Automated DevOps Pipeline Generation for Code Repositories using Large Language Models

TL;DR

This paper explores using GPT 3.5 and GPT 4 to automatically generate and evaluate GitHub Action workflows, enhancing DevOps automation with a new GitHub App and novel evaluation metrics.

Contribution

It introduces a methodology for leveraging large language models to generate DevOps workflows and evaluates their effectiveness, especially highlighting GPT 4's improvements.

Findings

GPT 4 outperforms GPT 3.5 in syntax correctness and DevOps awareness

The study develops a new DevOps Aware score for workflow evaluation

A GitHub App is created to facilitate automated workflow generation

Abstract

Automating software development processes through the orchestration of GitHub Action workflows has revolutionized the efficiency and agility of software delivery pipelines. This paper presents a detailed investigation into the use of Large Language Models (LLMs) specifically, GPT 3.5 and GPT 4 to generate and evaluate GitHub Action workflows for DevOps tasks. Our methodology involves data collection from public GitHub repositories, prompt engineering for LLM utilization, and evaluation metrics encompassing exact match scores, BLEU scores, and a novel DevOps Aware score. The research scrutinizes the proficiency of GPT 3.5 and GPT 4 in generating GitHub workflows, while assessing the influence of various prompt elements in constructing the most efficient pipeline. Results indicate substantial advancements in GPT 4, particularly in DevOps awareness and syntax correctness. The research introduces a GitHub App built on Probot, empowering users to automate workflow generation within GitHub ecosystem. This study contributes insights into the evolving landscape of AI-driven automation in DevOps practices.