feat: support gpt-4o model

Update README.md

.github/workflows/deploy-image-arm.yml

@@ -19,6 +19,7 @@ env:
 
 jobs:
   build-and-push-image:
+    if: github.repository == 'zhayujie/chatgpt-on-wechat'
     runs-on: ubuntu-latest
     permissions:
       contents: read

.github/workflows/deploy-image.yml

@@ -19,6 +19,7 @@ env:
 
 jobs:
   build-and-push-image:
+    if: github.repository == 'zhayujie/chatgpt-on-wechat'
     runs-on: ubuntu-latest
     permissions:
       contents: read

.gitignore

@@ -29,4 +29,5 @@ plugins/banwords/lib/__pycache__
 !plugins/hello
 !plugins/role
 !plugins/keyword
-!plugins/linkai
+!plugins/linkai
+client_config.json

README.md

@@ -1,32 +1,53 @@
 # 简介
 
-> ChatGPT近期以强大的对话和信息整合能力风靡全网，可以写代码、改论文、讲故事，几乎无所不能，这让人不禁有个大胆的想法，能否用他的对话模型把我们的微信打造成一个智能机器人，可以在与好友对话中给出意想不到的回应，而且再也不用担心女朋友影响我们 ~~打游戏~~ 工作了。
+> chatgpt-on-wechat（简称CoW）项目是基于大模型的智能对话机器人，支持微信公众号、企业微信应用、微信、飞书、钉钉接入，可选择GPT3.5/GPT4.0/Claude/Gemini/LinkAI/ChatGLM/KIMI/文心一言/讯飞星火/通义千问/LinkAI，能处理文本、语音和图片，通过插件访问操作系统和互联网等外部资源，支持基于自有知识库定制企业AI应用。
 
 最新版本支持的功能如下：
 
-- [x] **多端部署：** 有多种部署方式可选择且功能完备，目前已支持个人微信，微信公众号和企业微信应用等部署方式
-- [x] **基础对话：** 私聊及群聊的消息智能回复，支持多轮会话上下文记忆，支持 GPT-3.5, GPT-4, claude, 文心一言, 讯飞星火
-- [x] **语音识别：** 可识别语音消息，通过文字或语音回复，支持 azure, baidu, google, openai(whisper/tts) 等多种语音模型
-- [x] **图片生成：** 支持图片生成 和 图生图（如照片修复），可选择 Dall-E, stable diffusion, replicate, midjourney模型
-- [x] **丰富插件：** 支持个性化插件扩展，已实现多角色切换、文字冒险、敏感词过滤、聊天记录总结、文档总结和对话等插件
-- [X] **Tool工具：** 与操作系统和互联网交互，支持最新信息搜索、数学计算、天气和资讯查询、网页总结，基于 [chatgpt-tool-hub](https://github.com/goldfishh/chatgpt-tool-hub) 实现
-- [x] **知识库：** 通过上传知识库文件自定义专属机器人，可作为数字分身、领域知识库、智能客服使用，基于 [LinkAI](https://link-ai.tech/console) 实现
+-  ✅   **多端部署：** 有多种部署方式可选择且功能完备，目前已支持微信生态下公众号、企业微信应用、飞书、钉钉等部署方式
+-  ✅   **基础对话：** 私聊及群聊的消息智能回复，支持多轮会话上下文记忆，支持 GPT-3.5, GPT-4, GPT-4o, Claude-3, Gemini, 文心一言, 讯飞星火, 通义千问，ChatGLM-4，Kimi(月之暗面)
+-  ✅   **语音能力：** 可识别语音消息，通过文字或语音回复，支持 azure, baidu, google, openai(whisper/tts) 等多种语音模型
+-  ✅   **图像能力：** 支持图片生成、图片识别、图生图（如照片修复），可选择 Dall-E-3, stable diffusion, replicate, midjourney, CogView-3, vision模型
+-  ✅   **丰富插件：** 支持个性化插件扩展，已实现多角色切换、文字冒险、敏感词过滤、聊天记录总结、文档总结和对话、联网搜索等插件
+-  ✅   **知识库：** 通过上传知识库文件自定义专属机器人，可作为数字分身、智能客服、私域助手使用，基于 [LinkAI](https://link-ai.tech) 实现
 
-> 欢迎接入更多应用，参考 [Terminal代码](https://github.com/zhayujie/chatgpt-on-wechat/blob/master/channel/terminal/terminal_channel.py)实现接收和发送消息逻辑即可接入。 同时欢迎增加新的插件，参考 [插件说明文档](https://github.com/zhayujie/chatgpt-on-wechat/tree/master/plugins)。
-
-# 演示
+## 演示
 
 https://github.com/zhayujie/chatgpt-on-wechat/assets/26161723/d5154020-36e3-41db-8706-40ce9f3f1b1e
 
-Demo made by [Visionn](https://www.wangpc.cc/)
+## 社区
 
-# 交流群
+添加小助手微信加入开源项目交流群：
 
-添加小助手微信进群，请备注 "wechat"：
+<img width="160" src="https://img-1317903499.cos.ap-guangzhou.myqcloud.com/docs/open-community.png">
 
-<img width="240" src="./docs/images/contact.jpg">
+<br>
 
-# 更新日志
+# 企业服务
+
+<a href="https://link-ai.tech" target="_blank"><img width="800" src="https://img-1317903499.cos.ap-guangzhou.myqcloud.com/docs/github-linkai-intro-v2.png"></a>
+
+> [LinkAI](https://link-ai.tech/) 是面向企业和开发者的一站式AI应用平台，聚合多模态大模型、知识库、Agent 插件、工作流等能力，支持一键接入主流平台并进行管理，支持SaaS、私有化部署多种模式。
+>
+> LinkAI 目前 已在私域运营、智能客服、企业效率助手等场景积累了丰富的 AI 解决方案， 在电商、文教、健康、新消费、科技制造等各行业沉淀了大模型落地应用的最佳实践，致力于帮助更多企业和开发者拥抱 AI 生产力。
+
+**企业服务和产品咨询** 可联系产品顾问：
+
+<img width="160" src="https://img-1317903499.cos.ap-guangzhou.myqcloud.com/docs/github-product-consult.png">
+
+<br>
+
+# 🏷 更新日志
+
+>**2024.05.14：** [1.6.5版本](https://github.com/zhayujie/chatgpt-on-wechat/releases/tag/1.6.5)，新增 gpt-4o 模型支持
+
+>**2024.04.26：** [1.6.0版本](https://github.com/zhayujie/chatgpt-on-wechat/releases/tag/1.6.0)，新增 Kimi 接入、gpt-4-turbo版本升级、文件总结和语音识别问题修复
+
+>**2024.03.26：** [1.5.8版本](https://github.com/zhayujie/chatgpt-on-wechat/releases/tag/1.5.8) 和 [1.5.7版本](https://github.com/zhayujie/chatgpt-on-wechat/releases/tag/1.5.7)，新增 GLM-4、Claude-3 模型，edge-tts 语音支持
+
+>**2024.01.26：** [1.5.6版本](https://github.com/zhayujie/chatgpt-on-wechat/releases/tag/1.5.6) 和 [1.5.5版本](https://github.com/zhayujie/chatgpt-on-wechat/releases/tag/1.5.5)，钉钉接入，tool插件升级，4-turbo模型更新
+
+>**2023.11.11：** [1.5.3版本](https://github.com/zhayujie/chatgpt-on-wechat/releases/tag/1.5.3) 和 [1.5.4版本](https://github.com/zhayujie/chatgpt-on-wechat/releases/tag/1.5.4)，新增通义千问模型、Google Gemini
 
 >**2023.11.10：** [1.5.2版本](https://github.com/zhayujie/chatgpt-on-wechat/releases/tag/1.5.2)，新增飞书通道、图像识别对话、黑名单配置
 
@@ -38,23 +59,17 @@ Demo made by [Visionn](https://www.wangpc.cc/)
 
 >**2023.08.08：** 接入百度文心一言模型，通过 [插件](https://github.com/zhayujie/chatgpt-on-wechat/tree/master/plugins/linkai) 支持 Midjourney 绘图
 
->**2023.06.12：** 接入 [LinkAI](https://link-ai.tech/console) 平台，可在线创建领域知识库，并接入微信、公众号及企业微信中，打造专属客服机器人。使用参考 [接入文档](https://link-ai.tech/platform/link-app/wechat)。
+>**2023.06.12：** 接入 [LinkAI](https://link-ai.tech/console) 平台，可在线创建领域知识库，打造专属客服机器人。使用参考 [接入文档](https://link-ai.tech/platform/link-app/wechat)。
 
->**2023.04.26：** 支持企业微信应用号部署，兼容插件，并支持语音图片交互，私人助理理想选择，[使用文档](https://github.com/zhayujie/chatgpt-on-wechat/blob/master/channel/wechatcom/README.md)。(contributed by [@lanvent](https://github.com/lanvent) in [#944](https://github.com/zhayujie/chatgpt-on-wechat/pull/944))
+更早更新日志查看: [归档日志](/docs/version/old-version.md)
 
->**2023.04.05：** 支持微信公众号部署，兼容插件，并支持语音图片交互，[使用文档](https://github.com/zhayujie/chatgpt-on-wechat/blob/master/channel/wechatmp/README.md)。(contributed by [@JS00000](https://github.com/JS00000) in [#686](https://github.com/zhayujie/chatgpt-on-wechat/pull/686))
+<br>
 
->**2023.04.05：** 增加能让ChatGPT使用工具的`tool`插件，[使用文档](https://github.com/goldfishh/chatgpt-on-wechat/blob/master/plugins/tool/README.md)。工具相关issue可反馈至[chatgpt-tool-hub](https://github.com/goldfishh/chatgpt-tool-hub)。(contributed by [@goldfishh](https://github.com/goldfishh) in [#663](https://github.com/zhayujie/chatgpt-on-wechat/pull/663))
+# 🚀 快速开始
 
->**2023.03.25：** 支持插件化开发，目前已实现 多角色切换、文字冒险游戏、管理员指令、Stable Diffusion等插件，使用参考 [#578](https://github.com/zhayujie/chatgpt-on-wechat/issues/578)。(contributed by [@lanvent](https://github.com/lanvent) in [#565](https://github.com/zhayujie/chatgpt-on-wechat/pull/565))
+快速开始详细文档：[项目搭建文档](https://docs.link-ai.tech/cow/quick-start)
 
->**2023.03.09：** 基于 `whisper API`(后续已接入更多的语音`API`服务) 实现对微信语音消息的解析和回复，添加配置项 `"speech_recognition":true` 即可启用，使用参考 [#415](https://github.com/zhayujie/chatgpt-on-wechat/issues/415)。(contributed by [wanggang1987](https://github.com/wanggang1987) in [#385](https://github.com/zhayujie/chatgpt-on-wechat/pull/385))
-
->**2023.02.09：** 扫码登录存在账号限制风险，请谨慎使用，参考[#58](https://github.com/AutumnWhj/ChatGPT-wechat-bot/issues/158)
-
-# 快速开始
-
-## 准备
+## 一、准备
 
 ### 1. 账号注册
 
@@ -78,6 +93,8 @@ git clone https://github.com/zhayujie/chatgpt-on-wechat
 cd chatgpt-on-wechat/
 ```
 
+注: 如遇到网络问题可选择国内镜像 https://gitee.com/zhayujie/chatgpt-on-wechat
+
 **(2) 安装核心依赖 (必选)：**
 > 能够使用`itchat`创建机器人，并具有文字交流功能所需的最小依赖集合。
 ```bash
@@ -89,25 +106,9 @@ pip3 install -r requirements.txt
 ```bash
 pip3 install -r requirements-optional.txt
 ```
-> 如果某项依赖安装失败请注释掉对应的行再继续。
+> 如果某项依赖安装失败可注释掉对应的行再继续
 
-其中`tiktoken`要求`python`版本在3.8以上，它用于精确计算会话使用的tokens数量，强烈建议安装。
-
-
-使用`google`或`baidu`语音识别需安装`ffmpeg`，
-
-默认的`openai`语音识别不需要安装`ffmpeg`。
-
-参考[#415](https://github.com/zhayujie/chatgpt-on-wechat/issues/415)
-
-使用`azure`语音功能需安装依赖，并参考[文档](https://learn.microsoft.com/en-us/azure/cognitive-services/speech-service/quickstarts/setup-platform?pivots=programming-language-python&tabs=linux%2Cubuntu%2Cdotnet%2Cjre%2Cmaven%2Cnodejs%2Cmac%2Cpypi)的环境要求。
-:
-
-```bash
-pip3 install azure-cognitiveservices-speech
-```
-
-## 配置
+## 二、配置
 
 配置文件的模板在根目录的`config-template.json`中，需复制该模板创建最终生效的 `config.json` 文件：
 
@@ -115,13 +116,13 @@ pip3 install azure-cognitiveservices-speech
   cp config-template.json config.json
 ```
 
-然后在`config.json`中填入配置，以下是对默认配置的说明，可根据需要进行自定义修改（请去掉注释）：
+然后在`config.json`中填入配置，以下是对默认配置的说明，可根据需要进行自定义修改（注意实际使用时请去掉注释，保证JSON格式的完整）：
 
 ```bash
 # config.json文件内容示例
 {
-  "open_ai_api_key": "YOUR API KEY",                          # 填入上面创建的 OpenAI API KEY
-  "model": "gpt-3.5-turbo",                                   # 模型名称, 支持 gpt-3.5-turbo, gpt-3.5-turbo-16k, gpt-4, wenxin, xunfei
+  "model": "gpt-3.5-turbo",                                   # 模型名称, 支持 gpt-3.5-turbo, gpt-4, gpt-4-turbo, wenxin, xunfei, glm-4, claude-3-haiku, moonshot
+  "open_ai_api_key": "YOUR API KEY",                          # 如果使用openAI模型则填入上面创建的 OpenAI API KEY
   "proxy": "",                                                # 代理客户端的ip和端口，国内环境开启代理的需要填写该项，如 "127.0.0.1:7890"
   "single_chat_prefix": ["bot", "@bot"],                      # 私聊时文本需要包含该前缀才能触发机器人回复
   "single_chat_reply_prefix": "[bot] ",                       # 私聊时自动回复的前缀，用于区分真人
@@ -132,10 +133,8 @@ pip3 install azure-cognitiveservices-speech
   "conversation_max_tokens": 1000,                            # 支持上下文记忆的最多字符数
   "speech_recognition": false,                                # 是否开启语音识别
   "group_speech_recognition": false,                          # 是否开启群组语音识别
-  "use_azure_chatgpt": false,                                 # 是否使用Azure ChatGPT service代替openai ChatGPT service. 当设置为true时需要设置 open_ai_api_base，如 https://xxx.openai.azure.com/
-  "azure_deployment_id": "",                                  # 采用Azure ChatGPT时，模型部署名称
-  "azure_api_version": "",                                    # 采用Azure ChatGPT时，API版本
-  "character_desc": "你是ChatGPT, 一个由OpenAI训练的大型语言模型, 你旨在回答并解决人们的任何问题，并且可以使用多种语言与人交流。",  # 人格描述
+  "voice_reply_voice": false,                                 # 是否使用语音回复语音
+  "character_desc": "你是基于大语言模型的AI智能助手，旨在回答并解决人们的任何问题，并且可以使用多种语言与人交流。",  # 人格描述
   # 订阅消息，公众号和企业微信channel中请填写，当被订阅时会自动回复，可使用特殊占位符。目前支持的占位符有{trigger_prefix}，在程序中它会自动替换成bot的触发词。
   "subscribe_msg": "感谢您的关注！\n这里是ChatGPT，可以自由对话。\n支持语音对话。\n支持图片输出，画字开头的消息将按要求创作图片。\n支持角色扮演和文字冒险等丰富插件。\n输入{trigger_prefix}#help 查看详细指令。",
   "use_linkai": false,                                        # 是否使用LinkAI接口，默认关闭，开启后可国内访问，使用知识库和MJ
@@ -165,7 +164,7 @@ pip3 install azure-cognitiveservices-speech
 
 **4.其他配置**
 
-+ `model`: 模型名称，目前支持 `gpt-3.5-turbo`, `text-davinci-003`, `gpt-4`, `gpt-4-32k`, `wenxin` , `claude` ,  `xunfei`(其中gpt-4 api暂未完全开放，申请通过后可使用)
++ `model`: 模型名称，目前支持 `gpt-3.5-turbo`, `gpt-4o`, `gpt-4-turbo`, `gpt-4`, `wenxin` , `claude` , `gemini`, `glm-4`,  `xunfei`, `moonshot`
 + `temperature`,`frequency_penalty`,`presence_penalty`: Chat API接口参数，详情参考[OpenAI官方文档。](https://platform.openai.com/docs/api-reference/chat)
 + `proxy`：由于目前 `openai` 接口国内无法访问，需配置代理客户端的地址，详情参考  [#351](https://github.com/zhayujie/chatgpt-on-wechat/issues/351)
 + 对于图像生成，在满足个人或群组触发条件外，还需要额外的关键词前缀来触发，对应配置 `image_create_prefix `
@@ -185,7 +184,7 @@ pip3 install azure-cognitiveservices-speech
 
 **本说明文档可能会未及时更新，当前所有可选的配置项均在该[`config.py`](https://github.com/zhayujie/chatgpt-on-wechat/blob/master/config.py)中列出。**
 
-## 运行
+## 三、运行
 
 ### 1.本地运行
 
@@ -195,14 +194,13 @@ pip3 install azure-cognitiveservices-speech
 python3 app.py                                    # windows环境下该命令通常为 python app.py
 ```
 
-终端输出二维码后，使用微信进行扫码，当输出 "Start auto replying" 时表示自动回复程序已经成功运行了（注意：用于登录的微信需要在支付处已完成实名认证）。扫码登录后你的账号就成为机器人了，可以在微信手机端通过配置的关键词触发自动回复 (任意好友发送消息给你，或是自己发消息给好友)，参考[#142](https://github.com/zhayujie/chatgpt-on-wechat/issues/142)。
+终端输出二维码后，使用微信进行扫码，当输出 "Start auto replying" 时表示自动回复程序已经成功运行了（注意：用于登录的微信需要在支付处已完成实名认证）。扫码登录后你的账号就成为机器人了，可以在手机端通过配置的关键词触发自动回复 (任意好友发送消息给你，或是自己发消息给好友)，参考[#142](https://github.com/zhayujie/chatgpt-on-wechat/issues/142)。
 
 ### 2.服务器部署
 
 使用nohup命令在后台运行程序：
 
 ```bash
-touch nohup.out                                   # 首次运行需要新建日志文件  
 nohup python3 app.py & tail -f nohup.out          # 在后台运行程序并通过日志输出二维码
 ```
 扫码登录后程序即可运行于服务器后台，此时可通过 `ctrl+c` 关闭日志，不会影响后台程序的运行。使用 `ps -ef | grep app.py | grep -v grep` 命令可查看运行于后台的进程，如果想要重新启动程序可以先 `kill` 掉对应的进程。日志关闭后如果想要再次打开只需输入 `tail -f nohup.out`。此外，`scripts` 目录下有一键运行、关闭程序的脚本供使用。
@@ -218,7 +216,7 @@ nohup python3 app.py & tail -f nohup.out          # 在后台运行程序并通
 
 > 前提是需要安装好 `docker` 及 `docker-compose`，安装成功的表现是执行 `docker -v` 和 `docker-compose version` (或 docker compose version) 可以查看到版本号，可前往 [docker官网](https://docs.docker.com/engine/install/) 进行下载。
 
-#### (1) 下载 docker-compose.yml 文件
+**(1) 下载 docker-compose.yml 文件**
 
 ```bash
 wget https://open-1317903499.cos.ap-guangzhou.myqcloud.com/docker-compose.yml
@@ -226,7 +224,7 @@ wget https://open-1317903499.cos.ap-guangzhou.myqcloud.com/docker-compose.yml
 
 下载完成后打开 `docker-compose.yml` 修改所需配置，如 `OPEN_AI_API_KEY` 和 `GROUP_NAME_WHITE_LIST` 等。
 
