Analyzing Declarative Deployment Code with Large Language Models

Giacomo Lanciano, Manuel Stein, Volker Hilt, Tommaso Cucinotta

2023

Abstract

In the cloud-native era, developers have at their disposal an unprecedented landscape of services to build scalable distributed systems. The DevOps paradigm emerged as a response to the increasing necessity of better automations, capable of dealing with the complexity of modern cloud systems. For instance, Infrastructure-as-Code tools provide a declarative way to define, track, and automate changes to the infrastructure underlying a cloud application. Assuring the quality of this part of a code base is of utmost importance. However, learning to produce robust deployment specifications is not an easy feat, and for the domain experts it is time-consuming to conduct code-reviews and transfer the appropriate knowledge to novice members of the team. Given the abundance of data generated throughout the DevOps cycle, machine learning (ML) techniques seem a promising way to tackle this problem. In this work, we propose an approach based on Large Language Models to analyze declarative deployment code and automatically provide QA-related recommendations to developers, such that they can benefit of established best practices and design patterns. We developed a prototype of our proposed ML pipeline, and empirically evaluated our approach on a collection of Kubernetes manifests exported from a repository of internal projects at Nokia Bell Labs.

Paper Citation

in Harvard Style

Lanciano G., Stein M., Hilt V. and Cucinotta T. (2023). Analyzing Declarative Deployment Code with Large Language Models. In Proceedings of the 13th International Conference on Cloud Computing and Services Science - Volume 1: CLOSER, ISBN 978-989-758-650-7, SciTePress, pages 289-296. DOI: 10.5220/0011991200003488

in Bibtex Style

@conference{closer23,
author={Giacomo Lanciano and Manuel Stein and Volker Hilt and Tommaso Cucinotta},
title={Analyzing Declarative Deployment Code with Large Language Models},
booktitle={Proceedings of the 13th International Conference on Cloud Computing and Services Science - Volume 1: CLOSER,},
year={2023},
pages={289-296},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011991200003488},
isbn={978-989-758-650-7},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 13th International Conference on Cloud Computing and Services Science - Volume 1: CLOSER,
TI - Analyzing Declarative Deployment Code with Large Language Models
SN - 978-989-758-650-7
AU - Lanciano G.
AU - Stein M.
AU - Hilt V.
AU - Cucinotta T.
PY - 2023
SP - 289
EP - 296
DO - 10.5220/0011991200003488
PB - SciTePress