fix: api base bug

Image generation supports custom endpoint

.gitignore

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

README.md

@@ -4,8 +4,8 @@
 
 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、业微信、飞书等部署方式
-- [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] **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、飞书等部署方式
+- [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, Gemini, 文心一言, 讯飞星火, 通义千问
 - [x] **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
 - [x] **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, vision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
@@ -28,6 +28,8 @@ Demo made by [Visionn](https://www.wangpc.cc/)
 
 # 更新日志
 
+>**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Google Gemini、通义千问模型
+
 >**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
 
 >**2023.11.10：** [1.5.0版本](https://github.com/zhayujie/chatgpt-on-wechat/releases/tag/1.5.0)，新增 `gpt-4-turbo`, `dall-e-3`, `tts` 模型接入，完善图像理解&生成、语音识别&生成的多模态能力

app.py

@@ -8,6 +8,7 @@ from channel import channel_factory
 from common import const
 from config import load_config
 from plugins import *
+import threading
 
 
 def sigterm_handler_wrap(_signo):
@@ -43,11 +44,19 @@ def run():
             # 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]:
+        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
+
         # startup channel
         channel.startup()
+
     except Exception as e:
         logger.error("App startup failed!")
         logger.exception(e)

bot/linkai/link_ai_bot.py

@@ -16,7 +16,6 @@ import threading
 from common import memory, utils
 import base64
 
-
 class LinkAIBot(Bot):
     # authentication failed
     AUTH_FAILED_CODE = 401
@@ -83,7 +82,6 @@ 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,
@@ -92,7 +90,25 @@ 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,
+                "channel_type": conf().get("channel_type")
             }
+            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:
+                            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
@@ -230,7 +246,7 @@ 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")

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"

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/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
+        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/wechat/wechat_channel.py

@@ -109,6 +109,7 @@ 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
@@ -120,6 +121,8 @@ class WechatChannel(ChatChannel):
             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
@@ -127,6 +130,14 @@ class WechatChannel(ChatChannel):
         # start message listener
         itchat.run()
 
+    def exitCallback(self):
+        self.auto_login_times += 1
+        if self.auto_login_times < 100:
+            self.startup()
+
+    def loginCallback(self):
+        pass
+
     # 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
     #   type 消息类型, 包括TEXT、VOICE、IMAGE_CREATE

common/const.py

@@ -22,3 +22,4 @@ MODEL_LIST = ["gpt-3.5-turbo", "gpt-3.5-turbo-16k", "gpt-4", "wenxin", "wenxin-4
 
 # channel
 FEISHU = "feishu"
+DINGTALK = "dingtalk"   

common/linkai_client.py

@@ -0,0 +1,28 @@
+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
+
+
+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 start(channel):
+    client = ChatClient(api_key=conf().get("linkai_api_key"),
+                        host="link-ai.chat", channel=channel)
+    client.start()

config-template.json

@@ -19,9 +19,6 @@
     "ChatGPT测试群",
     "ChatGPT测试群2"
   ],
-  "group_chat_in_one_session": [
-    "ChatGPT测试群"
-  ],
   "image_create_prefix": [
     "画"
   ],
@@ -32,8 +29,7 @@
   "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。",
   "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

@@ -132,7 +132,11 @@ 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

requirements-optional.txt

@@ -13,12 +13,7 @@ langid # language detect
 #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
 
@@ -33,3 +28,12 @@ curl_cffi
 
 # tongyi qwen
 broadscope_bailian
+
+# google
+google-generativeai
+
+# linkai
+linkai
+
+# dingtalk
+dingtalk_stream