Merge pull request #2206 from VanJohnPK/master

fix azure voice error 修复Azure语音服务报错问题

README.md

@@ -46,6 +46,8 @@ DEMO视频：https://cdn.link-ai.tech/doc/cow_demo.mp4
 
 # 🏷 更新日志
 
+>**2024.08.02：** [1.7.0版本](https://github.com/zhayujie/chatgpt-on-wechat/releases/tag/1.6.9) 新增 讯飞4.0 模型、知识库引用来源展示、相关插件优化
+
 >**2024.07.19：** [1.6.9版本](https://github.com/zhayujie/chatgpt-on-wechat/releases/tag/1.6.9) 新增 gpt-4o-mini 模型、阿里语音识别、企微应用渠道路由优化
 
 >**2024.07.05：** [1.6.8版本](https://github.com/zhayujie/chatgpt-on-wechat/releases/tag/1.6.8) 和 [1.6.7版本](https://github.com/zhayujie/chatgpt-on-wechat/releases/tag/1.6.7)，Claude3.5, Gemini 1.5 Pro, MiniMax模型、工作流图片输入、模型列表完善

bot/baidu/baidu_wenxin.py

@@ -19,6 +19,11 @@ class BaiduWenxinBot(Bot):
     def __init__(self):
         super().__init__()
         wenxin_model = conf().get("baidu_wenxin_model")
+        self.prompt_enabled = conf().get("baidu_wenxin_prompt_enabled")
+        if self.prompt_enabled:
+            self.prompt = conf().get("character_desc", "")
+            if self.prompt == "":
+                logger.warn("[BAIDU] Although you enabled model prompt, character_desc is not specified.")
         if wenxin_model is not None:
             wenxin_model = conf().get("baidu_wenxin_model") or "eb-instant"
         else:
@@ -84,7 +89,7 @@ class BaiduWenxinBot(Bot):
             headers = {
                 'Content-Type': 'application/json'
             }
-            payload = {'messages': session.messages}
+            payload = {'messages': session.messages, 'system': self.prompt} if self.prompt_enabled else {'messages': session.messages}
             response = requests.request("POST", url, headers=headers, data=json.dumps(payload))
             response_text = json.loads(response.text)
             logger.info(f"[BAIDU] response text={response_text}")

bot/chatgpt/chat_gpt_bot.py

@@ -208,11 +208,33 @@ class AzureChatGPTBot(ChatGPTBot):
             headers = {"api-key": api_key, "Content-Type": "application/json"}
             try:
                 body = {"prompt": query, "size": conf().get("image_create_size", "1024x1024"), "quality": conf().get("dalle3_image_quality", "standard")}
-                submission = requests.post(url, headers=headers, json=body)
-                image_url = submission.json()['data'][0]['url']
-                return True, image_url
+                response = requests.post(url, headers=headers, json=body)
+                response.raise_for_status()  # 检查请求是否成功
+                data = response.json()
+
+                # 检查响应中是否包含图像 URL
+                if 'data' in data and len(data['data']) > 0 and 'url' in data['data'][0]:
+                    image_url = data['data'][0]['url']
+                    return True, image_url
+                else:
+                    error_message = "响应中没有图像 URL"
+                    logger.error(error_message)
+                    return False, "图片生成失败"
+
+            except requests.exceptions.RequestException as e:
+                # 捕获所有请求相关的异常
+                try:
+                    error_detail = response.json().get('error', {}).get('message', str(e))
+                except ValueError:
+                    error_detail = str(e)
+                error_message = f"{error_detail}"
+                logger.error(error_message)
+                return False, error_message
+
             except Exception as e:
-                logger.error("create image error: {}".format(e))
+                # 捕获所有其他异常
+                error_message = f"生成图像时发生错误: {e}"
+                logger.error(error_message)
                 return False, "图片生成失败"
         else:
             return False, "图片生成失败，未配置text_to_image参数"

