HuixiangDou Versions Save

What's Changed

Frontend

• Add web server and front-end by @JiaYingLii @Echo-minn @lanbitou-tech @fly2tomato
• Implement Android APP support WeChat group by @lmhh
• Support Lark @tpoisonooo

Feature

• Support rag.py for SFT data annotation @tpoisonooo
• Support deepseek, xi-api, alles-apin, puyu and kimi auto model selection @tpoisonooo
• Update architecture_zh.md by @tpoisonooo in https://github.com/InternLM/HuixiangDou/pull/63
• Add for 2G memory by @tpoisonooo in https://github.com/InternLM/HuixiangDou/pull/100
• Support pdf,word, excel, pptx and html file format by @tpoisonooo
• Add github issue crawler by @sanbuphy in https://github.com/InternLM/HuixiangDou/pull/69
• Support zhipuai and add test query gradio by @sanbuphy in https://github.com/InternLM/HuixiangDou/pull/116
• Split feature_store and retriever by @tpoisonooo in https://github.com/InternLM/HuixiangDou/pull/99

Docs

• Add WeChat and architecture by @JimmyMa99 @tpoisonooo
• Add FAQ by @Modas-Li in https://github.com/InternLM/HuixiangDou/pull/44
• Add arch by @tpoisonooo in https://github.com/InternLM/HuixiangDou/pull/61
• Fix No module named 'faiss.swigfaiss_avx2' by @chg0901 in https://github.com/InternLM/HuixiangDou/pull/215
• New clean REAMDE @tpoisonooo

Fix

• Fix installation by @LzMingYueShanPao in https://github.com/InternLM/HuixiangDou/pull/224
• De-serialization relies loading a pickle file need allow_dangerous_deserialization=True by @weedge in https://github.com/InternLM/HuixiangDou/pull/151
• Fix installation by @chg0901 in https://github.com/InternLM/HuixiangDou/pull/217
• Change sg_search prompt KEYWORDS_TEMPLATE, between keywords use , separate by @weedge in https://github.com/InternLM/HuixiangDou/pull/158
• Use List instead of list by @LzMingYueShanPao in https://github.com/InternLM/HuixiangDou/pull/222

New Contributors

• @JimmyMa99 made their first contribution in https://github.com/InternLM/HuixiangDou/pull/18
• @Modas-Li made their first contribution in https://github.com/InternLM/HuixiangDou/pull/44
• @fly2tomato made their first contribution in https://github.com/InternLM/HuixiangDou/pull/46
• @JiaYingLii made their first contribution in https://github.com/InternLM/HuixiangDou/pull/54
• @sanbuphy made their first contribution in https://github.com/InternLM/HuixiangDou/pull/69
• @lmhh made their first contribution in https://github.com/InternLM/HuixiangDou/pull/47
• @weedge made their first contribution in https://github.com/InternLM/HuixiangDou/pull/151
• @chg0901 made their first contribution in https://github.com/InternLM/HuixiangDou/pull/215
• @LzMingYueShanPao made their first contribution in https://github.com/InternLM/HuixiangDou/pull/222

Full Changelog: https://github.com/InternLM/HuixiangDou/compare/v0.1.0rc1...20240415

HuixiangDou is a group chat assistant based on LLM (Large Language Model).

Advantages:

1. Design a two-stage pipeline of rejection and response to cope with group chat scenario, answer user questions without message flooding, see arxiv2401.08772
2. Low cost, requiring only 1.5GB memory and no need for training
3. Offers a complete suite of Web, Android, and pipeline source code, which is industrial-grade and commercially viable

Check out the scenes in which HuixiangDou are running and join WeChat Group to try AI assistant inside.

If this helps you, please give it a star ⭐