HuixiangDou: Overcoming Group Chat Scenarios with LLM-based Technical Assistance

This system is designed to assist algorithm developers by providing insightful responses to questions related to open-source algorithm projects, such as computer vision and deep learning projects from OpenMM-Lab. We further explore the integration of this assistant into the group chats of instant messaging (IM) tools such as WeChat and Lark. Through several iterative improvements and trials, we have developed a sophisticated technical chat assistant capable of effectively answering users' technical questions without causing message flooding. This paper's contributions include: 1) Designing an algorithm pipeline specifically for group chat scenarios; 2) Verifying the reliable performance of text2vec in task rejection; 3) Identifying three critical requirements for LLMs in technical-assistant-like products, namely scoring ability, In-Context Learning (ICL), and Long Context. HuixiangDou is applicable to any group chat within IM tools. Authors of open-source projects often set up user groups on IM tools(like WeChat, Slack, Discord, etc.) for discussing project-related technical questions. As the number of users gradually increases, the maintainers, aiming to reduce the time spent on answering user questions while ensuring these questions are addressed, tend to pin some content or set up a bot to automatically answer FAQs. However, user inquiries are strongly correlated with their local development environments, and most messages in the group are unrelated to the project. However, traditional NLP solutions can neither parse the users' intent nor often provide the answers they desire.