---
title: "PageIndex"
type: "tool"
slug: "vectifyai-pageindex"
canonical_url: "https://www.graphcanon.com/tools/vectifyai-pageindex"
github_url: "https://github.com/VectifyAI/PageIndex"
homepage_url: "https://pageindex.ai"
stars: 33857
forks: 2961
primary_language: "Python"
license: "MIT"
categories: ["ai-agents", "data-retrieval"]
tags: ["agents", "llm", "reasoning", "rag", "agentic-ai", "retrieval-augmented-generation"]
updated_at: "2026-07-07T18:20:32.896697+00:00"
---
# PageIndex
> PropertyParams π PageIndex: Document Index for Vectorless, Reasoning-based RAG
PageIndex is a Python repository designed for reasoning-based Retrieval-Augmented Generation (RAG) without using vector databases or document chunking. It offers context-aware retrieval and aims to simulate human-like reading and comprehension of documents.
## Facts
- Repository: https://github.com/VectifyAI/PageIndex
- Homepage: https://pageindex.ai
- Stars: 33,857 Β· Forks: 2,961 Β· Open issues: 134 Β· Watchers: 140
- Primary language: Python
- License: MIT
- Last pushed: 2026-07-07T10:25:14+00:00
## Categories
- [AI Agents](/categories/ai-agents.md)
- [Data & Retrieval](/categories/data-retrieval.md)
## Tags
agents, llm, reasoning, rag, agentic-ai, retrieval-augmented-generation
## Related tools
- [ECC](/tools/affaan-m-ecc.md) - The agent harness performance optimization system (β
226,962)
- [hermes-agent](/tools/nousresearch-hermes-agent.md) - The self-improving AI agent built by Nous Research (β
210,880)
- [AutoGPT](/tools/significant-gravitas-autogpt.md) - AutoGPT: Build, Deploy, and Run AI Agents (β
185,417)
- [ollama](/tools/ollama-ollama.md) - Get up and running with Kimi-K2.6, GLM-5.1, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models. (β
175,659)
- [transformers](/tools/huggingface-transformers.md) - π€ Transformers: the model-definition framework for state-of-the-art machine learning models (β
162,347)
- [langflow](/tools/langflow-ai-langflow.md) - Langflow is a powerful platform for building and deploying AI-powered agents and workflows. (β
151,298)
- [dify](/tools/langgenius-dify.md) - Production-ready platform for agentic workflow development (β
148,070)
- [firecrawl](/tools/firecrawl-firecrawl.md) - The API to search, scrape, and interact with the web at scale. (β
147,117)
## README (excerpt)
```text
# PageIndex: Vectorless, Reasoning-based RAG
Reasoning-based RAG β¦ No Vector DB, No Chunking β¦ Context-Aware Retrieval β¦ Reads Like a Human
π’ Updates
- π₯ [**Agentic Vectorless RAG**](https://github.com/VectifyAI/PageIndex/blob/main/examples/agentic_vectorless_rag_demo.py) β A simple agentic, vectorless RAG [example](#-agentic-vectorless-rag-an-example) with *self-hosted PageIndex*, using OpenAI Agents SDK.
- [**Scale PageIndex to Millions of Documents**](https://pageindex.ai/blog/pageindex-filesystem) β *PageIndex File System* is a file-level tree indexing layer that lets PageIndex reason over an entire corpus, not just a single document, enabling massive-scale document search.
- [PageIndex Chat](https://chat.pageindex.ai) β Human-like document analysis agent [platform](https://chat.pageindex.ai) for professional long documents. Also available via [MCP](https://pageindex.ai/developer) or [API](https://pageindex.ai/developer).
- [PageIndex Framework](https://pageindex.ai/blog/pageindex-intro) β Deep dive into PageIndex: an *agentic, in-context tree index* that enables LLMs to perform *reasoning-based, context-aware retrieval* over long documents.
---
# π 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 β relevance** β what we truly need in retrieval is **relevance**, and that requires **reasoning**. When working with professional documents that demand *contextual understanding*, domain expertise, and multi-step reasoning, similarity search often falls short β missing what's relevant but not similar, and returning what's similar yet not relevant.
Inspired by AlphaGo, we propose **[PageIndex](https://vectify.ai/pageindex)** β a **vectorless**, **reasoning-based RAG** system that builds a **hierarchical tree index** from long documents, and uses LLMs to **reason** *over that index* for **agentic, context-aware retrieval**. The retrieval is *traceable* and *explainable*, with no vector DBs or chunking.
PageIndex 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 βTable-of-Contentsβ **tree structure index** of documents
2. Perform (agentic) reasoning-based retrieval through **tree search**
### π― Core Features
> PageIndex is a vectorless, reasoning-based RAG engine that mirrors how humans read, delivering traceable, explainable, and context-aware retrieval, without vector datab
```
---
**Machine-readable endpoints**
- JSON: [`/api/graphcanon/tools/vectifyai-pageindex`](/api/graphcanon/tools/vectifyai-pageindex)
- LLM index: [/llms.txt](/llms.txt)
- Full corpus: [/llms-full.txt](/llms-full.txt)
_GraphCanon - The knowledge graph for AI development. https://www.graphcanon.com/_