Merge pull request #549 from a5225662/master

明确config.py中config.json的查找目录为当前目录 #547

.github/ISSUE_TEMPLATE.md

@@ -1,6 +1,6 @@
 ### 前置确认
 
-1. 网络能够访问openai接口 [#351](https://github.com/zhayujie/chatgpt-on-wechat/issues/351)
+1. 网络能够访问openai接口
 2. python 已安装：版本在 3.7 ~ 3.10 之间，依赖已安装
 3. 在已有 issue 中未搜索到类似问题
 4. [FAQS](https://github.com/zhayujie/chatgpt-on-wechat/wiki/FAQs) 中无类似问题

.gitignore

@@ -1,5 +1,6 @@
 .DS_Store
 .idea
+.wechaty/
 __pycache__/
 venv*
 *.pyc

README.md

@@ -15,11 +15,11 @@
 
 # 更新日志
 
->**2023.03.09：** 基于 `whisper API` 实现对微信语音消息的解析和回复，添加配置项 `"speech_recognition":true` 即可启用。(contributed by [wanggang1987](https://github.com/wanggang1987) in [#385](https://github.com/zhayujie/chatgpt-on-wechat/pull/385))
+>**2023.03.09：** 基于 `whisper API` 实现对微信语音消息的解析和回复，添加配置项 `"speech_recognition":true` 即可启用，使用参考 [#415](https://github.com/zhayujie/chatgpt-on-wechat/issues/415)。(contributed by [wanggang1987](https://github.com/wanggang1987) in [#385](https://github.com/zhayujie/chatgpt-on-wechat/pull/385))
 
 >**2023.03.02：** 接入[ChatGPT API](https://platform.openai.com/docs/guides/chat) (gpt-3.5-turbo)，默认使用该模型进行对话，需升级openai依赖 (`pip3 install --upgrade openai`)。网络问题参考 [#351](https://github.com/zhayujie/chatgpt-on-wechat/issues/351)
 
->**2023.02.20：** 增加 [python-wechaty](https://github.com/wechaty/python-wechaty) 作为可选渠道，使用Pad协议相对稳定，但Token收费 (使用参考[#244](https://github.com/zhayujie/chatgpt-on-wechat/pull/244)，contributed by [ZQ7](https://github.com/ZQ7))
+>**2023.02.20：** 增加 [python-wechaty](https://github.com/wechaty/python-wechaty) 作为可选渠道，使用Pad协议，但Token收费 (使用参考[#244](https://github.com/zhayujie/chatgpt-on-wechat/pull/244)，contributed by [ZQ7](https://github.com/ZQ7))
 
 >**2023.02.09：** 扫码登录存在封号风险，请谨慎使用，参考[#58](https://github.com/AutumnWhj/ChatGPT-wechat-bot/issues/158)
 
@@ -62,15 +62,14 @@
 支持 Linux、MacOS、Windows 系统（可在Linux服务器上长期运行)，同时需安装 `Python`。 
 > 建议Python版本在 3.7.1~3.9.X 之间，3.10及以上版本在 MacOS 可用，其他系统上不确定能否正常运行。
 
-
-1.克隆项目代码：
+**(1) 克隆项目代码：**
 
 ```bash
 git clone https://github.com/zhayujie/chatgpt-on-wechat
 cd chatgpt-on-wechat/
 ```
 
-2.安装所需核心依赖：
+**(2) 安装核心依赖 (必选)：**
 
 ```bash
 pip3 install itchat-uos==1.5.0.dev0
@@ -78,13 +77,17 @@ pip3 install --upgrade openai
 ```
 注：`itchat-uos`使用指定版本1.5.0.dev0，`openai`使用最新版本，需高于0.27.0。
 
+**(3) 拓展依赖 (可选)：**
+
+语音识别及语音回复相关依赖：[#415](https://github.com/zhayujie/chatgpt-on-wechat/issues/415)。
+
 
 ## 配置
 
 配置文件的模板在根目录的`config-template.json`中，需复制该模板创建最终生效的 `config.json` 文件：
 
 ```bash
-cp config-template.json config.json
+  cp config-template.json config.json
 ```
 
