PageIndex: vectorless RAG with no embeddings or chunking hits 98.7% on FinanceBench
dr_cintas · x · 2026-11-21
Researchers open-sourced PageIndex, a "vectorless" reasoning-based RAG approach: no embeddings, no chunking, no vector DB, no similarity search. Instead it builds a tree index of documents and lets the LLM reason through it like a human reading a book.
- Scores 98.7% on FinanceBench, reportedly beating every vector RAG on the leaderboard.
- Hit #1 on GitHub Trending; ships with a self-hosted agentic RAG example using the OpenAI Agents SDK, plus a PageIndex Chat document-analysis platform available via MCP and API.
More from coding & agent
- Full workflow fixes Fable 5.2 video audio entirely inside Claude — AIwithGhotai · 2026-11-21
- Claude Opus 5.5 drives Onshape CAD via computer use, with surprisingly delightful results — adhamelarabawy · 2026-11-21
- Inkling 2 Mini runs fully offline on a MacBook, builds an airplane simulator in minutes — LiTianleli · 2026-11-21
- Inkling 2 Mini runs locally in 16GB RAM: 5.4B-active MoE tops its size class — simonguozirui · 2026-11-21
- Replit engineer: 'I no longer need anything locally for my job' — amasad · 2026-11-21
- Replit Agent lands in Microsoft Teams to turn chats into action — amasad · 2026-11-21