Engineering RAG Systems for Real-World Applications: Design, Development, and Evaluation

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

Abstract

Retrieval-Augmented Generation (RAG) systems are emerging as a key approach for grounding Large Language Models (LLMs) in external knowledge, addressing limitations in factual accuracy and contextual relevance. However, there is a lack of empirical studies that report on the development of RAG-based implementations grounded in real-world use cases, evaluated through general user involvement, and accompanied by systematic documentation of lessons learned. This paper presents five domain-specific RAG applications developed for real-world scenarios across governance, cybersecurity, agriculture, industrial research, and medical diagnostics. Each system incorporates multilingual OCR, semantic retrieval via vector embeddings, and domain-adapted LLMs, deployed through local servers or cloud APIs to meet distinct user needs. A web-based evaluation involving a total of 100 participants assessed the systems across six dimensions: (i) Ease of Use, (ii) Relevance, (iii) Transparency, (iv) Responsiveness, (v) Accuracy, and (vi) Likelihood of Recommendation. Based on user feedback and our development experience, we documented twelve key lessons learned, highlighting technical, operational, and ethical challenges affecting the reliability and usability of RAG systems in practice.

Original languageEnglish
Title of host publicationSoftware Engineering and Advanced Applications - 51st Euromicro Conference, SEAA 2025, Proceedings
EditorsDavide Taibi, Darja Smite
PublisherSpringer
Pages143-158
Number of pages16
ISBN (Electronic)978-3-032-04200-2
ISBN (Print)9783032041999
DOIs
Publication statusPublished - 2025
Publication typeA4 Article in conference proceedings
EventEuromicro Conference on Software Engineering and Advanced Applications - Salerno, Italy
Duration: 10 Sept 202512 Sept 2025

Publication series

NameLecture Notes in Computer Science
Volume16082 LNCS
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

ConferenceEuromicro Conference on Software Engineering and Advanced Applications
Country/TerritoryItaly
CitySalerno
Period10/09/2512/09/25

Keywords

  • AI System Lifecycle
  • Empirical Software Engineering
  • Generative AI
  • Human Centred Evaluation
  • LLMs
  • RAG
  • System Design
  • System Implementation

Publication forum classification

  • Publication forum level 1

ASJC Scopus subject areas

  • Theoretical Computer Science
  • General Computer Science

Fingerprint

Dive into the research topics of 'Engineering RAG Systems for Real-World Applications: Design, Development, and Evaluation'. Together they form a unique fingerprint.

Cite this