 然后在`config.json`中填入配置，以下是对默认配置的说明，可根据需要进行自定义修改：
@@ -93,6 +96,7 @@ cp config-template.json config.json
 # config.json文件内容示例
 { 
   "open_ai_api_key": "YOUR API KEY",                          # 填入上面创建的 OpenAI API KEY
+  "model": "gpt-3.5-turbo",                                   # 模型名称
   "proxy": "127.0.0.1:7890",                                  # 代理客户端的ip和端口
   "single_chat_prefix": ["bot", "@bot"],                      # 私聊时文本需要包含该前缀才能触发机器人回复
   "single_chat_reply_prefix": "[bot] ",                       # 私聊时自动回复的前缀，用于区分真人
@@ -100,7 +104,8 @@ cp config-template.json config.json
   "group_name_white_list": ["ChatGPT测试群", "ChatGPT测试群2"], # 开启自动回复的群名称列表
   "image_create_prefix": ["画", "看", "找"],                   # 开启图片回复的前缀
   "conversation_max_tokens": 1000,                            # 支持上下文记忆的最多字符数
-  "character_desc": "你是ChatGPT, 一个由OpenAI训练的大型语言模型, 你旨在回答并解决人们的任何问题，并且可以使用多种语言与人交流。"  # 人格描述
+  "speech_recognition": false,                                # 是否开启语音识别
+  "character_desc": "你是ChatGPT, 一个由OpenAI训练的大型语言模型, 你旨在回答并解决人们的任何问题，并且可以使用多种语言与人交流。",  # 人格描述
 }
 ```
 **配置说明：**
@@ -117,15 +122,21 @@ cp config-template.json config.json
 + 可选配置: `group_name_keyword_white_list`配置项支持模糊匹配群名称，`group_chat_keyword`配置项则支持模糊匹配群消息内容，用法与上述两个配置项相同。（Contributed by [evolay](https://github.com/evolay))
 
 **3.语音识别**
+
 + 添加 `"speech_recognition": true` 将开启语音识别，默认使用openai的whisper模型识别为文字，同时以文字回复，目前只支持私聊 (注意由于语音消息无法匹配前缀，一旦开启将对所有语音自动回复)；
 + 添加 `"voice_reply_voice": true` 将开启语音回复语音，但是需要配置对应语音合成平台的key，由于itchat协议的限制，只能发送语音mp3文件，若使用wechaty则回复的是微信语音。
 
 **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`  (其中gpt-4 api暂未开放)
++ `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 `
 + 关于OpenAI对话及图片接口的参数配置（内容自由度、回复字数限制、图片大小等），可以参考 [对话接口](https://beta.openai.com/docs/api-reference/completions) 和 [图像接口](https://beta.openai.com/docs/api-reference/completions)  文档直接在 [代码](https://github.com/zhayujie/chatgpt-on-wechat/blob/master/bot/openai/open_ai_bot.py) `bot/openai/open_ai_bot.py` 中进行调整。
 + `conversation_max_tokens`：表示能够记忆的上下文最大字数（一问一答为一组对话，如果累积的对话字数超出限制，就会优先移除最早的一组对话）
++ `rate_limit_chatgpt`，`rate_limit_dalle`：每分钟最高问答速率、画图速率，超速后排队按序处理。
++ `clear_memory_commands`: 对话内指令，主动清空前文记忆，字符串数组可自定义指令别名。
++ `hot_reload`: 程序退出后，暂存微信扫码状态，默认关闭。
 + `character_desc` 配置中保存着你对机器人说的一段话，他会记住这段话并作为他的设定，你可以为他定制任何人格      (关于会话上下文的更多内容参考该 [issue](https://github.com/zhayujie/chatgpt-on-wechat/issues/43))
 
 
@@ -149,8 +160,7 @@ python3 app.py
 touch nohup.out                                   # 首次运行需要新建日志文件                     
 nohup python3 app.py & tail -f nohup.out          # 在后台运行程序并通过日志输出二维码
 ```
-扫码登录后程序即可运行于服务器后台，此时可通过 `ctrl+c` 关闭日志，不会影响后台程序的运行。使用 `ps -ef | grep app.py | grep -v grep` 命令可查看运行于后台的进程，如果想要重新启动程序可以先 `kill` 掉对应的进程。日志关闭后如果想要再次打开只需输入 `tail -f nohup.out`。
-scripts/目录有相应的脚本可以调用
+扫码登录后程序即可运行于服务器后台，此时可通过 `ctrl+c` 关闭日志，不会影响后台程序的运行。使用 `ps -ef | grep app.py | grep -v grep` 命令可查看运行于后台的进程，如果想要重新启动程序可以先 `kill` 掉对应的进程。日志关闭后如果想要再次打开只需输入 `tail -f nohup.out`。此外，`scripts` 目录下有一键运行、关闭程序的脚本供使用。
 
 > **注意：** 如果 扫码后手机提示登录验证需要等待5s，而终端的二维码再次刷新并提示 `Log in time out, reloading QR code`，此时需参考此 [issue](https://github.com/zhayujie/chatgpt-on-wechat/issues/8) 修改一行代码即可解决。
 

bot/bot_factory.py

@@ -1,6 +1,7 @@
 """
 channel factory
 """
+from common import const
 
 
 def create_bot(bot_type):
@@ -9,17 +10,17 @@ def create_bot(bot_type):
     :param channel_type: channel type code
     :return: channel instance
     """
-    if bot_type == 'baidu':
+    if bot_type == const.BAIDU:
         # Baidu Unit对话接口
         from bot.baidu.baidu_unit_bot import BaiduUnitBot
         return BaiduUnitBot()
 
-    elif bot_type == 'chatGPT':
+    elif bot_type == const.CHATGPT:
         # ChatGPT 网页端web接口
         from bot.chatgpt.chat_gpt_bot import ChatGPTBot
         return ChatGPTBot()
 
