Merge branch 'zhayujie:master' into dingdinggpt

.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

README.md

@@ -4,10 +4,10 @@
 
 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] **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, 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
 - [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
@@ -28,6 +28,10 @@ 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
 
 >**2023.10.16：** 支持通过意图识别使用LinkAI联网搜索、数学计算、网页访问等插件，参考[插件文档](https://docs.link-ai.tech/platform/plugins)
@@ -52,6 +56,8 @@ Demo made by [Visionn](https://www.wangpc.cc/)
 
 # 快速开始
 
+快速开始文档：[项目搭建文档](https://docs.link-ai.tech/cow/quick-start)
+
 ## 准备
 
 ### 1. 账号注册

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

@@ -43,4 +43,13 @@ def create_bot(bot_type):
     elif bot_type == const.CLAUDEAI:
         from bot.claude.claude_ai_bot import ClaudeAIBot
         return ClaudeAIBot()
+
+    elif bot_type == const.QWEN:
+        from bot.ali.ali_qwen_bot import AliQwenBot
+        return AliQwenBot()
+
+    elif bot_type == const.GEMINI:
+        from bot.gemini.google_gemini_bot import GoogleGeminiBot
+        return GoogleGeminiBot()
+
     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

@@ -57,7 +57,7 @@ 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

bot/gemini/google_gemini_bot.py

@@ -0,0 +1,75 @@
+"""
+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)
+
+    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
+
+    def _filter_messages(self, messages: list):
+        res = []
+        turn = "user"
+        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
@@ -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"]
@@ -92,7 +96,7 @@ class LinkAIBot(Bot):
             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
@@ -118,6 +122,9 @@ 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:
@@ -164,6 +171,18 @@ 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:
@@ -336,6 +355,14 @@ 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:
@@ -362,7 +389,7 @@ 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 +397,9 @@ 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/xunfei/xunfei_spark_bot.py

@@ -40,10 +40,13 @@ 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"
+        # 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"
         self.spark_url = "ws://spark-api.xf-yun.com/v3.1/chat"
         self.host = urlparse(self.spark_url).netloc
         self.path = urlparse(self.spark_url).path

bridge/bridge.py

@@ -27,12 +27,18 @@ 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.GEMINI]:
+            self.btype["chat"] = const.GEMINI
+
         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 = {}

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

channel/chat_channel.py

@@ -184,8 +184,6 @@ 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)

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

@@ -170,7 +170,7 @@ 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))

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

@@ -128,6 +128,18 @@ 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 +191,7 @@ 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

@@ -6,6 +6,8 @@ XUNFEI = "xunfei"
 CHATGPTONAZURE = "chatGPTOnAzure"
 LINKAI = "linkai"
 CLAUDEAI = "claude"
+QWEN = "qwen"
+GEMINI = "gemini"
 
 # model
 GPT35 = "gpt-3.5-turbo"
@@ -16,7 +18,7 @@ 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", "gpt-4-turbo", GPT4_TURBO_PREVIEW, QWEN, GEMINI]
 
 # channel
 FEISHU = "feishu"

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 +67,14 @@ available_setting = {
     # claude 配置
     "claude_api_cookie": "",
     "claude_uuid": "",
+    # 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
+    # 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

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]:
                         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]:
                                 channel.cancel_all_session()
                                 bot.sessions.clear_all_session()
                                 ok, result = True, "重置所有会话成功"

plugins/hello/hello.py

@@ -22,15 +22,16 @@ class Hello(Plugin):
         super().__init__()
         self.handlers[Event.ON_HANDLE_CONTEXT] = self.on_handle_context
         logger.info("[Hello] inited")
+        self.config = super().load_config()
 
     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
-
         if e_context["context"].type == ContextType.JOIN_GROUP:
             if "group_welcome_msg" in conf():
                 reply = Reply()
@@ -43,13 +44,27 @@ class Hello(Plugin):
             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.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
+                msg: ChatMessage = e_context["context"]["msg"]
+                e_context["context"].content = f'请你随机使用一种风格跟其他群用户说他违反规则"{msg.actual_user_nickname}"退出群聊。'
+                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.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

plugins/linkai/midjourney.py

@@ -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":

requirements-optional.txt

@@ -30,3 +30,6 @@ websocket-client==1.2.0
 
 # claude bot
 curl_cffi
+
+# tongyi qwen
+broadscope_bailian

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/factory.py

@@ -36,5 +36,10 @@ 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()
     raise RuntimeError

voice/linkai/linkai_voice.py

@@ -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

@@ -33,7 +33,8 @@ 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'