📑 What is PageIndex?
PageIndex is a vectorless, reasoning-based RAG (retrieval) framework that simulates how human experts navigate and extract knowledge from long, complex documents. Instead of relying on vector similarity search, it transforms documents into a tree structure and enables LLMs to perform agentic reasoning over that tree for context-aware retrieval. The retrieval is traceable and explainable, and requires no vector database and no chunking.
PageIndex Workflow: Tree index generation; and agentic LLM reasoning over the index for context-aware retrieval
Analyze and chat with your documents, directly in your browser
Integrate PageIndex into your agents or applications, via MCP or API
Dedicated cluster, or private deployment in your VPC for organizations
To learn more about PageIndex, please see a detailed introduction to the PageIndex framework . Also check out our GitHub repo for open-source code, and the cookbooks, tutorials, and blog for more usage guides and examples.