bot/xunfei/xunfei_spark_bot.py

@@ -3,7 +3,7 @@
 import requests, json
 from bot.bot import Bot
 from bot.session_manager import SessionManager
-from bot.baidu.baidu_wenxin_session import BaiduWenxinSession
+from bot.chatgpt.chat_gpt_session import ChatGPTSession
 from bridge.context import ContextType, Context
 from bridge.reply import Reply, ReplyType
 from common.log import logger
@@ -41,18 +41,19 @@ class XunFeiBot(Bot):
         self.api_key = conf().get("xunfei_api_key")
         self.api_secret = conf().get("xunfei_api_secret")
         # 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"
+        # Spark Lite请求地址(spark_url): wss://spark-api.xf-yun.com/v1.1/chat, 对应的domain参数为: "general"
+        # Spark V2.0请求地址(spark_url): wss://spark-api.xf-yun.com/v2.1/chat, 对应的domain参数为: "generalv2"
+        # Spark Pro 请求地址(spark_url): wss://spark-api.xf-yun.com/v3.1/chat, 对应的domain参数为: "generalv3"
+        # Spark Pro-128K请求地址(spark_url):  wss://spark-api.xf-yun.com/chat/pro-128k, 对应的domain参数为: "pro-128k"
+        # Spark Max 请求地址(spark_url): wss://spark-api.xf-yun.com/v3.5/chat, 对应的domain参数为: "generalv3.5"
+        # Spark4.0 Ultra 请求地址(spark_url): wss://spark-api.xf-yun.com/v4.0/chat, 对应的domain参数为: "4.0Ultra"
+        # 后续模型更新，对应的参数可以参考官网文档获取：https://www.xfyun.cn/doc/spark/Web.html
+        self.domain = conf().get("xunfei_domain", "generalv3.5")
+        self.spark_url = conf().get("xunfei_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
-        self.sessions = SessionManager(BaiduWenxinSession, model=const.XUNFEI)
+        self.sessions = SessionManager(ChatGPTSession, model=const.XUNFEI)
 
     def reply(self, query, context: Context = None) -> Reply:
         if context.type == ContextType.TEXT:

channel/dingtalk/dingtalk_channel.py

@@ -100,7 +100,7 @@ class DingTalkChanel(ChatChannel, dingtalk_stream.ChatbotHandler):
         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(conf().get("expires_in_seconds"))
+        self.receivedMsgs = ExpiredDict(conf().get("expires_in_seconds", 3600))
         logger.info("[DingTalk] client_id={}, client_secret={} ".format(
             self.dingtalk_client_id, self.dingtalk_client_secret))
         # 无需群校验和前缀

channel/wechat/wechat_channel.py

@@ -9,7 +9,6 @@ import json
 import os
 import threading
 import time
-
 import requests
 
 from bridge.context import *
@@ -21,6 +20,7 @@ from common.expired_dict import ExpiredDict
 from common.log import logger
 from common.singleton import singleton
 from common.time_check import time_checker
+from common.utils import convert_webp_to_png
 from config import conf, get_appdata_dir
 from lib import itchat
 from lib.itchat.content import *
@@ -109,7 +109,7 @@ class WechatChannel(ChatChannel):
 
     def __init__(self):
         super().__init__()
-        self.receivedMsgs = ExpiredDict(conf().get("expires_in_seconds"))
+        self.receivedMsgs = ExpiredDict(conf().get("expires_in_seconds", 3600))
         self.auto_login_times = 0
 
     def startup(self):
@@ -202,7 +202,7 @@ class WechatChannel(ChatChannel):
             logger.debug(f"[WX]receive attachment msg, file_name={cmsg.content}")
         else:
             logger.debug("[WX]receive group msg: {}".format(cmsg.content))
-        context = self._compose_context(cmsg.ctype, cmsg.content, isgroup=True, msg=cmsg)
+        context = self._compose_context(cmsg.ctype, cmsg.content, isgroup=True, msg=cmsg, no_need_at=conf().get("no_need_at", False))
         if context:
             self.produce(context)
 
