Merge branch 'zhayujie:master' into chenzk

README.md

@@ -5,7 +5,7 @@
 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, GPT-3.5, GPT-4, 文心一言, 讯飞星火
+- [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, 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 Dell-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、聊天记录总结等插件
@@ -27,6 +27,7 @@ Demo made by [Visionn](https://www.wangpc.cc/)
 <img width="240" src="./docs/images/contact.jpg">
 
 # 更新日志
+>**2023.09.01：** 接入讯飞星火，claude机器人
 
 >**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
 
@@ -157,7 +158,7 @@ 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`  (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`, `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)
 + `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 `
@@ -175,6 +176,26 @@ pip3 install azure-cognitiveservices-speech
 + `linkai_api_key`: LinkAI Api Key，可在 [控制台](https://chat.link-ai.tech/console/interface) 创建
 + `linkai_app_code`: LinkAI 应用code，选填
 
+**6.wenxin配置 (可选 model 为 wenxin 时生效)**
+
++ `baidu_wenxin_api_key`: 文心一言官网api key。
++ `baidu_wenxin_secret_key`: 文心一言官网secret key。
+
+
+**6.Claude配置 (可选 model 为 claude 时生效)**
+
++ `claude_api_cookie`: claude官网聊天界面复制完整 cookie 字符串。
++ `claude_uuid`: 可以指定对话id，默认新建对话实体。
+
+
+**7.xunfei配置 (可选 model 为 xunfei 时生效)**
+
++ `xunfei_app_id`: 讯飞星火app id。
++ `xunfei_api_key`: 讯飞星火 api key。
++ `xunfei_api_secret`: 讯飞星火 secret。
+
+
+
 **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

bot/bot_factory.py

@@ -39,4 +39,8 @@ def create_bot(bot_type):
     elif bot_type == const.LINKAI:
         from bot.linkai.link_ai_bot import LinkAIBot
         return LinkAIBot()
+
+    elif bot_type == const.CLAUDEAI:
+        from bot.claude.claude_ai_bot import ClaudeAIBot
+        return ClaudeAIBot()
     raise RuntimeError

