Pursuing Best Industrial Practices for Retrieval-Augmented Generation in the Medical Domain

TL;DR

This paper analyzes and proposes best practices for building retrieval-augmented generation systems in the medical domain, focusing on component organization, implementation, and performance trade-offs.

Contribution

It provides a systematic analysis of RAG components and evaluates practical alternatives to establish industry best practices in the medical field.

Findings

Identifies optimal component configurations for RAG systems

Reveals trade-offs between performance and efficiency in RAG implementations

Provides guidelines for practical deployment in medical applications

Abstract

While retrieval augmented generation (RAG) has been swiftly adopted in industrial applications based on large language models (LLMs), there is no consensus on what are the best practices for building a RAG system in terms of what are the components, how to organize these components and how to implement each component for the industrial applications, especially in the medical domain. In this work, we first carefully analyze each component of the RAG system and propose practical alternatives for each component. Then, we conduct systematic evaluations on three types of tasks, revealing the best practices for improving the RAG system and how LLM-based RAG systems make trade-offs between performance and efficiency.