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:

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)→

Original post →

More from coding & agent

coding & agent channel →