cd /news/artificial-intelligence/pageindex-emerges-as-vectorless-rag-… · home › topics › artificial-intelligence › article
[ARTICLE · art-141636] src=x.com ↗ pub= topic=artificial-intelligence verified=true sentiment=· neutral

PageIndex Emerges as Vectorless RAG Alternative for AI Retrieval

PageIndex, a vectorless retrieval-augmented generation approach that builds a hierarchical tree from a document's natural structure instead of using embeddings, chunking, or vector search, reached 98.7% accuracy on FinanceBench through the Mafin 2.5 system built on it, according to a summary of posts on X. That figure compares with 45% for Perplexity and 31% for GPT-4o on the same benchmark, though commenters noted FinanceBench mainly tests questions answered from a single document and called for an ablation isolating the tree index. Developers praised PageIndex for structured documents such as financial filings and technical manuals while debating its scalability, latency, and fit for broader searches.

by read2 min views1 publishedSep 29, 2026
PageIndex Emerges as Vectorless RAG Alternative for AI Retrieval
Image: source

PageIndex Emerges as Vectorless RAG Alternative for AI Retrieval

Last updated Sep 28, 2026

PageIndex builds a hierarchical tree from a document's natural structure, skipping embeddings, chunking, and vector searches. An LLM then reasons through the tree using summaries and titles for precise retrieval. On FinanceBench, the Mafin 2.5 system hit 98.7% accuracy—well above vector-based tools like Perplexity at 45% or GPT-4o at 31%—while preserving context and explainability for financial filings and technical manuals. Developers praise its potential for structured docs but debate scalability, latency, and fit for broader searches.

This story is a summary of posts on X and may evolve over time. Grok can make mistakes, verify its outputs.

The entire RAG industry is about to get cooked. Researchers developed a new RAG approach that bypasses almost everything traditional RAG depends on.

  • No vector DB
  • No data embeddings
  • No chunking
  • No similarity search It's called PageIndex. Instead of splitting yourShow more

The entire RAG industry is about to get cooked. Researchers developed a new RAG approach that bypasses almost everything traditional RAG depends on.

  • No vector DB
  • No data embeddings
  • No chunking
  • No similarity search It's called PageIndex. Instead of splitting yourShow more

Obviously you can replace a reranker with Jev But I don't see how you replace embeddings (i.e. first-cut search) unless your dataset is so small that you never needed embeddings in the first place

98.7% is a result for Mafin 2.5, a full system built on PageIndex. Even its authors say FinanceBench mainly tests questions answered from a single document. Show me an ablation proving the tree index caused the gain, plus a matched comparison against strong hybrid RAG onShow more

55

1.1K1.1K

Been wanting people to use Jev for this for a while now :) Semantic hierarchical search! just like a human would. check out our hierarchical classification cookbook

The entire RAG industry is about to get cooked. Researchers developed a new RAG approach that bypasses almost everything traditional RAG depends on.

  • No vector DB
  • No data embeddings
  • No chunking
  • No similarity search It's called PageIndex. Instead of splitting yourShow more
── more in #artificial-intelligence 4 stories · sorted by recency
── more on @pageindex 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
→ Live at https://your-agent.zahid.host ✓
Get free account → Pricing
from €0/mo · no card required
LIVE [news/pageindex-emerges-as…] indexed:0 read:2min 2026-09-29 · —