Retrieval-Augmented Generation in Industry: An Interview Study on Use Cases, Requirements, Challenges, and Evaluation

TL;DR

This study explores how industry practitioners adopt Retrieval-Augmented Generation (RAG), highlighting use cases, requirements, challenges, and evaluation practices through interviews, revealing that RAG is mainly used for domain-specific QA and faces practical hurdles.

Contribution

It provides the first comprehensive industry-focused analysis of RAG application, detailing real-world use cases, system requirements, challenges, and evaluation methods from practitioner interviews.

Findings

RAG is mainly used for domain-specific question answering.

Systems are mostly in prototype stages.

Evaluation is primarily human-based.

Abstract

Retrieval-Augmented Generation (RAG) is a well-established and rapidly evolving field within AI that enhances the outputs of large language models by integrating relevant information retrieved from external knowledge sources. While industry adoption of RAG is now beginning, there is a significant lack of research on its practical application in industrial contexts. To address this gap, we conducted a semistructured interview study with 13 industry practitioners to explore the current state of RAG adoption in real-world settings. Our study investigates how companies apply RAG in practice, providing (1) an overview of industry use cases, (2) a consolidated list of system requirements, (3) key challenges and lessons learned from practical experiences, and (4) an analysis of current industry evaluation methods. Our main findings show that current RAG applications are mostly limited to domain-specific QA tasks, with systems still in prototype stages; industry requirements focus primarily on data protection, security, and quality, while issues such as ethics, bias, and scalability receive less attention; data preprocessing remains a key challenge, and system evaluation is predominantly conducted by humans rather than automated methods.