@@ -229,6 +229,12 @@ class WechatChannel(ChatChannel):
                 image_storage.write(block)
             logger.info(f"[WX] download image success, size={size}, img_url={img_url}")
             image_storage.seek(0)
+            if ".webp" in img_url:
+                try:
+                    image_storage = convert_webp_to_png(image_storage)
+                except Exception as e:
+                    logger.error(f"Failed to convert image: {e}")
+                    return
             itchat.send_image(image_storage, toUserName=receiver)
             logger.info("[WX] sendImage url={}, receiver={}".format(img_url, receiver))
         elif reply.type == ReplyType.IMAGE:  # 从文件读取图片
@@ -266,6 +272,7 @@ def _send_login_success():
     except Exception as e:
         pass
 
+
 def _send_logout():
     try:
         from common.linkai_client import chat_client
@@ -274,6 +281,7 @@ def _send_logout():
     except Exception as e:
         pass
 
+
 def _send_qr_code(qrcode_list: list):
     try:
         from common.linkai_client import chat_client
@@ -281,3 +289,4 @@ def _send_qr_code(qrcode_list: list):
             chat_client.send_qrcode(qrcode_list)
     except Exception as e:
         pass
+

channel/wechat/wechat_message.py

@@ -14,6 +14,11 @@ class WechatMessage(ChatMessage):
         self.create_time = itchat_msg["CreateTime"]
         self.is_group = is_group
 
+        notes_join_group = ["加入群聊", "加入了群聊", "invited", "joined"]  # 可通过添加对应语言的加入群聊通知中的关键词适配更多
+        notes_bot_join_group = ["邀请你", "invited you", "You've joined", "你通过扫描"]
+        notes_exit_group = ["移出了群聊", "removed"]  # 可通过添加对应语言的踢出群聊通知中的关键词适配更多
+        notes_patpat = ["拍了拍我", "tickled my", "tickled me"] # 可通过添加对应语言的拍一拍通知中的关键词适配更多
+
         if itchat_msg["Type"] == TEXT:
             self.ctype = ContextType.TEXT
             self.content = itchat_msg["Text"]
@@ -26,30 +31,42 @@ class WechatMessage(ChatMessage):
             self.content = TmpDir().path() + itchat_msg["FileName"]  # content直接存临时目录路径
             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"]):
+            if is_group:
+                if any(note_bot_join_group in itchat_msg["Content"] for note_bot_join_group in notes_bot_join_group):  # 邀请机器人加入群聊
+                    logger.warn("机器人加入群聊消息，不处理~")
+                    pass
+                elif any(note_join_group in itchat_msg["Content"] for note_join_group in notes_join_group): # 若有任何在notes_join_group列表中的字符串出现在NOTE中
                 # 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
+                    if "加入群聊" not in itchat_msg["Content"]:
+                        self.ctype = ContextType.JOIN_GROUP
+                        self.content = itchat_msg["Content"]
+                        if "invited" in itchat_msg["Content"]: # 匹配英文信息
+                            self.actual_user_nickname = re.findall(r'invited\s+(.+?)\s+to\s+the\s+group\s+chat', itchat_msg["Content"])[0]
+                        elif "joined" in itchat_msg["Content"]: # 匹配通过二维码加入的英文信息
+                            self.actual_user_nickname = re.findall(r'"(.*?)" joined the group chat via the QR Code shared by', itchat_msg["Content"])[0]
+                        elif "加入了群聊" in 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 any(note_exit_group in itchat_msg["Content"] for note_exit_group in notes_exit_group):  # 若有任何在notes_exit_group列表中的字符串出现在NOTE中
+                    self.ctype = ContextType.EXIT_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"]
-            elif "拍了拍我" in itchat_msg["Content"]:
+            elif any(note_patpat in itchat_msg["Content"] for note_patpat in notes_patpat):  # 若有任何在notes_patpat列表中的字符串出现在NOTE中:
                 self.ctype = ContextType.PATPAT
                 self.content = itchat_msg["Content"]
                 if is_group:
-                    self.actual_user_nickname = re.findall(r"\"(.*?)\"", itchat_msg["Content"])[0]
+                    if "拍了拍我" in itchat_msg["Content"]:  # 识别中文
+                        self.actual_user_nickname = re.findall(r"\"(.*?)\"", itchat_msg["Content"])[0]
+                    elif ("tickled my" in itchat_msg["Content"] or "tickled me" in itchat_msg["Content"]):
+                        self.actual_user_nickname = re.findall(r'^(.*?)(?:tickled my|tickled me)', itchat_msg["Content"])[0]
             else:
                 raise NotImplementedError("Unsupported note message: " + itchat_msg["Content"])
         elif itchat_msg["Type"] == ATTACHMENT:

