[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"tag-vector-database":3},{"tag":4,"articles":11},{"id":5,"name":6,"slug":7,"article_count":8,"description_zh":9,"description_en":10},"cb44bdbf-9d02-43d7-96a4-eaed664a9a06","vector database","vector-database",6,"向量資料庫是 RAG、語意搜尋與 AI agent 記憶的核心基礎，負責把嵌入向量做高效檢索與相似度比對。這個主題會涵蓋 Qdrant、Milvus、Weaviate 等選型，以及延遲、規模、混合搜尋、成本與部署取捨。","Vector databases power RAG, semantic search, and agent memory by storing embeddings and retrieving nearest neighbors at speed. This tag covers trade-offs in latency, scale, hybrid search, cost, and operational fit across tools like Qdrant, Milvus, and Weaviate.",[12,21,28,35,43,50,58,65],{"id":13,"slug":14,"title":15,"summary":16,"category":17,"image_url":18,"cover_image":18,"language":19,"created_at":20},"c5c4bac4-e9c6-40b4-a59a-0996f919832e","why-pinecone-compiled-vector-artifacts-ai-agents-en","Why Pinecone’s compiled vector artifacts are the right move for AI ag…","Pinecone is right: AI agents need precompiled knowledge artifacts, not raw vector hunting.","ai-agent","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1778328644009-szc0.png","en","2026-05-09T12:10:24.121914+00:00",{"id":22,"slug":23,"title":24,"summary":25,"category":17,"image_url":26,"cover_image":26,"language":19,"created_at":27},"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":29,"slug":30,"title":31,"summary":32,"category":17,"image_url":33,"cover_image":33,"language":19,"created_at":34},"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":36,"slug":37,"title":38,"summary":39,"category":40,"image_url":41,"cover_image":41,"language":19,"created_at":42},"36d0b97b-94e0-4f38-8a0a-cc7fb8491320","why-qdrant-cloud-enterprise-push-matters-ai-retrieval-en","Why Qdrant Cloud’s enterprise push matters for AI retrieval","Qdrant Cloud’s new GPU indexing, Multi-AZ clusters, and audit logs are the right move for production AI.","tools","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1777859605781-7sat.png","2026-05-04T01:52:58.603668+00:00",{"id":44,"slug":45,"title":46,"summary":47,"category":40,"image_url":48,"cover_image":48,"language":19,"created_at":49},"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":51,"slug":52,"title":53,"summary":54,"category":55,"image_url":56,"cover_image":56,"language":19,"created_at":57},"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.","research","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1776125931570-zfe2.png","2026-04-14T00:18:35.637601+00:00",{"id":59,"slug":60,"title":61,"summary":62,"category":40,"image_url":63,"cover_image":63,"language":19,"created_at":64},"791d8348-be8a-4a76-8a14-9a036e0a292c","ferresdb-production-rust-vector-db-updates-en","What FerresDB Shipped for Production Rust Search","FerresDB adds PolarQuant, HNSW auto-tuning, PITR, reranking, and Raft-backed distributed storage for production vector search.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1775168162480-w90i.png","2026-04-02T22:15:42.39107+00:00",{"id":66,"slug":67,"title":68,"summary":69,"category":17,"image_url":70,"cover_image":70,"language":19,"created_at":71},"01299403-0ffd-4a04-abbb-5b4d792fd01c","agent-memory-framework-analysis-en","Agent Memory: How AI Agents Keep State","Agent memory lets AI agents retain state across tasks. Here’s how short-, long-, and external memory shape real agent systems.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1775058027759-90qv.png","2026-04-01T10:21:33.504368+00:00"]