📄🧠 PageIndex: Document Index for Reasoning-based RAG

Reasoning-based RAG  ◦  No Vector DB  ◦  No Chunking  ◦  Human-like Retrieval

🏠 Homepage  •   🚀 Agent  •   🔌 MCP  •   🖥️ Dashboard  •   📚 API  •   💬 Discord  •   ✉️ Contact 

• 📑 PageIndex Chat: The world's first human-like document analyst agent, designed for professional long documents.
• 🔌 PageIndex MCP: Bring PageIndex into Claude, Cursor, or any MCP-enabled agents. Chat to long PDFs the human-like, reasoning-based way 📖

Are you frustrated with vector database retrieval accuracy for long professional documents? Traditional vector-based RAG relies on semantic similarity rather than true relevance. But similarity ≠ relevance — what we truly need in retrieval is relevance, and that requires reasoning. When working with professional documents that demand domain expertise and multi-step reasoning, similarity search often falls short.

Inspired by AlphaGo, we propose PageIndex, a reasoning-based RAG system that builds a tree index over long documents and reasons over that index for retrieval. It simulates how human experts navigate and extract knowledge from long documents through tree search, enabling LLMs to think and reason their way to the most relevant document sections. It performs retrieval in two steps:

1. Generate a "Table-of-Contents" tree structure index of documents
2. Perform reasoning-based retrieval through tree search

Compared to traditional vector-based RAG, PageIndex features:

• No Vectors Needed: Uses document structure and LLM reasoning for retrieval.
• No Chunking Needed: Documents are organized into natural sections, not artificial chunks.
• Human-like Retrieval: Simulates how human experts navigate and extract knowledge from complex documents.
• Transparent Retrieval Process: Retrieval based on reasoning — say goodbye to approximate vector search ("vibe retrieval").

PageIndex powers a reasoning-based RAG system that achieved 98.7% accuracy on FinanceBench, showing state-of-the-art performance in professional document analysis (see our blog post for details).

• 🛠️ Self-host — run locally with this open-source repo
• ☁️ Cloud Service — try instantly with our 🚀 Agent, 🖥️ Dashboard or 🔌 API, no setup required

Check out this simple Vectorless RAG Notebook — a minimal, hands-on, reasoning-based RAG pipeline using PageIndex.

PageIndex can transform lengthy PDF documents into a semantic tree structure, similar to a "table of contents" but optimized for use with Large Language Models (LLMs). It's ideal for: financial reports, regulatory filings, academic textbooks, legal or technical manuals, and any document that exceeds LLM context limits.

Here is an example output. See more example documents and generated trees.

...
{
  "title": "Financial Stability",
  "node_id": "0006",
  "start_index": 21,
  "end_index": 22,
  "summary": "The Federal Reserve ...",
  "nodes": [
    {
      "title": "Monitoring Financial Vulnerabilities",
      "node_id": "0007",
      "start_index": 22,
      "end_index": 28,
      "summary": "The Federal Reserve's monitoring ..."
    },
    {
      "title": "Domestic and International Cooperation and Coordination",
      "node_id": "0008",
      "start_index": 28,
      "end_index": 31,
      "summary": "In 2023, the Federal Reserve collaborated ..."
    }
  ]
}
...

You can either generate the PageIndex tree structure with this open-source repo or try our ☁️ Cloud Service — instantly accessible via our 🚀 Agent, 🖥️ Dashboard or 🔌 API, with no setup required.

You can follow these steps to generate a PageIndex tree from a PDF document.

pip3 install --upgrade -r requirements.txt

Create a .env file in the root directory and add your API key:

CHATGPT_API_KEY=your_openai_key_here

python3 run_pageindex.py --pdf_path /path/to/your/document.pdf

--model                 OpenAI model to use (default: gpt-4o-2024-11-20)
--toc-check-pages       Pages to check for table of contents (default: 20)
--max-pages-per-node    Max pages per node (default: 10)
--max-tokens-per-node   Max tokens per node (default: 20000)
--if-add-node-id        Add node ID (yes/no, default: yes)
--if-add-node-summary   Add node summary (yes/no, default: yes)
--if-add-doc-description Add doc description (yes/no, default: yes)

python3 run_pageindex.py --md_path /path/to/your/document.md

This repo is designed for generating PageIndex tree structure for simple PDFs, but many real-world use cases involve complex PDFs that are hard to parsed by classic python tools. However, extracting high-quality text from PDF documents remains a non-trivial challenge. Most OCR tools only extract page-level content, losing the broader document context and hierarchy.

To address this, we introduced PageIndex OCR — the first long-context OCR model designed to preserve the global structure of documents. PageIndex OCR significantly outperforms other leading OCR tools, such as those from Mistral and Contextual AI, in recognizing true hierarchy and semantic relationships across document pages.

• Experience next-level OCR quality with PageIndex OCR at our Dashboard.
• Integrate seamlessly PageIndex OCR into your stack via our API.

Mafin 2.5 is a state-of-the-art reasoning-based RAG model designed specifically for financial document analysis. Powered by PageIndex, it achieved a market-leading 98.7% accuracy on the FinanceBench benchmark — significantly outperforming traditional vector-based RAG systems.

PageIndex's hierarchical indexing enabled precise navigation and extraction of relevant content from complex financial reports, such as SEC filings and earnings disclosures.

👉 See the full benchmark results and our blog post for detailed comparisons and performance metrics.

• 📖 Explore our Tutorials for practical guides and strategies, including Document Search and Tree Search.
• 🧪 Browse the Cookbook for practical recipes and advanced use cases.
• ⚙️ Refer to the API Documentation for integration details and configuration options.

Leave a star if you like our project. Thank you!

© 2025 Vectify AI