-#### (2) 启动容器
+**(2) 启动容器**
 
 在 `docker-compose.yml` 所在目录下执行以下命令启动容器：
 
@@ -247,7 +245,7 @@ sudo docker compose up -d
 sudo docker logs -f chatgpt-on-wechat
 ```
 
-#### (3) 插件使用
+**(3) 插件使用**
 
 如果需要在docker容器中修改插件配置，可通过挂载的方式完成，将 [插件配置文件](https://github.com/zhayujie/chatgpt-on-wechat/blob/master/plugins/config.json.template)
 重命名为 `config.json`，放置于 `docker-compose.yml` 相同目录下，并在 `docker-compose.yml` 中的 `chatgpt-on-wechat` 部分下添加 `volumes` 映射:
@@ -269,12 +267,22 @@ volumes:
   
   [![Deploy on Railway](https://railway.app/button.svg)](https://railway.app/template/qApznZ?referralCode=RC3znh)
 
-## 常见问题
+<br>
+
+# 🔎 常见问题
 
 FAQs： <https://github.com/zhayujie/chatgpt-on-wechat/wiki/FAQs>
 
-或直接在线咨询 [项目小助手](https://link-ai.tech/app/Kv2fXJcH)  (beta版本，语料完善中，回复仅供参考)
+或直接在线咨询 [项目小助手](https://link-ai.tech/app/Kv2fXJcH)  (语料持续完善中，回复仅供参考)
 
-## 联系
+# 🛠️ 开发
 
-欢迎提交PR、Issues，以及Star支持一下。程序运行遇到问题可以查看 [常见问题列表](https://github.com/zhayujie/chatgpt-on-wechat/wiki/FAQs) ，其次前往 [Issues](https://github.com/zhayujie/chatgpt-on-wechat/issues) 中搜索。参与更多讨论可加入技术交流群。
+欢迎接入更多应用，参考 [Terminal代码](https://github.com/zhayujie/chatgpt-on-wechat/blob/master/channel/terminal/terminal_channel.py) 实现接收和发送消息逻辑即可接入。 同时欢迎增加新的插件，参考 [插件说明文档](https://github.com/zhayujie/chatgpt-on-wechat/tree/master/plugins)。
+
+# ✉ 联系
+
+欢迎提交PR、Issues，以及Star支持一下。程序运行遇到问题可以查看 [常见问题列表](https://github.com/zhayujie/chatgpt-on-wechat/wiki/FAQs) ，其次前往 [Issues](https://github.com/zhayujie/chatgpt-on-wechat/issues) 中搜索。个人开发者可加入开源交流群参与更多讨论，企业用户可联系[产品顾问](https://img-1317903499.cos.ap-guangzhou.myqcloud.com/docs/product-manager-qrcode.jpg)咨询。
+
+# 🌟 贡献者
+
+![cow contributors](https://contrib.rocks/image?repo=zhayujie/chatgpt-on-wechat&max=1000)

app.py

@@ -3,11 +3,13 @@
 import os
 import signal
 import sys
+import time
 
 from channel import channel_factory
 from common import const
 from config import load_config
 from plugins import *
+import threading
 
 
 def sigterm_handler_wrap(_signo):
@@ -23,6 +25,21 @@ def sigterm_handler_wrap(_signo):
     signal.signal(_signo, func)
 
 
+def start_channel(channel_name: str):
+    channel = channel_factory.create_channel(channel_name)
+    if channel_name in ["wx", "wxy", "terminal", "wechatmp", "wechatmp_service", "wechatcom_app", "wework",
+                        const.FEISHU, const.DINGTALK]:
+        PluginManager().load_plugins()
+
+    if conf().get("use_linkai"):
+        try:
+            from common import linkai_client
+            threading.Thread(target=linkai_client.start, args=(channel,)).start()
+        except Exception as e:
+            pass
+    channel.startup()
+
+
 def run():
     try:
         # load config
@@ -40,14 +57,11 @@ def run():
 
         if channel_name == "wxy":
             os.environ["WECHATY_LOG"] = "warn"
-            # os.environ['WECHATY_PUPPET_SERVICE_ENDPOINT'] = '127.0.0.1:9001'
 
-        channel = channel_factory.create_channel(channel_name)
-        if channel_name in ["wx", "wxy", "terminal", "wechatmp", "wechatmp_service", "wechatcom_app", "wework", const.FEISHU]:
-            PluginManager().load_plugins()
+        start_channel(channel_name)
 
-        # startup channel
-        channel.startup()
+        while True:
+            time.sleep(1)
     except Exception as e:
         logger.error("App startup failed!")
         logger.exception(e)

bot/ali/ali_qwen_bot.py

@@ -0,0 +1,214 @@
+# encoding:utf-8
+
+import json
+import time
+from typing import List, Tuple
+
+import openai
+import openai.error
+import broadscope_bailian
+from broadscope_bailian import ChatQaMessage
+
+from bot.bot import Bot
+from bot.ali.ali_qwen_session import AliQwenSession
+from bot.session_manager import SessionManager
+from bridge.context import ContextType
+from bridge.reply import Reply, ReplyType
+from common.log import logger
+from common import const
+from config import conf, load_config
+
+class AliQwenBot(Bot):
+    def __init__(self):
+        super().__init__()
+        self.api_key_expired_time = self.set_api_key()
+        self.sessions = SessionManager(AliQwenSession, model=conf().get("model", const.QWEN))
+
+    def api_key_client(self):
+        return broadscope_bailian.AccessTokenClient(access_key_id=self.access_key_id(), access_key_secret=self.access_key_secret())
+
+    def access_key_id(self):
+        return conf().get("qwen_access_key_id")
+
+    def access_key_secret(self):
+        return conf().get("qwen_access_key_secret")
+
+    def agent_key(self):
+        return conf().get("qwen_agent_key")
+
+    def app_id(self):
+        return conf().get("qwen_app_id")
+
+    def node_id(self):
+        return conf().get("qwen_node_id", "")
+
+    def temperature(self):
+        return conf().get("temperature", 0.2 )
+
+    def top_p(self):
+        return conf().get("top_p", 1)
+
+    def reply(self, query, context=None):
+        # acquire reply content
+        if context.type == ContextType.TEXT:
+            logger.info("[QWEN] query={}".format(query))
+
+            session_id = context["session_id"]
+            reply = None
+            clear_memory_commands = conf().get("clear_memory_commands", ["#清除记忆"])
+            if query in clear_memory_commands:
+                self.sessions.clear_session(session_id)
+                reply = Reply(ReplyType.INFO, "记忆已清除")
+            elif query == "#清除所有":
+                self.sessions.clear_all_session()
+                reply = Reply(ReplyType.INFO, "所有人记忆已清除")
+            elif query == "#更新配置":
+                load_config()
+                reply = Reply(ReplyType.INFO, "配置已更新")
+            if reply:
+                return reply
+            session = self.sessions.session_query(query, session_id)
+            logger.debug("[QWEN] session query={}".format(session.messages))
+
+            reply_content = self.reply_text(session)
+            logger.debug(
+                "[QWEN] new_query={}, session_id={}, reply_cont={}, completion_tokens={}".format(
+                    session.messages,
+                    session_id,
+                    reply_content["content"],
+                    reply_content["completion_tokens"],
+                )
+            )
+            if reply_content["completion_tokens"] == 0 and len(reply_content["content"]) > 0:
+                reply = Reply(ReplyType.ERROR, reply_content["content"])
+            elif reply_content["completion_tokens"] > 0:
+                self.sessions.session_reply(reply_content["content"], session_id, reply_content["total_tokens"])
+                reply = Reply(ReplyType.TEXT, reply_content["content"])
+            else:
+                reply = Reply(ReplyType.ERROR, reply_content["content"])
+                logger.debug("[QWEN] reply {} used 0 tokens.".format(reply_content))
+            return reply
+
+        else:
+            reply = Reply(ReplyType.ERROR, "Bot不支持处理{}类型的消息".format(context.type))
+            return reply
+
+    def reply_text(self, session: AliQwenSession, retry_count=0) -> dict:
+        """
+        call bailian's ChatCompletion to get the answer
+        :param session: a conversation session
+        :param retry_count: retry count
+        :return: {}
+        """
+        try:
+            prompt, history = self.convert_messages_format(session.messages)
+            self.update_api_key_if_expired()
+            # NOTE 阿里百炼的call()函数未提供temperature参数，考虑到temperature和top_p参数作用相同，取两者较小的值作为top_p参数传入，详情见文档 https://help.aliyun.com/document_detail/2587502.htm
+            response = broadscope_bailian.Completions().call(app_id=self.app_id(), prompt=prompt, history=history, top_p=min(self.temperature(), self.top_p()))
+            completion_content = self.get_completion_content(response, self.node_id())
+            completion_tokens, total_tokens = self.calc_tokens(session.messages, completion_content)
+            return {
+                "total_tokens": total_tokens,
+                "completion_tokens": completion_tokens,
+                "content": completion_content,
+            }
+        except Exception as e:
+            need_retry = retry_count < 2
+            result = {"completion_tokens": 0, "content": "我现在有点累了，等会再来吧"}
+            if isinstance(e, openai.error.RateLimitError):
+                logger.warn("[QWEN] RateLimitError: {}".format(e))
+                result["content"] = "提问太快啦，请休息一下再问我吧"
+                if need_retry:
+                    time.sleep(20)
+            elif isinstance(e, openai.error.Timeout):
+                logger.warn("[QWEN] Timeout: {}".format(e))
+                result["content"] = "我没有收到你的消息"
+                if need_retry:
+                    time.sleep(5)
+            elif isinstance(e, openai.error.APIError):
+                logger.warn("[QWEN] Bad Gateway: {}".format(e))
+                result["content"] = "请再问我一次"
+                if need_retry:
+                    time.sleep(10)
+            elif isinstance(e, openai.error.APIConnectionError):
+                logger.warn("[QWEN] APIConnectionError: {}".format(e))
+                need_retry = False
+                result["content"] = "我连接不到你的网络"
+            else:
+                logger.exception("[QWEN] Exception: {}".format(e))
+                need_retry = False
+                self.sessions.clear_session(session.session_id)
+
+            if need_retry:
+                logger.warn("[QWEN] 第{}次重试".format(retry_count + 1))
+                return self.reply_text(session, retry_count + 1)
+            else:
+                return result
+
+    def set_api_key(self):
+        api_key, expired_time = self.api_key_client().create_token(agent_key=self.agent_key())
+        broadscope_bailian.api_key = api_key
+        return expired_time
+
+    def update_api_key_if_expired(self):
+        if time.time() > self.api_key_expired_time:
+            self.api_key_expired_time = self.set_api_key()
+
+    def convert_messages_format(self, messages) -> Tuple[str, List[ChatQaMessage]]:
+        history = []
+        user_content = ''
+        assistant_content = ''
+        system_content = ''
+        for message in messages:
+            role = message.get('role')
+            if role == 'user':
+                user_content += message.get('content')
+            elif role == 'assistant':
+                assistant_content = message.get('content')
+                history.append(ChatQaMessage(user_content, assistant_content))
+                user_content = ''
+                assistant_content = ''
+            elif role =='system':
+                system_content += message.get('content')
+        if user_content == '':
+            raise Exception('no user message')
+        if system_content != '':
+            # NOTE 模拟系统消息，测试发现人格描述以"你需要扮演ChatGPT"开头能够起作用，而以"你是ChatGPT"开头模型会直接否认
+            system_qa = ChatQaMessage(system_content, '好的，我会严格按照你的设定回答问题')
+            history.insert(0, system_qa)
+        logger.debug("[QWEN] converted qa messages: {}".format([item.to_dict() for item in history]))
+        logger.debug("[QWEN] user content as prompt: {}".format(user_content))
+        return user_content, history
+
+    def get_completion_content(self, response, node_id):
+        if not response['Success']:
+            return f"[ERROR]\n{response['Code']}:{response['Message']}"
+        text = response['Data']['Text']
+        if node_id == '':
+            return text
+        # TODO: 当使用流程编排创建大模型应用时，响应结构如下，最终结果在['finalResult'][node_id]['response']['text']中，暂时先这么写
+        # {
+        #     'Success': True,
+        #     'Code': None,
+        #     'Message': None,
+        #     'Data': {
+        #         'ResponseId': '9822f38dbacf4c9b8daf5ca03a2daf15',
+        #         'SessionId': 'session_id',
+        #         'Text': '{"finalResult":{"LLM_T7islK":{"params":{"modelId":"qwen-plus-v1","prompt":"${systemVars.query}${bizVars.Text}"},"response":{"text":"作为一个AI语言模型，我没有年龄，因为我没有生日。\n我只是一个程序，没有生命和身体。"}}}}',
+        #         'Thoughts': [],
+        #         'Debug': {},
+        #         'DocReferences': []
+        #     },
+        #     'RequestId': '8e11d31551ce4c3f83f49e6e0dd998b0',
+        #     'Failed': None
+        # }
+        text_dict = json.loads(text)
+        completion_content =  text_dict['finalResult'][node_id]['response']['text']
+        return completion_content
+
+    def calc_tokens(self, messages, completion_content):
+        completion_tokens = len(completion_content)
+        prompt_tokens = 0
+        for message in messages:
+            prompt_tokens += len(message["content"])
+        return completion_tokens, prompt_tokens + completion_tokens

bot/ali/ali_qwen_session.py

@@ -0,0 +1,62 @@
+from bot.session_manager import Session
+from common.log import logger
+
+"""
+    e.g.
+    [
+        {"role": "system", "content": "You are a helpful assistant."},
+        {"role": "user", "content": "Who won the world series in 2020?"},
+        {"role": "assistant", "content": "The Los Angeles Dodgers won the World Series in 2020."},
+        {"role": "user", "content": "Where was it played?"}
+    ]
+"""
+
+class AliQwenSession(Session):
+    def __init__(self, session_id, system_prompt=None, model="qianwen"):
+        super().__init__(session_id, system_prompt)
+        self.model = model
+        self.reset()
+
+    def discard_exceeding(self, max_tokens, cur_tokens=None):
+        precise = True
+        try:
+            cur_tokens = self.calc_tokens()
+        except Exception as e:
+            precise = False
+            if cur_tokens is None:
+                raise e
+            logger.debug("Exception when counting tokens precisely for query: {}".format(e))
+        while cur_tokens > max_tokens:
+            if len(self.messages) > 2:
+                self.messages.pop(1)
+            elif len(self.messages) == 2 and self.messages[1]["role"] == "assistant":
+                self.messages.pop(1)
+                if precise:
+                    cur_tokens = self.calc_tokens()
+                else:
+                    cur_tokens = cur_tokens - max_tokens
+                break
+            elif len(self.messages) == 2 and self.messages[1]["role"] == "user":
+                logger.warn("user message exceed max_tokens. total_tokens={}".format(cur_tokens))
+                break
+            else:
+                logger.debug("max_tokens={}, total_tokens={}, len(messages)={}".format(max_tokens, cur_tokens, len(self.messages)))
+                break
+            if precise:
+                cur_tokens = self.calc_tokens()
+            else:
+                cur_tokens = cur_tokens - max_tokens
+        return cur_tokens
+
+    def calc_tokens(self):
+        return num_tokens_from_messages(self.messages, self.model)
+
+def num_tokens_from_messages(messages, model):
+    """Returns the number of tokens used by a list of messages."""
+    # 官方token计算规则："对于中文文本来说，1个token通常对应一个汉字；对于英文文本来说，1个token通常对应3至4个字母或1个单词"
+    # 详情请产看文档：https://help.aliyun.com/document_detail/2586397.html
+    # 目前根据字符串长度粗略估计token数，不影响正常使用
+    tokens = 0
+    for msg in messages:
+        tokens += len(msg["content"])
+    return tokens

bot/bot_factory.py

@@ -2,6 +2,7 @@
 channel factory
 """
 from common import const
+from common.log import logger
 
 
 def create_bot(bot_type):
@@ -43,4 +44,26 @@ def create_bot(bot_type):
     elif bot_type == const.CLAUDEAI:
         from bot.claude.claude_ai_bot import ClaudeAIBot
         return ClaudeAIBot()
+    elif bot_type == const.CLAUDEAPI:
+        from bot.claudeapi.claude_api_bot import ClaudeAPIBot
+        return ClaudeAPIBot()
+    elif bot_type == const.QWEN:
+        from bot.ali.ali_qwen_bot import AliQwenBot
+        return AliQwenBot()
+    elif bot_type == const.QWEN_DASHSCOPE:
+        from bot.dashscope.dashscope_bot import DashscopeBot
+        return DashscopeBot()
+    elif bot_type == const.GEMINI:
+        from bot.gemini.google_gemini_bot import GoogleGeminiBot
+        return GoogleGeminiBot()
+
+    elif bot_type == const.ZHIPU_AI:
+        from bot.zhipuai.zhipuai_bot import ZHIPUAIBot
+        return ZHIPUAIBot()
+
+    elif bot_type == const.MOONSHOT:
+        from bot.moonshot.moonshot_bot import MoonshotBot
+        return MoonshotBot()
+
+
     raise RuntimeError

bot/chatgpt/chat_gpt_bot.py

@@ -148,8 +148,9 @@ class ChatGPTBot(Bot, OpenAIImage):
                     time.sleep(10)
             elif isinstance(e, openai.error.APIConnectionError):
                 logger.warn("[CHATGPT] APIConnectionError: {}".format(e))
-                need_retry = False
                 result["content"] = "我连接不到你的网络"
+                if need_retry:
+                    time.sleep(5)
             else:
                 logger.exception("[CHATGPT] Exception: {}".format(e))
                 need_retry = False

bot/chatgpt/chat_gpt_session.py

@@ -57,17 +57,20 @@ class ChatGPTSession(Session):
 def num_tokens_from_messages(messages, model):
     """Returns the number of tokens used by a list of messages."""
 
-    if model in ["wenxin", "xunfei"]:
+    if model in ["wenxin", "xunfei", const.GEMINI]:
         return num_tokens_by_character(messages)
 
     import tiktoken
 
-    if model in ["gpt-3.5-turbo-0301", "gpt-35-turbo", "gpt-3.5-turbo-1106"]:
+    if model in ["gpt-3.5-turbo-0301", "gpt-35-turbo", "gpt-3.5-turbo-1106", "moonshot", const.LINKAI_35]:
         return num_tokens_from_messages(messages, model="gpt-3.5-turbo")
     elif model in ["gpt-4-0314", "gpt-4-0613", "gpt-4-32k", "gpt-4-32k-0613", "gpt-3.5-turbo-0613",
-                   "gpt-3.5-turbo-16k", "gpt-3.5-turbo-16k-0613", "gpt-35-turbo-16k", const.GPT4_TURBO_PREVIEW, const.GPT4_VISION_PREVIEW]:
+                   "gpt-3.5-turbo-16k", "gpt-3.5-turbo-16k-0613", "gpt-35-turbo-16k", "gpt-4-turbo-preview",
+                   "gpt-4-1106-preview", const.GPT4_TURBO_PREVIEW, const.GPT4_VISION_PREVIEW, const.GPT4_TURBO_01_25,
+                   const.GPT_4o, const.LINKAI_4o, const.LINKAI_4_TURBO]:
         return num_tokens_from_messages(messages, model="gpt-4")
-
+    elif model.startswith("claude-3"):
+        return num_tokens_from_messages(messages, model="gpt-3.5-turbo")
     try:
         encoding = tiktoken.encoding_for_model(model)
     except KeyError:

bot/claudeapi/claude_api_bot.py

@@ -0,0 +1,133 @@
+# encoding:utf-8
+
+import time
+
+import openai
+import openai.error
+import anthropic
+
+from bot.bot import Bot
+from bot.openai.open_ai_image import OpenAIImage
+from bot.chatgpt.chat_gpt_session import ChatGPTSession
+from bot.gemini.google_gemini_bot import GoogleGeminiBot
+from bot.session_manager import SessionManager
+from bridge.context import ContextType
+from bridge.reply import Reply, ReplyType
+from common.log import logger
+from config import conf
+
+user_session = dict()
+
+
+# OpenAI对话模型API (可用)
+class ClaudeAPIBot(Bot, OpenAIImage):
+    def __init__(self):
+        super().__init__()
+        self.claudeClient = anthropic.Anthropic(
+            api_key=conf().get("claude_api_key")
+        )
+        openai.api_key = conf().get("open_ai_api_key")
+        if conf().get("open_ai_api_base"):
+            openai.api_base = conf().get("open_ai_api_base")
+        proxy = conf().get("proxy")
+        if proxy:
+            openai.proxy = proxy
+
+        self.sessions = SessionManager(ChatGPTSession, model=conf().get("model") or "text-davinci-003")
+
+    def reply(self, query, context=None):
+        # acquire reply content
+        if context and context.type:
+            if context.type == ContextType.TEXT:
+                logger.info("[CLAUDE_API] query={}".format(query))
+                session_id = context["session_id"]
+                reply = None
+                if query == "#清除记忆":
+                    self.sessions.clear_session(session_id)
+                    reply = Reply(ReplyType.INFO, "记忆已清除")
+                elif query == "#清除所有":
+                    self.sessions.clear_all_session()
+                    reply = Reply(ReplyType.INFO, "所有人记忆已清除")
+                else:
+                    session = self.sessions.session_query(query, session_id)
+                    result = self.reply_text(session)
+                    logger.info(result)
+                    total_tokens, completion_tokens, reply_content = (
+                        result["total_tokens"],
+                        result["completion_tokens"],
+                        result["content"],
+                    )
+                    logger.debug(
+                        "[CLAUDE_API] new_query={}, session_id={}, reply_cont={}, completion_tokens={}".format(str(session), session_id, reply_content, completion_tokens)
+                    )
+
+                    if total_tokens == 0:
+                        reply = Reply(ReplyType.ERROR, reply_content)
+                    else:
+                        self.sessions.session_reply(reply_content, session_id, total_tokens)
+                        reply = Reply(ReplyType.TEXT, reply_content)
+                return reply
+            elif context.type == ContextType.IMAGE_CREATE:
+                ok, retstring = self.create_img(query, 0)
+                reply = None
+                if ok:
+                    reply = Reply(ReplyType.IMAGE_URL, retstring)
+                else:
+                    reply = Reply(ReplyType.ERROR, retstring)
+                return reply
+
+    def reply_text(self, session: ChatGPTSession, retry_count=0):
+        try:
+            actual_model = self._model_mapping(conf().get("model"))
+            response = self.claudeClient.messages.create(
+                model=actual_model,
+                max_tokens=1024,
+                # system=conf().get("system"),
+                messages=GoogleGeminiBot.filter_messages(session.messages)
+            )
+            # response = openai.Completion.create(prompt=str(session), **self.args)
+            res_content = response.content[0].text.strip().replace("<|endoftext|>", "")
+            total_tokens = response.usage.input_tokens+response.usage.output_tokens
+            completion_tokens = response.usage.output_tokens
+            logger.info("[CLAUDE_API] reply={}".format(res_content))
+            return {
+                "total_tokens": total_tokens,
+                "completion_tokens": completion_tokens,
+                "content": res_content,
+            }
+        except Exception as e:
+            need_retry = retry_count < 2
+            result = {"completion_tokens": 0, "content": "我现在有点累了，等会再来吧"}
+            if isinstance(e, openai.error.RateLimitError):
+                logger.warn("[CLAUDE_API] RateLimitError: {}".format(e))
+                result["content"] = "提问太快啦，请休息一下再问我吧"
+                if need_retry:
+                    time.sleep(20)
+            elif isinstance(e, openai.error.Timeout):
+                logger.warn("[CLAUDE_API] Timeout: {}".format(e))
+                result["content"] = "我没有收到你的消息"
+                if need_retry:
+                    time.sleep(5)
+            elif isinstance(e, openai.error.APIConnectionError):
+                logger.warn("[CLAUDE_API] APIConnectionError: {}".format(e))
+                need_retry = False
+                result["content"] = "我连接不到你的网络"
+            else:
+                logger.warn("[CLAUDE_API] Exception: {}".format(e))
+                need_retry = False
+                self.sessions.clear_session(session.session_id)
+
+            if need_retry:
+                logger.warn("[CLAUDE_API] 第{}次重试".format(retry_count + 1))
+                return self.reply_text(session, retry_count + 1)
+            else:
+                return result
+
+    def _model_mapping(self, model) -> str:
+        if model == "claude-3-opus":
+            return "claude-3-opus-20240229"
+        elif model == "claude-3-sonnet":
+            return "claude-3-sonnet-20240229"
+        elif model == "claude-3-haiku":
+            return "claude-3-haiku-20240307"
+        return model

bot/dashscope/dashscope_bot.py

@@ -0,0 +1,117 @@
+# encoding:utf-8
+
+from bot.bot import Bot
+from bot.session_manager import SessionManager
+from bridge.context import ContextType
+from bridge.reply import Reply, ReplyType
+from common.log import logger
+from config import conf, load_config
+from .dashscope_session import DashscopeSession
+import os
+import dashscope
+from http import HTTPStatus
+
+
+
+dashscope_models = {
+    "qwen-turbo": dashscope.Generation.Models.qwen_turbo,
+    "qwen-plus": dashscope.Generation.Models.qwen_plus,
+    "qwen-max": dashscope.Generation.Models.qwen_max,
+    "qwen-bailian-v1": dashscope.Generation.Models.bailian_v1
+}
+# ZhipuAI对话模型API
+class DashscopeBot(Bot):
+    def __init__(self):
+        super().__init__()
+        self.sessions = SessionManager(DashscopeSession, model=conf().get("model") or "qwen-plus")
+        self.model_name = conf().get("model") or "qwen-plus"
+        self.api_key = conf().get("dashscope_api_key")
+        os.environ["DASHSCOPE_API_KEY"] = self.api_key
+        self.client = dashscope.Generation
+
+    def reply(self, query, context=None):
+        # acquire reply content
+        if context.type == ContextType.TEXT:
+            logger.info("[DASHSCOPE] query={}".format(query))
+
+            session_id = context["session_id"]
+            reply = None
