Enregistré dans:
Détails bibliographiques
Auteurs principaux: Ueno, Masaru, Uchiumi, Tetsuya
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:https://arxiv.org/abs/2408.11428
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866913475613163520
author Ueno, Masaru
Uchiumi, Tetsuya
author_facet Ueno, Masaru
Uchiumi, Tetsuya
contents Although Kubernetes has become a widespread open-source system that automates the management of containerized applications, its complexity can be a significant barrier, particularly for application developers unfamiliar with it. One approach employs large language models (LLMs) to assist developers in generating Kubernetes manifests; however it is currently impossible to determine whether the output satisfies given specifications and is comprehensible. In this study, we proposed a benchmarking method for evaluating the effectiveness of LLMs in synthesizing manifests, using the Compose specification -- a standard widely adopted by application developers -- as input. The proposed benchmarking method revealed that LLMs generally produce accurate results that compensate for simple specification gaps. However, we also observed that inline comments for readability were often omitted, and completion accuracy was low for atypical inputs with unclear intentions.
format Preprint
id arxiv_https___arxiv_org_abs_2408_11428
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Migrating Existing Container Workload to Kubernetes -- LLM Based Approach and Evaluation
Ueno, Masaru
Uchiumi, Tetsuya
Software Engineering
Although Kubernetes has become a widespread open-source system that automates the management of containerized applications, its complexity can be a significant barrier, particularly for application developers unfamiliar with it. One approach employs large language models (LLMs) to assist developers in generating Kubernetes manifests; however it is currently impossible to determine whether the output satisfies given specifications and is comprehensible. In this study, we proposed a benchmarking method for evaluating the effectiveness of LLMs in synthesizing manifests, using the Compose specification -- a standard widely adopted by application developers -- as input. The proposed benchmarking method revealed that LLMs generally produce accurate results that compensate for simple specification gaps. However, we also observed that inline comments for readability were often omitted, and completion accuracy was low for atypical inputs with unclear intentions.
title Migrating Existing Container Workload to Kubernetes -- LLM Based Approach and Evaluation
topic Software Engineering
url https://arxiv.org/abs/2408.11428