{"id":"2051527272675651923","url":"https://x.com/HowToAI_/status/2051527272675651923","text":"The entire RAG industry is about to get cooked.\n\nResearchers have built a new RAG approach that:\n\n- does not need a vector DB.\n- does not embed data.\n- involves no chunking.\n- performs no similarity search.\n\nIt's called PageIndex. Instead of chunking your docs and stuffing them into pinecone, it builds a tree index and lets the LLM reason through it like a human reading a book.\n\nhit 98.7% on financebench. beats every vector RAG on the leaderboard.\n\nno embeddings. no chunking. no vector DB.\n\n100% open source.","author":{"name":"How To AI","username":"HowToAI_","avatarUrl":"https://pbs.twimg.com/profile_images/2009866827518881792/Th8eH2US_200x200.jpg"},"createdAt":"Tue May 05 04:59:51 +0000 2026","engagement":{"replies":223,"retweets":779,"likes":6903,"views":616121},"media":{"photos":[{"url":"https://pbs.twimg.com/media/HHh82gnbsAALkeL.jpg?name=orig","width":1340,"height":1204}],"videos":[]},"adhxContext":{"savedByCount":1,"publicTags":[],"previewUrl":"https://adhx.com/HowToAI_/status/2051527272675651923"}}