+            clear_memory_commands = conf().get("clear_memory_commands", ["#清除记忆"])
+            if query in clear_memory_commands:
+                self.sessions.clear_session(session_id)
+                reply = Reply(ReplyType.INFO, "记忆已清除")
+            elif query == "#清除所有":
+                self.sessions.clear_all_session()
+                reply = Reply(ReplyType.INFO, "所有人记忆已清除")
+            elif query == "#更新配置":
+                load_config()
+                reply = Reply(ReplyType.INFO, "配置已更新")
+            if reply:
+                return reply
+            session = self.sessions.session_query(query, session_id)
+            logger.debug("[DASHSCOPE] session query={}".format(session.messages))
+
+            reply_content = self.reply_text(session)
+            logger.debug(
+                "[DASHSCOPE] new_query={}, session_id={}, reply_cont={}, completion_tokens={}".format(
+                    session.messages,
+                    session_id,
+                    reply_content["content"],
+                    reply_content["completion_tokens"],
+                )
+            )
+            if reply_content["completion_tokens"] == 0 and len(reply_content["content"]) > 0:
+                reply = Reply(ReplyType.ERROR, reply_content["content"])
+            elif reply_content["completion_tokens"] > 0:
+                self.sessions.session_reply(reply_content["content"], session_id, reply_content["total_tokens"])
+                reply = Reply(ReplyType.TEXT, reply_content["content"])
+            else:
+                reply = Reply(ReplyType.ERROR, reply_content["content"])
+                logger.debug("[DASHSCOPE] reply {} used 0 tokens.".format(reply_content))
+            return reply
+        else:
+            reply = Reply(ReplyType.ERROR, "Bot不支持处理{}类型的消息".format(context.type))
+            return reply
+
+    def reply_text(self, session: DashscopeSession, retry_count=0) -> dict:
+        """
+        call openai's ChatCompletion to get the answer
+        :param session: a conversation session
+        :param session_id: session id
+        :param retry_count: retry count
+        :return: {}
+        """
+        try:
+            dashscope.api_key = self.api_key
+            response = self.client.call(
+                dashscope_models[self.model_name],
+                messages=session.messages,
+                result_format="message"
+            )
+            if response.status_code == HTTPStatus.OK:
+                content = response.output.choices[0]["message"]["content"]
+                return {
+                    "total_tokens": response.usage["total_tokens"],
+                    "completion_tokens": response.usage["output_tokens"],
+                    "content": content,
+                }
+            else:
+                logger.error('Request id: %s, Status code: %s, error code: %s, error message: %s' % (
+                    response.request_id, response.status_code,
+                    response.code, response.message
+                ))
+                result = {"completion_tokens": 0, "content": "我现在有点累了，等会再来吧"}
+                need_retry = retry_count < 2
+                result = {"completion_tokens": 0, "content": "我现在有点累了，等会再来吧"}
+                if need_retry:
+                    return self.reply_text(session, retry_count + 1)
+                else:
+                    return result
+        except Exception as e:
+            logger.exception(e)
+            need_retry = retry_count < 2
+            result = {"completion_tokens": 0, "content": "我现在有点累了，等会再来吧"}
+            if need_retry:
+                return self.reply_text(session, retry_count + 1)
+            else:
+                return result

bot/dashscope/dashscope_session.py

@@ -0,0 +1,51 @@
+from bot.session_manager import Session
+from common.log import logger
+
+
+class DashscopeSession(Session):
+    def __init__(self, session_id, system_prompt=None, model="qwen-turbo"):
+        super().__init__(session_id)
+        self.reset()
+
+    def discard_exceeding(self, max_tokens, cur_tokens=None):
+        precise = True
+        try:
+            cur_tokens = self.calc_tokens()
+        except Exception as e:
+            precise = False
+            if cur_tokens is None:
+                raise e
+            logger.debug("Exception when counting tokens precisely for query: {}".format(e))
+        while cur_tokens > max_tokens:
+            if len(self.messages) > 2:
+                self.messages.pop(1)
+            elif len(self.messages) == 2 and self.messages[1]["role"] == "assistant":
+                self.messages.pop(1)
+                if precise:
+                    cur_tokens = self.calc_tokens()
+                else:
+                    cur_tokens = cur_tokens - max_tokens
+                break
+            elif len(self.messages) == 2 and self.messages[1]["role"] == "user":
+                logger.warn("user message exceed max_tokens. total_tokens={}".format(cur_tokens))
+                break
+            else:
+                logger.debug("max_tokens={}, total_tokens={}, len(messages)={}".format(max_tokens, cur_tokens,
+                                                                                       len(self.messages)))
+                break
+            if precise:
+                cur_tokens = self.calc_tokens()
+            else:
+                cur_tokens = cur_tokens - max_tokens
+        return cur_tokens
+
+    def calc_tokens(self):
+        return num_tokens_from_messages(self.messages)
+
+
+def num_tokens_from_messages(messages):
+    # 只是大概，具体计算规则：https://help.aliyun.com/zh/dashscope/developer-reference/token-api?spm=a2c4g.11186623.0.0.4d8b12b0BkP3K9
+    tokens = 0
+    for msg in messages:
+        tokens += len(msg["content"])
+    return tokens

bot/gemini/google_gemini_bot.py

@@ -0,0 +1,79 @@
+"""
+Google gemini bot
+
+@author zhayujie
+@Date 2023/12/15
+"""
+# encoding:utf-8
+
+from bot.bot import Bot
+import google.generativeai as genai
+from bot.session_manager import SessionManager
+from bridge.context import ContextType, Context
+from bridge.reply import Reply, ReplyType
+from common.log import logger
+from config import conf
+from bot.baidu.baidu_wenxin_session import BaiduWenxinSession
+
+
+# OpenAI对话模型API (可用)
+class GoogleGeminiBot(Bot):
+
+    def __init__(self):
+        super().__init__()
+        self.api_key = conf().get("gemini_api_key")
+        # 复用文心的token计算方式
+        self.sessions = SessionManager(BaiduWenxinSession, model=conf().get("model") or "gpt-3.5-turbo")
+
+    def reply(self, query, context: Context = None) -> Reply:
+        try:
+            if context.type != ContextType.TEXT:
+                logger.warn(f"[Gemini] Unsupported message type, type={context.type}")
+                return Reply(ReplyType.TEXT, None)
+            logger.info(f"[Gemini] query={query}")
+            session_id = context["session_id"]
+            session = self.sessions.session_query(query, session_id)
+            gemini_messages = self._convert_to_gemini_messages(self.filter_messages(session.messages))
+            genai.configure(api_key=self.api_key)
+            model = genai.GenerativeModel('gemini-pro')
+            response = model.generate_content(gemini_messages)
+            reply_text = response.text
+            self.sessions.session_reply(reply_text, session_id)
+            logger.info(f"[Gemini] reply={reply_text}")
+            return Reply(ReplyType.TEXT, reply_text)
+        except Exception as e:
+            logger.error("[Gemini] fetch reply error, may contain unsafe content")
+            logger.error(e)
+            return Reply(ReplyType.ERROR, "invoke [Gemini] api failed!")
+
+    def _convert_to_gemini_messages(self, messages: list):
+        res = []
+        for msg in messages:
+            if msg.get("role") == "user":
+                role = "user"
+            elif msg.get("role") == "assistant":
+                role = "model"
+            else:
+                continue
+            res.append({
+                "role": role,
+                "parts": [{"text": msg.get("content")}]
+            })
+        return res
+
+    @staticmethod
+    def filter_messages(messages: list):
+        res = []
+        turn = "user"
+        if not messages:
+            return res
+        for i in range(len(messages) - 1, -1, -1):
+            message = messages[i]
+            if message.get("role") != turn:
+                continue
+            res.insert(0, message)
+            if turn == "user":
+                turn = "assistant"
+            elif turn == "assistant":
+                turn = "user"
+        return res

bot/linkai/link_ai_bot.py

@@ -1,10 +1,10 @@
 # access LinkAI knowledge base platform
 # docs: https://link-ai.tech/platform/link-app/wechat
 
+import re
 import time
-
 import requests
-
+import config
 from bot.bot import Bot
 from bot.chatgpt.chat_gpt_session import ChatGPTSession
 from bot.session_manager import SessionManager
@@ -15,7 +15,7 @@ from config import conf, pconf
 import threading
 from common import memory, utils
 import base64
-
+import os
 
 class LinkAIBot(Bot):
     # authentication failed
@@ -31,6 +31,9 @@ class LinkAIBot(Bot):
         if context.type == ContextType.TEXT:
             return self._chat(query, context)
         elif context.type == ContextType.IMAGE_CREATE:
+            if not conf().get("text_to_image"):
+                logger.warn("[LinkAI] text_to_image is not enabled, ignore the IMAGE_CREATE request")
+                return Reply(ReplyType.TEXT, "")
             ok, res = self.create_img(query, 0)
             if ok:
                 reply = Reply(ReplyType.IMAGE_URL, res)
@@ -60,7 +63,8 @@ class LinkAIBot(Bot):
                 logger.info(f"[LINKAI] won't set appcode because a plugin ({context['generate_breaked_by']}) affected the context")
                 app_code = None
             else:
-                app_code = context.kwargs.get("app_code") or conf().get("linkai_app_code")
+                plugin_app_code = self._find_group_mapping_code(context)
+                app_code = context.kwargs.get("app_code") or plugin_app_code or conf().get("linkai_app_code")
             linkai_api_key = conf().get("linkai_api_key")
 
             session_id = context["session_id"]
@@ -79,7 +83,6 @@ class LinkAIBot(Bot):
             if session_message[0].get("role") == "system":
                 if app_code or model == "wenxin":
                     session_message.pop(0)
-
             body = {
                 "app_code": app_code,
                 "messages": session_message,
@@ -88,15 +91,38 @@ class LinkAIBot(Bot):
                 "top_p": conf().get("top_p", 1),
                 "frequency_penalty": conf().get("frequency_penalty", 0.0),  # [-2,2]之间，该值越大则更倾向于产生不同的内容
                 "presence_penalty": conf().get("presence_penalty", 0.0),  # [-2,2]之间，该值越大则更倾向于产生不同的内容
+                "session_id": session_id,
+                "sender_id": session_id,
+                "channel_type": conf().get("channel_type", "wx")
             }
+            try:
+                from linkai import LinkAIClient
+                client_id = LinkAIClient.fetch_client_id()
+                if client_id:
+                    body["client_id"] = client_id
+                    # start: client info deliver
+                    if context.kwargs.get("msg"):
+                        body["session_id"] = context.kwargs.get("msg").from_user_id
+                        if context.kwargs.get("msg").is_group:
+                            body["is_group"] = True
+                            body["group_name"] = context.kwargs.get("msg").from_user_nickname
+                            body["sender_name"] = context.kwargs.get("msg").actual_user_nickname
+                        else:
+                            if body.get("channel_type") in ["wechatcom_app"]:
+                                body["sender_name"] = context.kwargs.get("msg").from_user_id
+                            else:
+                                body["sender_name"] = context.kwargs.get("msg").from_user_nickname
+
+            except Exception as e:
+                pass
             file_id = context.kwargs.get("file_id")
             if file_id:
                 body["file_id"] = file_id
-            logger.info(f"[LINKAI] query={query}, app_code={app_code}, mode={body.get('model')}, file_id={file_id}")
+            logger.info(f"[LINKAI] query={query}, app_code={app_code}, model={body.get('model')}, file_id={file_id}")
             headers = {"Authorization": "Bearer " + linkai_api_key}
 
             # do http request
-            base_url = conf().get("linkai_api_base", "https://api.link-ai.chat")
+            base_url = conf().get("linkai_api_base", "https://api.link-ai.tech")
             res = requests.post(url=base_url + "/v1/chat/completions", json=body, headers=headers,
                                 timeout=conf().get("request_timeout", 180))
             if res.status_code == 200:
@@ -104,9 +130,12 @@ class LinkAIBot(Bot):
                 response = res.json()
                 reply_content = response["choices"][0]["message"]["content"]
                 total_tokens = response["usage"]["total_tokens"]
-                logger.info(f"[LINKAI] reply={reply_content}, total_tokens={total_tokens}")
-                self.sessions.session_reply(reply_content, session_id, total_tokens, query=query)
-    
+                res_code = response.get('code')
+                logger.info(f"[LINKAI] reply={reply_content}, total_tokens={total_tokens}, res_code={res_code}")
+                if res_code == 429:
+                    logger.warn(f"[LINKAI] 用户访问超出限流配置，sender_id={body.get('sender_id')}")
+                else:
+                    self.sessions.session_reply(reply_content, session_id, total_tokens, query=query)
                 agent_suffix = self._fetch_agent_suffix(response)
                 if agent_suffix:
                     reply_content += agent_suffix
@@ -118,6 +147,9 @@ class LinkAIBot(Bot):
                 if response["choices"][0].get("img_urls"):
                     thread = threading.Thread(target=self._send_image, args=(context.get("channel"), context, response["choices"][0].get("img_urls")))
                     thread.start()
+                    if response["choices"][0].get("text_content"):
+                        reply_content = response["choices"][0].get("text_content")
+                reply_content = self._process_url(reply_content)
                 return Reply(ReplyType.TEXT, reply_content)
 
             else:
@@ -132,7 +164,10 @@ class LinkAIBot(Bot):
                     logger.warn(f"[LINKAI] do retry, times={retry_count}")
                     return self._chat(query, context, retry_count + 1)
 
-                return Reply(ReplyType.TEXT, "提问太快啦，请休息一下再问我吧")
+                error_reply = "提问太快啦，请休息一下再问我吧"
+                if res.status_code == 409:
+                    error_reply = "这个问题我还没有学会，请问我其它问题吧"
+                return Reply(ReplyType.TEXT, error_reply)
 
         except Exception as e:
             logger.exception(e)
@@ -164,6 +199,18 @@ class LinkAIBot(Bot):
         except Exception as e:
             logger.exception(e)
 
+    def _find_group_mapping_code(self, context):
+        try:
+            if context.kwargs.get("isgroup"):
+                group_name = context.kwargs.get("msg").from_user_nickname
+                if config.plugin_config and config.plugin_config.get("linkai"):
+                    linkai_config = config.plugin_config.get("linkai")
+                    group_mapping = linkai_config.get("group_app_map")
+                    if group_mapping and group_name:
+                        return group_mapping.get(group_name)
+        except Exception as e:
+            logger.exception(e)
+            return None
 
     def _build_vision_msg(self, query: str, path: str):
         try:
@@ -211,10 +258,10 @@ class LinkAIBot(Bot):
             }
             if self.args.get("max_tokens"):
                 body["max_tokens"] = self.args.get("max_tokens")
-            headers = {"Authorization": "Bearer " +  conf().get("linkai_api_key")}
+            headers = {"Authorization": "Bearer " + conf().get("linkai_api_key")}
 
             # do http request
-            base_url = conf().get("linkai_api_base", "https://api.link-ai.chat")
+            base_url = conf().get("linkai_api_base", "https://api.link-ai.tech")
             res = requests.post(url=base_url + "/v1/chat/completions", json=body, headers=headers,
                                 timeout=conf().get("request_timeout", 180))
             if res.status_code == 200:
@@ -257,7 +304,7 @@ class LinkAIBot(Bot):
     def _fetch_app_info(self, app_code: str):
         headers = {"Authorization": "Bearer " + conf().get("linkai_api_key")}
         # do http request
-        base_url = conf().get("linkai_api_base", "https://api.link-ai.chat")
+        base_url = conf().get("linkai_api_base", "https://api.link-ai.tech")
         params = {"app_code": app_code}
         res = requests.get(url=base_url + "/v1/app/info", params=params, headers=headers, timeout=(5, 10))
         if res.status_code == 200:
@@ -279,7 +326,7 @@ class LinkAIBot(Bot):
                 "response_format": "url",
                 "img_proxy": conf().get("image_proxy")
             }
-            url = conf().get("linkai_api_base", "https://api.link-ai.chat") + "/v1/images/generations"
+            url = conf().get("linkai_api_base", "https://api.link-ai.tech") + "/v1/images/generations"
             res = requests.post(url, headers=headers, json=data, timeout=(5, 90))
             t2 = time.time()
             image_url = res.json()["data"][0]["url"]
@@ -325,7 +372,9 @@ class LinkAIBot(Bot):
                         suffix += f"{turn.get('thought')}\n"
                     if plugin_name:
                         plugin_list.append(turn.get('plugin_name'))
-                        suffix += f"{turn.get('plugin_icon')} {turn.get('plugin_name')}"
+                        if turn.get('plugin_icon'):
+                            suffix += f"{turn.get('plugin_icon')} "
+                        suffix += f"{turn.get('plugin_name')}"
                         if turn.get('plugin_input'):
                             suffix += f"：{turn.get('plugin_input')}"
                     if i < len(chain) - 1:
@@ -336,18 +385,58 @@ class LinkAIBot(Bot):
         except Exception as e:
             logger.exception(e)
 
+    def _process_url(self, text):
+        try:
+            url_pattern = re.compile(r'\[(.*?)\]\((http[s]?://.*?)\)')
+            def replace_markdown_url(match):
+                return f"{match.group(2)}"
+            return url_pattern.sub(replace_markdown_url, text)
+        except Exception as e:
+            logger.error(e)
 
     def _send_image(self, channel, context, image_urls):
         if not image_urls:
             return
+        max_send_num = conf().get("max_media_send_count")
+        send_interval = conf().get("media_send_interval")
         try:
+            i = 0
             for url in image_urls:
-                reply = Reply(ReplyType.IMAGE_URL, url)
+                if max_send_num and i >= max_send_num:
+                    continue
+                i += 1
+                if url.endswith(".mp4"):
+                    reply_type = ReplyType.VIDEO_URL
+                elif url.endswith(".pdf") or url.endswith(".doc") or url.endswith(".docx") or url.endswith(".csv"):
+                    reply_type = ReplyType.FILE
+                    url = _download_file(url)
+                    if not url:
+                        continue
+                else:
+                    reply_type = ReplyType.IMAGE_URL
+                reply = Reply(reply_type, url)
                 channel.send(reply, context)
+                if send_interval:
+                    time.sleep(send_interval)
         except Exception as e:
             logger.error(e)
 
 
+def _download_file(url: str):
+    try:
+        file_path = "tmp"
+        if not os.path.exists(file_path):
+            os.makedirs(file_path)
+        file_name = url.split("/")[-1]  # 获取文件名
+        file_path = os.path.join(file_path, file_name)
+        response = requests.get(url)
+        with open(file_path, "wb") as f:
+            f.write(response.content)
+        return file_path
+    except Exception as e:
+        logger.warn(e)
+
+
 class LinkAISessionManager(SessionManager):
     def session_msg_query(self, query, session_id):
         session = self.build_session(session_id)
@@ -362,7 +451,7 @@ class LinkAISessionManager(SessionManager):
         try:
             max_tokens = conf().get("conversation_max_tokens", 2500)
             tokens_cnt = session.discard_exceeding(max_tokens, total_tokens)
-            logger.info(f"[LinkAI] chat history discard, before tokens={total_tokens}, now tokens={tokens_cnt}")
+            logger.debug(f"[LinkAI] chat history, before tokens={total_tokens}, now tokens={tokens_cnt}")
         except Exception as e:
             logger.warning("Exception when counting tokens precisely for session: {}".format(str(e)))
         return session
@@ -370,12 +459,9 @@ class LinkAISessionManager(SessionManager):
 
 class LinkAISession(ChatGPTSession):
     def calc_tokens(self):
-        try:
-            cur_tokens = super().calc_tokens()
-        except Exception as e:
-            logger.debug("Exception when counting tokens precisely for query: {}".format(e))
-            cur_tokens = len(str(self.messages))
-        return cur_tokens
+        if not self.messages:
+            return 0
+        return len(str(self.messages))
 
     def discard_exceeding(self, max_tokens, cur_tokens=None):
         cur_tokens = self.calc_tokens()

bot/moonshot/moonshot_bot.py

@@ -0,0 +1,143 @@
+# encoding:utf-8
+
+import time
+
+import openai
+import openai.error
+from bot.bot import Bot
+from bot.session_manager import SessionManager
+from bridge.context import ContextType
+from bridge.reply import Reply, ReplyType
+from common.log import logger
+from config import conf, load_config
+from .moonshot_session import MoonshotSession
+import requests
+
+
+# ZhipuAI对话模型API
+class MoonshotBot(Bot):
+    def __init__(self):
+        super().__init__()
+        self.sessions = SessionManager(MoonshotSession, model=conf().get("model") or "moonshot-v1-128k")
+        self.args = {
+            "model": conf().get("model") or "moonshot-v1-128k",  # 对话模型的名称
+            "temperature": conf().get("temperature", 0.3),  # 如果设置，值域须为 [0, 1] 我们推荐 0.3，以达到较合适的效果。
+            "top_p": conf().get("top_p", 1.0),  # 使用默认值
+        }
+        self.api_key = conf().get("moonshot_api_key")
+        self.base_url = conf().get("moonshot_base_url", "https://api.moonshot.cn/v1/chat/completions")
+
+    def reply(self, query, context=None):
+        # acquire reply content
+        if context.type == ContextType.TEXT:
+            logger.info("[MOONSHOT_AI] query={}".format(query))
+
+            session_id = context["session_id"]
+            reply = None
+            clear_memory_commands = conf().get("clear_memory_commands", ["#清除记忆"])
+            if query in clear_memory_commands:
+                self.sessions.clear_session(session_id)
+                reply = Reply(ReplyType.INFO, "记忆已清除")
+            elif query == "#清除所有":
+                self.sessions.clear_all_session()
+                reply = Reply(ReplyType.INFO, "所有人记忆已清除")
+            elif query == "#更新配置":
+                load_config()
+                reply = Reply(ReplyType.INFO, "配置已更新")
+            if reply:
+                return reply
+            session = self.sessions.session_query(query, session_id)
+            logger.debug("[MOONSHOT_AI] session query={}".format(session.messages))
+
+            model = context.get("moonshot_model")
+            new_args = self.args.copy()
+            if model:
+                new_args["model"] = model
+            # if context.get('stream'):
+            #     # reply in stream
+            #     return self.reply_text_stream(query, new_query, session_id)
+
+            reply_content = self.reply_text(session, args=new_args)
+            logger.debug(
+                "[MOONSHOT_AI] new_query={}, session_id={}, reply_cont={}, completion_tokens={}".format(
+                    session.messages,
+                    session_id,
+                    reply_content["content"],
+                    reply_content["completion_tokens"],
+                )
+            )
+            if reply_content["completion_tokens"] == 0 and len(reply_content["content"]) > 0:
+                reply = Reply(ReplyType.ERROR, reply_content["content"])
+            elif reply_content["completion_tokens"] > 0:
+                self.sessions.session_reply(reply_content["content"], session_id, reply_content["total_tokens"])
+                reply = Reply(ReplyType.TEXT, reply_content["content"])
+            else:
+                reply = Reply(ReplyType.ERROR, reply_content["content"])
+                logger.debug("[MOONSHOT_AI] reply {} used 0 tokens.".format(reply_content))
+            return reply
+        else:
+            reply = Reply(ReplyType.ERROR, "Bot不支持处理{}类型的消息".format(context.type))