bot/claude/claude_ai_bot.py

@@ -0,0 +1,218 @@
+import re
+import time
+import json
+import uuid
+from curl_cffi import requests
+from bot.bot import Bot
+from bot.claude.claude_ai_session import ClaudeAiSession
+from bot.openai.open_ai_image import OpenAIImage
+from bot.session_manager import SessionManager
+from bridge.context import Context, ContextType
+from bridge.reply import Reply, ReplyType
+from common.log import logger
+from config import conf
+
+
+class ClaudeAIBot(Bot, OpenAIImage):
+    def __init__(self):
+        super().__init__()
+        self.sessions = SessionManager(ClaudeAiSession, model=conf().get("model") or "gpt-3.5-turbo")
+        self.claude_api_cookie = conf().get("claude_api_cookie")
+        self.proxy = conf().get("proxy")
+        self.con_uuid_dic = {}
+        if self.proxy:
+            self.proxies = {
+            "http": self.proxy,
+            "https": self.proxy
+        }
+        else:
+            self.proxies = None
+        self.org_uuid = self.get_organization_id()
+
+    def generate_uuid(self):
+        random_uuid = uuid.uuid4()
+        random_uuid_str = str(random_uuid)
+        formatted_uuid = f"{random_uuid_str[0:8]}-{random_uuid_str[9:13]}-{random_uuid_str[14:18]}-{random_uuid_str[19:23]}-{random_uuid_str[24:]}"
+        return formatted_uuid
+
+    def get_uuid(self):
+        if conf().get("claude_uuid") != None:
+            self.con_uuid = conf().get("claude_uuid")
+        else:
+            con_uuid = self.generate_uuid()
+            self.create_new_chat(con_uuid)
+
+    def get_organization_id(self):
+        url = "https://claude.ai/api/organizations"
+        headers = {
+            'User-Agent':
+                'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:109.0) Gecko/20100101 Firefox/115.0',
+            'Accept-Language': 'en-US,en;q=0.5',
+            'Referer': 'https://claude.ai/chats',
+            'Content-Type': 'application/json',
+            'Sec-Fetch-Dest': 'empty',
+            'Sec-Fetch-Mode': 'cors',
+            'Sec-Fetch-Site': 'same-origin',
+            'Connection': 'keep-alive',
+            'Cookie': f'{self.claude_api_cookie}'
+        }
+        response = requests.get(url, headers=headers,impersonate="chrome110",proxies=self.proxies)
+        res = json.loads(response.text)
+        uuid = res[0]['uuid']
+        return uuid
+        
+    def reply(self, query, context: Context = None) -> Reply:
+        if context.type == ContextType.TEXT:
+            return self._chat(query, context)
+        elif context.type == ContextType.IMAGE_CREATE:
+            ok, res = self.create_img(query, 0)
+            if ok:
+                reply = Reply(ReplyType.IMAGE_URL, res)
+            else:
+                reply = Reply(ReplyType.ERROR, res)
+            return reply
+        else:
+            reply = Reply(ReplyType.ERROR, "Bot不支持处理{}类型的消息".format(context.type))
+            return reply
+
+    def get_organization_id(self):
+        url = "https://claude.ai/api/organizations"
+        headers = {
+            'User-Agent':
+                'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:109.0) Gecko/20100101 Firefox/115.0',
+            'Accept-Language': 'en-US,en;q=0.5',
+            'Referer': 'https://claude.ai/chats',
+            'Content-Type': 'application/json',
+            'Sec-Fetch-Dest': 'empty',
+            'Sec-Fetch-Mode': 'cors',
+            'Sec-Fetch-Site': 'same-origin',
+            'Connection': 'keep-alive',
+            'Cookie': f'{self.claude_api_cookie}'
+        }
+        try:
+            response = requests.get(url, headers=headers,impersonate="chrome110",proxies =self.proxies )
+            res = json.loads(response.text)
+            uuid = res[0]['uuid']
+        except:
+            print(response.text)
+        return uuid
+
+    def conversation_share_check(self,session_id):
+        if session_id not in self.con_uuid_dic:
+            self.con_uuid_dic[session_id] = self.generate_uuid()
+            self.create_new_chat(self.con_uuid_dic[session_id])
+        return self.con_uuid_dic[session_id]
+
+    def create_new_chat(self, con_uuid):
+        url = f"https://claude.ai/api/organizations/{self.org_uuid}/chat_conversations"
+        payload = json.dumps({"uuid": con_uuid, "name": ""})
+        headers = {
+            'User-Agent':
+                'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:109.0) Gecko/20100101 Firefox/115.0',
+            'Accept-Language': 'en-US,en;q=0.5',
+            'Referer': 'https://claude.ai/chats',
+            'Content-Type': 'application/json',
+            'Origin': 'https://claude.ai',
+            'DNT': '1',
+            'Connection': 'keep-alive',
+            'Cookie': self.claude_api_cookie,
+            'Sec-Fetch-Dest': 'empty',
+            'Sec-Fetch-Mode': 'cors',
+            'Sec-Fetch-Site': 'same-origin',
+            'TE': 'trailers'
+        }
+        response = requests.post(url, headers=headers, data=payload,impersonate="chrome110", proxies= self.proxies)
+        # Returns JSON of the newly created conversation information
+        return response.json()
+        
+    def _chat(self, query, context, retry_count=0) -> Reply:
+        """
+        发起对话请求
+        :param query: 请求提示词
+        :param context: 对话上下文
+        :param retry_count: 当前递归重试次数
+        :return: 回复
+        """
+        if retry_count >= 2:
+            # exit from retry 2 times
+            logger.warn("[CLAUDEAI] failed after maximum number of retry times")
+            return Reply(ReplyType.ERROR, "请再问我一次吧")
+
+        try:
+            session_id = context["session_id"]
+            session = self.sessions.session_query(query, session_id)
+            con_uuid = self.conversation_share_check(session_id)
+            model = conf().get("model") or "gpt-3.5-turbo"
+            # remove system message
+            if session.messages[0].get("role") == "system":
+                if model == "wenxin" or model == "claude":
+                    session.messages.pop(0)
+            logger.info(f"[CLAUDEAI] query={query}")
+
+            # do http request
+            base_url = "https://claude.ai"
+            payload = json.dumps({
+                "completion": {
+                    "prompt": f"{query}",
+                    "timezone": "Asia/Kolkata",
+                    "model": "claude-2"
+                },
+                "organization_uuid": f"{self.org_uuid}",
+                "conversation_uuid": f"{con_uuid}",
+                "text": f"{query}",
+                "attachments": []
+            })
+            headers = {
+                'User-Agent':
+                    'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:109.0) Gecko/20100101 Firefox/115.0',
+                'Accept': 'text/event-stream, text/event-stream',
+                'Accept-Language': 'en-US,en;q=0.5',
+                'Referer': 'https://claude.ai/chats',
+                'Content-Type': 'application/json',
+                'Origin': 'https://claude.ai',
+                'DNT': '1',
+                'Connection': 'keep-alive',
+                'Cookie': f'{self.claude_api_cookie}',
+                'Sec-Fetch-Dest': 'empty',
+                'Sec-Fetch-Mode': 'cors',
+                'Sec-Fetch-Site': 'same-origin',
+                'TE': 'trailers'
+            }
+
+            res = requests.post(base_url + "/api/append_message", headers=headers, data=payload,impersonate="chrome110",proxies= self.proxies,timeout=400)
+            if res.status_code == 200 or "pemission" in res.text:
+                # execute success
+                decoded_data = res.content.decode("utf-8")
+                decoded_data = re.sub('\n+', '\n', decoded_data).strip()
+                data_strings = decoded_data.split('\n')
+                completions = []
+                for data_string in data_strings:
+                    json_str = data_string[6:].strip()
+                    data = json.loads(json_str)
+                    if 'completion' in data:
+                        completions.append(data['completion'])
+
+                reply_content = ''.join(completions)
+                logger.info(f"[CLAUDE] reply={reply_content}, total_tokens=invisible")
+
+                self.sessions.session_reply(reply_content, session_id, 100)
+                return Reply(ReplyType.TEXT, reply_content)
+            else:
+                response = res.json()
+                error = response.get("error")
+                logger.error(f"[CLAUDE] chat failed, status_code={res.status_code}, "
+                             f"msg={error.get('message')}, type={error.get('type')}, detail: {res.text}, uuid: {con_uuid}")
+
+                if res.status_code >= 500:
+                    # server error, need retry
+                    time.sleep(2)
+                    logger.warn(f"[CLAUDE] do retry, times={retry_count}")
+                    return self._chat(query, context, retry_count + 1)
+                return Reply(ReplyType.ERROR, "提问太快啦，请休息一下再问我吧")
+
+        except Exception as e:
+            logger.exception(e)
+            # retry
+            time.sleep(2)
+            logger.warn(f"[CLAUDE] do retry, times={retry_count}")
+            return self._chat(query, context, retry_count + 1)

