In this work, we present HuixiangDou, a technical assistant powered by Large
Language Models (LLM). 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 OpenMMLab. 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. We have made the
software and source code available at this https URL
to aid in future research and application. HuixiangDou is applicable to any
group chat within IM tools.

本研究提出了一种由大型语言模型（LLM）驱动的技术助手 ——HuixiangDou。该系统旨在通过为与开源算法项目相关的问题提供深入的回答来帮助算法开发人员，例如来自 OpenMMLab 的计算机视觉和深度学习项目。我们进一步探索了将该助手集成到即时通讯工具（如微信和 Lark）的群聊中的方法。通过多次迭代的改进和试验，我们开发了一种复杂的技术聊天助手，能够有效地回答用户的技术问题而不会引起消息泛滥。本文的贡献包括：1）为群聊场景设计了一种算法流程；2）验证了 text2vec 在任务拒绝方面的可靠性表现；3）确定了技术助手类产品中 LLMs 的三个关键要求，即得分能力、上下文学习和长时间上下文。我们已经将软件和源代码发布在此 https URL 上，以便未来的研究和应用。HuixiangDou 适用于即时通讯工具中的任何群聊。