+            return reply
+
+    def reply_text(self, session: MoonshotSession, args=None, retry_count=0) -> dict:
+        """
+        call openai's ChatCompletion to get the answer
+        :param session: a conversation session
+        :param session_id: session id
+        :param retry_count: retry count
+        :return: {}
+        """
+        try:
+            headers = {
+                "Content-Type": "application/json",
+                "Authorization": "Bearer " + self.api_key
+            }
+            body = args
+            body["messages"] = session.messages
+            # logger.debug("[MOONSHOT_AI] response={}".format(response))
+            # logger.info("[MOONSHOT_AI] reply={}, total_tokens={}".format(response.choices[0]['message']['content'], response["usage"]["total_tokens"]))
+            res = requests.post(
+                self.base_url,
+                headers=headers,
+                json=body
+            )
+            if res.status_code == 200:
+                response = res.json()
+                return {
+                    "total_tokens": response["usage"]["total_tokens"],
+                    "completion_tokens": response["usage"]["completion_tokens"],
+                    "content": response["choices"][0]["message"]["content"]
+                }
+            else:
+                response = res.json()
+                error = response.get("error")
+                logger.error(f"[MOONSHOT_AI] chat failed, status_code={res.status_code}, "
+                             f"msg={error.get('message')}, type={error.get('type')}")
+
+                result = {"completion_tokens": 0, "content": "提问太快啦，请休息一下再问我吧"}
+                need_retry = False
+                if res.status_code >= 500:
+                    # server error, need retry
+                    logger.warn(f"[MOONSHOT_AI] do retry, times={retry_count}")
+                    need_retry = retry_count < 2
+                elif res.status_code == 401:
+                    result["content"] = "授权失败，请检查API Key是否正确"
+                elif res.status_code == 429:
+                    result["content"] = "请求过于频繁，请稍后再试"
+                    need_retry = retry_count < 2
+                else:
+                    need_retry = False
+
+                if need_retry:
+                    time.sleep(3)
+                    return self.reply_text(session, args, retry_count + 1)
+                else:
+                    return result
+        except Exception as e:
+            logger.exception(e)
+            need_retry = retry_count < 2
+            result = {"completion_tokens": 0, "content": "我现在有点累了，等会再来吧"}
+            if need_retry:
+                return self.reply_text(session, args, retry_count + 1)
+            else:
+                return result

bot/moonshot/moonshot_session.py

@@ -0,0 +1,51 @@
+from bot.session_manager import Session
+from common.log import logger
+
+
+class MoonshotSession(Session):
+    def __init__(self, session_id, system_prompt=None, model="moonshot-v1-128k"):
+        super().__init__(session_id, system_prompt)
+        self.model = model
+        self.reset()
+
+    def discard_exceeding(self, max_tokens, cur_tokens=None):
+        precise = True
+        try:
+            cur_tokens = self.calc_tokens()
+        except Exception as e:
+            precise = False
+            if cur_tokens is None:
+                raise e
+            logger.debug("Exception when counting tokens precisely for query: {}".format(e))
+        while cur_tokens > max_tokens:
+            if len(self.messages) > 2:
+                self.messages.pop(1)
+            elif len(self.messages) == 2 and self.messages[1]["role"] == "assistant":
+                self.messages.pop(1)
+                if precise:
+                    cur_tokens = self.calc_tokens()
+                else:
+                    cur_tokens = cur_tokens - max_tokens
+                break
+            elif len(self.messages) == 2 and self.messages[1]["role"] == "user":
+                logger.warn("user message exceed max_tokens. total_tokens={}".format(cur_tokens))
+                break
+            else:
+                logger.debug("max_tokens={}, total_tokens={}, len(messages)={}".format(max_tokens, cur_tokens,
+                                                                                       len(self.messages)))
+                break
+            if precise:
+                cur_tokens = self.calc_tokens()
+            else:
+                cur_tokens = cur_tokens - max_tokens
+        return cur_tokens
+
+    def calc_tokens(self):
+        return num_tokens_from_messages(self.messages, self.model)
+
+
+def num_tokens_from_messages(messages, model):
+    tokens = 0
+    for msg in messages:
+        tokens += len(msg["content"])
+    return tokens

bot/openai/open_ai_image.py

@@ -15,7 +15,7 @@ class OpenAIImage(object):
         if conf().get("rate_limit_dalle"):
             self.tb4dalle = TokenBucket(conf().get("rate_limit_dalle", 50))
 
-    def create_img(self, query, retry_count=0, api_key=None):
+    def create_img(self, query, retry_count=0, api_key=None, api_base=None):
         try:
             if conf().get("rate_limit_dalle") and not self.tb4dalle.get_token():
                 return False, "请求太快了，请休息一下再问我吧"

bot/xunfei/xunfei_spark_bot.py

@@ -40,11 +40,15 @@ class XunFeiBot(Bot):
         self.app_id = conf().get("xunfei_app_id")
         self.api_key = conf().get("xunfei_api_key")
         self.api_secret = conf().get("xunfei_api_secret")
-        # 默认使用v3.0版本，2.0版本可设置为generalv2，  1.5版本可设置为 general
-        self.domain = "generalv2"
-        # 默认使用v3.0版本，1.5版本可设置为 "ws://spark-api.xf-yun.com/v1.1/chat"，
-        # 2.0版本可设置为 "ws://spark-api.xf-yun.com/v2.1/chat"
-        self.spark_url = "ws://spark-api.xf-yun.com/v3.1/chat"
+        # 默认使用v2.0版本: "generalv2"
+        # v1.5版本为 "general"
+        # v3.0版本为: "generalv3"
+        self.domain = "generalv3"
+        # 默认使用v2.0版本: "ws://spark-api.xf-yun.com/v2.1/chat"
+        # v1.5版本为: "ws://spark-api.xf-yun.com/v1.1/chat"
+        # v3.0版本为: "ws://spark-api.xf-yun.com/v3.1/chat"
+        # v3.5版本为: "wss://spark-api.xf-yun.com/v3.5/chat"
+        self.spark_url = "wss://spark-api.xf-yun.com/v3.5/chat"
         self.host = urlparse(self.spark_url).netloc
         self.path = urlparse(self.spark_url).path
         # 和wenxin使用相同的session机制

bot/zhipuai/zhipu_ai_image.py

@@ -0,0 +1,29 @@
+from common.log import logger
+from config import conf
+
+
+# ZhipuAI提供的画图接口
+
+class ZhipuAIImage(object):
+    def __init__(self):
+        from zhipuai import ZhipuAI
+        self.client = ZhipuAI(api_key=conf().get("zhipu_ai_api_key"))
+
+    def create_img(self, query, retry_count=0, api_key=None, api_base=None):
+        try:
+            if conf().get("rate_limit_dalle"):
+                return False, "请求太快了，请休息一下再问我吧"
+            logger.info("[ZHIPU_AI] image_query={}".format(query))
+            response = self.client.images.generations(
+                prompt=query,
+                n=1,  # 每次生成图片的数量
+                model=conf().get("text_to_image") or "cogview-3",
+                size=conf().get("image_create_size", "1024x1024"),  # 图片大小,可选有 256x256, 512x512, 1024x1024
+                quality="standard",
+            )
+            image_url = response.data[0].url
+            logger.info("[ZHIPU_AI] image_url={}".format(image_url))
+            return True, image_url
+        except Exception as e:
+            logger.exception(e)
+            return False, "画图出现问题，请休息一下再问我吧"

bot/zhipuai/zhipu_ai_session.py

@@ -0,0 +1,53 @@
+from bot.session_manager import Session
+from common.log import logger
+
+
+class ZhipuAISession(Session):
+    def __init__(self, session_id, system_prompt=None, model="glm-4"):
+        super().__init__(session_id, system_prompt)
+        self.model = model
+        self.reset()
+        if not system_prompt:
+            logger.warn("[ZhiPu] `character_desc` can not be empty")
+
+    def discard_exceeding(self, max_tokens, cur_tokens=None):
+        precise = True
+        try:
+            cur_tokens = self.calc_tokens()
+        except Exception as e:
+            precise = False
+            if cur_tokens is None:
+                raise e
+            logger.debug("Exception when counting tokens precisely for query: {}".format(e))
+        while cur_tokens > max_tokens:
+            if len(self.messages) > 2:
+                self.messages.pop(1)
+            elif len(self.messages) == 2 and self.messages[1]["role"] == "assistant":
+                self.messages.pop(1)
+                if precise:
+                    cur_tokens = self.calc_tokens()
+                else:
+                    cur_tokens = cur_tokens - max_tokens
+                break
+            elif len(self.messages) == 2 and self.messages[1]["role"] == "user":
+                logger.warn("user message exceed max_tokens. total_tokens={}".format(cur_tokens))
+                break
+            else:
+                logger.debug("max_tokens={}, total_tokens={}, len(messages)={}".format(max_tokens, cur_tokens,
+                                                                                       len(self.messages)))
+                break
+            if precise:
+                cur_tokens = self.calc_tokens()
+            else:
+                cur_tokens = cur_tokens - max_tokens
+        return cur_tokens
+
+    def calc_tokens(self):
+        return num_tokens_from_messages(self.messages, self.model)
+
+
+def num_tokens_from_messages(messages, model):
+    tokens = 0
+    for msg in messages:
+        tokens += len(msg["content"])
+    return tokens

bot/zhipuai/zhipuai_bot.py

@@ -0,0 +1,149 @@
+# encoding:utf-8
+
+import time
+
+import openai
+import openai.error
+from bot.bot import Bot
+from bot.zhipuai.zhipu_ai_session import ZhipuAISession
+from bot.zhipuai.zhipu_ai_image import ZhipuAIImage
+from bot.session_manager import SessionManager
+from bridge.context import ContextType
+from bridge.reply import Reply, ReplyType
+from common.log import logger
+from config import conf, load_config
+from zhipuai import ZhipuAI
+
+
+# ZhipuAI对话模型API
+class ZHIPUAIBot(Bot, ZhipuAIImage):
+    def __init__(self):
+        super().__init__()
+        self.sessions = SessionManager(ZhipuAISession, model=conf().get("model") or "ZHIPU_AI")
+        self.args = {
+            "model": conf().get("model") or "glm-4",  # 对话模型的名称
+            "temperature": conf().get("temperature", 0.9),  # 值在(0,1)之间(智谱AI 的温度不能取 0 或者 1)
+            "top_p": conf().get("top_p", 0.7),  # 值在(0,1)之间(智谱AI 的 top_p 不能取 0 或者 1)
+        }
+        self.client = ZhipuAI(api_key=conf().get("zhipu_ai_api_key"))
+
+    def reply(self, query, context=None):
+        # acquire reply content
+        if context.type == ContextType.TEXT:
+            logger.info("[ZHIPU_AI] query={}".format(query))
+
+            session_id = context["session_id"]
+            reply = None
+            clear_memory_commands = conf().get("clear_memory_commands", ["#清除记忆"])
+            if query in clear_memory_commands:
+                self.sessions.clear_session(session_id)
+                reply = Reply(ReplyType.INFO, "记忆已清除")
+            elif query == "#清除所有":
+                self.sessions.clear_all_session()
+                reply = Reply(ReplyType.INFO, "所有人记忆已清除")
+            elif query == "#更新配置":
+                load_config()
+                reply = Reply(ReplyType.INFO, "配置已更新")
+            if reply:
+                return reply
+            session = self.sessions.session_query(query, session_id)
+            logger.debug("[ZHIPU_AI] session query={}".format(session.messages))
+
+            api_key = context.get("openai_api_key") or openai.api_key
+            model = context.get("gpt_model")
+            new_args = None
+            if model:
+                new_args = self.args.copy()
+                new_args["model"] = model
+            # if context.get('stream'):
+            #     # reply in stream
+            #     return self.reply_text_stream(query, new_query, session_id)
+
+            reply_content = self.reply_text(session, api_key, args=new_args)
+            logger.debug(
+                "[ZHIPU_AI] new_query={}, session_id={}, reply_cont={}, completion_tokens={}".format(
+                    session.messages,
+                    session_id,
+                    reply_content["content"],
+                    reply_content["completion_tokens"],
+                )
+            )
+            if reply_content["completion_tokens"] == 0 and len(reply_content["content"]) > 0:
+                reply = Reply(ReplyType.ERROR, reply_content["content"])
+            elif reply_content["completion_tokens"] > 0:
+                self.sessions.session_reply(reply_content["content"], session_id, reply_content["total_tokens"])
+                reply = Reply(ReplyType.TEXT, reply_content["content"])
+            else:
+                reply = Reply(ReplyType.ERROR, reply_content["content"])
+                logger.debug("[ZHIPU_AI] reply {} used 0 tokens.".format(reply_content))
+            return reply
+        elif context.type == ContextType.IMAGE_CREATE:
+            ok, retstring = self.create_img(query, 0)
+            reply = None
+            if ok:
+                reply = Reply(ReplyType.IMAGE_URL, retstring)
+            else:
+                reply = Reply(ReplyType.ERROR, retstring)
+            return reply
+
+        else:
+            reply = Reply(ReplyType.ERROR, "Bot不支持处理{}类型的消息".format(context.type))
+            return reply
+
+    def reply_text(self, session: ZhipuAISession, api_key=None, args=None, retry_count=0) -> dict:
+        """
+        call openai's ChatCompletion to get the answer
+        :param session: a conversation session
+        :param session_id: session id
+        :param retry_count: retry count
+        :return: {}
+        """
+        try:
+            # if conf().get("rate_limit_chatgpt") and not self.tb4chatgpt.get_token():
+            #     raise openai.error.RateLimitError("RateLimitError: rate limit exceeded")
+            # if api_key == None, the default openai.api_key will be used
+            if args is None:
+                args = self.args
+            # response = openai.ChatCompletion.create(api_key=api_key, messages=session.messages, **args)
+            response = self.client.chat.completions.create(messages=session.messages, **args)
+            # logger.debug("[ZHIPU_AI] response={}".format(response))
+            # logger.info("[ZHIPU_AI] reply={}, total_tokens={}".format(response.choices[0]['message']['content'], response["usage"]["total_tokens"]))
+
+            return {
+                "total_tokens": response.usage.total_tokens,
+                "completion_tokens": response.usage.completion_tokens,
+                "content": response.choices[0].message.content,
+            }
+        except Exception as e:
+            need_retry = retry_count < 2
+            result = {"completion_tokens": 0, "content": "我现在有点累了，等会再来吧"}
+            if isinstance(e, openai.error.RateLimitError):
+                logger.warn("[ZHIPU_AI] RateLimitError: {}".format(e))
+                result["content"] = "提问太快啦，请休息一下再问我吧"
+                if need_retry:
+                    time.sleep(20)
+            elif isinstance(e, openai.error.Timeout):
+                logger.warn("[ZHIPU_AI] Timeout: {}".format(e))
+                result["content"] = "我没有收到你的消息"
+                if need_retry:
+                    time.sleep(5)
+            elif isinstance(e, openai.error.APIError):
+                logger.warn("[ZHIPU_AI] Bad Gateway: {}".format(e))
+                result["content"] = "请再问我一次"
+                if need_retry:
+                    time.sleep(10)
+            elif isinstance(e, openai.error.APIConnectionError):
+                logger.warn("[ZHIPU_AI] APIConnectionError: {}".format(e))
+                result["content"] = "我连接不到你的网络"
+                if need_retry:
+                    time.sleep(5)
+            else:
+                logger.exception("[ZHIPU_AI] Exception: {}".format(e), e)
+                need_retry = False
+                self.sessions.clear_session(session.session_id)
+
+            if need_retry:
+                logger.warn("[ZHIPU_AI] 第{}次重试".format(retry_count + 1))
+                return self.reply_text(session, api_key, args, retry_count + 1)
+            else:
+                return result

bridge/bridge.py

@@ -18,6 +18,7 @@ class Bridge(object):
             "text_to_voice": conf().get("text_to_voice", "google"),
             "translate": conf().get("translate", "baidu"),
         }
+        # 这边取配置的模型
         model_type = conf().get("model") or const.GPT35
         if model_type in ["text-davinci-003"]:
             self.btype["chat"] = const.OPEN_AI
@@ -27,17 +28,34 @@ class Bridge(object):
             self.btype["chat"] = const.BAIDU
         if model_type in ["xunfei"]:
             self.btype["chat"] = const.XUNFEI
+        if model_type in [const.QWEN]:
+            self.btype["chat"] = const.QWEN
+        if model_type in [const.QWEN_TURBO, const.QWEN_PLUS, const.QWEN_MAX]:
+            self.btype["chat"] = const.QWEN_DASHSCOPE
+        if model_type in [const.GEMINI]:
+            self.btype["chat"] = const.GEMINI
+        if model_type in [const.ZHIPU_AI]:
+            self.btype["chat"] = const.ZHIPU_AI
+        if model_type and model_type.startswith("claude-3"):
+            self.btype["chat"] = const.CLAUDEAPI
+
+        if model_type in ["claude"]:
+            self.btype["chat"] = const.CLAUDEAI
+
+        if model_type in ["moonshot-v1-8k", "moonshot-v1-32k", "moonshot-v1-128k"]:
+            self.btype["chat"] = const.MOONSHOT
+
         if conf().get("use_linkai") and conf().get("linkai_api_key"):
             self.btype["chat"] = const.LINKAI
             if not conf().get("voice_to_text") or conf().get("voice_to_text") in ["openai"]:
                 self.btype["voice_to_text"] = const.LINKAI
             if not conf().get("text_to_voice") or conf().get("text_to_voice") in ["openai", const.TTS_1, const.TTS_1_HD]:
                 self.btype["text_to_voice"] = const.LINKAI
-        if model_type in ["claude"]:
-            self.btype["chat"] = const.CLAUDEAI
+
         self.bots = {}
         self.chat_bots = {}
 
+    # 模型对应的接口
     def get_bot(self, typename):
         if self.bots.get(typename) is None:
             logger.info("create bot {} for {}".format(self.btype[typename], typename))

bridge/context.py

@@ -16,6 +16,8 @@ class ContextType(Enum):
     JOIN_GROUP = 20  # 加入群聊
     PATPAT = 21  # 拍了拍
     FUNCTION = 22  # 函数调用
+    EXIT_GROUP = 23 #退出
+
 
     def __str__(self):
         return self.name

bridge/reply.py

@@ -11,7 +11,7 @@ class ReplyType(Enum):
     VIDEO_URL = 5  # 视频URL
     FILE = 6  # 文件
     CARD = 7  # 微信名片，仅支持ntchat
-    InviteRoom = 8  # 邀请好友进群
+    INVITE_ROOM = 8  # 邀请好友进群
     INFO = 9
     ERROR = 10
     TEXT_ = 11  # 强制文本

channel/channel.py

@@ -8,6 +8,7 @@ from bridge.reply import *
 
 
 class Channel(object):
+    channel_type = ""
     NOT_SUPPORT_REPLYTYPE = [ReplyType.VOICE, ReplyType.IMAGE]
 
     def startup(self):

channel/channel_factory.py

@@ -2,43 +2,44 @@
 channel factory
 """
 from common import const
+from .channel import Channel
 
-def create_channel(channel_type):
+
+def create_channel(channel_type) -> Channel:
     """
     create a channel instance
     :param channel_type: channel type code
     :return: channel instance
     """
+    ch = Channel()
     if channel_type == "wx":
         from channel.wechat.wechat_channel import WechatChannel
-
-        return WechatChannel()
+        ch = WechatChannel()
     elif channel_type == "wxy":
         from channel.wechat.wechaty_channel import WechatyChannel
-
-        return WechatyChannel()
+        ch = WechatyChannel()
     elif channel_type == "terminal":
         from channel.terminal.terminal_channel import TerminalChannel
-
-        return TerminalChannel()
+        ch = TerminalChannel()
     elif channel_type == "wechatmp":
         from channel.wechatmp.wechatmp_channel import WechatMPChannel
-
-        return WechatMPChannel(passive_reply=True)
+        ch = WechatMPChannel(passive_reply=True)
     elif channel_type == "wechatmp_service":
         from channel.wechatmp.wechatmp_channel import WechatMPChannel
-
-        return WechatMPChannel(passive_reply=False)
+        ch = WechatMPChannel(passive_reply=False)
     elif channel_type == "wechatcom_app":
         from channel.wechatcom.wechatcomapp_channel import WechatComAppChannel
-
-        return WechatComAppChannel()
+        ch = WechatComAppChannel()
     elif channel_type == "wework":
         from channel.wework.wework_channel import WeworkChannel
-        return WeworkChannel()
-
+        ch = WeworkChannel()
     elif channel_type == const.FEISHU:
         from channel.feishu.feishu_channel import FeiShuChanel
-        return FeiShuChanel()
-
-    raise RuntimeError
+        ch = FeiShuChanel()
+    elif channel_type == const.DINGTALK:
+        from channel.dingtalk.dingtalk_channel import DingTalkChanel
+        ch = DingTalkChanel()
+    else:
+        raise RuntimeError
+    ch.channel_type = channel_type
+    return ch

channel/chat_channel.py

@@ -17,6 +17,8 @@ try:
 except Exception as e:
     pass
 
+handler_pool = ThreadPoolExecutor(max_workers=8)  # 处理消息的线程池
+
 
 # 抽象类, 它包含了与消息通道无关的通用处理逻辑
 class ChatChannel(Channel):
@@ -25,7 +27,6 @@ class ChatChannel(Channel):
     futures = {}  # 记录每个session_id提交到线程池的future对象, 用于重置会话时把没执行的future取消掉，正在执行的不会被取消
     sessions = {}  # 用于控制并发，每个session_id同时只能有一个context在处理
     lock = threading.Lock()  # 用于控制对sessions的访问
-    handler_pool = ThreadPoolExecutor(max_workers=8)  # 处理消息的线程池
 
     def __init__(self):
         _thread = threading.Thread(target=self.consume)
@@ -73,6 +74,7 @@ class ChatChannel(Channel):
                     ):
                         session_id = group_id
                 else:
+                    logger.debug(f"No need reply, groupName not in whitelist, group_name={group_name}")
                     return None
                 context["session_id"] = session_id
                 context["receiver"] = group_id
@@ -168,11 +170,13 @@ class ChatChannel(Channel):
         reply = self._generate_reply(context)
 
         logger.debug("[WX] ready to decorate reply: {}".format(reply))
-        # reply的包装步骤
-        reply = self._decorate_reply(context, reply)
 
-        # reply的发送步骤
-        self._send_reply(context, reply)
+        # reply的包装步骤
+        if reply and reply.content:
+            reply = self._decorate_reply(context, reply)
+
+            # reply的发送步骤
+            self._send_reply(context, reply)
 
     def _generate_reply(self, context: Context, reply: Reply = Reply()) -> Reply:
         e_context = PluginManager().emit_event(
@@ -184,8 +188,6 @@ class ChatChannel(Channel):
         reply = e_context["reply"]
         if not e_context.is_pass():
             logger.debug("[WX] ready to handle context: type={}, content={}".format(context.type, context.content))
-            if e_context.is_break():
-                context["generate_breaked_by"] = e_context["breaked_by"]
             if context.type == ContextType.TEXT or context.type == ContextType.IMAGE_CREATE:  # 文字和图片消息
                 context["channel"] = e_context["channel"]
                 reply = super().build_reply_content(context.content, context)
@@ -341,7 +343,7 @@ class ChatChannel(Channel):
                         if not context_queue.empty():
                             context = context_queue.get()
                             logger.debug("[WX] consume context: {}".format(context))
-                            future: Future = self.handler_pool.submit(self._handle, context)
+                            future: Future = handler_pool.submit(self._handle, context)
                             future.add_done_callback(self._thread_pool_callback(session_id, context=context))
                             if session_id not in self.futures:
                                 self.futures[session_id] = []

channel/dingtalk/dingtalk_channel.py

@@ -0,0 +1,100 @@
+"""
+钉钉通道接入
+
+@author huiwen
+@Date 2023/11/28
+"""
+
+# -*- coding=utf-8 -*-
+from channel.dingtalk.dingtalk_message import DingTalkMessage
+from bridge.context import Context
+from bridge.reply import Reply
+from common.log import logger
+from common.singleton import singleton
+from config import conf
+from common.expired_dict import ExpiredDict
+from bridge.context import ContextType
+from channel.chat_channel import ChatChannel
+import logging
+from dingtalk_stream import AckMessage
+import dingtalk_stream
+
+
+@singleton
+class DingTalkChanel(ChatChannel, dingtalk_stream.ChatbotHandler):
+    dingtalk_client_id = conf().get('dingtalk_client_id')
+    dingtalk_client_secret = conf().get('dingtalk_client_secret')
+
+    def setup_logger(self):
+        logger = logging.getLogger()
+        handler = logging.StreamHandler()
+        handler.setFormatter(
+            logging.Formatter('%(asctime)s %(name)-8s %(levelname)-8s %(message)s [%(filename)s:%(lineno)d]'))
