An Agile Method for Implementing Retrieval Augmented Generation Tools in Industrial SMEs

TL;DR

This paper presents EASI-RAG, an agile method to deploy Retrieval-Augmented Generation tools in industrial SMEs, enabling quick, accurate, and reliable NLP solutions despite limited resources.

Contribution

The paper introduces EASI-RAG, a structured, agile method based on method engineering principles for deploying RAG systems in industrial SME environments.

Findings

Rapid deployment within a month by non-experts

High user adoption and accurate responses

Improved data reliability and system trustworthiness

Abstract

Retrieval-Augmented Generation (RAG) has emerged as a powerful solution to mitigate the limitations of Large Language Models (LLMs), such as hallucinations and outdated knowledge. However, deploying RAG-based tools in Small and Medium Enterprises (SMEs) remains a challenge due to their limited resources and lack of expertise in natural language processing (NLP). This paper introduces EASI-RAG, Enterprise Application Support for Industrial RAG, a structured, agile method designed to facilitate the deployment of RAG systems in industrial SME contexts. EASI-RAG is based on method engineering principles and comprises well-defined roles, activities, and techniques. The method was validated through a real-world case study in an environmental testing laboratory, where a RAG tool was implemented to answer operators queries using data extracted from operational procedures. The system was deployed in under a month by a team with no prior RAG experience and was later iteratively improved based on user feedback. Results demonstrate that EASI-RAG supports fast implementation, high user adoption, delivers accurate answers, and enhances the reliability of underlying data. This work highlights the potential of RAG deployment in industrial SMEs. Future works include the need for generalization across diverse use cases and further integration with fine-tuned models.