-    elif bot_type == 'openAI':
+    elif bot_type == const.OPEN_AI:
         # OpenAI 官方对话模型API
         from bot.openai.open_ai_bot import OpenAIBot
         return OpenAIBot()

bot/chatgpt/chat_gpt_bot.py

@@ -1,8 +1,9 @@
 # encoding:utf-8
 
 from bot.bot import Bot
-from config import conf
+from config import conf, load_config
 from common.log import logger
+from common.token_bucket import TokenBucket
 from common.expired_dict import ExpiredDict
 import openai
 import time
@@ -16,21 +17,31 @@ else:
 class ChatGPTBot(Bot):
     def __init__(self):
         openai.api_key = conf().get('open_ai_api_key')
+        if conf().get('open_ai_api_base'):
+            openai.api_base = conf().get('open_ai_api_base')
         proxy = conf().get('proxy')
         if proxy:
             openai.proxy = proxy
+        if conf().get('rate_limit_chatgpt'):
+            self.tb4chatgpt = TokenBucket(conf().get('rate_limit_chatgpt', 20))
+        if conf().get('rate_limit_dalle'):
+            self.tb4dalle = TokenBucket(conf().get('rate_limit_dalle', 50))
 
     def reply(self, query, context=None):
         # acquire reply content
         if not context or not context.get('type') or context.get('type') == 'TEXT':
             logger.info("[OPEN_AI] query={}".format(query))
-            session_id = context['session_id']
-            if query == '#清除记忆':
+            session_id = context.get('session_id') or context.get('from_user_id')
+            clear_memory_commands = conf().get('clear_memory_commands', ['#清除记忆'])
+            if query in clear_memory_commands:
                 Session.clear_session(session_id)
                 return '记忆已清除'
             elif query == '#清除所有':
                 Session.clear_all_session()
-                return '所有人记忆已清除'            
+                return '所有人记忆已清除'
+            elif query == '#更新配置':
+                load_config()
+                return '配置已更新'
 
             session = Session.build_session_query(query, session_id)
             logger.debug("[OPEN_AI] session query={}".format(session))
@@ -57,14 +68,16 @@ class ChatGPTBot(Bot):
         :return: {}
         '''
         try:
+            if conf().get('rate_limit_chatgpt') and not self.tb4chatgpt.get_token():
+                return {"completion_tokens": 0, "content": "提问太快啦，请休息一下再问我吧"}
             response = openai.ChatCompletion.create(
-                model="gpt-3.5-turbo",  # 对话模型的名称
+                model= conf().get("model") or "gpt-3.5-turbo",  # 对话模型的名称
                 messages=session,
-                temperature=0.9,  # 值在[0,1]之间，越大表示回复越具有不确定性
+                temperature=conf().get('temperature', 0.9),  # 值在[0,1]之间，越大表示回复越具有不确定性
                 #max_tokens=4096,  # 回复最大的字符数
                 top_p=1,
-                frequency_penalty=0.0,  # [-2,2]之间，该值越大则更倾向于产生不同的内容
-                presence_penalty=0.0,  # [-2,2]之间，该值越大则更倾向于产生不同的内容
+                frequency_penalty=conf().get('frequency_penalty', 0.0),  # [-2,2]之间，该值越大则更倾向于产生不同的内容
+                presence_penalty=conf().get('presence_penalty', 0.0),  # [-2,2]之间，该值越大则更倾向于产生不同的内容
             )
             # logger.info("[ChatGPT] reply={}, total_tokens={}".format(response.choices[0]['message']['content'], response["usage"]["total_tokens"]))
             return {"total_tokens": response["usage"]["total_tokens"], 
@@ -96,6 +109,8 @@ class ChatGPTBot(Bot):
 
     def create_img(self, query, retry_count=0):
         try:
+            if conf().get('rate_limit_dalle') and not self.tb4dalle.get_token():
+                return "请求太快了，请休息一下再问我吧"
             logger.info("[OPEN_AI] image_query={}".format(query))
             response = openai.Image.create(
                 prompt=query,    #图片描述
@@ -112,7 +127,7 @@ class ChatGPTBot(Bot):
                 logger.warn("[OPEN_AI] ImgCreate RateLimit exceed, 第{}次重试".format(retry_count+1))
                 return self.create_img(query, retry_count+1)
             else:
-                return "提问太快啦，请休息一下再问我吧"
+                return "请求太快啦，请休息一下再问我吧"
         except Exception as e:
             logger.exception(e)
             return None

bot/openai/open_ai_bot.py

@@ -12,13 +12,17 @@ user_session = dict()
 class OpenAIBot(Bot):
     def __init__(self):
         openai.api_key = conf().get('open_ai_api_key')
-
+        if conf().get('open_ai_api_base'):
+            openai.api_base = conf().get('open_ai_api_base')
+        proxy = conf().get('proxy')
+        if proxy:
+            openai.proxy = proxy
 
     def reply(self, query, context=None):
         # acquire reply content
         if not context or not context.get('type') or context.get('type') == 'TEXT':
             logger.info("[OPEN_AI] query={}".format(query))
-            from_user_id = context['from_user_id']
+            from_user_id = context.get('from_user_id') or context.get('session_id')
             if query == '#清除记忆':
                 Session.clear_session(from_user_id)
                 return '记忆已清除'
@@ -41,7 +45,7 @@ class OpenAIBot(Bot):
     def reply_text(self, query, user_id, retry_count=0):
         try:
             response = openai.Completion.create(
-                model="text-davinci-003",  # 对话模型的名称
+                model= conf().get("model") or "text-davinci-003",  # 对话模型的名称
                 prompt=query,
                 temperature=0.9,  # 值在[0,1]之间，越大表示回复越具有不确定性
                 max_tokens=1200,  # 回复最大的字符数
@@ -163,4 +167,4 @@ class Session(object):
 
