🔆 New Features

📖 Support Status

📦 Hardware Requirements

🔥 Running the Standard Edition

I. Download and install dependencies

huggingface-cli login

# parsing `word` format requirementsapt updateapt install python-dev libxml2-dev libxslt1-dev antiword unrtf poppler-utils pstotext tesseract-ocr flac ffmpeg lame libmad0 libsox-fmt-mp3 sox libjpeg-dev swig libpulse-dev# python requirementspip install -r requirements.txt# For python3.8, install faiss-gpu instead of faiss

II. Create knowledge base

# Download the knowledge base, we only take the some documents as example. You can put any of your own documents under `repodir`cd HuixiangDoumkdir repodircp -rf resource/data* repodir/# Build knowledge base, this will save the features of repodir to workdir, and update the positive and negative example thresholds into `config.ini`mkdir workdirpython3 -m huixiangdou.services.store# You can also build knowledge base from QA pairs (CSV or JSON format)# CSV: First column is key (question), second column is value (answer)# JSON: {"question1": "answer1", "question2": "answer2", ...}# python3 -m huixiangdou.services.store --qa-pair resource/data/qa_pair.csv

III. Setup LLM API and test

vllm serve /path/to/Qwen-2.5-7B-Instruct --served-model-name vllm --enable-prefix-caching --served-model-name Qwen-2.5-7B-Instruct

[llm.server]remote_type ="kimi"remote_api_key ="sk-dp3GriuhhLXnYo0KUuWbFUWWKOXXXXXXXXXX"remote_llm_model ="auto"# remote_type = "step"# remote_api_key = "5CpPyYNPhQMkIzs5SYfcdbTHXq3a72H5XXXXXXXXXXXXX"# remote_llm_model = "auto"# remote_type = "deepseek"# remote_api_key = "sk-86db9a205aa9422XXXXXXXXXXXXXX"# remote_llm_model = "deepseek-chat"# remote_type = "vllm"# remote_api_key = "EMPTY"# remote_llm_model = "Qwen2.5-7B-Instruct"# remote_type = "siliconcloud"# remote_api_key = "sk-xxxxxxxxxxxxx"# remote_llm_model = "alibaba/Qwen1.5-110B-Chat"# remote_type = "ppio"# remote_api_key = "sk-xxxxxxxxxxxxx"# remote_llm_model = "thudm/glm-4-9b-chat"

# Respond to questions related to the Hundred-Plant Garden (related to the knowledge base), but do not respond to weather questions.python3 -m huixiangdou.main+-----------------------+---------+--------------------------------+-----------------+|         Query         |  State  |         Reply                  |   References    |+=======================+=========+================================+=================+| What is in the Hundred-Plant Garden? | success | The Hundred-Plant Garden has a rich variety of natural landscapes and life... | installation.md |--------------------------------------------------------------------------------------| How is the weather today?         | Init state| ..                           |                 |+-----------------------+---------+--------------------------------+-----------------+🔆 Input your question here, type `bye` for exit:..

python3 -m huixiangdou.gradio_ui

python3 -m huixiangdou.api_server# test async APIcurl -X POST http://127.0.0.1:23333/huixiangdou_stream  -H"Content-Type: application/json" -d'{"text": "how to install mmpose","image": ""}'# cURL sync APIcurl -X POST http://127.0.0.1:23333/huixiangdou_inference  -H"Content-Type: application/json" -d'{"text": "how to install mmpose","image": ""}'

IV. Integration

To Feishu, WeChat group

To web front and backend

To readthedocs.io

🍴 Other Configurations

CPU-only Edition

# Start containerdocker run -v /path/to/huixiangdou:/huixiangdou -p 7860:7860 -p 23333:23333 -it continuumio/miniconda3 /bin/bash# Install dependenciesapt updateapt install python-dev libxml2-dev libxslt1-dev antiword unrtf poppler-utils pstotext tesseract-ocr flac ffmpeg lame libmad0 libsox-fmt-mp3 sox libjpeg-dev swig libpulse-devpython3 -m pip install -r requirements-cpu.txt# Establish knowledge basepython3 -m huixiangdou.services.store --config_path config-cpu.ini# Q&A testpython3 -m huixiangdou.main --config_path config-cpu.ini# gradio UIpython3 -m huixiangdou.gradio_ui --config_path config-cpu.ini

10G Multimodal Edition

# config-multimodal.ini# !!! Download `https://huggingface.co/BAAI/bge-visualized/blob/main/Visualized_m3.pth`    to `bge-m3` folder !!!embedding_model_path ="BAAI/bge-m3"reranker_model_path ="BAAI/bge-reranker-v2-minicpm-layerwise"

python3 tests/test_query_gradio.py

Furthermore

🛠️ FAQ

🍀 Acknowledgements

📝 Citation

@misc{kong2024huixiangdou,      title={HuiXiangDou: Overcoming Group Chat Scenarios with LLM-based Technical Assistance},      author={Huanjun Kong and Songyang Zhang and Jiaying Li and Min Xiao and Jun Xu and Kai Chen},      year={2024},      eprint={2401.08772},      archivePrefix={arXiv},      primaryClass={cs.CL}}@misc{kong2024labelingsupervisedfinetuningdata,      title={Labeling supervised fine-tuning data with the scaling law},       author={Huanjun Kong},      year={2024},      eprint={2405.02817},      archivePrefix={arXiv},      primaryClass={cs.CL},      url={https://arxiv.org/abs/2405.02817}, }@misc{kong2025huixiangdou2robustlyoptimizedgraphrag,      title={HuixiangDou2: A Robustly Optimized GraphRAG Approach},       author={Huanjun Kong and Zhefan Wang and Chenyang Wang and Zhe Ma and Nanqing Dong},      year={2025},      eprint={2503.06474},      archivePrefix={arXiv},      primaryClass={cs.IR},      url={https://arxiv.org/abs/2503.06474}, }