DOLLmC: DevOps for Large Language model Customization

TL;DR

This paper introduces DOLLmC, a DevOps framework tailored for large language model customization, integrating ontologies and prompt engineering to improve deployment, continuous learning, and version control, demonstrated through an agricultural chatbot.

Contribution

The paper presents a novel DevOps-based framework for LLM customization that incorporates knowledge maps and prompt engineering, enhancing scalability and operational efficiency.

Findings

Effective domain-specific chatbot development for agriculture

Enhanced LLM deployment and version control processes

Framework promotes scalability and continuous learning

Abstract

The rapid integration of Large Language Models (LLMs) into various industries presents both revolutionary opportunities and unique challenges. This research aims to establish a scalable and efficient framework for LLM customization, exploring how DevOps practices should be adapted to meet the specific demands of LLM customization. By integrating ontologies, knowledge maps, and prompt engineering into the DevOps pipeline, we propose a robust framework that enhances continuous learning, seamless deployment, and rigorous version control of LLMs. This methodology is demonstrated through the development of a domain-specific chatbot for the agricultural sector, utilizing heterogeneous data to deliver actionable insights. The proposed methodology, so called DOLLmC, not only addresses the immediate challenges of LLM customization but also promotes scalability and operational efficiency. However, the methodology's primary limitation lies in the need for extensive testing, validation, and broader adoption across different domains.