Graphs RAG at Scale: Beyond Retrieval-Augmented Generation With Labeled Property Graphs and Resource Description Framework for Complex and Unknown Search Spaces

TL;DR

This paper introduces Graph RAG, a novel framework combining Labeled Property Graph and RDF architectures to improve retrieval-augmented generation for complex, semi-structured, and unknown search spaces, outperforming traditional methods.

Contribution

The paper presents an end-to-end Graph RAG framework that enables dynamic document retrieval, seamless integration of semi-structured data, and real-time translation of text queries to Cypher with high accuracy.

Findings

Graph RAG outperforms traditional embedding-based RAG in accuracy and response quality.

Achieves over 90% accuracy in translating text queries to Cypher.

Effectively handles complex, semi-structured search tasks.

Abstract

Recent advances in Retrieval-Augmented Generation (RAG) have revolutionized knowledge-intensive tasks, yet traditional RAG methods struggle when the search space is unknown or when documents are semi-structured or structured. We introduce a novel end-to-end Graph RAG framework that leverages both Labeled Property Graph (LPG) and Resource Description Framework (RDF) architectures to overcome these limitations. Our approach enables dynamic document retrieval without the need to pre-specify the number of documents and eliminates inefficient reranking. We propose an innovative method for converting documents into RDF triplets using JSON key-value pairs, facilitating seamless integration of semi-structured data. Additionally, we present a text to Cypher framework for LPG, achieving over 90% accuracy in real-time translation of text queries to Cypher, enabling fast and reliable query generation suitable for online applications. Our empirical evaluation demonstrates that Graph RAG significantly outperforms traditional embedding-based RAG in accuracy, response quality, and reasoning, especially for complex, semi-structured tasks. These findings establish Graph RAG as a transformative solution for next-generation retrieval-augmented systems.