RGL: A Graph-Centric, Modular Framework for Efficient Retrieval-Augmented Generation on Graphs

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Yuan, Hu, Jun, Jiang, Jiaxin, Liu, Zemin, Hooi, Bryan, He, Bingsheng
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908283732754432
author Li, Yuan
Hu, Jun
Jiang, Jiaxin
Liu, Zemin
Hooi, Bryan
He, Bingsheng
author_facet Li, Yuan
Hu, Jun
Jiang, Jiaxin
Liu, Zemin
Hooi, Bryan
He, Bingsheng
contents Recent advances in graph learning have paved the way for innovative retrieval-augmented generation (RAG) systems that leverage the inherent relational structures in graph data. However, many existing approaches suffer from rigid, fixed settings and significant engineering overhead, limiting their adaptability and scalability. Additionally, the RAG community has largely overlooked the decades of research in the graph database community regarding the efficient retrieval of interesting substructures on large-scale graphs. In this work, we introduce the RAG-on-Graphs Library (RGL), a modular framework that seamlessly integrates the complete RAG pipeline-from efficient graph indexing and dynamic node retrieval to subgraph construction, tokenization, and final generation-into a unified system. RGL addresses key challenges by supporting a variety of graph formats and integrating optimized implementations for essential components, achieving speedups of up to 143x compared to conventional methods. Moreover, its flexible utilities, such as dynamic node filtering, allow for rapid extraction of pertinent subgraphs while reducing token consumption. Our extensive evaluations demonstrate that RGL not only accelerates the prototyping process but also enhances the performance and applicability of graph-based RAG systems across a range of tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2503_19314
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle RGL: A Graph-Centric, Modular Framework for Efficient Retrieval-Augmented Generation on Graphs
Li, Yuan
Hu, Jun
Jiang, Jiaxin
Liu, Zemin
Hooi, Bryan
He, Bingsheng
Information Retrieval
Machine Learning
Recent advances in graph learning have paved the way for innovative retrieval-augmented generation (RAG) systems that leverage the inherent relational structures in graph data. However, many existing approaches suffer from rigid, fixed settings and significant engineering overhead, limiting their adaptability and scalability. Additionally, the RAG community has largely overlooked the decades of research in the graph database community regarding the efficient retrieval of interesting substructures on large-scale graphs. In this work, we introduce the RAG-on-Graphs Library (RGL), a modular framework that seamlessly integrates the complete RAG pipeline-from efficient graph indexing and dynamic node retrieval to subgraph construction, tokenization, and final generation-into a unified system. RGL addresses key challenges by supporting a variety of graph formats and integrating optimized implementations for essential components, achieving speedups of up to 143x compared to conventional methods. Moreover, its flexible utilities, such as dynamic node filtering, allow for rapid extraction of pertinent subgraphs while reducing token consumption. Our extensive evaluations demonstrate that RGL not only accelerates the prototyping process but also enhances the performance and applicability of graph-based RAG systems across a range of tasks.
title RGL: A Graph-Centric, Modular Framework for Efficient Retrieval-Augmented Generation on Graphs
topic Information Retrieval
Machine Learning
url https://arxiv.org/abs/2503.19314