+        logger.addHandler(handler)
+        logger.setLevel(logging.INFO)
+        return logger
+
+    def __init__(self):
+        super().__init__()
+        super(dingtalk_stream.ChatbotHandler, self).__init__()
+        self.logger = self.setup_logger()
+        # 历史消息id暂存，用于幂等控制
+        self.receivedMsgs = ExpiredDict(60 * 60 * 7.1)
+        logger.info("[dingtalk] client_id={}, client_secret={} ".format(
+            self.dingtalk_client_id, self.dingtalk_client_secret))
+        # 无需群校验和前缀
+        conf()["group_name_white_list"] = ["ALL_GROUP"]
+
+    def startup(self):
+        credential = dingtalk_stream.Credential(self.dingtalk_client_id, self.dingtalk_client_secret)
+        client = dingtalk_stream.DingTalkStreamClient(credential)
+        client.register_callback_handler(dingtalk_stream.chatbot.ChatbotMessage.TOPIC, self)
+        client.start_forever()
+
+    def handle_single(self, cmsg: DingTalkMessage):
+        # 处理单聊消息
+        if cmsg.ctype == ContextType.VOICE:
+            logger.debug("[dingtalk]receive voice msg: {}".format(cmsg.content))
+        elif cmsg.ctype == ContextType.IMAGE:
+            logger.debug("[dingtalk]receive image msg: {}".format(cmsg.content))
+        elif cmsg.ctype == ContextType.PATPAT:
+            logger.debug("[dingtalk]receive patpat msg: {}".format(cmsg.content))
+        elif cmsg.ctype == ContextType.TEXT:
+            expression = cmsg.my_msg
+        cmsg.content = conf()["single_chat_prefix"][0] + cmsg.content
+        context = self._compose_context(cmsg.ctype, cmsg.content, isgroup=False, msg=cmsg)
+        if context:
+            self.produce(context)
+
+    def handle_group(self, cmsg: DingTalkMessage):
+        # 处理群聊消息
+        if cmsg.ctype == ContextType.VOICE:
+            logger.debug("[dingtalk]receive voice msg: {}".format(cmsg.content))
+        elif cmsg.ctype == ContextType.IMAGE:
+            logger.debug("[dingtalk]receive image msg: {}".format(cmsg.content))
+        elif cmsg.ctype == ContextType.PATPAT:
+            logger.debug("[dingtalk]receive patpat msg: {}".format(cmsg.content))
+        elif cmsg.ctype == ContextType.TEXT:
+            expression = cmsg.my_msg
+        cmsg.content = conf()["group_chat_prefix"][0] + cmsg.content
+        context = self._compose_context(cmsg.ctype, cmsg.content, isgroup=True, msg=cmsg)
+        context['no_need_at'] = True
+        if context:
+            self.produce(context)
+
+    async def process(self, callback: dingtalk_stream.CallbackMessage):
+        try:
+            incoming_message = dingtalk_stream.ChatbotMessage.from_dict(callback.data)
+            dingtalk_msg = DingTalkMessage(incoming_message)
+            if incoming_message.conversation_type == '1':
+                self.handle_single(dingtalk_msg)
+            else:
+                self.handle_group(dingtalk_msg)
+            return AckMessage.STATUS_OK, 'OK'
+        except Exception as e:
+            logger.error(e)
+            return self.FAILED_MSG
+
+    def send(self, reply: Reply, context: Context):
+        incoming_message = context.kwargs['msg'].incoming_message
+        self.reply_text(reply.content, incoming_message)

channel/dingtalk/dingtalk_message.py

@@ -0,0 +1,44 @@
+from bridge.context import ContextType
+from channel.chat_message import ChatMessage
+import json
+import requests
+from common.log import logger
+from common.tmp_dir import TmpDir
+from common import utils
+from dingtalk_stream import ChatbotMessage
+
+class DingTalkMessage(ChatMessage):
+    def __init__(self, event: ChatbotMessage):
+        super().__init__(event)
+        
+        self.msg_id = event.message_id
+        msg_type = event.message_type
+        self.incoming_message =event
+        self.sender_staff_id = event.sender_staff_id
+        self.other_user_id = event.conversation_id
+        self.create_time = event.create_at
+        if event.conversation_type=="1":
+            self.is_group = False
+        else:
+            self.is_group = True
+        
+
+        if msg_type == "text":
+            self.ctype = ContextType.TEXT
+            
+            self.content = event.text.content.strip()
+        elif msg_type == "audio":
+            
+            # 钉钉支持直接识别语音，所以此处将直接提取文字，当文字处理
+            self.content = event.extensions['content']['recognition'].strip()
+            self.ctype = ContextType.TEXT
+        if self.is_group:
+            self.from_user_id = event.conversation_id
+            self.actual_user_id = event.sender_id
+        else:
+            self.from_user_id = event.sender_id
+        self.to_user_id = event.chatbot_user_id
+        self.other_user_nickname = event.conversation_title
+        
+        user_id = event.sender_id
+        nickname =event.sender_nick

channel/feishu/feishu_channel.py

@@ -51,10 +51,14 @@ class FeiShuChanel(ChatChannel):
         web.httpserver.runsimple(app.wsgifunc(), ("0.0.0.0", port))
 
     def send(self, reply: Reply, context: Context):
-        msg = context["msg"]
+        msg = context.get("msg")
         is_group = context["isgroup"]
+        if msg:
+            access_token = msg.access_token
+        else:
+            access_token = self.fetch_access_token()
         headers = {
-            "Authorization": "Bearer " + msg.access_token,
+            "Authorization": "Bearer " + access_token,
             "Content-Type": "application/json",
         }
         msg_type = "text"
@@ -63,7 +67,7 @@ class FeiShuChanel(ChatChannel):
         content_key = "text"
         if reply.type == ReplyType.IMAGE_URL:
             # 图片上传
-            reply_content = self._upload_image_url(reply.content, msg.access_token)
+            reply_content = self._upload_image_url(reply.content, access_token)
             if not reply_content:
                 logger.warning("[FeiShu] upload file failed")
                 return
@@ -79,7 +83,7 @@ class FeiShuChanel(ChatChannel):
             res = requests.post(url=url, headers=headers, json=data, timeout=(5, 10))
         else:
             url = "https://open.feishu.cn/open-apis/im/v1/messages"
-            params = {"receive_id_type": context.get("receive_id_type")}
+            params = {"receive_id_type": context.get("receive_id_type") or "open_id"}
             data = {
                 "receive_id": context.get("receiver"),
                 "msg_type": msg_type,

channel/feishu/feishu_message.py

@@ -46,35 +46,6 @@ class FeishuMessage(ChatMessage):
                 else:
                     logger.info(f"[FeiShu] Failed to download file, key={file_key}, res={response.text}")
             self._prepare_fn = _download_file
-
-        # elif msg.type == "voice":
-        #     self.ctype = ContextType.VOICE
-        #     self.content = TmpDir().path() + msg.media_id + "." + msg.format  # content直接存临时目录路径
-        #
-        #     def download_voice():
-        #         # 如果响应状态码是200，则将响应内容写入本地文件
-        #         response = client.media.download(msg.media_id)
-        #         if response.status_code == 200:
-        #             with open(self.content, "wb") as f:
-        #                 f.write(response.content)
-        #         else:
-        #             logger.info(f"[wechatcom] Failed to download voice file, {response.content}")
-        #
-        #     self._prepare_fn = download_voice
-        # elif msg.type == "image":
-        #     self.ctype = ContextType.IMAGE
-        #     self.content = TmpDir().path() + msg.media_id + ".png"  # content直接存临时目录路径
-        #
-        #     def download_image():
-        #         # 如果响应状态码是200，则将响应内容写入本地文件
-        #         response = client.media.download(msg.media_id)
-        #         if response.status_code == 200:
-        #             with open(self.content, "wb") as f:
-        #                 f.write(response.content)
-        #         else:
-        #             logger.info(f"[wechatcom] Failed to download image file, {response.content}")
-        #
-        #     self._prepare_fn = download_image
         else:
             raise NotImplementedError("Unsupported message type: Type:{} ".format(msg_type))
 

channel/wechat/wechat_channel.py

@@ -15,6 +15,7 @@ import requests
 from bridge.context import *
 from bridge.reply import *
 from channel.chat_channel import ChatChannel
+from channel import chat_channel
 from channel.wechat.wechat_message import *
 from common.expired_dict import ExpiredDict
 from common.log import logger
@@ -95,7 +96,7 @@ def qrCallback(uuid, status, qrcode):
         print(qr_api4)
         print(qr_api2)
         print(qr_api1)
-
+        _send_qr_code([qr_api3, qr_api4, qr_api2, qr_api1])
         qr = qrcode.QRCode(border=1)
         qr.add_data(url)
         qr.make(fit=True)
@@ -109,23 +110,46 @@ class WechatChannel(ChatChannel):
     def __init__(self):
         super().__init__()
         self.receivedMsgs = ExpiredDict(60 * 60)
+        self.auto_login_times = 0
 
     def startup(self):
-        itchat.instance.receivingRetryCount = 600  # 修改断线超时时间
-        # login by scan QRCode
-        hotReload = conf().get("hot_reload", False)
-        status_path = os.path.join(get_appdata_dir(), "itchat.pkl")
-        itchat.auto_login(
-            enableCmdQR=2,
-            hotReload=hotReload,
-            statusStorageDir=status_path,
-            qrCallback=qrCallback,
-        )
-        self.user_id = itchat.instance.storageClass.userName
-        self.name = itchat.instance.storageClass.nickName
-        logger.info("Wechat login success, user_id: {}, nickname: {}".format(self.user_id, self.name))
-        # start message listener
-        itchat.run()
+        try:
+            itchat.instance.receivingRetryCount = 600  # 修改断线超时时间
+            # login by scan QRCode
+            hotReload = conf().get("hot_reload", False)
+            status_path = os.path.join(get_appdata_dir(), "itchat.pkl")
+            itchat.auto_login(
+                enableCmdQR=2,
+                hotReload=hotReload,
+                statusStorageDir=status_path,
+                qrCallback=qrCallback,
+                exitCallback=self.exitCallback,
+                loginCallback=self.loginCallback
+            )
+            self.user_id = itchat.instance.storageClass.userName
+            self.name = itchat.instance.storageClass.nickName
+            logger.info("Wechat login success, user_id: {}, nickname: {}".format(self.user_id, self.name))
+            # start message listener
+            itchat.run()
+        except Exception as e:
+            logger.exception(e)
+
+    def exitCallback(self):
+        try:
+            from common.linkai_client import chat_client
+            if chat_client.client_id and conf().get("use_linkai"):
+                _send_logout()
+                time.sleep(2)
+                self.auto_login_times += 1
+                if self.auto_login_times < 100:
+                    chat_channel.handler_pool._shutdown = False
+                    self.startup()
+        except Exception as e:
+            pass
+
+    def loginCallback(self):
+        logger.debug("Login success")
+        _send_login_success()
 
     # handle_* 系列函数处理收到的消息后构造Context，然后传入produce函数中处理Context和发送回复
     # Context包含了消息的所有信息，包括以下属性
@@ -138,7 +162,6 @@ class WechatChannel(ChatChannel):
     #        msg: ChatMessage消息对象
     #        origin_ctype: 原始消息类型，语音转文字后，私聊时如果匹配前缀失败，会根据初始消息是否是语音来放宽触发规则
     #        desire_rtype: 希望回复类型，默认是文本回复，设置为ReplyType.VOICE是语音回复
-
     @time_checker
     @_check
     def handle_single(self, cmsg: ChatMessage):
@@ -170,7 +193,7 @@ class WechatChannel(ChatChannel):
             logger.debug("[WX]receive voice for group msg: {}".format(cmsg.content))
         elif cmsg.ctype == ContextType.IMAGE:
             logger.debug("[WX]receive image for group msg: {}".format(cmsg.content))
-        elif cmsg.ctype in [ContextType.JOIN_GROUP, ContextType.PATPAT, ContextType.ACCEPT_FRIEND]:
+        elif cmsg.ctype in [ContextType.JOIN_GROUP, ContextType.PATPAT, ContextType.ACCEPT_FRIEND, ContextType.EXIT_GROUP]:
             logger.debug("[WX]receive note msg: {}".format(cmsg.content))
         elif cmsg.ctype == ContextType.TEXT:
             # logger.debug("[WX]receive group msg: {}, cmsg={}".format(json.dumps(cmsg._rawmsg, ensure_ascii=False), cmsg))
@@ -234,3 +257,27 @@ class WechatChannel(ChatChannel):
             video_storage.seek(0)
             itchat.send_video(video_storage, toUserName=receiver)
             logger.info("[WX] sendVideo url={}, receiver={}".format(video_url, receiver))
+
+def _send_login_success():
+    try:
+        from common.linkai_client import chat_client
+        if chat_client.client_id:
+            chat_client.send_login_success()
+    except Exception as e:
+        pass
+
+def _send_logout():
+    try:
+        from common.linkai_client import chat_client
+        if chat_client.client_id:
+            chat_client.send_logout()
+    except Exception as e:
+        pass
+
+def _send_qr_code(qrcode_list: list):
+    try:
+        from common.linkai_client import chat_client
+        if chat_client.client_id:
+            chat_client.send_qrcode(qrcode_list)
+    except Exception as e:
+        pass

channel/wechat/wechat_message.py

@@ -27,13 +27,21 @@ class WechatMessage(ChatMessage):
             self._prepare_fn = lambda: itchat_msg.download(self.content)
         elif itchat_msg["Type"] == NOTE and itchat_msg["MsgType"] == 10000:
             if is_group and ("加入群聊" in itchat_msg["Content"] or "加入了群聊" in itchat_msg["Content"]):
-                self.ctype = ContextType.JOIN_GROUP
-                self.content = itchat_msg["Content"]
                 # 这里只能得到nickname， actual_user_id还是机器人的id
                 if "加入了群聊" in itchat_msg["Content"]:
+                    self.ctype = ContextType.JOIN_GROUP
+                    self.content = itchat_msg["Content"]
                     self.actual_user_nickname = re.findall(r"\"(.*?)\"", itchat_msg["Content"])[-1]
                 elif "加入群聊" in itchat_msg["Content"]:
+                    self.ctype = ContextType.JOIN_GROUP
+                    self.content = itchat_msg["Content"]
                     self.actual_user_nickname = re.findall(r"\"(.*?)\"", itchat_msg["Content"])[0]
+
+            elif is_group and ("移出了群聊" in itchat_msg["Content"]):
+                self.ctype = ContextType.EXIT_GROUP
+                self.content = itchat_msg["Content"]
+                self.actual_user_nickname = re.findall(r"\"(.*?)\"", itchat_msg["Content"])[0]
+                    
             elif "你已添加了" in itchat_msg["Content"]:  #通过好友请求
                 self.ctype = ContextType.ACCEPT_FRIEND
                 self.content = itchat_msg["Content"]
@@ -90,5 +98,5 @@ class WechatMessage(ChatMessage):
         if self.is_group:
             self.is_at = itchat_msg["IsAt"]
             self.actual_user_id = itchat_msg["ActualUserName"]
-            if self.ctype not in [ContextType.JOIN_GROUP, ContextType.PATPAT]:
+            if self.ctype not in [ContextType.JOIN_GROUP, ContextType.PATPAT, ContextType.EXIT_GROUP]:
                 self.actual_user_nickname = itchat_msg["ActualNickName"]

channel/wework/wework_channel.py

@@ -120,7 +120,7 @@ def _check(func):
 
 
 @wework.msg_register(
-    [ntwork.MT_RECV_TEXT_MSG, ntwork.MT_RECV_IMAGE_MSG, 11072, ntwork.MT_RECV_VOICE_MSG])
+    [ntwork.MT_RECV_TEXT_MSG, ntwork.MT_RECV_IMAGE_MSG, 11072, ntwork.MT_RECV_LINK_CARD_MSG,ntwork.MT_RECV_FILE_MSG, ntwork.MT_RECV_VOICE_MSG])
 def all_msg_handler(wework_instance: ntwork.WeWork, message):
     logger.debug(f"收到消息: {message}")
     if 'data' in message:

channel/wework/wework_message.py

@@ -64,7 +64,10 @@ def cdn_download(wework, message, file_name):
         }
         result = wework._WeWork__send_sync(send_type.MT_WXCDN_DOWNLOAD_MSG, data)  # 直接用wx_cdn_download的接口内部实现来调用
     elif "file_id" in data["cdn"].keys():
-        file_type = 2
+        if message["type"] == 11042:
+            file_type = 2
+        elif message["type"] == 11045:
+            file_type = 5
         file_id = data["cdn"]["file_id"]
         result = wework.c2c_cdn_download(file_id, aes_key, file_size, file_type, save_path)
     else:
@@ -128,6 +131,18 @@ class WeworkMessage(ChatMessage):
                 self.ctype = ContextType.IMAGE
                 self.content = os.path.join(current_dir, "tmp", file_name)
                 self._prepare_fn = lambda: cdn_download(wework, wework_msg, file_name)
+            elif wework_msg["type"] == 11045:  # 文件消息
+                print("文件消息")
+                print(wework_msg)
+                file_name = datetime.datetime.now().strftime('%Y%m%d%H%M%S')
+                file_name = file_name + wework_msg['data']['cdn']['file_name']
+                current_dir = os.getcwd()
+                self.ctype = ContextType.FILE
+                self.content = os.path.join(current_dir, "tmp", file_name)
+                self._prepare_fn = lambda: cdn_download(wework, wework_msg, file_name)
+            elif wework_msg["type"] == 11047:  # 链接消息
+                self.ctype = ContextType.SHARING
+                self.content = wework_msg['data']['url']
             elif wework_msg["type"] == 11072:  # 新成员入群通知
                 self.ctype = ContextType.JOIN_GROUP
                 member_list = wework_msg['data']['member_list']
@@ -179,6 +194,7 @@ class WeworkMessage(ChatMessage):
                 if conversation_id:
                     room_info = get_room_info(wework=wework, conversation_id=conversation_id)
                     self.other_user_nickname = room_info.get('nickname', None) if room_info else None
+                    self.from_user_nickname = room_info.get('nickname', None) if room_info else None
                     at_list = data.get('at_list', [])
                     tmp_list = []
                     for at in at_list:

common/const.py

@@ -6,17 +6,39 @@ XUNFEI = "xunfei"
 CHATGPTONAZURE = "chatGPTOnAzure"
 LINKAI = "linkai"
 CLAUDEAI = "claude"
+CLAUDEAPI= "claudeAPI"
+QWEN = "qwen"
+
+QWEN_DASHSCOPE = "dashscope"
+QWEN_TURBO = "qwen-turbo"
+QWEN_PLUS = "qwen-plus"
+QWEN_MAX = "qwen-max"
+
+GEMINI = "gemini"
+ZHIPU_AI = "glm-4"
+MOONSHOT = "moonshot"
+
 
 # model
+CLAUDE3 = "claude-3-opus-20240229"
 GPT35 = "gpt-3.5-turbo"
 GPT4 = "gpt-4"
-GPT4_TURBO_PREVIEW = "gpt-4-1106-preview"
+GPT_4o = "gpt-4o"
+LINKAI_35 = "linkai-3.5"
+LINKAI_4_TURBO = "linkai-4-turbo"
+LINKAI_4o = "linkai-4o"
+GPT4_TURBO_PREVIEW = "gpt-4-turbo-2024-04-09"
+GPT4_TURBO_04_09 = "gpt-4-turbo-2024-04-09"
+GPT4_TURBO_01_25 = "gpt-4-0125-preview"
 GPT4_VISION_PREVIEW = "gpt-4-vision-preview"
 WHISPER_1 = "whisper-1"
 TTS_1 = "tts-1"
 TTS_1_HD = "tts-1-hd"
 
-MODEL_LIST = ["gpt-3.5-turbo", "gpt-3.5-turbo-16k", "gpt-4", "wenxin", "wenxin-4", "xunfei", "claude", "gpt-4-turbo", GPT4_TURBO_PREVIEW]
+MODEL_LIST = ["gpt-3.5-turbo", "gpt-3.5-turbo-16k", "gpt-4", "wenxin", "wenxin-4", "xunfei", "claude", "claude-3-opus-20240229", "gpt-4-turbo",
+              "gpt-4-turbo-preview", "gpt-4-1106-preview", GPT4_TURBO_PREVIEW, GPT4_TURBO_01_25, GPT_4o, QWEN, GEMINI, ZHIPU_AI, MOONSHOT,
+              QWEN_TURBO, QWEN_PLUS, QWEN_MAX, LINKAI_35, LINKAI_4_TURBO, LINKAI_4o]
 
 # channel
 FEISHU = "feishu"
+DINGTALK = "dingtalk"   

common/linkai_client.py

@@ -0,0 +1,102 @@
+from bridge.context import Context, ContextType
+from bridge.reply import Reply, ReplyType
+from common.log import logger
+from linkai import LinkAIClient, PushMsg
+from config import conf, pconf, plugin_config, available_setting
+from plugins import PluginManager
+import time
+
+
+chat_client: LinkAIClient
+
+
+class ChatClient(LinkAIClient):
+    def __init__(self, api_key, host, channel):
+        super().__init__(api_key, host)
+        self.channel = channel
+        self.client_type = channel.channel_type
+
+    def on_message(self, push_msg: PushMsg):
+        session_id = push_msg.session_id
+        msg_content = push_msg.msg_content
+        logger.info(f"receive msg push, session_id={session_id}, msg_content={msg_content}")
+        context = Context()
+        context.type = ContextType.TEXT
+        context["receiver"] = session_id
+        context["isgroup"] = push_msg.is_group
+        self.channel.send(Reply(ReplyType.TEXT, content=msg_content), context)
+
+    def on_config(self, config: dict):
+        if not self.client_id:
+            return
+        logger.info(f"[LinkAI] 从客户端管理加载远程配置: {config}")
+        if config.get("enabled") != "Y":
+            return
+
+        local_config = conf()
+        for key in config.keys():
+            if key in available_setting and config.get(key) is not None:
+                local_config[key] = config.get(key)
+        # 语音配置
+        reply_voice_mode = config.get("reply_voice_mode")
+        if reply_voice_mode:
+            if reply_voice_mode == "voice_reply_voice":
+                local_config["voice_reply_voice"] = True
+            elif reply_voice_mode == "always_reply_voice":
+                local_config["always_reply_voice"] = True
+
+        if config.get("admin_password") and plugin_config.get("Godcmd"):
+            plugin_config["Godcmd"]["password"] = config.get("admin_password")
+            PluginManager().instances["GODCMD"].reload()
+
+        if config.get("group_app_map") and pconf("linkai"):
+            local_group_map = {}
+            for mapping in config.get("group_app_map"):
+                local_group_map[mapping.get("group_name")] = mapping.get("app_code")
+            pconf("linkai")["group_app_map"] = local_group_map
+            PluginManager().instances["LINKAI"].reload()
+
+        if config.get("text_to_image") and config.get("text_to_image") == "midjourney" and pconf("linkai"):
+            if pconf("linkai")["midjourney"]:
+                pconf("linkai")["midjourney"]["enabled"] = True
+                pconf("linkai")["midjourney"]["use_image_create_prefix"] = True
+        elif config.get("text_to_image") and config.get("text_to_image") in ["dall-e-2", "dall-e-3"]:
+            if pconf("linkai")["midjourney"]:
+                pconf("linkai")["midjourney"]["use_image_create_prefix"] = False
+
+
+def start(channel):
+    global chat_client
+    chat_client = ChatClient(api_key=conf().get("linkai_api_key"), host="", channel=channel)
+    chat_client.config = _build_config()
+    chat_client.start()
+    time.sleep(1.5)
+    if chat_client.client_id:
+        logger.info("[LinkAI] 可前往控制台进行线上登录和配置：https://link-ai.tech/console/clients")
+
+
+def _build_config():
+    local_conf = conf()
+    config = {
+        "linkai_app_code": local_conf.get("linkai_app_code"),
+        "single_chat_prefix": local_conf.get("single_chat_prefix"),
+        "single_chat_reply_prefix": local_conf.get("single_chat_reply_prefix"),
+        "single_chat_reply_suffix": local_conf.get("single_chat_reply_suffix"),
+        "group_chat_prefix": local_conf.get("group_chat_prefix"),
+        "group_chat_reply_prefix": local_conf.get("group_chat_reply_prefix"),
+        "group_chat_reply_suffix": local_conf.get("group_chat_reply_suffix"),
+        "group_name_white_list": local_conf.get("group_name_white_list"),
+        "nick_name_black_list": local_conf.get("nick_name_black_list"),
+        "speech_recognition": "Y" if local_conf.get("speech_recognition") else "N",
+        "text_to_image": local_conf.get("text_to_image"),
+        "image_create_prefix": local_conf.get("image_create_prefix")
+    }
+    if local_conf.get("always_reply_voice"):
+        config["reply_voice_mode"] = "always_reply_voice"
+    elif local_conf.get("voice_reply_voice"):
+        config["reply_voice_mode"] = "voice_reply_voice"
+    if pconf("linkai"):
+        config["group_app_map"] = pconf("linkai").get("group_app_map")
+    if plugin_config.get("Godcmd"):
+        config["admin_password"] = plugin_config.get("Godcmd").get("password")
+    return config

config-template.json

@@ -2,6 +2,7 @@
   "channel_type": "wx",
   "model": "",
   "open_ai_api_key": "YOUR API KEY",
+  "claude_api_key": "YOUR API KEY",
   "text_to_image": "dall-e-2",
   "voice_to_text": "openai",
   "text_to_voice": "openai",
@@ -19,9 +20,6 @@
     "ChatGPT测试群",
     "ChatGPT测试群2"
   ],
-  "group_chat_in_one_session": [
-    "ChatGPT测试群"
-  ],
   "image_create_prefix": [
     "画"
   ],
@@ -30,10 +28,9 @@
   "voice_reply_voice": false,
   "conversation_max_tokens": 2500,
   "expires_in_seconds": 3600,
-  "character_desc": "你是ChatGPT, 一个由OpenAI训练的大型语言模型, 你旨在回答并解决人们的任何问题，并且可以使用多种语言与人交流。",
+  "character_desc": "你是基于大语言模型的AI智能助手，旨在回答并解决人们的任何问题，并且可以使用多种语言与人交流。",
   "temperature": 0.7,
-  "top_p": 1,
-  "subscribe_msg": "感谢您的关注！\n这里是ChatGPT，可以自由对话。\n支持语音对话。\n支持图片输入。\n支持图片输出，画字开头的消息将按要求创作图片。\n支持tool、角色扮演和文字冒险等丰富的插件。\n输入{trigger_prefix}#help 查看详细指令。",
+  "subscribe_msg": "感谢您的关注！\n这里是AI智能助手，可以自由对话。\n支持语音对话。\n支持图片输入。\n支持图片输出，画字开头的消息将按要求创作图片。\n支持tool、角色扮演和文字冒险等丰富的插件。\n输入{trigger_prefix}#help 查看详细指令。",
   "use_linkai": false,
   "linkai_api_key": "",
   "linkai_app_code": ""

config.py

@@ -16,7 +16,7 @@ available_setting = {
     "open_ai_api_base": "https://api.openai.com/v1",
     "proxy": "",  # openai使用的代理
     # chatgpt模型， 当use_azure_chatgpt为true时，其名称为Azure上model deployment名称
-    "model": "gpt-3.5-turbo",  # 还支持 gpt-4, gpt-4-turbo, wenxin, xunfei
+    "model": "gpt-3.5-turbo",  # 还支持 gpt-4, gpt-4-turbo, wenxin, xunfei, qwen