     @staticmethod
     def clear_all_session():
-        user_session.clear()
+        user_session.clear()

bridge/bridge.py

@@ -1,5 +1,7 @@
 from bot import bot_factory
 from voice import voice_factory
+from config import conf
+from common import const
 
 
 class Bridge(object):
@@ -7,7 +9,13 @@ class Bridge(object):
         pass
 
     def fetch_reply_content(self, query, context):
-        return bot_factory.create_bot("chatGPT").reply(query, context)
+        bot_type = const.CHATGPT
+        model_type = conf().get("model")
+        if model_type in ["gpt-3.5-turbo", "gpt-4", "gpt-4-32k"]:
+            bot_type = const.CHATGPT
+        elif model_type in ["text-davinci-003"]:
+            bot_type = const.OPEN_AI
+        return bot_factory.create_bot(bot_type).reply(query, context)
 
     def fetch_voice_to_text(self, voiceFile):
         return voice_factory.create_voice("openai").voiceToText(voiceFile)

channel/channel_factory.py

@@ -14,4 +14,7 @@ def create_channel(channel_type):
     elif channel_type == 'wxy':
         from channel.wechat.wechaty_channel import WechatyChannel
         return WechatyChannel()
+    elif channel_type == 'terminal':
+        from channel.terminal.terminal_channel import TerminalChannel
+        return TerminalChannel()
     raise RuntimeError

channel/terminal/terminal_channel.py

@@ -0,0 +1,29 @@
+from channel.channel import Channel
+import sys
+
+class TerminalChannel(Channel):
+    def startup(self):
+        context = {"from_user_id": "User"}
+        print("\nPlease input your question")
+        while True:
+            try:
+                prompt = self.get_input("User:\n")
+            except KeyboardInterrupt:
+                print("\nExiting...")
+                sys.exit()
+
+            print("Bot:")
+            sys.stdout.flush()
+            for res in super().build_reply_content(prompt, context):
+                print(res, end="")
+                sys.stdout.flush()
+            print("\n")
+
+
+    def get_input(self, prompt):
+        """
+        Multi-line input function
+        """
+        print(prompt, end="")
+        line = input()
+        return line

channel/wechat/wechat_channel.py

@@ -14,6 +14,7 @@ from common.tmp_dir import TmpDir
 from config import conf
 import requests
 import io
+import time
 
 thread_pool = ThreadPoolExecutor(max_workers=8)
 
@@ -42,7 +43,7 @@ class WechatChannel(Channel):
 
     def startup(self):
         # login by scan QRCode
-        itchat.auto_login(enableCmdQR=2)
+        itchat.auto_login(enableCmdQR=2, hotReload=conf().get('hot_reload', False))
 
         # start message listener
         itchat.run()
@@ -74,7 +75,11 @@ class WechatChannel(Channel):
         from_user_id = msg['FromUserName']
         to_user_id = msg['ToUserName']              # 接收人id
         other_user_id = msg['User']['UserName']     # 对手方id
+        create_time = msg['CreateTime']             # 消息时间
         match_prefix = self.check_prefix(content, conf().get('single_chat_prefix'))
+        if conf().get('hot_reload') == True and int(create_time) < int(time.time()) - 60:    #跳过1分钟前的历史消息
+            logger.debug("[WX]history message skipped")
+            return
         if "」\n- - - - - - - - - - - - - - -" in content:
             logger.debug("[WX]reference query skipped")
             return
@@ -108,6 +113,10 @@ class WechatChannel(Channel):
         logger.debug("[WX]receive group msg: " + json.dumps(msg, ensure_ascii=False))
         group_name = msg['User'].get('NickName', None)
         group_id = msg['User'].get('UserName', None)
+        create_time = msg['CreateTime']             # 消息时间
+        if conf().get('hot_reload') == True and int(create_time) < int(time.time()) - 60:    #跳过1分钟前的历史消息
+            logger.debug("[WX]history group message skipped")
+            return
         if not group_name:
             return ""
         origin_content = msg['Content']

channel/wechat/wechaty_channel.py

@@ -10,12 +10,16 @@ import json
 import time
 import asyncio
 import requests
+import pysilk
+import wave
+from pydub import AudioSegment
 from typing import Optional, Union
 from wechaty_puppet import MessageType, FileBox, ScanStatus  # type: ignore
 from wechaty import Wechaty, Contact
 from wechaty.user import Message, Room, MiniProgram, UrlLink
 from channel.channel import Channel
 from common.log import logger
+from common.tmp_dir import TmpDir
 from config import conf
 
