docs: update readme

Ensure compatibility for /wxcomapp URL with trailing slash

README.md

@@ -5,7 +5,7 @@
 最新版本支持的功能如下：
 
 -  ✅   **多端部署：** 有多种部署方式可选择且功能完备，目前已支持微信公众号、企业微信应用、飞书、钉钉等部署方式
--  ✅   **基础对话：** 私聊及群聊的消息智能回复，支持多轮会话上下文记忆，支持 GPT-3.5, GPT-4, GPT-4o, Claude-3.5, Gemini, 文心一言, 讯飞星火, 通义千问，ChatGLM-4，Kimi(月之暗面), MiniMax
+-  ✅   **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-4o-mini, GPT-4o,  GPT-4, Claude-3.5, Gemini, 文心一言, 讯飞星火, 通义千问，ChatGLM-4，Kimi(月之暗面), MiniMax
 -  ✅   **语音能力：** 可识别语音消息，通过文字或语音回复，支持 azure, baidu, google, openai(whisper/tts) 等多种语音模型
 -  ✅   **图像能力：** 支持图片生成、图片识别、图生图（如照片修复），可选择 Dall-E-3, stable diffusion, replicate, midjourney, CogView-3, vision模型
 -  ✅   **丰富插件：** 支持个性化插件扩展，已实现多角色切换、文字冒险、敏感词过滤、聊天记录总结、文档总结和对话、联网搜索等插件
@@ -46,6 +46,8 @@ DEMO视频：https://cdn.link-ai.tech/doc/cow_demo.mp4
 
 # 🏷 更新日志
 
+>**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
 
 >**2024.06.04：** [1.6.6版本](https://github.com/zhayujie/chatgpt-on-wechat/releases/tag/1.6.6) 和 [1.6.5版本](https://github.com/zhayujie/chatgpt-on-wechat/releases/tag/1.6.5)，gpt-4o模型、钉钉流式卡片、讯飞语音识别/合成
@@ -173,7 +175,7 @@ pip3 install -r requirements-optional.txt
 
 **4.其他配置**
 
-+ `model`: 模型名称，目前支持 `gpt-3.5-turbo`, `gpt-4o`, `gpt-4-turbo`, `gpt-4`, `wenxin` , `claude` , `gemini`, `glm-4`,  `xunfei`, `moonshot`等，全部模型名称参考[common/const.py](https://github.com/zhayujie/chatgpt-on-wechat/blob/master/common/const.py)文件
++ `model`: 模型名称，目前支持 `gpt-3.5-turbo`, `gpt-4o-mini`, `gpt-4o`, `gpt-4`, `wenxin` , `claude` , `gemini`, `glm-4`,  `xunfei`, `moonshot`等，全部模型名称参考[common/const.py](https://github.com/zhayujie/chatgpt-on-wechat/blob/master/common/const.py)文件
 + `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 `

bot/chatgpt/chat_gpt_session.py

@@ -67,7 +67,7 @@ def num_tokens_from_messages(messages, model):
     elif model in ["gpt-4-0314", "gpt-4-0613", "gpt-4-32k", "gpt-4-32k-0613", "gpt-3.5-turbo-0613",
                    "gpt-3.5-turbo-16k", "gpt-3.5-turbo-16k-0613", "gpt-35-turbo-16k", "gpt-4-turbo-preview",
                    "gpt-4-1106-preview", const.GPT4_TURBO_PREVIEW, const.GPT4_VISION_PREVIEW, const.GPT4_TURBO_01_25,
-                   const.GPT_4o, const.LINKAI_4o, const.LINKAI_4_TURBO]:
+                   const.GPT_4o, const.GPT_4o_MINI, const.LINKAI_4o, const.LINKAI_4_TURBO]:
         return num_tokens_from_messages(messages, model="gpt-4")
     elif model.startswith("claude-3"):
         return num_tokens_from_messages(messages, model="gpt-3.5-turbo")

