A Novel Approach for Rapid Development Based on ChatGPT and Prompt Engineering

TL;DR

This paper presents a web-based code generation platform utilizing ChatGPT and a dynamic Prompt Builder, significantly improving code accuracy and practical validation in software development.

Contribution

It introduces a Prompt Builder that dynamically enhances ChatGPT's code generation, addressing practical development needs and demonstrating substantial performance improvements.

Findings

65.06% improvement in EM

98.5% test case validation success

Significant performance gains across multiple metrics

Abstract

Code generation stands as a powerful technique in modern software development, improving development efficiency, reducing errors, and fostering standardization and consistency. Recently, ChatGPT has exhibited immense potential in automatic code generation. However, existing researches on code generation lack guidance for practical software development process. In this study, we utilized ChatGPT to develop a web-based code generation platform consisting of key components: User Interface, Prompt Builder and Backend Service. Specifically, Prompt Builder dynamically generated comprehensive prompts to enhance model generation performance. We conducted experiments on 2 datasets, evaluating the generated code through 8 widely used metrics.The results demonstrate that (1) Our Prompt Builder is effective, resulting in a 65.06% improvement in EM, a 38.45% improvement in BLEU, a 15.70% improvement in CodeBLEU, and a 50.64% improvement in Pass@1. (2) In real development scenarios, 98.5% of test cases can be validated through manual validation, highlighting the genuine assistance provided by the ChatGPT-based code generation approach.