How deeply does Knowledge Graphs and LLMs in Action cover knowledge graph-enhanced document retriever?

Explains entity- and relationship-based selection and shows a partial Neo4j tool implementation, without detailing full agent orchestration.

Knowledge graph-enhanced document retriever

As explained in Knowledge Graphs and LLMs in Action

A document-retrieval technique that uses knowledge-graph entities and relationships to select documents associated with the requested information.

A knowledge graph-enhanced document retriever selects documents through graph-linked entities and relationships rather than semantic similarity alone. In a text-paired graph, it can return only documents mentioning every entity in a question or a specified relationship, reducing vector-search failures and irrelevant context. section 13.4.3

A practical retrieval pipeline:

Identify the entities or relationship requested by the user. section 13.4.3
Match those graph elements to documents through traced entity and relationship links. section 13.4.3

Cross-source retrieval

To answer a question about a criminal group leader’s transactions, retrieve the person’s name from a law-enforcement knowledge graph, then search financial documents for that entity. section 13.4.3

How Knowledge Graphs and LLMs in Action covers it

Cover of Knowledge Graphs and LLMs in Action

liveBook manning.com

Read Knowledge Graphs and LLMs in Action on liveBook Get the book at manning.com

Related concepts

text-paired graphused by · A text-paired graph is a graph associated with documents or other textual resources and their metadata.
similarity searchcontrasts with · Similarity search is a retrieval technique that finds or ranks items by comparing their representations with a query according to a similarity or distance measure.

This explainer was generated by Manning's knowledge graph from the text of Knowledge Graphs and LLMs in Action. The section links point to the parts of the book it draws on.