     "use_azure_chatgpt": False,  # 是否使用azure的chatgpt
     "azure_deployment_id": "",  # azure 模型部署名称
     "azure_api_version": "",  # azure api版本
@@ -40,6 +40,7 @@ available_setting = {
     "image_create_prefix": ["画", "看", "找"],  # 开启图片回复的前缀
     "concurrency_in_session": 1,  # 同一会话最多有多少条消息在处理中，大于1可能乱序
     "image_create_size": "256x256",  # 图片大小,可选有 256x256, 512x512, 1024x1024 (dall-e-3默认为1024x1024)
+    "group_chat_exit_group": False, 
     # chatgpt会话参数
     "expires_in_seconds": 3600,  # 无操作会话的过期时间
     # 人格描述
@@ -66,6 +67,18 @@ available_setting = {
     # claude 配置
     "claude_api_cookie": "",
     "claude_uuid": "",
+    # claude api key
+    "claude_api_key":"",
+    # 通义千问API, 获取方式查看文档 https://help.aliyun.com/document_detail/2587494.html
+    "qwen_access_key_id": "",
+    "qwen_access_key_secret": "",
+    "qwen_agent_key": "",
+    "qwen_app_id": "",
+    "qwen_node_id": "",  # 流程编排模型用到的id，如果没有用到qwen_node_id，请务必保持为空字符串
+    # 阿里灵积模型api key
+    "dashscope_api_key": "",
+    # Google Gemini Api Key
+    "gemini_api_key": "",
     # wework的通用配置
     "wework_smart": True,  # 配置wework是否使用已登录的企业微信，False为多开
     # 语音设置
@@ -74,7 +87,7 @@ available_setting = {
     "voice_reply_voice": False,  # 是否使用语音回复语音，需要设置对应语音合成引擎的api key
     "always_reply_voice": False,  # 是否一直使用语音回复
     "voice_to_text": "openai",  # 语音识别引擎，支持openai,baidu,google,azure
-    "text_to_voice": "openai",  # 语音合成引擎，支持openai,baidu,google,pytts(offline),azure,elevenlabs
+    "text_to_voice": "openai",  # 语音合成引擎，支持openai,baidu,google,pytts(offline),azure,elevenlabs,edge(online)
     "text_to_voice_model": "tts-1",
     "tts_voice_id": "alloy",
     # baidu 语音api配置， 使用百度语音识别和语音合成时需要
@@ -123,7 +136,11 @@ available_setting = {
     "feishu_app_secret": "",  # 飞书机器人APP secret
     "feishu_token": "",  # 飞书 verification token
     "feishu_bot_name": "",  # 飞书机器人的名字
-
+    
+    # 钉钉配置
+    "dingtalk_client_id": "",  # 钉钉机器人Client ID 
+    "dingtalk_client_secret": "",  # 钉钉机器人Client Secret 
+    
     # chatgpt指令自定义触发词
     "clear_memory_commands": ["#清除记忆"],  # 重置会话指令，必须以#开头
     # channel配置
@@ -135,11 +152,18 @@ available_setting = {
     "plugin_trigger_prefix": "$",  # 规范插件提供聊天相关指令的前缀，建议不要和管理员指令前缀"#"冲突
     # 是否使用全局插件配置
     "use_global_plugin_config": False,
-    # 知识库平台配置
+    "max_media_send_count": 3,     # 单次最大发送媒体资源的个数
+    "media_send_interval": 1,  # 发送图片的事件间隔，单位秒
+    # 智谱AI 平台配置
+    "zhipu_ai_api_key": "",
+    "zhipu_ai_api_base": "https://open.bigmodel.cn/api/paas/v4",
+    "moonshot_api_key": "",
+    "moonshot_base_url":"https://api.moonshot.cn/v1/chat/completions",
+    # LinkAI平台配置
     "use_linkai": False,
     "linkai_api_key": "",
     "linkai_app_code": "",
-    "linkai_api_base": "https://api.link-ai.chat",  # linkAI服务地址，若国内无法访问或延迟较高可改为 https://api.link-ai.tech
+    "linkai_api_base": "https://api.link-ai.tech",  # linkAI服务地址
 }
 
 
@@ -238,6 +262,8 @@ def load_config():
     config.load_user_datas()
 
 
+
+
 def get_root():
     return os.path.dirname(os.path.abspath(__file__))
 

docs/version/old-version.md

@@ -0,0 +1,13 @@
+## 归档更新日志
+
+2023.04.26： 支持企业微信应用号部署，兼容插件，并支持语音图片交互，私人助理理想选择，使用文档。(contributed by @lanvent in #944)
+
+2023.04.05： 支持微信公众号部署，兼容插件，并支持语音图片交互，使用文档。(contributed by @JS00000 in #686)
+
+2023.04.05： 增加能让ChatGPT使用工具的tool插件，使用文档。工具相关issue可反馈至chatgpt-tool-hub。(contributed by @goldfishh in #663)
+
+2023.03.25： 支持插件化开发，目前已实现 多角色切换、文字冒险游戏、管理员指令、Stable Diffusion等插件，使用参考 #578。(contributed by @lanvent in #565)
+
+2023.03.09： 基于 whisper API(后续已接入更多的语音API服务) 实现对微信语音消息的解析和回复，添加配置项 "speech_recognition":true 即可启用，使用参考 #415。(contributed by wanggang1987 in #385)
+
+2023.02.09： 扫码登录存在账号限制风险，请谨慎使用，参考#58

lib/itchat/LICENSE

@@ -0,0 +1,9 @@
+**The MIT License (MIT)**
+
+Copyright (c) 2017 LittleCoder ([littlecodersh@Github](https://github.com/littlecodersh))
+
+Permission is hereby granted, free of charge, to any person obtaining a copy of this software and associated documentation files (the "Software"), to deal in the Software without restriction, including without limitation the rights to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the Software, and to permit persons to whom the Software is furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

plugins/config.json.template

@@ -33,6 +33,12 @@
             "max_tasks": 3,
             "max_tasks_per_user": 1,
             "use_image_create_prefix": true
+        },
+        "summary": {
+            "enabled": true,
+            "group_enabled": true,
+            "max_file_size": 5000,
+            "type": ["FILE", "SHARING"]
         }
     }
 }

plugins/godcmd/godcmd.py

@@ -313,7 +313,7 @@ class Godcmd(Plugin):
                     except Exception as e:
                         ok, result = False, "你没有设置私有GPT模型"
                 elif cmd == "reset":
-                    if bottype in [const.OPEN_AI, const.CHATGPT, const.CHATGPTONAZURE, const.LINKAI, const.BAIDU, const.XUNFEI]:
+                    if bottype in [const.OPEN_AI, const.CHATGPT, const.CHATGPTONAZURE, const.LINKAI, const.BAIDU, const.XUNFEI, const.QWEN, const.GEMINI, const.ZHIPU_AI]:
                         bot.sessions.clear_session(session_id)
                         if Bridge().chat_bots.get(bottype):
                             Bridge().chat_bots.get(bottype).sessions.clear_session(session_id)
@@ -339,7 +339,7 @@ class Godcmd(Plugin):
                             ok, result = True, "配置已重载"
                         elif cmd == "resetall":
                             if bottype in [const.OPEN_AI, const.CHATGPT, const.CHATGPTONAZURE, const.LINKAI,
-                                           const.BAIDU, const.XUNFEI]:
+                                           const.BAIDU, const.XUNFEI, const.QWEN, const.GEMINI, const.ZHIPU_AI, const.MOONSHOT]:
                                 channel.cancel_all_session()
                                 bot.sessions.clear_all_session()
                                 ok, result = True, "重置所有会话成功"
@@ -475,3 +475,11 @@ class Godcmd(Plugin):
         if model == "gpt-4-turbo":
             return const.GPT4_TURBO_PREVIEW
         return model
+
+    def reload(self):
+        gconf = plugin_config[self.name]
+        if gconf:
+            if gconf.get("password"):
+                self.password = gconf["password"]
+            if gconf.get("admin_users"):
+                self.admin_users = gconf["admin_users"]

plugins/hello/README.md

@@ -0,0 +1,41 @@
+## 插件说明
+
+可以根据需求设置入群欢迎、群聊拍一拍、退群等消息的自定义提示词，也支持为每个群设置对应的固定欢迎语。
+
+该插件也是用户根据需求开发自定义插件的示例插件，参考[插件开发说明](https://github.com/zhayujie/chatgpt-on-wechat/tree/master/plugins)
+
+## 插件配置
+
+将 `plugins/hello` 目录下的 `config.json.template` 配置模板复制为最终生效的 `config.json`。 (如果未配置则会默认使用`config.json.template`模板中配置)。
+
+以下是插件配置项说明：
+
+```bash
+{
+    "group_welc_fixed_msg": {                   ## 这里可以为特定群里配置特定的固定欢迎语
+      "群聊1": "群聊1的固定欢迎语",
+      "群聊2": "群聊2的固定欢迎语"
+    },
+
+  "group_welc_prompt": "请你随机使用一种风格说一句问候语来欢迎新用户\"{nickname}\"加入群聊。",  ## 群聊随机欢迎语的提示词
+
+  "group_exit_prompt": "请你随机使用一种风格跟其他群用户说他违反规则\"{nickname}\"退出群聊。",  ## 移出群聊的提示词
+
+  "patpat_prompt": "请你随机使用一种风格介绍你自己，并告诉用户输入#help可以查看帮助信息。",  ## 群内拍一拍的提示词
+ 
+  "use_character_desc": false     ## 是否在Hello插件中使用LinkAI应用的系统设定
+}
+```
+
+
+注意：
+
+ - 设置全局的用户进群固定欢迎语，可以在***项目根目录下***的`config.json`文件里，可以添加参数`"group_welcome_msg": "" `，参考 [#1482](https://github.com/zhayujie/chatgpt-on-wechat/pull/1482)
+ - 为每个群设置固定的欢迎语，可以在`"group_welc_fixed_msg": {}`配置群聊名和对应的固定欢迎语，优先级高于全局固定欢迎语
+ - 如果没有配置以上两个参数，则使用随机欢迎语，如需设定风格，语言等，修改`"group_welc_prompt": `即可
+ - 如果使用LinkAI的服务，想在随机欢迎中结合LinkAI应用的设定，配置`"use_character_desc": true `
+ - 实际 `config.json` 配置中应保证json格式，不应携带 '#' 及后面的注释
+ - 如果是`docker`部署，可通过映射 `plugins/config.json` 到容器中来完成插件配置，参考[文档](https://github.com/zhayujie/chatgpt-on-wechat#3-%E6%8F%92%E4%BB%B6%E4%BD%BF%E7%94%A8)
+
+
+

plugins/hello/config.json.template

@@ -0,0 +1,14 @@
+{
+    "group_welc_fixed_msg": {
+      "群聊1": "群聊1的固定欢迎语",
+      "群聊2": "群聊2的固定欢迎语"
+    },
+
+  "group_welc_prompt": "请你随机使用一种风格说一句问候语来欢迎新用户\"{nickname}\"加入群聊。",
+
+  "group_exit_prompt": "请你随机使用一种风格跟其他群用户说他违反规则\"{nickname}\"退出群聊。",
+
+  "patpat_prompt": "请你随机使用一种风格介绍你自己，并告诉用户输入#help可以查看帮助信息。",
+
+  "use_character_desc": false
+}

plugins/hello/hello.py

@@ -17,39 +17,73 @@ from config import conf
     version="0.1",
     author="lanvent",
 )
+
+
 class Hello(Plugin):
+
+    group_welc_prompt = "请你随机使用一种风格说一句问候语来欢迎新用户\"{nickname}\"加入群聊。"
+    group_exit_prompt = "请你随机使用一种风格介绍你自己，并告诉用户输入#help可以查看帮助信息。"
+    patpat_prompt = "请你随机使用一种风格跟其他群用户说他违反规则\"{nickname}\"退出群聊。"
+
     def __init__(self):
         super().__init__()
-        self.handlers[Event.ON_HANDLE_CONTEXT] = self.on_handle_context
-        logger.info("[Hello] inited")
+        try:
+            self.config = super().load_config()
+            if not self.config:
+                self.config = self._load_config_template()
+            self.group_welc_fixed_msg = self.config.get("group_welc_fixed_msg", {})
+            self.group_welc_prompt = self.config.get("group_welc_prompt", self.group_welc_prompt)
+            self.group_exit_prompt = self.config.get("group_exit_prompt", self.group_exit_prompt)
+            self.patpat_prompt = self.config.get("patpat_prompt", self.patpat_prompt)
+            logger.info("[Hello] inited")
+            self.handlers[Event.ON_HANDLE_CONTEXT] = self.on_handle_context
+        except Exception as e:
+            logger.error(f"[Hello]初始化异常：{e}")
+            raise "[Hello] init failed, ignore "
 
     def on_handle_context(self, e_context: EventContext):
         if e_context["context"].type not in [
             ContextType.TEXT,
             ContextType.JOIN_GROUP,
             ContextType.PATPAT,
+            ContextType.EXIT_GROUP
         ]:
             return
-
+        msg: ChatMessage = e_context["context"]["msg"]
+        group_name = msg.from_user_nickname
         if e_context["context"].type == ContextType.JOIN_GROUP:
-            if "group_welcome_msg" in conf():
+            if "group_welcome_msg" in conf() or group_name in self.group_welc_fixed_msg:
                 reply = Reply()
                 reply.type = ReplyType.TEXT
-                reply.content = conf().get("group_welcome_msg", "")
+                if group_name in self.group_welc_fixed_msg:
+                    reply.content = self.group_welc_fixed_msg.get(group_name, "")
+                else:
+                    reply.content = conf().get("group_welcome_msg", "")
                 e_context["reply"] = reply
                 e_context.action = EventAction.BREAK_PASS  # 事件结束，并跳过处理context的默认逻辑
                 return
             e_context["context"].type = ContextType.TEXT
-            msg: ChatMessage = e_context["context"]["msg"]
-            e_context["context"].content = f'请你随机使用一种风格说一句问候语来欢迎新用户"{msg.actual_user_nickname}"加入群聊。'
+            e_context["context"].content = self.group_welc_prompt.format(nickname=msg.actual_user_nickname)
             e_context.action = EventAction.BREAK  # 事件结束，进入默认处理逻辑
+            if not self.config or not self.config.get("use_character_desc"):
+                e_context["context"]["generate_breaked_by"] = EventAction.BREAK
             return
-
+        
+        if e_context["context"].type == ContextType.EXIT_GROUP:
+            if conf().get("group_chat_exit_group"):
+                e_context["context"].type = ContextType.TEXT
+                e_context["context"].content = self.group_exit_prompt.format(nickname=msg.actual_user_nickname)
+                e_context.action = EventAction.BREAK  # 事件结束，进入默认处理逻辑
+                return
+            e_context.action = EventAction.BREAK
+            return
+            
         if e_context["context"].type == ContextType.PATPAT:
             e_context["context"].type = ContextType.TEXT
-            msg: ChatMessage = e_context["context"]["msg"]
-            e_context["context"].content = f"请你随机使用一种风格介绍你自己，并告诉用户输入#help可以查看帮助信息。"
+            e_context["context"].content = self.patpat_prompt
             e_context.action = EventAction.BREAK  # 事件结束，进入默认处理逻辑
+            if not self.config or not self.config.get("use_character_desc"):
+                e_context["context"]["generate_breaked_by"] = EventAction.BREAK
             return
 
         content = e_context["context"].content
@@ -57,7 +91,6 @@ class Hello(Plugin):
         if content == "Hello":
             reply = Reply()
             reply.type = ReplyType.TEXT
-            msg: ChatMessage = e_context["context"]["msg"]
             if e_context["context"]["isgroup"]:
                 reply.content = f"Hello, {msg.actual_user_nickname} from {msg.from_user_nickname}"
             else:
@@ -81,3 +114,14 @@ class Hello(Plugin):
     def get_help_text(self, **kwargs):
         help_text = "输入Hello，我会回复你的名字\n输入End，我会回复你世界的图片\n"
         return help_text
+
+    def _load_config_template(self):
+        logger.debug("No Hello plugin config.json, use plugins/hello/config.json.template")
+        try:
+            plugin_config_path = os.path.join(self.path, "config.json.template")
+            if os.path.exists(plugin_config_path):
+                with open(plugin_config_path, "r", encoding="utf-8") as f:
+                    plugin_conf = json.load(f)
+                    return plugin_conf
+        except Exception as e:
+            logger.exception(e)

plugins/linkai/linkai.py

@@ -10,6 +10,7 @@ from common import const
 import os
 from .utils import Util
 
+
 @plugins.register(
     name="linkai",
     desc="A plugin that supports knowledge base and midjourney drawing.",
@@ -32,7 +33,6 @@ class LinkAI(Plugin):
             self.sum_config = self.config.get("summary")
         logger.info(f"[LinkAI] inited, config={self.config}")
 
-
     def on_handle_context(self, e_context: EventContext):
         """
         消息处理逻辑
@@ -42,7 +42,8 @@ class LinkAI(Plugin):
             return
 
         context = e_context['context']
-        if context.type not in [ContextType.TEXT, ContextType.IMAGE, ContextType.IMAGE_CREATE, ContextType.FILE, ContextType.SHARING]:
+        if context.type not in [ContextType.TEXT, ContextType.IMAGE, ContextType.IMAGE_CREATE, ContextType.FILE,
+                                ContextType.SHARING]:
             # filter content no need solve
             return
 
@@ -76,7 +77,8 @@ class LinkAI(Plugin):
             if not res:
                 _set_reply_text("因为神秘力量无法获取文章内容，请稍后再试吧~", e_context, level=ReplyType.TEXT)
                 return
-            _set_reply_text(res.get("summary") + "\n\n💬 发送 \"开启对话\" 可以开启与文章内容的对话", e_context, level=ReplyType.TEXT)
+            _set_reply_text(res.get("summary") + "\n\n💬 发送 \"开启对话\" 可以开启与文章内容的对话", e_context,
+                            level=ReplyType.TEXT)
             USER_FILE_MAP[_find_user_id(context) + "-sum_id"] = res.get("summary_id")
             return
 
@@ -99,7 +101,8 @@ class LinkAI(Plugin):
                 _set_reply_text("开启对话失败，请稍后再试吧", e_context)
                 return
             USER_FILE_MAP[_find_user_id(context) + "-file_id"] = res.get("file_id")
-            _set_reply_text("💡你可以问我关于这篇文章的任何问题，例如：\n\n" + res.get("questions") + "\n\n发送 \"退出对话\" 可以关闭与文章的对话", e_context, level=ReplyType.TEXT)
+            _set_reply_text("💡你可以问我关于这篇文章的任何问题，例如：\n\n" + res.get(
+                "questions") + "\n\n发送 \"退出对话\" 可以关闭与文章的对话", e_context, level=ReplyType.TEXT)
             return
 
         if context.type == ContextType.TEXT and context.content == "退出对话" and _find_file_id(context):
@@ -117,12 +120,10 @@ class LinkAI(Plugin):
             e_context.action = EventAction.BREAK_PASS
             return
 
-
         if self._is_chat_task(e_context):
             # 文本对话任务处理
             self._process_chat_task(e_context)
 
-
     # 插件管理功能
     def _process_admin_cmd(self, e_context: EventContext):
         context = e_context['context']
@@ -177,7 +178,9 @@ class LinkAI(Plugin):
                 tips_text = "关闭"
                 is_open = False
             if not self.sum_config:
-                _set_reply_text(f"插件未启用summary功能，请参考以下链添加插件配置\n\nhttps://github.com/zhayujie/chatgpt-on-wechat/blob/master/plugins/linkai/README.md", e_context, level=ReplyType.INFO)
+                _set_reply_text(
+                    f"插件未启用summary功能，请参考以下链添加插件配置\n\nhttps://github.com/zhayujie/chatgpt-on-wechat/blob/master/plugins/linkai/README.md",
+                    e_context, level=ReplyType.INFO)
             else:
                 self.sum_config["enabled"] = is_open
                 _set_reply_text(f"文章总结功能{tips_text}", e_context, level=ReplyType.INFO)
@@ -254,6 +257,9 @@ class LinkAI(Plugin):
         except Exception as e:
             logger.exception(e)
 
+    def reload(self):
+        self.config = super().load_config()
+
 
 def _send_info(e_context: EventContext, content: str):
     reply = Reply(ReplyType.TEXT, content)
@@ -273,15 +279,19 @@ def _set_reply_text(content: str, e_context: EventContext, level: ReplyType = Re
     e_context["reply"] = reply
     e_context.action = EventAction.BREAK_PASS
 
+
 def _get_trigger_prefix():
     return conf().get("plugin_trigger_prefix", "$")
 
+
 def _find_sum_id(context):
     return USER_FILE_MAP.get(_find_user_id(context) + "-sum_id")
 
+
 def _find_file_id(context):
     user_id = _find_user_id(context)
     if user_id:
         return USER_FILE_MAP.get(user_id + "-file_id")
 
+
 USER_FILE_MAP = ExpiredDict(conf().get("expires_in_seconds") or 60 * 30)

plugins/linkai/midjourney.py

@@ -68,7 +68,7 @@ class MJTask:
 # midjourney bot
 class MJBot:
     def __init__(self, config):
-        self.base_url = conf().get("linkai_api_base", "https://api.link-ai.chat") + "/v1/img/midjourney"
+        self.base_url = conf().get("linkai_api_base", "https://api.link-ai.tech") + "/v1/img/midjourney"
         self.headers = {"Authorization": "Bearer " + conf().get("linkai_api_key")}
         self.config = config
         self.tasks = {}
@@ -88,6 +88,8 @@ class MJBot:
         context = e_context['context']
         if context.type == ContextType.TEXT:
             cmd_list = context.content.split(maxsplit=1)
+            if not cmd_list:
+                return None
             if cmd_list[0].lower() == f"{trigger_prefix}mj":
                 return TaskType.GENERATE
             elif cmd_list[0].lower() == f"{trigger_prefix}mju":

plugins/linkai/summary.py

@@ -2,6 +2,7 @@ import requests
 from config import conf
 from common.log import logger
 import os
+import html
 
 
 class LinkSummary:
@@ -18,6 +19,7 @@ class LinkSummary:
         return self._parse_summary_res(res)
 
     def summary_url(self, url: str):
+        url = html.unescape(url)
         body = {
             "url": url
         }
@@ -59,7 +61,7 @@ class LinkSummary:
             return None
 
     def base_url(self):
-        return conf().get("linkai_api_base", "https://api.link-ai.chat")
+        return conf().get("linkai_api_base", "https://api.link-ai.tech")
 
     def headers(self):
         return {"Authorization": "Bearer " + conf().get("linkai_api_key")}

plugins/plugin.py

@@ -46,3 +46,6 @@ class Plugin:
 
     def get_help_text(self, **kwargs):
         return "暂无帮助信息"
+
+    def reload(self):
+        pass

plugins/plugin_manager.py

@@ -99,7 +99,7 @@ class PluginManager:
                     try:
                         self.current_plugin_path = plugin_path
                         if plugin_path in self.loaded:
-                            if self.loaded[plugin_path] == None:
+                            if plugin_name.upper() != 'GODCMD':
                                 logger.info("reload module %s" % plugin_name)
                                 self.loaded[plugin_path] = importlib.reload(sys.modules[import_path])
                                 dependent_module_names = [name for name in sys.modules.keys() if name.startswith(import_path + ".")]
@@ -141,19 +141,21 @@ class PluginManager:
         failed_plugins = []
         for name, plugincls in self.plugins.items():
             if plugincls.enabled:
-                if name not in self.instances:
-                    try:
-                        instance = plugincls()
-                    except Exception as e:
-                        logger.warn("Failed to init %s, diabled. %s" % (name, e))
-                        self.disable_plugin(name)
-                        failed_plugins.append(name)
-                        continue
-                    self.instances[name] = instance
-                    for event in instance.handlers:
-                        if event not in self.listening_plugins:
-                            self.listening_plugins[event] = []
-                        self.listening_plugins[event].append(name)
+                if 'GODCMD' in self.instances and name == 'GODCMD':
+                    continue
+                # if name not in self.instances:
+                try:
+                    instance = plugincls()
+                except Exception as e:
+                    logger.warn("Failed to init %s, diabled. %s" % (name, e))
+                    self.disable_plugin(name)
+                    failed_plugins.append(name)
+                    continue
+                self.instances[name] = instance
+                for event in instance.handlers:
+                    if event not in self.listening_plugins:
+                        self.listening_plugins[event] = []
+                    self.listening_plugins[event].append(name)
         self.refresh_order()
         return failed_plugins
 

plugins/source.json

@@ -19,6 +19,14 @@
     "Apilot": {
       "url": "https://github.com/6vision/Apilot.git",
       "desc": "通过api直接查询早报、热榜、快递、天气等实用信息的插件"
+    },
+    "pictureChange": {
+      "url": "https://github.com/Yanyutin753/pictureChange.git",
+      "desc": "利用stable-diffusion和百度Ai进行图生图或者画图的插件"
+    },
+    "Blackroom": {
+      "url": "https://github.com/dividduang/blackroom.git",
+      "desc": "小黑屋插件，被拉进小黑屋的人将不能使用@bot的功能的插件"
     }
   }
 }

plugins/tool/README.md

@@ -3,11 +3,19 @@
 使用说明(默认trigger_prefix为$)：  
 ```text
 #help tool: 查看tool帮助信息，可查看已加载工具列表  
-$tool 命令: 根据给出的{命令}使用一些可用工具尽力为你得到结果。  
+$tool 工具名 命令: （pure模式）根据给出的{命令}使用指定 一个 可用工具尽力为你得到结果。
+$tool 命令: （多工具模式）根据给出的{命令}使用 一些 可用工具尽力为你得到结果。  
 $tool reset: 重置工具。  
 ```
 ### 本插件所有工具同步存放至专用仓库：[chatgpt-tool-hub](https://github.com/goldfishh/chatgpt-tool-hub)
 
+2024.01.16更新
+1. 新增工具pure模式，支持单个工具调用
+2. 新增消息转发工具：email, sms, wechat, 可以根据规则向其他平台发送消息
+3. 替换visual-dl（更名为visual）实现，目前识别图片链接效果较好。
+4. 修复了0.4版本大部分工具返回结果不可靠问题
+
+新版本工具名共19个，不一一列举，相应工具需要的环境参数见`tool.py`里的`_build_tool_kwargs`函数
 
 ## 使用说明
 使用该插件后将默认使用4个工具, 无需额外配置长期生效：
@@ -24,7 +32,7 @@ $tool reset: 重置工具。
 
 > 注1：url-get默认配置、browser需额外配置，browser依赖google-chrome，你需要提前安装好
 
-> 注2：当检测到长文本时会进入summary tool总结长文本，tokens可能会大量消耗！
+> 注2：（可通过`browser_use_summary`或 `url_get_use_summary`开关）当检测到长文本时会进入summary tool总结长文本，tokens可能会大量消耗！
 
 这是debian端安装google-chrome教程，其他系统请自行查找
 > https://www.linuxjournal.com/content/how-can-you-install-google-browser-debian
@@ -34,9 +42,10 @@ $tool reset: 重置工具。
 
 > terminal调优记录：https://github.com/zhayujie/chatgpt-on-wechat/issues/776#issue-1659347640
 
-### 4. meteo-weather
+### 4. meteo
 ###### 回答你有关天气的询问, 需要获取时间、地点上下文信息，本工具使用了[meteo open api](https://open-meteo.com/)
 注：该工具需要较高的对话技巧，不保证你问的任何问题均能得到满意的回复
+注2：当前版本可只使用这个工具，返回结果较可控。
 
 > meteo调优记录：https://github.com/zhayujie/chatgpt-on-wechat/issues/776#issuecomment-1500771334
 
@@ -65,18 +74,12 @@ $tool reset: 重置工具。
 #### 6.2. morning-news *
 ###### 每日60秒早报，每天凌晨一点更新，本工具使用了[alapi-每日60秒早报](https://alapi.cn/api/view/93)
 
-```text
-可配置参数：
-1. morning_news_use_llm: 是否使用LLM润色结果，默认false（可能会慢）
-```
-
 > 该tool每天返回内容相同
 
 #### 6.3. finance-news
 ###### 获取实时的金融财政新闻
 
-> 该工具需要解决browser tool 的google-chrome依赖安装
-
+> 该工具需要用到browser工具解决反爬问题
 
 
 ### 7. bing-search *
@@ -99,18 +102,33 @@ $tool reset: 重置工具。
 > 0.4.2更新，例子：帮我找一篇吴恩达写的论文
 
 ### 11. summary
-###### 总结工具，该工具必须输入一个本地文件的绝对路径
+###### 总结工具，该工具可以支持输入url
 
 > 该工具目前是和其他工具配合使用，暂未测试单独使用效果
 
-### 12. image2text
-###### 将图片转换成文字，底层调用imageCaption模型，该工具必须输入一个本地文件的绝对路径
+### 12. visual
+###### 将图片转换成文字，底层调用ali dashscope `qwen-vl-plus`模型
 
 ### 13. searxng-search *
 ###### 一个私有化的搜索引擎工具
 
 > 安装教程：https://docs.searxng.org/admin/installation.html
 
+### 14. email *
+###### 发送邮件
+
+### 15. sms *
+###### 发送短信
+
+### 16. stt *
+###### speak to text 语音识别
+
+### 17. tts *
+###### text to speak 文生语音
+
+### 18. wechat *
+###### 向好友、群组发送微信
+
 ---
 
 ###### 注1：带*工具需要获取api-key才能使用(在config.json内的kwargs添加项)，部分工具需要外网支持  
@@ -120,7 +138,7 @@ $tool reset: 重置工具。
 ###### 默认工具无需配置，其它工具需手动配置，以增加morning-news和bing-search两个工具为例：
 ```json
 {
-  "tools": ["bing-search", "news", "你想要添加的其他工具"],  // 填入你想用到的额外工具名，这里加入了工具"bing-search"和工具"news"(news工具会自动加载morning-news、finance-news等子工具)
+  "tools": ["bing-search", "morning-news", "你想要添加的其他工具"],  // 填入你想用到的额外工具名，这里加入了工具"bing-search"和工具"morning-news"
   "kwargs": {
       "debug": true, // 当你遇到问题求助时，需要配置
       "request_timeout": 120,  // openai接口超时时间
@@ -137,7 +155,6 @@ $tool reset: 重置工具。
   - `debug`: 输出chatgpt-tool-hub额外信息用于调试
   - `request_timeout`: 访问openai接口的超时时间，默认与wechat-on-chatgpt配置一致，可单独配置
   - `no_default`: 用于配置默认加载4个工具的行为，如果为true则仅使用tools列表工具，不加载默认工具
-  - `top_k_results`: 控制所有有关搜索的工具返回条目数，数字越高则参考信息越多，但无用信息可能干扰判断，该值一般为2
   - `model_name`: 用于控制tool插件底层使用的llm模型，目前暂未测试3.5以外的模型，一般保持默认
 
