Unveiling the Potential of a Conversational Agent in Developer Support: Insights from Mozilla's PDF.js']js Project

被引:0
|
作者
Correia, Joao [1 ]
Nicholson, Morgan C. [2 ]
Coutinho, Daniel [1 ]
Barbosa, Caio [1 ]
Castelluccio, Marco [3 ]
Gerosa, Marco [4 ]
Garcia, Alessandro [1 ]
Steinmacher, Igor [4 ]
机构
[1] Pontificia Univ Catolica Rio de Janeiro, Rio de Janeiro, RJ, Brazil
[2] Univ Sao Paulo, Sao Paulo, SP, Brazil
[3] Mozilla Corp, London, England
[4] No Arizona Univ, Flagstaff, AZ 86011 USA
基金
美国国家科学基金会;
关键词
Large Language Models; Conversational Agents; Developer Assistance; Software Development; Software Engineering;
D O I
10.1145/3664646.3664758
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Large language models and other foundation models (FMs) boost productivity by automating code generation, supporting bug fixes, and generating documentation. We propose that FMs can further support Open Source Software (OSS) projects by assisting developers and guiding the community. Currently, core developers and maintainers answer queries about processes, architecture, and source code, but their time is limited, often leading to delays. To address this, we introduce DevMentorAI, a tool that enhances developerproject interactions by leveraging source code and technical documentation. DevMentorAI uses the Retrieval Augmented Generation (RAG) architecture to identify and retrieve relevant content for queries. We evaluated DevMentorAI with a case study on PDF.js project, using real questions from a development chat room and comparing the answers provided by DevMentorAI to those from humans. A Mozilla expert rated the answers, finding DevMentorAI's responses more satisfactory in 8/14 of cases, equally satisfactory in 3/14, and less satisfactory in 3/14. These results demonstrate the potential of using foundation models and the RAG approach to support developers and reduce the burden on core developers.
引用
收藏
页码:10 / 18
页数:9
相关论文
empty
未找到相关数据