channel/wechatcom/wechatcomapp_channel.py

@@ -17,7 +17,7 @@ from channel.wechatcom.wechatcomapp_client import WechatComAppClient
 from channel.wechatcom.wechatcomapp_message import WechatComAppMessage
 from common.log import logger
 from common.singleton import singleton
-from common.utils import compress_imgfile, fsize, split_string_by_utf8_length
+from common.utils import compress_imgfile, fsize, split_string_by_utf8_length, convert_webp_to_png
 from config import conf, subscribe_msg
 from voice.audio_convert import any_to_amr, split_audio
 
@@ -99,6 +99,12 @@ class WechatComAppChannel(ChatChannel):
                 image_storage = compress_imgfile(image_storage, 10 * 1024 * 1024 - 1)
                 logger.info("[wechatcom] image compressed, sz={}".format(fsize(image_storage)))
             image_storage.seek(0)
+            if ".webp" in img_url:
+                try:
+                    image_storage = convert_webp_to_png(image_storage)
+                except Exception as e:
+                    logger.error(f"Failed to convert image: {e}")
+                    return
             try:
                 response = self.client.media.upload("image", image_storage)
                 logger.debug("[wechatcom] upload image response: {}".format(response))
@@ -156,11 +162,12 @@ class Query:
         logger.debug("[wechatcom] receive message: {}, msg= {}".format(message, msg))
         if msg.type == "event":
             if msg.event == "subscribe":
-                reply_content = subscribe_msg()
-                if reply_content:
-                    reply = create_reply(reply_content, msg).render()
-                    res = channel.crypto.encrypt_message(reply, nonce, timestamp)
-                    return res
+                pass
+                # reply_content = subscribe_msg()
+                # if reply_content:
+                #     reply = create_reply(reply_content, msg).render()
+                #     res = channel.crypto.encrypt_message(reply, nonce, timestamp)
+                #     return res
         else:
             try:
                 wechatcom_msg = WechatComAppMessage(msg, client=channel.client)

common/utils.py

@@ -2,7 +2,7 @@ import io
 import os
 from urllib.parse import urlparse
 from PIL import Image
-
+from common.log import logger
 
 def fsize(file):
     if isinstance(file, io.BytesIO):
@@ -54,3 +54,17 @@ def split_string_by_utf8_length(string, max_length, max_split=0):
 def get_path_suffix(path):
     path = urlparse(path).path
     return os.path.splitext(path)[-1].lstrip('.')
+
+
+def convert_webp_to_png(webp_image):
+    from PIL import Image
+    try:
+        webp_image.seek(0)
+        img = Image.open(webp_image).convert("RGBA")
+        png_image = io.BytesIO()
+        img.save(png_image, format="PNG")
+        png_image.seek(0)
+        return png_image
+    except Exception as e:
+        logger.error(f"Failed to convert WEBP to PNG: {e}")
+        raise

config.py

@@ -27,6 +27,7 @@ available_setting = {
     "single_chat_reply_prefix": "[bot] ",  # 私聊时自动回复的前缀，用于区分真人
     "single_chat_reply_suffix": "",  # 私聊时自动回复的后缀，\n 可以换行
     "group_chat_prefix": ["@bot"],  # 群聊时包含该前缀则会触发机器人回复
+    "no_need_at": False,  # 群聊回复时是否不需要艾特
     "group_chat_reply_prefix": "",  # 群聊时自动回复的前缀
     "group_chat_reply_suffix": "",  # 群聊时自动回复的后缀，\n 可以换行
     "group_chat_keyword": [],  # 群聊时包含该关键词则会触发机器人回复
@@ -69,10 +70,13 @@ available_setting = {
     "baidu_wenxin_model": "eb-instant",  # 默认使用ERNIE-Bot-turbo模型
     "baidu_wenxin_api_key": "",  # Baidu api key
     "baidu_wenxin_secret_key": "",  # Baidu secret key
+    "baidu_wenxin_prompt_enabled": False,  # Enable prompt if you are using ernie character model
     # 讯飞星火API
     "xunfei_app_id": "",  # 讯飞应用ID
     "xunfei_api_key": "",  # 讯飞 API key
     "xunfei_api_secret": "",  # 讯飞 API secret
+    "xunfei_domain": "",  # 讯飞模型对应的domain参数，Spark4.0 Ultra为 4.0Ultra，其他模型详见: https://www.xfyun.cn/doc/spark/Web.html
+    "xunfei_spark_url": "",  # 讯飞模型对应的请求地址，Spark4.0 Ultra为 wss://spark-api.xf-yun.com/v4.0/chat，其他模型参考详见: https://www.xfyun.cn/doc/spark/Web.html
     # claude 配置
     "claude_api_cookie": "",
     "claude_uuid": "",