 
@@ -89,6 +93,48 @@ class WechatyChannel(Channel):
                     await self._do_send_img(content, to_user_id)
                 else:
                     await self._do_send(content, to_user_id)
+        elif room is None and msg.type() == MessageType.MESSAGE_TYPE_AUDIO:
+            if not msg.is_self(): # 接收语音消息
+                # 下载语音文件
+                voice_file = await msg.to_file_box()
+                silk_file = TmpDir().path() + voice_file.name
+                await voice_file.to_file(silk_file)
+                logger.info("[WX]receive voice file: " + silk_file)
+                # 将文件转成wav格式音频
+                wav_file = silk_file.replace(".slk", ".wav")
+                with open(silk_file, 'rb') as f:
+                    silk_data = f.read()
+                pcm_data = pysilk.decode(silk_data)
+
+                with wave.open(wav_file, 'wb') as wav_data:
+                    wav_data.setnchannels(1)
+                    wav_data.setsampwidth(2)
+                    wav_data.setframerate(24000)
+                    wav_data.writeframes(pcm_data)
+                if os.path.exists(wav_file): 
+                    converter_state = "true" # 转换wav成功
+                else:
+                    converter_state = "false" # 转换wav失败
+                logger.info("[WX]receive voice converter: " + converter_state)
+                # 语音识别为文本
+                query = super().build_voice_to_text(wav_file)
+                # 交验关键字
+                match_prefix = self.check_prefix(query, conf().get('single_chat_prefix'))
+                if match_prefix is not None:
+                    if match_prefix != '':
+                        str_list = query.split(match_prefix, 1)
+                        if len(str_list) == 2:
+                            query = str_list[1].strip()
+                    # 返回消息
+                    if conf().get('voice_reply_voice'):
+                        await self._do_send_voice(query, from_user_id)
+                    else:
+                        await self._do_send(query, from_user_id)
+                else:
+                    logger.info("[WX]receive voice check prefix: " + 'False')
+                # 清除缓存文件
+                os.remove(wav_file)
+                os.remove(silk_file)
         elif room and msg.type() == MessageType.MESSAGE_TYPE_TEXT:
             # 群组&文本消息
             room_id = room.room_id
@@ -101,6 +147,13 @@ class WechatyChannel(Channel):
             match_prefix = (is_at and not config.get("group_at_off", False)) \
                            or self.check_prefix(content, config.get('group_chat_prefix')) \
                            or self.check_contain(content, config.get('group_chat_keyword'))
+            # Wechaty判断is_at为True，返回的内容是过滤掉@之后的内容；而is_at为False，则会返回完整的内容
+            # 故判断如果匹配到自定义前缀，则返回过滤掉前缀+空格后的内容，用于实现类似自定义+前缀触发生成AI图片的功能
+            prefixes = config.get('group_chat_prefix')
+            for prefix in prefixes:
+                if content.startswith(prefix):
+                    content = content.replace(prefix, '', 1).strip()
+                    break
             if ('ALL_GROUP' in config.get('group_name_white_list') or room_name in config.get(
                     'group_name_white_list') or self.check_contain(room_name, config.get(
                 'group_name_keyword_white_list'))) and match_prefix:
@@ -135,6 +188,39 @@ class WechatyChannel(Channel):
         except Exception as e:
             logger.exception(e)
 
+
+    async def _do_send_voice(self, query, reply_user_id):
+        try:
+            if not query:
+                return
+            context = dict()
+            context['session_id'] = reply_user_id
+            reply_text = super().build_reply_content(query, context)
+            if reply_text:
+                # 转换 mp3 文件为 silk 格式
+                mp3_file = super().build_text_to_voice(reply_text)
+                silk_file = mp3_file.replace(".mp3", ".silk")
+                # Load the MP3 file
+                audio = AudioSegment.from_file(mp3_file, format="mp3")
+                # Convert to WAV format
+                audio = audio.set_frame_rate(24000).set_channels(1)
+                wav_data = audio.raw_data
+                sample_width = audio.sample_width
+                # Encode to SILK format
+                silk_data = pysilk.encode(wav_data, 24000)
+                # Save the silk file
+                with open(silk_file, "wb") as f:
+                    f.write(silk_data)
+                # 发送语音
+                t = int(time.time())
+                file_box = FileBox.from_file(silk_file, name=str(t) + '.silk')
+                await self.send(file_box, reply_user_id)
+                # 清除缓存文件
+                os.remove(mp3_file)
+                os.remove(silk_file)
+        except Exception as e:
+            logger.exception(e)
+            
     async def _do_send_img(self, query, reply_user_id):
         try:
             if not query:

common/const.py

@@ -0,0 +1,4 @@
+# bot_type
+OPEN_AI = "openAI"
+CHATGPT = "chatGPT"
+BAIDU = "baidu"

