loading
Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Paper

Don't Train, Just Prompt: Towards a Prompt Engineering Approach for a More Generative Container Orchestration Management

Topics: Cloud Management and Operations; Cloud Optimization and Automation; Container Composition and Orchestration; Development Methods for Cloud Applications; Microservices: Automation, Deployment and Management, Resource Allocation Elasticity, Service State and Resilience; Native Cloud Applications; Service Management; Service Modeling and Specification

Authors: Nane Kratzke 1 and André Drews 2

Affiliations: 1 Department of Electrical Engineering and Computer Science, Lübeck University of Applied Sciences, Germany ; 2 Expert Group Artificial Intelligence in Applications, Lübeck University of Applied Sciences, Germany

Keyword(s): Prompt Engineering, Large Language Model, cloud-native, Container, Orchestration, Automation, Intelligent, Service Management, Kubernetes, LLM, GPT-3.5, GPT-4, Llama2, Mistral, DevOps.

Abstract: Background: The intricate architecture of container orchestration systems like Kubernetes relies on the critical role of declarative manifest files that serve as the blueprints for orchestration. However, managing these manifest files often presents complex challenges requiring significant DevOps expertise. Methodology: This position paper explores using Large Language Models (LLMs) to automate the generation of Kubernetes manifest files through natural language specifications and prompt engineering, aiming to simplify Kubernetes management. The study evaluates these LLMs using Zero-Shot, Few-Shot, and Prompt-Chaining techniques against DevOps requirements and the ability to support fully automated deployment pipelines. Results show that LLMs can produce Kubernetes manifests with varying degrees of manual intervention, with GPT-4 and GPT-3.5 showing potential for fully automated deployments. Interestingly, smaller models sometimes outperform larger ones, questioning the assumption th at bigger is always better. Conclusion: The study emphasizes that prompt engineering is critical to optimizing LLM outputs for Kubernetes. It suggests further research into prompt strategies and LLM comparisons and highlights a promising research direction for integrating LLMs into automatic deployment pipelines. (More)

CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 3.145.51.115

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Kratzke, N. and Drews, A. (2024). Don't Train, Just Prompt: Towards a Prompt Engineering Approach for a More Generative Container Orchestration Management. In Proceedings of the 14th International Conference on Cloud Computing and Services Science - CLOSER; ISBN 978-989-758-701-6; ISSN 2184-5042, SciTePress, pages 248-256. DOI: 10.5220/0012710300003711

@conference{closer24,
author={Nane Kratzke. and André Drews.},
title={Don't Train, Just Prompt: Towards a Prompt Engineering Approach for a More Generative Container Orchestration Management},
booktitle={Proceedings of the 14th International Conference on Cloud Computing and Services Science - CLOSER},
year={2024},
pages={248-256},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012710300003711},
isbn={978-989-758-701-6},
issn={2184-5042},
}

TY - CONF

JO - Proceedings of the 14th International Conference on Cloud Computing and Services Science - CLOSER
TI - Don't Train, Just Prompt: Towards a Prompt Engineering Approach for a More Generative Container Orchestration Management
SN - 978-989-758-701-6
IS - 2184-5042
AU - Kratzke, N.
AU - Drews, A.
PY - 2024
SP - 248
EP - 256
DO - 10.5220/0012710300003711
PB - SciTePress