plugins/config.json.template

@@ -10,9 +10,7 @@
     },
     "tool": {
         "tools": [
-            "python",
             "url-get",
-            "terminal",
             "meteo-weather"
         ],
         "kwargs": {

plugins/keyword/keyword.py

@@ -55,7 +55,7 @@ class Keyword(Plugin):
             reply_text = self.keyword[content]
 
             # 判断匹配内容的类型
-            if (reply_text.startswith("http://") or reply_text.startswith("https://")) and any(reply_text.endswith(ext) for ext in [".jpg", ".jpeg", ".png", ".gif", ".img"]):
+            if (reply_text.startswith("http://") or reply_text.startswith("https://")) and any(reply_text.endswith(ext) for ext in [".jpg", ".webp", ".jpeg", ".png", ".gif", ".img"]):
             # 如果是以 http:// 或 https:// 开头，且".jpg", ".jpeg", ".png", ".gif", ".img"结尾，则认为是图片 URL。
                 reply = Reply()
                 reply.type = ReplyType.IMAGE_URL

plugins/role/role.py

@@ -99,7 +99,8 @@ class Role(Plugin):
         if e_context["context"].type != ContextType.TEXT:
             return
         btype = Bridge().get_bot_type("chat")
-        if btype not in [const.OPEN_AI, const.CHATGPT, const.CHATGPTONAZURE, const.LINKAI]:
+        if btype not in [const.OPEN_AI, const.CHATGPT, const.CHATGPTONAZURE, const.QWEN_DASHSCOPE, const.XUNFEI, const.BAIDU, const.ZHIPU_AI, const.MOONSHOT, const.MiniMax, const.LINKAI]:
+            logger.debug(f'不支持的bot: {btype}')
             return
         bot = Bridge().get_bot("chat")
         content = e_context["context"].content[:]

plugins/tool/config.json.template

@@ -1,8 +1,6 @@
 {
   "tools": [
-    "python",
     "url-get",
-    "terminal",
     "meteo"
   ],
   "kwargs": {

plugins/tool/tool.py

@@ -22,11 +22,13 @@ class Tool(Plugin):
     def __init__(self):
         super().__init__()
         self.handlers[Event.ON_HANDLE_CONTEXT] = self.on_handle_context
-
         self.app = self._reset_app()
-
+        if not self.tool_config.get("tools"):
+            logger.warn("[tool] init failed, ignore ")
+            raise Exception("config.json not found")
         logger.info("[tool] inited")
 
+
     def get_help_text(self, verbose=False, **kwargs):
         help_text = "这是一个能让chatgpt联网，搜索，数字运算的插件，将赋予强大且丰富的扩展能力。"
         trigger_prefix = conf().get("plugin_trigger_prefix", "$")

voice/azure/azure_voice.py

@@ -65,7 +65,7 @@ class AzureVoice(Voice):
             reply = Reply(ReplyType.TEXT, result.text)
         else:
             cancel_details = result.cancellation_details
-            logger.error("[Azure] voiceToText error, result={}, errordetails={}".format(result, cancel_details.error_details))
+            logger.error("[Azure] voiceToText error, result={}, errordetails={}".format(result, cancel_details))
             reply = Reply(ReplyType.ERROR, "抱歉，语音识别失败")
         return reply