Unveiling the Potential of a Conversational Agent in Developer Support: Insights from Mozilla’s PDF.js Project
This paper presents an investigation into whether AI can be leveraged to assist developers and guide open source community members. It introduces DevMentorAI, an LLM-based tool that uses a RAG approach to answer developer questions, which is then evaluated with a case study on Mozilla's PDF.js proje
Overview
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 developer-project 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.