diff --git a/README.md b/README.md index abea506..6d7383e 100644 --- a/README.md +++ b/README.md @@ -35,6 +35,16 @@ English/[简体中文](https://github.com/deepseek-ai/awesome-deepseek-integrati +### IM Application Plugins + + + + + + + +
Icon HuixiangDou
(wechat,lark) 		Domain knowledge assistant in personal WeChat and Feishu, focusing on answering questions
+ ### Browser Extensions diff --git a/README_cn.md b/README_cn.md index 10ffc48..3adb9e7 100644 --- a/README_cn.md +++ b/README_cn.md @@ -35,6 +35,16 @@
+### 即时通讯插件 + + + + + + + +
Icon 茴香豆
（个人微信/飞书） 		一个集成到个人微信群/飞书群的领域知识助手，专注解答问题不闲聊
+ ### 浏览器插件 diff --git a/docs/huixiangdou/README.md b/docs/huixiangdou/README.md new file mode 100644 index 0000000..7efda43 --- /dev/null +++ b/docs/huixiangdou/README.md @@ -0,0 +1,53 @@ + + +# [HuixiangDou](https://github.com/InternLM/HuixiangDou) +"HuixiangDou" is a domain knowledge assistant based on LLM. Features: + +1. Handles complex scenarios such as group chat and handle answer user questions without flooding messages. +2. Proposes a solution for technical issues through an algorithm pipeline. +3. Low cost, see [arxiv2401.08772](https://arxiv.org/abs/2401.08772) + +# Demonstration +HuixiangDou is a **assistant** +* Says it doesn't know in response to halluciations +* Personal Wechat supported +* Feishu supported + + + +HuixiangDou is a **group** assistant +* Ignores idle talk +* Only interacts with those who need help + + + +HuixiangDou is a **domain knowledge** group assistant +* Relies on an algorithm pipeline + LLM instead of training +* Has faced thousands of users, and has been "teased" over 20,000 times in half a year + + + +# Configuring deepseek API +**STEP1.** Apply for a token at deepseek open platform + +**STEP2.** Follow the HuixiangDou Advanced Configuration and fill in the config.ini with your token + +```ini +# config.ini +[llm] +enable_local = 0 +enable_remote = 1 +.. +[llm.server] +.. +remote_type = "deepseek" +remote_api_key = "YOUR-API-KEY" +remote_llm_max_text_length = 16000 +remote_llm_model = "deepseek-chat" +``` + +**STEP3.** Run + +```shell +python3 -m huixiangdou.main --standalone +``` \ No newline at end of file diff --git a/docs/huixiangdou/README_cn.md b/docs/huixiangdou/README_cn.md new file mode 100644 index 0000000..7000a40 --- /dev/null +++ b/docs/huixiangdou/README_cn.md @@ -0,0 +1,59 @@ + + +# [茴香豆](https://github.com/InternLM/HuixiangDou) + +“茴香豆”是一个基于 LLM 的领域知识助手。特点： + +1. 应对群聊这类复杂场景，解答用户问题的同时，不会消息泛滥 +2. 提出一套解答技术问题的算法 pipeline +3. 部署成本低，见[技术报告 arxiv2401.08772](https://arxiv.org/abs/2401.08772) + + +## 效果展示 + +1. 它是个**机器人** + + * 面对幻觉会说不知道 + * 支持微信 + * 支持飞书 + + + +2. 它是个**群组**机器人 + + * 不会搭理闲聊 + * 只找需要帮助的人 + + + +2. 它是个**领域知识**群组机器人 + + * 不依赖训练，依靠算法 pipeline + LLM + * 已经面对数千用户，半年被“调戏”了 2w 次以上 + + + +## 配置 deepseek API + +**STEP1.** 打开 [deepseek 开放平台](https://platform.deepseek.com) 申请 token + +**STEP2.** 参照 [HuixiangDou 高级配置](https://github.com/InternLM/HuixiangDou?tab=readme-ov-file#step4-advanced-version-optional)，把 token 填入 `config.ini` + +```ini +# config.ini +[llm] +enable_local = 0 +enable_remote = 1 +.. +[llm.server] +.. +remote_type = "deepseek" +remote_api_key = "YOUR-API-KEY" +remote_llm_max_text_length = 16000 +remote_llm_model = "deepseek-chat" +``` + +**STEP3.** 运行 +```shell +python3 -m huixiangdou.main --standalone +``` \ No newline at end of file