bot/linkai/link_ai_bot.py

@@ -399,6 +399,7 @@ class LinkAIBot(Bot):
             return
         max_send_num = conf().get("max_media_send_count")
         send_interval = conf().get("media_send_interval")
+        file_type = (".pdf", ".doc", ".docx", ".csv", ".xls", ".xlsx", ".txt", ".rtf", ".ppt", ".pptx")
         try:
             i = 0
             for url in image_urls:
@@ -407,7 +408,7 @@ class LinkAIBot(Bot):
                 i += 1
                 if url.endswith(".mp4"):
                     reply_type = ReplyType.VIDEO_URL
-                elif url.endswith(".pdf") or url.endswith(".doc") or url.endswith(".docx") or url.endswith(".csv"):
+                elif url.endswith(file_type):
                     reply_type = ReplyType.FILE
                     url = _download_file(url)
                     if not url:

channel/wechatcom/wechatcomapp_channel.py

@@ -44,7 +44,7 @@ class WechatComAppChannel(ChatChannel):
 
     def startup(self):
         # start message listener
-        urls = ("/wxcomapp", "channel.wechatcom.wechatcomapp_channel.Query")
+        urls = ("/wxcomapp/?", "channel.wechatcom.wechatcomapp_channel.Query")
         app = web.application(urls, globals(), autoreload=False)
         port = conf().get("wechatcomapp_port", 9898)
         web.httpserver.runsimple(app.wsgifunc(), ("0.0.0.0", port))

common/const.py

@@ -32,6 +32,7 @@ GPT4_TURBO_11_06 = "gpt-4-1106-preview"
 GPT4_VISION_PREVIEW = "gpt-4-vision-preview"
 
 GPT4 = "gpt-4"
+GPT_4o_MINI = "gpt-4o-mini"
 GPT4_32k = "gpt-4-32k"
 GPT4_06_13 = "gpt-4-0613"
 GPT4_32k_06_13 = "gpt-4-32k-0613"
@@ -57,7 +58,7 @@ GEMINI_15_PRO = "gemini-1.5-pro"
 
 MODEL_LIST = [
               GPT35, GPT35_0125, GPT35_1106, "gpt-3.5-turbo-16k",
-              GPT_4o, GPT4_TURBO, GPT4_TURBO_PREVIEW, GPT4_TURBO_01_25, GPT4_TURBO_11_06, GPT4, GPT4_32k, GPT4_06_13, GPT4_32k_06_13,
+              GPT_4o, GPT_4o_MINI, GPT4_TURBO, GPT4_TURBO_PREVIEW, GPT4_TURBO_01_25, GPT4_TURBO_11_06, GPT4, GPT4_32k, GPT4_06_13, GPT4_32k_06_13,
               WEN_XIN, WEN_XIN_4,
               XUNFEI, ZHIPU_AI, MOONSHOT, MiniMax,
               GEMINI, GEMINI_PRO, GEMINI_15_flash, GEMINI_15_PRO,

common/linkai_client.py

@@ -45,8 +45,11 @@ class ChatClient(LinkAIClient):
             elif reply_voice_mode == "always_reply_voice":
                 local_config["always_reply_voice"] = True
 
-        if config.get("admin_password") and plugin_config.get("Godcmd"):
-            plugin_config["Godcmd"]["password"] = config.get("admin_password")
+        if config.get("admin_password"):
+            if not plugin_config.get("Godcmd"):
+                plugin_config["Godcmd"] = {"password": config.get("admin_password"), "admin_users": []}
+            else:
+                plugin_config["Godcmd"]["password"] = config.get("admin_password")
             PluginManager().instances["GODCMD"].reload()
 
         if config.get("group_app_map") and pconf("linkai"):