bot/claude/claude_ai_session

@@ -0,0 +1,9 @@
+from bot.session_manager import Session
+
+
+class ClaudeAiSession(Session):
+    def __init__(self, session_id, system_prompt=None, model="claude"):
+        super().__init__(session_id, system_prompt)
+        self.model = model
+        # claude逆向不支持role prompt
+        # self.reset()

bridge/bridge.py

@@ -29,6 +29,8 @@ class Bridge(object):
             self.btype["chat"] = const.XUNFEI
         if conf().get("use_linkai") and conf().get("linkai_api_key"):
             self.btype["chat"] = const.LINKAI
+        if model_type in ["claude"]:
+            self.btype["chat"] = const.CLAUDEAI
         self.bots = {}
 
     def get_bot(self, typename):

channel/chat_channel.py

@@ -110,9 +110,10 @@ class ChatChannel(Channel):
                         flag = True
                     pattern = f"@{re.escape(self.name)}(\u2005|\u0020)"
                     subtract_res = re.sub(pattern, r"", content)
-                    for at in context["msg"].at_list:
-                        pattern = f"@{re.escape(at)}(\u2005|\u0020)"
-                        subtract_res = re.sub(pattern, r"", subtract_res)
+                    if isinstance(context["msg"].at_list, list):
+                        for at in context["msg"].at_list:
+                            pattern = f"@{re.escape(at)}(\u2005|\u0020)"
+                            subtract_res = re.sub(pattern, r"", subtract_res)
                     if subtract_res == content and context["msg"].self_display_name:
                         # 前缀移除后没有变化，使用群昵称再次移除
                         pattern = f"@{re.escape(context['msg'].self_display_name)}(\u2005|\u0020)"

common/const.py

@@ -8,4 +8,5 @@ LINKAI = "linkai"
 
 VERSION = "1.3.0"
 
-MODEL_LIST = ["gpt-3.5-turbo", "gpt-3.5-turbo-16k", "gpt-4", "wenxin", "xunfei"]
+CLAUDEAI = "claude"
+MODEL_LIST = ["gpt-3.5-turbo", "gpt-3.5-turbo-16k", "gpt-4", "wenxin", "xunfei","claude"]

config.py

@@ -59,6 +59,11 @@ available_setting = {
     "xunfei_app_id": "",  # 讯飞应用ID
     "xunfei_api_key": "",  # 讯飞 API key
     "xunfei_api_secret": "",  # 讯飞 API secret
+    # claude 配置
+    "claude_api_cookie": "",
+    "claude_uuid": "",
+    # 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
     "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
@@ -121,8 +126,6 @@ available_setting = {
     "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
-    # 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
 }
 
 

requirements-optional.txt

@@ -28,3 +28,6 @@ chatgpt_tool_hub==0.4.6
 
 # xunfei spark
 websocket-client==1.2.0
+
+# claude bot
+curl_cffi