FastRAG: Retrieval Augmented Generation for Semi-structured Data

TL;DR

FastRAG is a new retrieval-augmented generation method tailored for semi-structured network data, combining schema and script learning with knowledge graph querying to enhance accuracy and efficiency over existing approaches.

Contribution

FastRAG introduces a novel approach that leverages schema and script learning along with KG querying, addressing limitations of prior RAG methods for semi-structured data.

Findings

Achieves up to 90% improvement in processing time.

Reduces retrieval costs by up to 85%.

Provides accurate question answering on complex network data.

Abstract

Efficiently processing and interpreting network data is critical for the operation of increasingly complex networks. Recent advances in Large Language Models (LLM) and Retrieval-Augmented Generation (RAG) techniques have improved data processing in network management. However, existing RAG methods like VectorRAG and GraphRAG struggle with the complexity and implicit nature of semi-structured technical data, leading to inefficiencies in time, cost, and retrieval. This paper introduces FastRAG, a novel RAG approach designed for semi-structured data. FastRAG employs schema learning and script learning to extract and structure data without needing to submit entire data sources to an LLM. It integrates text search with knowledge graph (KG) querying to improve accuracy in retrieving context-rich information. Evaluation results demonstrate that FastRAG provides accurate question answering, while improving up to 90% in time and 85% in cost compared to GraphRAG.