png","2026-03-26T08:28:09.752027+00:00",{"id":165,"slug":166,"title":167,"summary":168,"category":169,"image_url":170,"cover_image":170,"language":19,"created_at":171},"bf36bb9e-3444-4fb8-ab19-0df6bc9d8271","rag-2026-indispensable-ai-bridge-en","RAG in 2026: The Indispensable AI Bridge","In 2026, advanced Retrieval Augmented Generation (RAG) systems are essential for bridging large language models with enterprise knowledge, ensuring informed AI outputs.","model-release","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1774499161803-x9u7.png","2026-03-26T01:28:34.472046+00:00"]