common/token_bucket.py

@@ -0,0 +1,45 @@
+import threading
+import time
+
+
+class TokenBucket:
+    def __init__(self, tpm, timeout=None):
+        self.capacity = int(tpm)  # 令牌桶容量
+        self.tokens = 0  # 初始令牌数为0
+        self.rate = int(tpm) / 60  # 令牌每秒生成速率
+        self.timeout = timeout  # 等待令牌超时时间
+        self.cond = threading.Condition()  # 条件变量
+        self.is_running = True
+        # 开启令牌生成线程
+        threading.Thread(target=self._generate_tokens).start()
+
+    def _generate_tokens(self):
+        """生成令牌"""
+        while self.is_running:
+            with self.cond:
+                if self.tokens < self.capacity:
+                    self.tokens += 1
+                self.cond.notify()  # 通知获取令牌的线程
+            time.sleep(1 / self.rate)
+
+    def get_token(self):
+        """获取令牌"""
+        with self.cond:
+            while self.tokens <= 0:
+                flag = self.cond.wait(self.timeout)
+                if not flag:  # 超时
+                    return False
+            self.tokens -= 1
+        return True
+
+    def close(self):
+        self.is_running = False
+
+
+if __name__ == "__main__":
+    token_bucket = TokenBucket(20, None)  # 创建一个每分钟生产20个tokens的令牌桶
+    # token_bucket = TokenBucket(20, 0.1)
+    for i in range(3):
+        if token_bucket.get_token():
+            print(f"第{i+1}次请求成功")
+    token_bucket.close()

config-template.json

@@ -1,14 +1,16 @@
-{
-  "open_ai_api_key": "YOUR API KEY",
-  "proxy": "",
-  "single_chat_prefix": ["bot", "@bot"],
-  "single_chat_reply_prefix": "[bot] ",
-  "group_chat_prefix": ["@bot"],
-  "group_chat_in_one_session": ["ChatGPT测试群"],
-  "group_name_white_list": ["ChatGPT测试群", "ChatGPT测试群2"],
-  "image_create_prefix": ["画", "看", "找"],
-  "conversation_max_tokens": 1000,
-  "speech_recognition": false,
-  "character_desc": "你是ChatGPT, 一个由OpenAI训练的大型语言模型, 你旨在回答并解决人们的任何问题，并且可以使用多种语言与人交流。",
-  "expires_in_seconds": 3600
-}
+ {
+   "open_ai_api_key": "YOUR API KEY",
+   "model": "gpt-3.5-turbo",
+   "proxy": "",
+   "single_chat_prefix": ["bot", "@bot"],
+   "single_chat_reply_prefix": "[bot] ",
+   "group_chat_prefix": ["@bot"],
+   "group_name_white_list": ["ChatGPT测试群", "ChatGPT测试群2"],
+   "image_create_prefix": ["画", "看", "找"],
+   "speech_recognition": false,
+   "voice_reply_voice": false,
+   "conversation_max_tokens": 1000,
+   "expires_in_seconds": 3600,
+   "character_desc": "你是ChatGPT, 一个由OpenAI训练的大型语言模型, 你旨在回答并解决人们的任何问题，并且可以使用多种语言与人交流。"
+ }
+

config.py

@@ -9,7 +9,7 @@ config = {}
 
 def load_config():
     global config
-    config_path = "config.json"
+    config_path = "./config.json"
     if not os.path.exists(config_path):
         raise Exception('配置文件不存在，请根据config-template.json模板创建config.json文件')
 

docker/build.alpine.sh

@@ -11,5 +11,6 @@ docker build -f Dockerfile.alpine \
              -t zhayujie/chatgpt-on-wechat .
 
 # tag image
-docker tag zhayujie/chatgpt-on-wechat zhayujie/chatgpt-on-wechat:$CHATGPT_ON_WECHAT_TAG-alpine 
+docker tag zhayujie/chatgpt-on-wechat zhayujie/chatgpt-on-wechat:alpine 
+docker tag zhayujie/chatgpt-on-wechat zhayujie/chatgpt-on-wechat:$CHATGPT_ON_WECHAT_TAG-alpine
            

docker/build.debian.sh

@@ -11,4 +11,5 @@ docker build -f Dockerfile.debian \
              -t zhayujie/chatgpt-on-wechat .
 
 # tag image
+docker tag zhayujie/chatgpt-on-wechat zhayujie/chatgpt-on-wechat:debian 
 docker tag zhayujie/chatgpt-on-wechat zhayujie/chatgpt-on-wechat:$CHATGPT_ON_WECHAT_TAG-debian

docker/chatgpt-on-wechat-voice-reply/Dockerfile.alpine

@@ -0,0 +1,23 @@
+FROM zhayujie/chatgpt-on-wechat:alpine
+
+LABEL maintainer="foo@bar.com"
+ARG TZ='Asia/Shanghai'
+
+USER root
+
+RUN apk add --no-cache \
+        ffmpeg  \
+        espeak \
+    && pip install --no-cache \
+        baidu-aip \ 
+        chardet \
+        SpeechRecognition
+
+# replace entrypoint
+ADD ./entrypoint.sh /entrypoint.sh
+
+RUN chmod +x /entrypoint.sh
+
+USER noroot
+
+ENTRYPOINT ["/entrypoint.sh"]

