VectifyAI/PageIndex
PageIndex is a vectorless, reasoning-based RAG system that builds hierarchical tree indexes for human-like, context-aware document retrieval, outperforming traditional vector-based methods.
Core Features
Detailed Introduction
PageIndex addresses the limitations of traditional vector-based RAG, which often struggles with relevance in long, professional documents due to relying on semantic similarity over true reasoning. Inspired by AlphaGo, PageIndex introduces a novel vectorless, reasoning-based RAG system. It constructs a hierarchical tree index from documents and leverages LLMs to reason over this index, mimicking how human experts navigate complex information. This approach enables agentic, context-aware retrieval, leading to superior accuracy and explainability compared to conventional methods.