liveBook · Manning

PageIndex

As explained in Retrieval Augmented Generation, The Foundational Ideas

PageIndex is a vectorless retrieval approach that builds a hierarchy from a document's native structure and uses an LLM agent to select relevant pages.

PageIndex is a vectorless retrieval approach for documents with reliable native structure. It builds a hierarchy from sections, subsections, and page ranges, then lets an LLM agent reason over that tree to select relevant content. section 10.7.3

Its retrieval workflow exposes focused tools to the agent:

Where it fits

Apply PageIndex to research papers, manuals, and contracts when their structural boundaries are clean. Avoid relying on it for unstructured prose, where little inherent hierarchy exists to guide the agent. section 10.7.3

By removing embeddings, clustering, and generated summaries, PageIndex avoids summary drift and embedding-pipeline complexity. Its tradeoff is dependence on clean document structure and agent reasoning at query time. section 10.7.3

How Retrieval Augmented Generation, The Foundational Ideas covers it

How deep it goes
Explains the hierarchy and three retrieval tools, but stops short of implementation details and evaluation results.
Examples
Uses research papers, manuals, and contracts as examples of structurally suitable corpora.
What you can do after
Evaluate whether a structured corpus can support agent-guided page retrieval without embeddings or generated summaries.
How it connects
Connects hierarchical retrieval with vector search, RAPTOR, document structure, and LLM agents.

Related concepts

This explainer was generated by Manning's knowledge graph from the text of Retrieval Augmented Generation, The Foundational Ideas. The section links point to the parts of the book it draws on.