Towards Message Brokers for Generative AI: Survey, Challenges, and Opportunities

TL;DR

This survey addresses the escalating data-communication needs of GenAI, arguing that robust pub/sub message brokers are critical infrastructure across the computing continuum. It systematically evaluates traditional and modern brokers—distinguishing open-source vs proprietary options and priority-support capabilities—and analyzes their fit for GenAI workloads. The paper then maps a spectrum of GenAI-enhancement strategies, including semantic communication, dynamic data/model management, training acceleration, model compression, dynamic orchestration, and MLOps/AIOps, highlighting both opportunities and limitations. By outlining concrete enhancement pathways and tradeoffs, the work provides a foundation for designing GenAI-ready broker frameworks that can scale with increasingly data-intensive AI applications.

Abstract

In today's digital world, Generative Artificial Intelligence (GenAI) such as Large Language Models (LLMs) is becoming increasingly prevalent, extending its reach across diverse applications. This surge in adoption has sparked a significant increase in demand for data-centric GenAI models, highlighting the necessity for robust data communication infrastructures. Central to this need are message brokers, which serve as essential channels for data transfer within various system components. This survey aims to delve into a comprehensive analysis of traditional and modern message brokers, offering a comparative study of prevalent platforms. Our study considers numerous criteria including, but not limited to, open-source availability, integrated monitoring tools, message prioritization mechanisms, capabilities for parallel processing, reliability, distribution and clustering functionalities, authentication processes, data persistence strategies, fault tolerance, and scalability. Furthermore, we explore the intrinsic constraints that the design and operation of each message broker might impose, recognizing that these limitations are crucial in understanding their real-world applicability. Finally, this study examines the enhancement of message broker mechanisms specifically for GenAI contexts, emphasizing the criticality of developing a versatile message broker framework. Such a framework would be poised for quick adaptation, catering to the dynamic and growing demands of GenAI in the foreseeable future. Through this dual-pronged approach, we intend to contribute a foundational compendium that can guide future innovations and infrastructural advancements in the realm of GenAI data communication.

Figures (7)

• Figure 1: The Publish/Subscribe paradigm.
• Figure 2: The timeline of message broker evolution from 1990 to present.
• Figure 3: The overall architecture of a GenAI agent, with possible integration points with message brokers.
• Figure 4: Benefits provided by integrating a message broker with a GenAI agent.
• Figure 5: GenAI for Message Brokers. This diagram illustrates how GenAI enhances traditional AI capabilities within a message broker system, optimizing routing decisions, error detection, and resource scaling based on real-time data analysis and predictive insights.