 ---

plugins/tool/config.json.template

@@ -3,10 +3,10 @@
     "python",
     "url-get",
     "terminal",
-    "meteo-weather"
+    "meteo"
   ],
   "kwargs": {
-    "top_k_results": 2,
+    "debug": false,
     "no_default": false,
     "model_name": "gpt-3.5-turbo"
   }

plugins/tool/tool.py

@@ -1,23 +1,20 @@
-import json
-import os
-
 from chatgpt_tool_hub.apps import AppFactory
 from chatgpt_tool_hub.apps.app import App
-from chatgpt_tool_hub.tools.all_tool_list import get_all_tool_names
+from chatgpt_tool_hub.tools.tool_register import main_tool_register
 
 import plugins
 from bridge.bridge import Bridge
 from bridge.context import ContextType
 from bridge.reply import Reply, ReplyType
 from common import const
-from config import conf
+from config import conf, get_appdata_dir
 from plugins import *
 
 
 @plugins.register(
     name="tool",
     desc="Arming your ChatGPT bot with various tools",
-    version="0.4",
+    version="0.5",
     author="goldfishh",
     desire_priority=0,
 )
@@ -36,10 +33,12 @@ class Tool(Plugin):
         if not verbose:
             return help_text
         help_text += "\n使用说明：\n"
-        help_text += f"{trigger_prefix}tool " + "命令: 根据给出的{命令}使用一些可用工具尽力为你得到结果。\n"
+        help_text += f"{trigger_prefix}tool " + "命令: 根据给出的{命令}模型来选择使用哪些工具尽力为你得到结果。\n"
+        help_text += f"{trigger_prefix}tool 工具名 " + "命令: 根据给出的{命令}使用指定工具尽力为你得到结果。\n"
         help_text += f"{trigger_prefix}tool reset: 重置工具。\n\n"
+
         help_text += f"已加载工具列表: \n"
-        for idx, tool in enumerate(self.app.get_tool_list()):
+        for idx, tool in enumerate(main_tool_register.get_registered_tool_names()):
             if idx != 0:
                 help_text += ", "
             help_text += f"{tool}"
@@ -91,17 +90,28 @@ class Tool(Plugin):
 
                     e_context.action = EventAction.BREAK
                     return
-
                 query = content_list[1].strip()
+                
+                use_one_tool = False
+                for tool_name in main_tool_register.get_registered_tool_names():
+                    if query.startswith(tool_name):
+                        use_one_tool = True
+                        query = query[len(tool_name):]
+                        break
 
                 # Don't modify bot name
                 all_sessions = Bridge().get_bot("chat").sessions
                 user_session = all_sessions.session_query(query, e_context["context"]["session_id"]).messages
 
-                # chatgpt-tool-hub will reply you with many tools
                 logger.debug("[tool]: just-go")
                 try:
-                    _reply = self.app.ask(query, user_session)
+                    if use_one_tool:
+                        _func, _ = main_tool_register.get_registered_tool()[tool_name]
+                        tool = _func(**self.app_kwargs)
+                        _reply = tool.run(query)
+                    else:
+                        # chatgpt-tool-hub will reply you with many tools
+                        _reply = self.app.ask(query, user_session)
                     e_context.action = EventAction.BREAK_PASS
                     all_sessions.session_reply(_reply, e_context["context"]["session_id"])
                 except Exception as e:
@@ -126,53 +136,111 @@ class Tool(Plugin):
         request_timeout = kwargs.get("request_timeout")
 
         return {
-            "debug": kwargs.get("debug", False),
-            "openai_api_key": conf().get("open_ai_api_key", ""),
-            "open_ai_api_base": conf().get("open_ai_api_base", "https://api.openai.com/v1"),
-            "deployment_id": conf().get("azure_deployment_id", ""),
-            "proxy": conf().get("proxy", ""),
+            # 全局配置相关
+            "log": False,  # tool 日志开关
+            "debug": kwargs.get("debug", False),  # 输出更多日志
+            "no_default": kwargs.get("no_default", False),  # 不要默认的工具，只加载自己导入的工具
+            "think_depth": kwargs.get("think_depth", 2),  # 一个问题最多使用多少次工具
+            "proxy": conf().get("proxy", ""),  # 科学上网
             "request_timeout": request_timeout if request_timeout else conf().get("request_timeout", 120),
+            "temperature": kwargs.get("temperature", 0),  # llm 温度，建议设置0
+            # LLM配置相关
+            "llm_api_key": conf().get("open_ai_api_key", ""),  # 如果llm api用key鉴权，传入这里
+            "llm_api_base_url": conf().get("open_ai_api_base", "https://api.openai.com/v1"),  # 支持openai接口的llm服务地址前缀
+            "deployment_id": conf().get("azure_deployment_id", ""),  # azure openai会用到
             # note: 目前tool暂未对其他模型测试，但这里仍对配置来源做了优先级区分，一般插件配置可覆盖全局配置
-            "model_name": tool_model_name if tool_model_name else conf().get("model", "gpt-3.5-turbo"),
-            "no_default": kwargs.get("no_default", False),
-            "top_k_results": kwargs.get("top_k_results", 3),
-            # for news tool
-            "news_api_key": kwargs.get("news_api_key", ""),
+            "model_name": tool_model_name if tool_model_name else conf().get("model", const.GPT35),
+            # 工具配置相关
+            # for arxiv tool
+            "arxiv_simple": kwargs.get("arxiv_simple", True),  # 返回内容更精简
+            "arxiv_top_k_results": kwargs.get("arxiv_top_k_results", 2),  # 只返回前k个搜索结果
+            "arxiv_sort_by": kwargs.get("arxiv_sort_by", "relevance"),  # 搜索排序方式 ["relevance","lastUpdatedDate","submittedDate"]
+            "arxiv_sort_order": kwargs.get("arxiv_sort_order", "descending"),  # 搜索排序方式 ["ascending", "descending"]
+            "arxiv_output_type": kwargs.get("arxiv_output_type", "text"),  # 搜索结果类型 ["text", "pdf", "all"]
             # for bing-search tool
             "bing_subscription_key": kwargs.get("bing_subscription_key", ""),
+            "bing_search_url": kwargs.get("bing_search_url", "https://api.bing.microsoft.com/v7.0/search"),  # 必应搜索的endpoint地址，无需修改
+            "bing_search_top_k_results": kwargs.get("bing_search_top_k_results", 2),  # 只返回前k个搜索结果
+            "bing_search_simple": kwargs.get("bing_search_simple", True),  # 返回内容更精简
+            "bing_search_output_type": kwargs.get("bing_search_output_type", "text"),  # 搜索结果类型 ["text", "json"]
+            # for email tool
+            "email_nickname_mapping": kwargs.get("email_nickname_mapping", "{}"),  # 关于人的代号对应的邮箱地址，可以不输入邮箱地址发送邮件。键为代号值为邮箱地址
+            "email_smtp_host": kwargs.get("email_smtp_host", ""),  # 例如 'smtp.qq.com'
+            "email_smtp_port": kwargs.get("email_smtp_port", ""),  # 例如 587
+            "email_sender": kwargs.get("email_sender", ""),  # 发送者的邮件地址
+            "email_authorization_code": kwargs.get("email_authorization_code", ""),  # 发送者验证秘钥（可能不是登录密码）
             # for google-search tool
             "google_api_key": kwargs.get("google_api_key", ""),
             "google_cse_id": kwargs.get("google_cse_id", ""),
+            "google_simple": kwargs.get("google_simple", True),   # 返回内容更精简
+            "google_output_type": kwargs.get("google_output_type", "text"),  # 搜索结果类型 ["text", "json"]
+            # for finance-news tool
+            "finance_news_filter": kwargs.get("finance_news_filter", False),  # 是否开启过滤
+            "finance_news_filter_list": kwargs.get("finance_news_filter_list", []),  # 过滤词列表
+            "finance_news_simple": kwargs.get("finance_news_simple", True),   # 返回内容更精简
+            "finance_news_repeat_news": kwargs.get("finance_news_repeat_news", False),  # 是否过滤不返回。该tool每次返回约50条新闻，可能有重复新闻
+            # for morning-news tool
+            "morning_news_api_key": kwargs.get("morning_news_api_key", ""),   # api-key
+            "morning_news_simple": kwargs.get("morning_news_simple", True),   # 返回内容更精简
+            "morning_news_output_type": kwargs.get("morning_news_output_type", "text"),  # 搜索结果类型 ["text", "image"]
+            # for news-api tool
+            "news_api_key": kwargs.get("news_api_key", ""),
             # for searxng-search tool
-            "searx_search_host": kwargs.get("searx_search_host", ""),
+            "searxng_search_host": kwargs.get("searxng_search_host", ""),
+            "searxng_search_top_k_results": kwargs.get("searxng_search_top_k_results", 2),  # 只返回前k个搜索结果
+            "searxng_search_output_type": kwargs.get("searxng_search_output_type", "text"),  # 搜索结果类型 ["text", "json"]
+            # for sms tool
+            "sms_nickname_mapping": kwargs.get("sms_nickname_mapping", "{}"),  # 关于人的代号对应的手机号，可以不输入手机号发送sms。键为代号值为手机号
+            "sms_username": kwargs.get("sms_username", ""),  # smsbao用户名
+            "sms_apikey": kwargs.get("sms_apikey", ""),  # smsbao
+            # for stt tool
+            "stt_api_key": kwargs.get("stt_api_key", ""),  # azure
+            "stt_api_region": kwargs.get("stt_api_region", ""),  # azure
+            "stt_recognition_language": kwargs.get("stt_recognition_language", "zh-CN"),  # 识别的语言类型 部分：en-US ja-JP ko-KR yue-CN zh-CN
+            # for tts tool
+            "tts_api_key": kwargs.get("tts_api_key", ""),  # azure
+            "tts_api_region": kwargs.get("tts_api_region", ""),  # azure
+            "tts_auto_detect": kwargs.get("tts_auto_detect", True),  # 是否自动检测语音的语言
+            "tts_speech_id": kwargs.get("tts_speech_id", "zh-CN-XiaozhenNeural"),  # 输出语音ID
+            # for summary tool
+            "summary_max_segment_length": kwargs.get("summary_max_segment_length", 2500),  # 每2500tokens分段，多段触发总结tool
+            # for terminal tool
+            "terminal_nsfc_filter": kwargs.get("terminal_nsfc_filter", True),  # 是否过滤llm输出的危险命令
+            "terminal_return_err_output": kwargs.get("terminal_return_err_output", True),  # 是否输出错误信息
+            "terminal_timeout": kwargs.get("terminal_timeout", 20),  # 允许命令最长执行时间
+            # for visual tool
+            "caption_api_key": kwargs.get("caption_api_key", ""),  # ali dashscope apikey
+            # for browser tool
+            "browser_use_summary": kwargs.get("browser_use_summary", True),  # 是否对返回结果使用tool功能
+            # for url-get tool
+            "url_get_use_summary": kwargs.get("url_get_use_summary", True),  # 是否对返回结果使用tool功能
+            # for wechat tool
+            "wechat_hot_reload": kwargs.get("wechat_hot_reload", True),  # 是否使用热重载的方式发送wechat
+            "wechat_cpt_path": kwargs.get("wechat_cpt_path", os.path.join(get_appdata_dir(), "itchat.pkl")),  # wechat 配置文件（`itchat.pkl`）
+            "wechat_send_group": kwargs.get("wechat_send_group", False),  # 是否向群组发送消息
+            "wechat_nickname_mapping": kwargs.get("wechat_nickname_mapping", "{}"),  # 关于人的代号映射关系。键为代号值为微信名（昵称、备注名均可）
+            # for wikipedia tool
+            "wikipedia_top_k_results": kwargs.get("wikipedia_top_k_results", 2),  # 只返回前k个搜索结果
             # for wolfram-alpha tool
             "wolfram_alpha_appid": kwargs.get("wolfram_alpha_appid", ""),
-            # for morning-news tool
-            "morning_news_api_key": kwargs.get("morning_news_api_key", ""),
-            # for visual_dl tool
-            "cuda_device": kwargs.get("cuda_device", "cpu"),
-            "think_depth": kwargs.get("think_depth", 3),
-            "arxiv_summary": kwargs.get("arxiv_summary", True),
-            "morning_news_use_llm": kwargs.get("morning_news_use_llm", False),
         }
 