config.py

@@ -17,7 +17,7 @@ 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",  # 可选择: gpt-4o, gpt-4-turbo, claude-3-sonnet, wenxin, moonshot, qwen-turbo, xunfei, glm-4, minimax, gemini等模型，全部可选模型详见common/const.py文件
+    "model": "gpt-3.5-turbo",  # 可选择: gpt-4o, pt-4o-mini, gpt-4-turbo, claude-3-sonnet, wenxin, moonshot, qwen-turbo, xunfei, glm-4, minimax, gemini等模型，全部可选模型详见common/const.py文件
     "bot_type": "",  # 可选配置，使用兼容openai格式的三方服务时候，需填"chatGPT"。bot具体名称详见common/const.py文件列出的bot_type，如不填根据model名称判断，
     "use_azure_chatgpt": False,  # 是否使用azure的chatgpt
     "azure_deployment_id": "",  # azure 模型部署名称
@@ -95,8 +95,8 @@ available_setting = {
     "group_speech_recognition": False,  # 是否开启群组语音识别
     "voice_reply_voice": False,  # 是否使用语音回复语音，需要设置对应语音合成引擎的api key
     "always_reply_voice": False,  # 是否一直使用语音回复
-    "voice_to_text": "openai",  # 语音识别引擎，支持openai,baidu,google,azure
-    "text_to_voice": "openai",  # 语音合成引擎，支持openai,baidu,google,pytts(offline),ali,azure,elevenlabs,edge(online)
+    "voice_to_text": "openai",  # 语音识别引擎，支持openai,baidu,google,azure,xunfei,ali
+    "text_to_voice": "openai",  # 语音合成引擎，支持openai,baidu,google,azure,xunfei,ali,pytts(offline),elevenlabs,edge(online)
     "text_to_voice_model": "tts-1",
     "tts_voice_id": "alloy",
     # baidu 语音api配置， 使用百度语音识别和语音合成时需要

plugins/plugin.py

@@ -18,6 +18,7 @@ class Plugin:
         if not plugin_conf:
             # 全局配置不存在，则获取插件目录下的配置
             plugin_config_path = os.path.join(self.path, "config.json")
+            logger.debug(f"loading plugin config, plugin_config_path={plugin_config_path}, exist={os.path.exists(plugin_config_path)}")
             if os.path.exists(plugin_config_path):
                 with open(plugin_config_path, "r", encoding="utf-8") as f:
                     plugin_conf = json.load(f)

plugins/source.json

@@ -22,7 +22,7 @@
     },
     "pictureChange": {
       "url": "https://github.com/Yanyutin753/pictureChange.git",
-      "desc": "利用stable-diffusion和百度Ai进行图生图或者画图的插件"
+      "desc": "1. 支持百度AI和Stable Diffusion WebUI进行图像处理，提供多种模型选择，支持图生图、文生图自定义模板。2. 支持Suno音乐AI可将图像和文字转为音乐。3. 支持自定义模型进行文件、图片总结功能。4. 支持管理员控制群聊内容与参数和功能改变。"
     },
     "Blackroom": {
       "url": "https://github.com/dividduang/blackroom.git",

voice/ali/ali_api.py

@@ -8,6 +8,7 @@ Description:
 
 """
 
+import http.client
 import json
 import time
 import requests
@@ -61,6 +62,69 @@ def text_to_speech_aliyun(url, text, appkey, token):
 