docker/chatgpt-on-wechat-voice-reply/Dockerfile.debian

@@ -0,0 +1,24 @@
+FROM zhayujie/chatgpt-on-wechat:debian
+
+LABEL maintainer="foo@bar.com"
+ARG TZ='Asia/Shanghai'
+
+USER root
+
+RUN apt-get update  \
+    && apt-get install -y --no-install-recommends \
+        ffmpeg \
+        espeak  \
+    && pip install --no-cache \
+        baidu-aip \ 
+        chardet \
+        SpeechRecognition
+
+# replace entrypoint
+ADD ./entrypoint.sh /entrypoint.sh
+
+RUN chmod +x /entrypoint.sh
+
+USER noroot
+
+ENTRYPOINT ["/entrypoint.sh"]

docker/chatgpt-on-wechat-voice-reply/docker-compose.yaml

@@ -0,0 +1,24 @@
+version: '2.0'
+services:
+  chatgpt-on-wechat:
+    build:
+      context: ./
+      dockerfile: Dockerfile.alpine
+    image: zhayujie/chatgpt-on-wechat-voice-reply
+    container_name: chatgpt-on-wechat-voice-reply
+    environment:
+      OPEN_AI_API_KEY: 'YOUR API KEY'
+      OPEN_AI_PROXY: ''
+      SINGLE_CHAT_PREFIX: '["bot", "@bot"]'
+      SINGLE_CHAT_REPLY_PREFIX: '"[bot] "'
+      GROUP_CHAT_PREFIX: '["@bot"]'
+      GROUP_NAME_WHITE_LIST: '["ChatGPT测试群", "ChatGPT测试群2"]'
+      IMAGE_CREATE_PREFIX: '["画", "看", "找"]'
+      CONVERSATION_MAX_TOKENS: 1000
+      SPEECH_RECOGNITION: 'true'
+      CHARACTER_DESC: '你是ChatGPT, 一个由OpenAI训练的大型语言模型, 你旨在回答并解决人们的任何问题，并且可以使用多种语言与人交流。'
+      EXPIRES_IN_SECONDS: 3600
+      VOICE_REPLY_VOICE: 'true'
+      BAIDU_APP_ID: 'YOUR BAIDU APP ID'
+      BAIDU_API_KEY: 'YOUR BAIDU API KEY'
+      BAIDU_SECRET_KEY: 'YOUR BAIDU SERVICE KEY'

