PageIndex/README.md

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

🏠 Homepage  •   🖥️ Chat Platform  •   🔌 MCP  •   📚 API Docs  •   💬 Discord  •   ✉️ Contact 

---

📢 Recent Updates

🔥 New Releases:

• PageIndex Chat: The first human-like document-analysis agent platform built for professional long documents. Could also be integrated via the MCP or API (beta).

✍️ Articles:

• PageIndex Framework: Introduces the PageIndex framework — an agentic, in-context tree index that enables LLMs to perform reasoning-based, human-like retrieval over long documents, without vector DB or chunking.

🧪 Cookbooks:

• Vectorless RAG: A minimal, hands-on example of reasoning-based RAG using PageIndex — no vectors, no chunking, and human-like retrieval.
• Vision-based Vectorless RAG: Experience OCR-free document understanding through PageIndex’s visual retrieval workflow that retrieves and reasons directly over PDF page images.

📑 Introduction to PageIndex

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 vectorless, reasoning-based RAG system that builds a hierarchical tree index for long documents and reasons over that index for retrieval. It simulates how human experts navigate and extract knowledge from complex 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

🧩 Features

Compared to traditional vector-based RAG, PageIndex features:

• No Vector DB: Uses document structure and LLM reasoning for retrieval, instead of vector search.
• No Chunking: Documents are organized into natural sections, not artificial chunks.
• Human-like Retrieval: Simulates how human experts navigate and extract knowledge from complex documents.
• Better Explainability and Traceability: Retrieval is based on reasoning — traceable and interpretable, with page and section references. No more opaque, approximate vector search ("vibe retrieval").

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

📍 Explore PageIndex

Please see a detailed introduction of the PageIndex framework. Check out this GitHub repo for open-source implementations, and our cookbook and tutorials for more examples. The PageIndex service is available as a ChatGPT-style chat platform, or could be integrated via MCP or API.

⚙️ Deployment Options

• 🛠️ Self-host — run locally with this open-source repo.
• ☁️ Cloud Service — try instantly with our 🖥️ Chat Platform, 🔌 MCP or 📚 API.

🧪 Quick Hands-on

• Try the Vectorless RAG Notebook — a minimal, hands-on example of reasoning-based RAG using PageIndex.
• Experiment with the Vision-based Vectorless RAG — no OCR; a minimal, reasoning-native RAG pipeline that works directly over page images.

  

---

🌲 PageIndex Tree Structure

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 API service.

---

📦 Package Usage

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

1. Install dependencies

pip3 install --upgrade -r requirements.txt

2. Set your OpenAI API key

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

CHATGPT_API_KEY=your_openai_key_here

3. Run PageIndex on your PDF

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

Optional parameters

You can customize the processing with additional optional arguments:

--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)

Markdown support

We also provide a markdown support for PageIndex. You can use the `-md_path` flag to generate a tree structure for a markdown file.

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

Notice: in this function, we use "#" to determine node heading and their levels. For example, "##" is level 2, "###" is level 3, etc. Make sure your markdown file is formatted correctly. If your Markdown file was converted from a PDF or HTML, we don’t recommend using this function, since most existing conversion tools cannot preserve the original hierarchy. Instead, use our PageIndex OCR, which is designed to preserve the original hierarchy, to convert the PDF to a markdown file and then use this function.

---

📈 Case Study: Leading Finance QA Benchmark

Mafin 2.5 is a reasoning-based RAG system for financial document analysis, powered by PageIndex. It achieved a state-of-the-art 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.

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

---

🧭 Resources

• 📖 Tutorials: practical guides and strategies, including Document Search and Tree Search.
• 🧪 Cookbooks: hands-on, runnable examples and advanced use cases.
• 📝 Blog: technical articles, research insights, and product updates
• ⚙️ MCP setup & API docs: integration details and configuration options.

---

⭐ Support Us

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

Connect with Us

     

---

© 2025 Vectify AI