Optimizing Retrieval Augmented Generation Architectures for Enterprise AI Applications

Venkata Ramana Reddy Kandula ()

Journal of Artificial Intelligence General science (JAIGS) ISSN:3006-4023, 2024, vol. 6, issue 1, 672-678

Abstract: Retrieval-Augmented Generation (RAG) has emerged as a powerful paradigm for enhancing enterprise AI applications by integrating large-scale knowledge retrieval with generative AI models. Optimizing RAG architectures is critical to improving efficiency, accuracy, and scalability in enterprise settings. This paper explores key strategies for enhancing RAG-based systems, including efficient document indexing, adaptive retrieval mechanisms, model fine-tuning, and latency reduction techniques. We analyze the impact of these optimizations on performance metrics such as response relevance, computational cost, and user satisfaction. Furthermore, we present case studies demonstrating the application of optimized RAG architectures in enterprise AI solutions, such as customer support automation, knowledge management, and decision support systems. Our findings provide actionable insights for deploying robust and efficient RAG systems tailored to enterprise requirements.

Keywords: Retrieval-Augmented Generation; RAG Optimization; Enterprise AI; Knowledge Retrieval; AI Architectures; Generative AI (search for similar items in EconPapers)
Date: 2024
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://newjaigs.com/index.php/JAIGS/article/view/324 (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:das:njaigs:v:6:y:2024:i:1:p:672-678:id:324

Access Statistics for this article

Journal of Artificial Intelligence General science (JAIGS) ISSN:3006-4023 is currently edited by Justyna Żywiołek

More articles in Journal of Artificial Intelligence General science (JAIGS) ISSN:3006-4023 from Open Knowledge
Bibliographic data for series maintained by Open Knowledge ().