Automatic Qiskit Code Refactoring Using Large Language Models

TL;DR

This paper introduces a method using large language models to automate the refactoring of Qiskit quantum code, leveraging a taxonomy of migration scenarios to improve compatibility with evolving APIs.

Contribution

It presents a novel approach combining domain-specific migration taxonomy with LLMs to automate Qiskit code refactoring, addressing context limitations and providing effective migration assistance.

Findings

LLMs can effectively identify migration scenarios in Qiskit code.

The approach improves automation of quantum code migration tasks.

Proven prompts and taxonomy enhance LLM guidance for code refactoring.

Abstract

As quantum software frameworks evolve, developers face increasing challenges in maintaining compatibility with rapidly changing APIs. In this work, we present a novel methodology for refactoring Qiskit code using large language models (LLMs). We begin by extracting a taxonomy of migration scenarios from the different sources of official Qiskit documentation (such as release notes), capturing common patterns such as migration of functionality to different modules and deprecated usage. This taxonomy, along with the original Python source code, is provided as input to an LLM, which is then tasked with identifying instances of migration scenarios in the code and suggesting appropriate refactoring solutions. Our approach is designed to address the context length limitations of current LLMs by structuring the input and reasoning process in a targeted, efficient manner. The results demonstrate that LLMs, when guided by domain-specific migration knowledge, can effectively assist in automating Qiskit code migration. This work contributes both a set of proven prompts and taxonomy for Qiskit code migration from earlier versions to version 0.46 and a methodology to asses the capabilities of LLMs to assist in the migration of quantum code.