InternLM/HuixiangDou
LLM-based knowledge assistant designed to assist in group chat scenarios using a three-stage preprocess-rejection-response pipeline.
Not currently ranked — collecting fresh signals.
star history
HuixiangDou is a professional knowledge assistant built on large language models for group chat environments. It processes technical queries by first preprocessing messages, then rejecting irrelevant ones, before generating responses using retrieval-augmented generation. The system integrates with platforms like WeChat and supports multimodal inputs including image retrieval. A successor version (HuixiangDou2) implements GraphRAG for specialized domain assistance.
Frequently asked
- What is InternLM/HuixiangDou?
- LLM-based knowledge assistant designed to assist in group chat scenarios using a three-stage preprocess-rejection-response pipeline.
- Is HuixiangDou open source?
- Yes — InternLM/HuixiangDou is open source, released under the BSD-3-Clause license.
- What language is HuixiangDou written in?
- InternLM/HuixiangDou is primarily written in Python.
- How popular is HuixiangDou?
- InternLM/HuixiangDou has 2.5k stars on GitHub.
- Where can I find HuixiangDou?
- InternLM/HuixiangDou is on GitHub at https://github.com/InternLM/HuixiangDou.