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

TL;DR

This paper reports on the development and evaluation of five real-world domain-specific RAG systems, providing empirical insights into their design, deployment, and user feedback across diverse applications.

Contribution

It offers a systematic study of RAG system implementation in real-world scenarios, including lessons learned and evaluation results involving user feedback.

Findings

User feedback identified key usability and reliability challenges.

Deployment across diverse domains demonstrates RAG adaptability.

Systematic documentation of lessons informs future RAG development.

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.