[HN Gopher] RAG Without Vectors - Reasoning-Based RAG using Page...
___________________________________________________________________
RAG Without Vectors - Reasoning-Based RAG using PageIndex
Traditional vector-based RAG often struggles with retrieval
accuracy because it optimizes for similarity, not relevance. But
what we truly need in retrieval is relevance, which requires
reasoning. When working with professional documents that require
domain expertise and multi-step reasoning, vector-based RAG and
similarity search often fall short. So we started exploring a more
reasoning-driven approach to RAG. Reasoning-based RAG enables LLMs
to think and reason their way to the most relevant document
sections. Inspired by AlphaGo, we propose to use tree search to
perform structured document retrieval. We open-sourced one of the
key components: PageIndex. PageIndex is a hierarchical Document
Indexing system that builds search trees from long documents (like
financial reports, regulatory documents, or textbooks), making them
ready for reasoning-based RAG. Some highlights: - Hierarchical
Structure: Organizes lengthy PDFs into LLM-friendly trees -- like a
smart table of contents. - Precise Referencing: Each node includes
a summary and exact physical page numbers. - Natural Segmentation:
Nodes align with document sections, preserving context -- no
arbitrary chunking. We've used PageIndex for financial document
analysis with reasoning-based RAG and saw significant improvements
in retrieval accuracy compared to vector-based systems. Would love
any feedback -- especially thoughts on reasoning-based RAG, or
ideas for where PageIndex could be applied!
Author : vectify_AI
Score : 19 points
Date : 2025-04-10 18:37 UTC (4 hours ago)
| casenmgreen wrote:
| Can this system explain its reasoning, and so explain its answer?
| vectify_AI wrote:
| Yes, the explanation and reasons for relevance can be included
| in the search and reflected in the answer.
| casenmgreen wrote:
| Looking through the repo, reading the doc, an LLM looks to be
| part of the implementation. LLMs cannot explain their
| reasoning, so if there is an LLM, then the system as a whole
| cannot explain its reasoning, because part of the system is a
| black box? reasoning can be explained up to the point the LLM
| comes into play, and also then afterwards, with whatever is
| done with LLM output?
| curl-up wrote:
| Can you explain your reasoning?
| BizarroLand wrote:
| Is there a plan to allow localhosting with ollama or pinokio or
| llmstudio?
___________________________________________________________________
(page generated 2025-04-10 23:01 UTC)