     def _filter_tool_list(self, tool_list: list):
         valid_list = []
         for tool in tool_list:
-            if tool in get_all_tool_names():
+            if tool in main_tool_register.get_registered_tool_names():
                 valid_list.append(tool)
             else:
                 logger.warning("[tool] filter invalid tool: " + repr(tool))
         return valid_list
 
     def _reset_app(self) -> App:
-        tool_config = self._read_json()
-        app_kwargs = self._build_tool_kwargs(tool_config.get("kwargs", {}))
+        self.tool_config = self._read_json()
+        self.app_kwargs = self._build_tool_kwargs(self.tool_config.get("kwargs", {}))
 
         app = AppFactory()
-        app.init_env(**app_kwargs)
-
+        app.init_env(**self.app_kwargs)
         # filter not support tool
-        tool_list = self._filter_tool_list(tool_config.get("tools", []))
+        tool_list = self._filter_tool_list(self.tool_config.get("tools", []))
 
-        return app.create_app(tools_list=tool_list, **app_kwargs)
+        return app.create_app(tools_list=tool_list, **self.app_kwargs)

requirements-optional.txt

@@ -7,26 +7,40 @@ gTTS>=2.3.1 # google text to speech
 pyttsx3>=2.90 # pytsx text to speech
 baidu_aip>=4.16.10 # baidu voice
 azure-cognitiveservices-speech # azure voice
+edge-tts # edge-tts
 numpy<=1.24.2
 langid # language detect
+elevenlabs==1.0.3 # elevenlabs TTS
 
 #install plugin
 dulwich
 
-# wechaty
-wechaty>=0.10.7
-wechaty_puppet>=0.4.23
-# pysilk_mod>=1.6.0 # needed by send voice only in wechaty
-
-# wechatmp wechatcom
+# wechatmp && wechatcom
 web.py
 wechatpy
 
 # chatgpt-tool-hub plugin
-chatgpt_tool_hub==0.4.6
+chatgpt_tool_hub==0.5.0
 
 # xunfei spark
 websocket-client==1.2.0
 
 # claude bot
 curl_cffi
+# claude API
+anthropic
+
+# tongyi qwen
+broadscope_bailian
+
+# google
+google-generativeai
+
+# dingtalk
+dingtalk_stream
+
+# zhipuai
+zhipuai>=2.0.1
+
+# tongyi qwen new sdk
+dashscope

requirements.txt

@@ -7,3 +7,4 @@ chardet>=5.1.0
 Pillow
 pre-commit
 web.py
+linkai>=0.0.6.0

voice/ali/ali_api.py

@@ -0,0 +1,152 @@
+# coding=utf-8
+"""
+Author: chazzjimel
+Email: chazzjimel@gmail.com
+wechat：cheung-z-x
+
+Description:
+
+"""
+
+import json
+import time
+import requests
+import datetime
+import hashlib
+import hmac
+import base64
+import urllib.parse
+import uuid
+
+from common.log import logger
+from common.tmp_dir import TmpDir
+
+
+def text_to_speech_aliyun(url, text, appkey, token):
+    """
+    使用阿里云的文本转语音服务将文本转换为语音。
+
+    参数:
+    - url (str): 阿里云文本转语音服务的端点URL。
+    - text (str): 要转换为语音的文本。
+    - appkey (str): 您的阿里云appkey。
+    - token (str): 阿里云API的认证令牌。
+
+    返回值:
+    - str: 成功时输出音频文件的路径，否则为None。
+    """
+    headers = {
+        "Content-Type": "application/json",
+    }
+
+    data = {
+        "text": text,
+        "appkey": appkey,
+        "token": token,
+        "format": "wav"
+    }
+
+    response = requests.post(url, headers=headers, data=json.dumps(data))
+
+    if response.status_code == 200 and response.headers['Content-Type'] == 'audio/mpeg':
+        output_file = TmpDir().path() + "reply-" + str(int(time.time())) + "-" + str(hash(text) & 0x7FFFFFFF) + ".wav"
+
+        with open(output_file, 'wb') as file:
+            file.write(response.content)
+        logger.debug(f"音频文件保存成功，文件名：{output_file}")
+    else:
+        logger.debug("响应状态码: {}".format(response.status_code))
+        logger.debug("响应内容: {}".format(response.text))
+        output_file = None
+
+    return output_file
+
+
+class AliyunTokenGenerator:
+    """
+    用于生成阿里云服务认证令牌的类。
+
+    属性:
+    - access_key_id (str): 您的阿里云访问密钥ID。
+    - access_key_secret (str): 您的阿里云访问密钥秘密。
+    """
+
+    def __init__(self, access_key_id, access_key_secret):
+        self.access_key_id = access_key_id
+        self.access_key_secret = access_key_secret
+
+    def sign_request(self, parameters):
+        """
+        为阿里云服务签名请求。
+
+        参数:
+        - parameters (dict): 请求的参数字典。
+
+        返回值:
+        - str: 请求的签名签章。
+        """
+        # 将参数按照字典顺序排序
+        sorted_params = sorted(parameters.items())
+
+        # 构造待签名的查询字符串
+        canonicalized_query_string = ''
+        for (k, v) in sorted_params:
+            canonicalized_query_string += '&' + self.percent_encode(k) + '=' + self.percent_encode(v)
+
+        # 构造用于签名的字符串
+        string_to_sign = 'GET&%2F&' + self.percent_encode(canonicalized_query_string[1:])  # 使用GET方法
+
+        # 使用HMAC算法计算签名
+        h = hmac.new((self.access_key_secret + "&").encode('utf-8'), string_to_sign.encode('utf-8'), hashlib.sha1)
+        signature = base64.encodebytes(h.digest()).strip()
+
+        return signature
+
+    def percent_encode(self, encode_str):
+        """
+        对字符串进行百分比编码。
+
+        参数:
+        - encode_str (str): 要编码的字符串。
+
+        返回值:
+        - str: 编码后的字符串。
+        """
+        encode_str = str(encode_str)
+        res = urllib.parse.quote(encode_str, '')
+        res = res.replace('+', '%20')
+        res = res.replace('*', '%2A')
+        res = res.replace('%7E', '~')
+        return res
+
+    def get_token(self):
+        """
+        获取阿里云服务的令牌。
+
+        返回值:
+        - str: 获取到的令牌。
+        """
+        # 设置请求参数
+        params = {
+            'Format': 'JSON',
+            'Version': '2019-02-28',
+            'AccessKeyId': self.access_key_id,
+            'SignatureMethod': 'HMAC-SHA1',
+            'Timestamp': datetime.datetime.utcnow().strftime("%Y-%m-%dT%H:%M:%SZ"),
+            'SignatureVersion': '1.0',
+            'SignatureNonce': str(uuid.uuid4()),  # 使用uuid生成唯一的随机数
+            'Action': 'CreateToken',
+            'RegionId': 'cn-shanghai'
+        }
+
+        # 计算签名
+        signature = self.sign_request(params)
+        params['Signature'] = signature
+
+        # 构造请求URL
+        url = 'http://nls-meta.cn-shanghai.aliyuncs.com/?' + urllib.parse.urlencode(params)
+
+        # 发送请求
+        response = requests.get(url)
+
+        return response.text

voice/ali/ali_voice.py

@@ -0,0 +1,81 @@
+# -*- coding: utf-8 -*-
+"""
+Author: chazzjimel
+Email: chazzjimel@gmail.com
+wechat：cheung-z-x
+
+Description:
+ali voice service
+
+"""
+import json
+import os
+import re
+import time
+
+from bridge.reply import Reply, ReplyType
+from common.log import logger
+from voice.voice import Voice
+from voice.ali.ali_api import AliyunTokenGenerator
+from voice.ali.ali_api import text_to_speech_aliyun
+from config import conf
+
+
+class AliVoice(Voice):
+    def __init__(self):
+        """
+        初始化AliVoice类，从配置文件加载必要的配置。
+        """
+        try:
+            curdir = os.path.dirname(__file__)
+            config_path = os.path.join(curdir, "config.json")
+            with open(config_path, "r") as fr:
+                config = json.load(fr)
+            self.token = None
+            self.token_expire_time = 0
+            # 默认复用阿里云千问的 access_key 和 access_secret
+            self.api_url = config.get("api_url")
+            self.app_key = config.get("app_key")
+            self.access_key_id = conf().get("qwen_access_key_id") or config.get("access_key_id")
+            self.access_key_secret = conf().get("qwen_access_key_secret") or config.get("access_key_secret")
+        except Exception as e:
+            logger.warn("AliVoice init failed: %s, ignore " % e)
+
+    def textToVoice(self, text):
+        """
+        将文本转换为语音文件。
+
+        :param text: 要转换的文本。
+        :return: 返回一个Reply对象，其中包含转换得到的语音文件或错误信息。
+        """
+        # 清除文本中的非中文、非英文和非基本字符
+        text = re.sub(r'[^\u4e00-\u9fa5\u3040-\u30FF\uAC00-\uD7AFa-zA-Z0-9'
+                      r'äöüÄÖÜáéíóúÁÉÍÓÚàèìòùÀÈÌÒÙâêîôûÂÊÎÔÛçÇñÑ，。！？,.]', '', text)
+        # 提取有效的token
+        token_id = self.get_valid_token()
+        fileName = text_to_speech_aliyun(self.api_url, text, self.app_key, token_id)
+        if fileName:
+            logger.info("[Ali] textToVoice text={} voice file name={}".format(text, fileName))
+            reply = Reply(ReplyType.VOICE, fileName)
+        else:
+            reply = Reply(ReplyType.ERROR, "抱歉，语音合成失败")
+        return reply
+
+    def get_valid_token(self):
+        """
+        获取有效的阿里云token。
+
+        :return: 返回有效的token字符串。
+        """
+        current_time = time.time()
+        if self.token is None or current_time >= self.token_expire_time:
+            get_token = AliyunTokenGenerator(self.access_key_id, self.access_key_secret)
+            token_str = get_token.get_token()
+            token_data = json.loads(token_str)
+            self.token = token_data["Token"]["Id"]
+            # 将过期时间减少一小段时间（例如5分钟），以避免在边界条件下的过期
+            self.token_expire_time = token_data["Token"]["ExpireTime"] - 300
+            logger.debug(f"新获取的阿里云token：{self.token}")
+        else:
+            logger.debug("使用缓存的token")
+        return self.token

voice/ali/config.json.template

@@ -0,0 +1,6 @@
+{
+    "api_url": "https://nls-gateway-cn-shanghai.aliyuncs.com/stream/v1/tts",
+    "app_key": "",
+    "access_key_id": "",
+    "access_key_secret": ""
+}

voice/audio_convert.py

@@ -6,7 +6,7 @@ from common.log import logger
 try:
     import pysilk
 except ImportError:
-    logger.warn("import pysilk failed, wechaty voice message will not be supported.")
+    logger.debug("import pysilk failed, wechaty voice message will not be supported.")
 
 from pydub import AudioSegment
 
@@ -64,7 +64,9 @@ def any_to_wav(any_path, wav_path):
     if any_path.endswith(".sil") or any_path.endswith(".silk") or any_path.endswith(".slk"):
         return sil_to_wav(any_path, wav_path)
     audio = AudioSegment.from_file(any_path)
-    audio.export(wav_path, format="wav")
+    audio.set_frame_rate(8000)    # 百度语音转写支持8000采样率, pcm_s16le, 单通道语音识别
+    audio.set_channels(1)
+    audio.export(wav_path, format="wav", codec='pcm_s16le')
 
 
 def any_to_sil(any_path, sil_path):

voice/baidu/baidu_voice.py

@@ -62,7 +62,7 @@ class BaiduVoice(Voice):
         # 识别本地文件
         logger.debug("[Baidu] voice file name={}".format(voice_file))
         pcm = get_pcm_from_wav(voice_file)
-        res = self.client.asr(pcm, "pcm", 16000, {"dev_pid": self.dev_id})
+        res = self.client.asr(pcm, "pcm", 8000, {"dev_pid": self.dev_id})
         if res["err_no"] == 0:
             logger.info("百度语音识别到了：{}".format(res["result"]))
             text = "".join(res["result"])

voice/edge/edge_voice.py

@@ -0,0 +1,50 @@
+import time
+
+import edge_tts
+import asyncio
+
+from bridge.reply import Reply, ReplyType
+from common.log import logger
+from common.tmp_dir import TmpDir
+from voice.voice import Voice
+
+
+class EdgeVoice(Voice):
+
+    def __init__(self):
+        '''
+        # 普通话
+        zh-CN-XiaoxiaoNeural
+        zh-CN-XiaoyiNeural
+        zh-CN-YunjianNeural
+        zh-CN-YunxiNeural
+        zh-CN-YunxiaNeural
+        zh-CN-YunyangNeural
+        # 地方口音
+        zh-CN-liaoning-XiaobeiNeural
+        zh-CN-shaanxi-XiaoniNeural
+        # 粤语
+        zh-HK-HiuGaaiNeural
+        zh-HK-HiuMaanNeural
+        zh-HK-WanLungNeural
+        # 湾湾腔
+        zh-TW-HsiaoChenNeural
+        zh-TW-HsiaoYuNeural
+        zh-TW-YunJheNeural
+        '''
+        self.voice = "zh-CN-YunjianNeural"
+
+    def voiceToText(self, voice_file):
+        pass
+
+    async def gen_voice(self, text, fileName):
+        communicate = edge_tts.Communicate(text, self.voice)
+        await communicate.save(fileName)
+
+    def textToVoice(self, text):
+        fileName = TmpDir().path() + "reply-" + str(int(time.time())) + "-" + str(hash(text) & 0x7FFFFFFF) + ".mp3"
+
+        asyncio.run(self.gen_voice(text, fileName))
+
+        logger.info("[EdgeTTS] textToVoice text={} voice file name={}".format(text, fileName))
+        return Reply(ReplyType.VOICE, fileName)

voice/elevent/elevent_voice.py

@@ -1,7 +1,7 @@
 import time
 
-from elevenlabs import set_api_key,generate
-
+from elevenlabs.client import ElevenLabs
+from elevenlabs import save
 from bridge.reply import Reply, ReplyType
 from common.log import logger
 from common.tmp_dir import TmpDir
@@ -9,7 +9,7 @@ from voice.voice import Voice
 from config import conf
 
 XI_API_KEY = conf().get("xi_api_key")
-set_api_key(XI_API_KEY)
+client = ElevenLabs(api_key=XI_API_KEY)
 name = conf().get("xi_voice_id")
 
 class ElevenLabsVoice(Voice):
@@ -21,13 +21,12 @@ class ElevenLabsVoice(Voice):
         pass
 
     def textToVoice(self, text):
-        audio = generate(
+        audio = client.generate(
             text=text,
             voice=name,
-            model='eleven_multilingual_v1'
+            model='eleven_multilingual_v2'
         )
         fileName = TmpDir().path() + "reply-" + str(int(time.time())) + "-" + str(hash(text) & 0x7FFFFFFF) + ".mp3"
-        with open(fileName, "wb") as f:
-            f.write(audio)
+        save(audio, fileName)
         logger.info("[ElevenLabs] textToVoice text={} voice file name={}".format(text, fileName))
         return Reply(ReplyType.VOICE, fileName)

voice/factory.py

@@ -36,5 +36,14 @@ def create_voice(voice_type):
 
     elif voice_type == "linkai":
         from voice.linkai.linkai_voice import LinkAIVoice
+
         return LinkAIVoice()
+    elif voice_type == "ali":
+        from voice.ali.ali_voice import AliVoice
+
+        return AliVoice()
+    elif voice_type == "edge":
+        from voice.edge.edge_voice import EdgeVoice
+
+        return EdgeVoice()
     raise RuntimeError

voice/linkai/linkai_voice.py

@@ -19,7 +19,7 @@ class LinkAIVoice(Voice):
     def voiceToText(self, voice_file):
         logger.debug("[LinkVoice] voice file name={}".format(voice_file))
         try:
-            url = conf().get("linkai_api_base", "https://api.link-ai.chat") + "/v1/audio/transcriptions"
+            url = conf().get("linkai_api_base", "https://api.link-ai.tech") + "/v1/audio/transcriptions"
             headers = {"Authorization": "Bearer " + conf().get("linkai_api_key")}
             model = None
             if not conf().get("text_to_voice") or conf().get("voice_to_text") == "openai":
@@ -54,7 +54,7 @@ class LinkAIVoice(Voice):
 
     def textToVoice(self, text):
         try:
-            url = conf().get("linkai_api_base", "https://api.link-ai.chat") + "/v1/audio/speech"
+            url = conf().get("linkai_api_base", "https://api.link-ai.tech") + "/v1/audio/speech"
             headers = {"Authorization": "Bearer " + conf().get("linkai_api_key")}
             model = const.TTS_1
             if not conf().get("text_to_voice") or conf().get("text_to_voice") in ["openai", const.TTS_1, const.TTS_1_HD]:
@@ -62,7 +62,8 @@ class LinkAIVoice(Voice):
             data = {
                 "model": model,
                 "input": text,
-                "voice": conf().get("tts_voice_id")
+                "voice": conf().get("tts_voice_id"),
+                "app_code": conf().get("linkai_app_code")
             }
             res = requests.post(url, headers=headers, json=data, timeout=(5, 120))
             if res.status_code == 200:

voice/openai/openai_voice.py

@@ -21,8 +21,21 @@ class OpenaiVoice(Voice):
         logger.debug("[Openai] voice file name={}".format(voice_file))
         try:
             file = open(voice_file, "rb")
-            result = openai.Audio.transcribe("whisper-1", file)
-            text = result["text"]
+            api_base = conf().get("open_ai_api_base") or "https://api.openai.com/v1"
+            url = f'{api_base}/audio/transcriptions'
+            headers = {
+                'Authorization': 'Bearer ' + conf().get("open_ai_api_key"),
+                # 'Content-Type': 'multipart/form-data' # 加了会报错，不知道什么原因
+            }
+            files = {
+                "file": file,
+            }
+            data = {
+                "model": "whisper-1",
+            }
+            response = requests.post(url, headers=headers, files=files, data=data)
+            response_data = response.json()
+            text = response_data['text']
             reply = Reply(ReplyType.TEXT, text)
             logger.info("[Openai] voiceToText text={} voice file name={}".format(text, voice_file))
         except Exception as e:
@@ -33,7 +46,8 @@ class OpenaiVoice(Voice):
 
     def textToVoice(self, text):
         try:
-            url = 'https://api.openai.com/v1/audio/speech'
+            api_base = conf().get("open_ai_api_base") or "https://api.openai.com/v1"
+            url = f'{api_base}/audio/speech'
             headers = {
                 'Authorization': 'Bearer ' + conf().get("open_ai_api_key"),
                 'Content-Type': 'application/json'