     return output_file
 
+def speech_to_text_aliyun(url, audioContent, appkey, token):
+    """
+    使用阿里云的语音识别服务识别音频文件中的语音。
+
+    参数:
+    - url (str): 阿里云语音识别服务的端点URL。
+    - audioContent (byte): pcm音频数据。
+    - appkey (str): 您的阿里云appkey。
+    - token (str): 阿里云API的认证令牌。
+
+    返回值:
+    - str: 成功时输出识别到的文本，否则为None。
+    """
+    format = 'pcm'
+    sample_rate = 16000
+    enablePunctuationPrediction  = True
+    enableInverseTextNormalization = True
+    enableVoiceDetection  = False
+
+    # 设置RESTful请求参数
+    request = url + '?appkey=' + appkey
+    request = request + '&format=' + format
+    request = request + '&sample_rate=' + str(sample_rate)
+
+    if enablePunctuationPrediction :
+        request = request + '&enable_punctuation_prediction=' + 'true'
+
+    if enableInverseTextNormalization :
+        request = request + '&enable_inverse_text_normalization=' + 'true'
+
+    if enableVoiceDetection :
+        request = request + '&enable_voice_detection=' + 'true'
+        
+    host = 'nls-gateway-cn-shanghai.aliyuncs.com'
+
+    # 设置HTTPS请求头部
+    httpHeaders = {
+        'X-NLS-Token': token,
+        'Content-type': 'application/octet-stream',
+        'Content-Length': len(audioContent)
+        }
+
+    conn = http.client.HTTPSConnection(host)
+    conn.request(method='POST', url=request, body=audioContent, headers=httpHeaders)
+
+    response = conn.getresponse()
+    body = response.read()
+    try:
+        body = json.loads(body)
+        status = body['status']
+        if status == 20000000 :
+            result = body['result']
+            if result :
+                logger.info(f"阿里云语音识别到了：{result}")
+            conn.close()
+            return result
+        else :
+            logger.error(f"语音识别失败，状态码: {status}")
+    except ValueError:
+        logger.error(f"语音识别失败，收到非JSON格式的数据: {body}")
+    conn.close()
+    return None
+
 
 class AliyunTokenGenerator:
     """

voice/ali/ali_voice.py

@@ -15,9 +15,9 @@ import time
 
 from bridge.reply import Reply, ReplyType
 from common.log import logger
+from voice.audio_convert import get_pcm_from_wav
 from voice.voice import Voice
-from voice.ali.ali_api import AliyunTokenGenerator
-from voice.ali.ali_api import text_to_speech_aliyun
+from voice.ali.ali_api import AliyunTokenGenerator, speech_to_text_aliyun, text_to_speech_aliyun
 from config import conf
 
 
@@ -34,7 +34,8 @@ class AliVoice(Voice):
             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.api_url_voice_to_text = config.get("api_url_voice_to_text")
+            self.api_url_text_to_voice = config.get("api_url_text_to_voice")
             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")
@@ -53,7 +54,7 @@ class AliVoice(Voice):
                       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)
+        fileName = text_to_speech_aliyun(self.api_url_text_to_voice, text, self.app_key, token_id)
         if fileName:
             logger.info("[Ali] textToVoice text={} voice file name={}".format(text, fileName))
             reply = Reply(ReplyType.VOICE, fileName)
@@ -61,6 +62,25 @@ class AliVoice(Voice):
             reply = Reply(ReplyType.ERROR, "抱歉，语音合成失败")
         return reply
 
+    def voiceToText(self, voice_file):
+        """
+        将语音文件转换为文本。
+
+        :param voice_file: 要转换的语音文件。
+        :return: 返回一个Reply对象，其中包含转换得到的文本或错误信息。
+        """
+        # 提取有效的token
+        token_id = self.get_valid_token()
+        logger.debug("[Ali] voice file name={}".format(voice_file))
+        pcm = get_pcm_from_wav(voice_file)
+        text = speech_to_text_aliyun(self.api_url_voice_to_text, pcm, self.app_key, token_id)
+        if text:
+            logger.info("[Ali] VoicetoText = {}".format(text))
+            reply = Reply(ReplyType.TEXT, text)
+        else:
+            reply = Reply(ReplyType.ERROR, "抱歉，语音识别失败")
+        return reply
+
     def get_valid_token(self):
         """
         获取有效的阿里云token。

voice/ali/config.json.template

@@ -1,5 +1,6 @@
 {
-    "api_url": "https://nls-gateway-cn-shanghai.aliyuncs.com/stream/v1/tts",
+    "api_url_text_to_voice": "https://nls-gateway-cn-shanghai.aliyuncs.com/stream/v1/tts",
+    "api_url_voice_to_text": "https://nls-gateway.cn-shanghai.aliyuncs.com/stream/v1/asr",
     "app_key": "",
     "access_key_id": "",
     "access_key_secret": ""