From e59f04a6b3291771bf0c6efc3b02260e15e944e6 Mon Sep 17 00:00:00 2001 From: Ray Date: Fri, 19 Dec 2025 05:06:46 +0800 Subject: [PATCH] Update README.md --- README.md | 22 +++++++++++----------- 1 file changed, 11 insertions(+), 11 deletions(-) diff --git a/README.md b/README.md index 4285eaa..ab38426 100644 --- a/README.md +++ b/README.md @@ -30,7 +30,7 @@

📢 Recent Updates

 **🔥 New Releases:** -- [**PageIndex Chat**](https://chat.pageindex.ai): The first human-like document-analysis agent platform built for professional long documents. Could also be integrated via the [MCP](https://pageindex.ai/mcp) or [API](https://docs.pageindex.ai/quickstart) (beta). +- [**PageIndex Chat**](https://chat.pageindex.ai): The first human-like document-analysis agent platform built for professional long documents. It can also be integrated via the [MCP](https://pageindex.ai/mcp) or [API](https://docs.pageindex.ai/quickstart) (beta). @@ -39,15 +39,15 @@ **🧪 Cookbooks:** -- [Vectorless RAG](https://docs.pageindex.ai/cookbook/vectorless-rag-pageindex): A minimal, hands-on example of reasoning-based RAG using **PageIndex** — no vectors, no chunking, and human-like retrieval. -- [Vision-based Vectorless RAG](https://docs.pageindex.ai/cookbook/vision-rag-pageindex): Experience OCR-free document understanding through PageIndex’s visual retrieval workflow that retrieves and reasons directly over PDF page images. +- [Vectorless RAG](https://docs.pageindex.ai/cookbook/vectorless-rag-pageindex): A minimal, hands-on example of reasoning-based RAG using PageIndex — no vectors, no chunking, and human-like retrieval. +- [Vision-based vectorless RAG](https://docs.pageindex.ai/cookbook/vision-rag-pageindex): 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](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: +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. PageIndex performs retrieval in two steps: 1. Generate a "Table-of-Contents" **tree structure index** of documents 2. Perform reasoning-based retrieval through **tree search** @@ -59,7 +59,7 @@ Inspired by AlphaGo, we propose **[PageIndex](https://vectify.ai/pageindex)** ### 🧩 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 Vector DB**: Uses document structure and LLM reasoning for retrieval, instead of vector similarity 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"). @@ -68,7 +68,7 @@ PageIndex powers a reasoning-based RAG system that achieved [98.7% accuracy](htt ### 📍 Explore PageIndex -Please see a detailed introduction of the [PageIndex framework](https://pageindex.ai/blog/pageindex-intro). Check out this GitHub repo for open-source implementations, and our [cookbook](https://docs.pageindex.ai/cookbook) and [tutorials](https://docs.pageindex.ai/tutorials) for more examples. The PageIndex service is available as a ChatGPT-style [chat platform](https://chat.pageindex.ai), or could be integrated via [MCP](https://pageindex.ai/mcp) or [API](https://docs.pageindex.ai/quickstart). +Please see a detailed introduction of the [PageIndex framework](https://pageindex.ai/blog/pageindex-intro). Check out our [GitHub repo](https://github.com/VectifyAI/PageIndex) for open-source code, and [cookbooks](https://docs.pageindex.ai/cookbook) and [tutorials](https://docs.pageindex.ai/tutorials) for additional usage guides and examples. The PageIndex service is available as a ChatGPT-style [chat platform](https://chat.pageindex.ai), or could be integrated via [MCP](https://pageindex.ai/mcp) or [API](https://docs.pageindex.ai/quickstart). ### ⚙️ Deployment Options - 🛠️ Self-host — run locally with this open-source repo. @@ -76,8 +76,8 @@ Please see a detailed introduction of the [PageIndex framework](https://pageinde ### 🧪 Quick Hands-on -- 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. +- 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.
@@ -171,13 +171,13 @@ You can customize the processing with additional optional arguments:
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. +We also provide markdown support for PageIndex. You can use the `-md_path` flag to generate a tree structure for a markdown file. ```bash 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](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. +> Note: 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.
--- @@ -197,7 +197,7 @@ To address this, we introduced PageIndex OCR — the first long-context OCR mode --- --> -# 📈 Case Study: Leading Finance QA Benchmark +# 📈 Case Study: PageIndex Leads Finance QA Benchmark [Mafin 2.5](https://vectify.ai/mafin) is a reasoning-based RAG system for financial document analysis, powered by **PageIndex**. It achieved a state-of-the-art [**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.