Open-source PageIndex ditches vector DBs for tree-based LLM reasoning, hits 98.7% on FinanceBench
DrDatta_AIIMS · x · 2026-09-30
Researchers have released PageIndex, an open-source RAG approach that abandons the standard vector pipeline entirely:
- No vector database, no embeddings, no chunking, no similarity search
- Instead it builds a tree-style index over documents and lets the LLM reason its way through it, like a human navigating a book
- Reports 98.7% accuracy on FinanceBench, claimed to beat every vector RAG on the leaderboard
- Fully free and open source
It points to a "reasoning-based retrieval" direction: replacing embedding similarity with LLM reasoning, potentially strongest on highly structured documents like financial reports.
Related event: PageIndex: Vectorless RAG Hits 36k GitHub Stars(3 posts)→
More from coding & agent
- Google Research open-sources PaperOrchestra, a multi-agent framework for writing AI papers — google-research · 2026-11-16
- ffmpeg-skill gives coding agents local video editing via 42 FFmpeg tools and MCP — kajisho5 · 2026-11-16
- Every's Frontier team on Claude Fable 5.2: overnight agent jobs, cost tradeoffs, real builds — every · 2026-11-16
- Agents Now Reply to Slack Messages on Their Own, Resolving a Prod Incident Ghost-to-Ghost — iamrobotbear · 2026-11-16
- Engineer's Interview Prep Method: Use Claude to Find Which Answers Undersell Your AI Work — brandon_galang · 2026-11-16
- DeepSeek open-sources its app frontend "chat-demo", already at 3.9k stars — NielsRogge · 2026-11-16