- 🔌 [**PageIndex MCP**](https://pageindex.ai/mcp): Bring PageIndex into Claude, Cursor, or any MCP-enabled agent. Chat with long PDFs the reasoning-based, human-like way.
* 🧩 [**“PageIndex: Next-Gen Vectorless, Reasoning-based RAG”**](https://pageindex.ai/blog/pageindex-intro): Introduces the **PageIndex** framework — an **agentic in-context index** that enables LLMs to perform **reasoning-based, human-like retrieval** over long documents, without vectors or chunking.
* 🧾 [**“Do We Still Need OCR?”**](https://pageindex.ai/blog/do-we-need-ocr): Explores how vision-based, reasoning-native RAG challenges the traditional OCR pipeline — and why the future of document AI might be *vectorless* and *vision-based*.
#### 🧪 **Cookbooks:**
* [**Vectorless RAG**](https://github.com/VectifyAI/PageIndex/blob/main/cookbook/pageindex_RAG_simple.ipynb): A minimal, hands-on example of reasoning-based RAG using **PageIndex** — no vectors, no chunking, and human-like retrieval.
* [**Vision-based Vectorless RAG**](https://github.com/VectifyAI/PageIndex/blob/main/cookbook/vision_RAG_pageindex.ipynb): Experience OCR-free document understanding through PageIndex’s visual retrieval workflow — retrieving and reasoning directly over PDF page images.
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](https://vectify.ai/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:
- **Transparent Retrieval Process**: Retrieval based on reasoning — traceable and interpretable. Say goodbye to approximate vector search ("vibe retrieval").
PageIndex powers a reasoning-based RAG system that achieved [98.7% accuracy](https://github.com/VectifyAI/Mafin2.5-FinanceBench) on FinanceBench, showing state-of-the-art performance in professional document analysis (see our [blog post](https://vectify.ai/blog/Mafin2.5) for details).
- Try the [_**Vectorless RAG Notebook**_](https://github.com/VectifyAI/PageIndex/blob/main/cookbook/pageindex_RAG_simple.ipynb) — a *minimal*, hands-on example of reasoning-based RAG using **PageIndex**.
- Experiment with the [*Vision-based Vectorless RAG*](https://github.com/VectifyAI/PageIndex/blob/main/cookbook/vision_RAG_pageindex.ipynb) — no OCR; a minimal, reasoning-native RAG pipeline that works directly over page images.
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](https://github.com/VectifyAI/PageIndex/tree/main/tests/pdfs) and [generated trees](https://github.com/VectifyAI/PageIndex/tree/main/tests/results).
You can either generate the PageIndex tree structure with this open-source repo, or try our ☁️ **Cloud Service** — instantly accessible via our 🚀 [Agent](https://chat.pageindex.ai/), 🖥️ [Dashboard](https://dash.pageindex.ai/) or 🔌 [API](https://docs.pageindex.ai/quickstart).
> 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](https://pageindex.ai/blog/ocr), which is designed to preserve the original hierarchy, to convert the PDF to a markdown file and then use this function.
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 parse 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](https://dash.pageindex.ai/).
[Mafin 2.5](https://vectify.ai/mafin) 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**](https://vectify.ai/blog/Mafin2.5) on the [FinanceBench](https://arxiv.org/abs/2311.11944) 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](https://github.com/VectifyAI/Mafin2.5-FinanceBench) and our [blog post](https://vectify.ai/blog/Mafin2.5) for detailed comparisons and performance metrics.
- 🧪 Browse the [Cookbooks](https://docs.pageindex.ai/cookbook/vectorless-rag-pageindex) for practical recipes and advanced use cases.
- ⚙️ Refer to the [MCP setup](https://pageindex.ai/mcp#quick-setup) or [API docs](https://docs.pageindex.ai/quickstart) for integration details and configuration options.
