PageIndex ditches vector DBs for tree-based reasoning RAG, hits 98.7% on FinanceBench
multiply_matrix · x · 2026-09-29
Researchers released an open-source RAG approach called PageIndex that bypasses nearly everything traditional RAG depends on:
- No vector DB, no embeddings, no chunking, no similarity search
- Instead of loading chunks into Pinecone, it builds a tree index that lets the LLM reason through documents like a human reading a book
- Scores 98.7% on FinanceBench, claimed to outperform every vector RAG on the leaderboard
- 100% free and open source
Commenters describe it as semantic hierarchical search, with a hierarchical classification cookbook released alongside. If it holds up, it could dramatically simplify document QA pipelines — removing vector stores entirely, though inference costs and long-document navigation remain to be tested.
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