docker/chatgpt-on-wechat-voice-reply/entrypoint.sh

@@ -0,0 +1,117 @@
+#!/bin/bash
+set -e
+
+# build prefix
+CHATGPT_ON_WECHAT_PREFIX=${CHATGPT_ON_WECHAT_PREFIX:-""}
+# path to config.json
+CHATGPT_ON_WECHAT_CONFIG_PATH=${CHATGPT_ON_WECHAT_CONFIG_PATH:-""}
+# execution command line
+CHATGPT_ON_WECHAT_EXEC=${CHATGPT_ON_WECHAT_EXEC:-""}
+
+OPEN_AI_API_KEY=${OPEN_AI_API_KEY:-""}
+OPEN_AI_PROXY=${OPEN_AI_PROXY:-""}
+SINGLE_CHAT_PREFIX=${SINGLE_CHAT_PREFIX:-""}
+SINGLE_CHAT_REPLY_PREFIX=${SINGLE_CHAT_REPLY_PREFIX:-""}
+GROUP_CHAT_PREFIX=${GROUP_CHAT_PREFIX:-""}
+GROUP_NAME_WHITE_LIST=${GROUP_NAME_WHITE_LIST:-""}
+IMAGE_CREATE_PREFIX=${IMAGE_CREATE_PREFIX:-""}
+CONVERSATION_MAX_TOKENS=${CONVERSATION_MAX_TOKENS:-""}
+SPEECH_RECOGNITION=${SPEECH_RECOGNITION:-""}
+CHARACTER_DESC=${CHARACTER_DESC:-""}
+EXPIRES_IN_SECONDS=${EXPIRES_IN_SECONDS:-""}
+
+VOICE_REPLY_VOICE=${VOICE_REPLY_VOICE:-""}
+BAIDU_APP_ID=${BAIDU_APP_ID:-""}
+BAIDU_API_KEY=${BAIDU_API_KEY:-""}
+BAIDU_SECRET_KEY=${BAIDU_SECRET_KEY:-""}
+
+# CHATGPT_ON_WECHAT_PREFIX is empty, use /app
+if [ "$CHATGPT_ON_WECHAT_PREFIX" == "" ] ; then
+    CHATGPT_ON_WECHAT_PREFIX=/app
+fi
+
+# CHATGPT_ON_WECHAT_CONFIG_PATH is empty, use '/app/config.json'
+if [ "$CHATGPT_ON_WECHAT_CONFIG_PATH" == "" ] ; then
+    CHATGPT_ON_WECHAT_CONFIG_PATH=$CHATGPT_ON_WECHAT_PREFIX/config.json
+fi
+
+# CHATGPT_ON_WECHAT_EXEC is empty, use ‘python app.py’
+if [ "$CHATGPT_ON_WECHAT_EXEC" == "" ] ; then
+    CHATGPT_ON_WECHAT_EXEC="python app.py"
+fi
+
+# modify content in config.json
+if [ "$OPEN_AI_API_KEY" != "" ] ; then
+    sed -i "s/\"open_ai_api_key\".*,$/\"open_ai_api_key\": \"$OPEN_AI_API_KEY\",/" $CHATGPT_ON_WECHAT_CONFIG_PATH
+else
+    echo -e "\033[31m[Warning] You need to set OPEN_AI_API_KEY before running!\033[0m"
+fi
+
+# use http_proxy as default
+if [ "$HTTP_PROXY" != "" ] ; then
+    sed -i "s/\"proxy\".*,$/\"proxy\": \"$HTTP_PROXY\",/" $CHATGPT_ON_WECHAT_CONFIG_PATH
+fi
+
+if [ "$OPEN_AI_PROXY" != "" ] ; then
+    sed -i "s/\"proxy\".*,$/\"proxy\": \"$OPEN_AI_PROXY\",/" $CHATGPT_ON_WECHAT_CONFIG_PATH
+fi
+
+if [ "$SINGLE_CHAT_PREFIX" != "" ] ; then
+    sed -i "s/\"single_chat_prefix\".*,$/\"single_chat_prefix\": $SINGLE_CHAT_PREFIX,/" $CHATGPT_ON_WECHAT_CONFIG_PATH
+fi
+
+if [ "$SINGLE_CHAT_REPLY_PREFIX" != "" ] ; then
+    sed -i "s/\"single_chat_reply_prefix\".*,$/\"single_chat_reply_prefix\": $SINGLE_CHAT_REPLY_PREFIX,/" $CHATGPT_ON_WECHAT_CONFIG_PATH
+fi
+
+if [ "$GROUP_CHAT_PREFIX" != "" ] ; then
+    sed -i "s/\"group_chat_prefix\".*,$/\"group_chat_prefix\": $GROUP_CHAT_PREFIX,/" $CHATGPT_ON_WECHAT_CONFIG_PATH
+fi
+
+if [ "$GROUP_NAME_WHITE_LIST" != "" ] ; then
+    sed -i "s/\"group_name_white_list\".*,$/\"group_name_white_list\": $GROUP_NAME_WHITE_LIST,/" $CHATGPT_ON_WECHAT_CONFIG_PATH
+fi
+
+if [ "$IMAGE_CREATE_PREFIX" != "" ] ; then
+    sed -i "s/\"image_create_prefix\".*,$/\"image_create_prefix\": $IMAGE_CREATE_PREFIX,/" $CHATGPT_ON_WECHAT_CONFIG_PATH
+fi
+
+if [ "$CONVERSATION_MAX_TOKENS" != "" ] ; then
+    sed -i "s/\"conversation_max_tokens\".*,$/\"conversation_max_tokens\": $CONVERSATION_MAX_TOKENS,/" $CHATGPT_ON_WECHAT_CONFIG_PATH
+fi
+
+if [ "$SPEECH_RECOGNITION" != "" ] ; then
+    sed -i "s/\"speech_recognition\".*,$/\"speech_recognition\": $SPEECH_RECOGNITION,/" $CHATGPT_ON_WECHAT_CONFIG_PATH
+fi
+
+if [ "$CHARACTER_DESC" != "" ] ; then
+    sed -i "s/\"character_desc\".*,$/\"character_desc\": \"$CHARACTER_DESC\",/" $CHATGPT_ON_WECHAT_CONFIG_PATH
+fi
+
+if [ "$EXPIRES_IN_SECONDS" != "" ] ; then
+    sed -i "s/\"expires_in_seconds\".*$/\"expires_in_seconds\": $EXPIRES_IN_SECONDS/" $CHATGPT_ON_WECHAT_CONFIG_PATH
+fi
+
+# append
+if [ "$BAIDU_SECRET_KEY" != "" ] ; then
+    sed -i "1a \ \ \"baidu_secret_key\": \"$BAIDU_SECRET_KEY\"," $CHATGPT_ON_WECHAT_CONFIG_PATH
+fi
+
+if [ "$BAIDU_API_KEY" != "" ] ; then
+    sed -i "1a \ \ \"baidu_api_key\": \"$BAIDU_API_KEY\"," $CHATGPT_ON_WECHAT_CONFIG_PATH
+fi
+
+if [ "$BAIDU_APP_ID" != "" ] ; then
+    sed -i "1a \ \ \"baidu_app_id\": \"$BAIDU_APP_ID\"," $CHATGPT_ON_WECHAT_CONFIG_PATH
+fi
+
+if [ "$VOICE_REPLY_VOICE" != "" ] ; then
+    sed -i "1a \ \ \"voice_reply_voice\": $VOICE_REPLY_VOICE," $CHATGPT_ON_WECHAT_CONFIG_PATH
+fi
+
+# go to prefix dir
+cd $CHATGPT_ON_WECHAT_PREFIX
+# excute
+$CHATGPT_ON_WECHAT_EXEC
+
+

docker/docker-compose.yaml

@@ -15,5 +15,6 @@ services:
       GROUP_NAME_WHITE_LIST: '["ChatGPT测试群", "ChatGPT测试群2"]'
       IMAGE_CREATE_PREFIX: '["画", "看", "找"]'
       CONVERSATION_MAX_TOKENS: 1000
+      SPEECH_RECOGNITION: 'false'
       CHARACTER_DESC: '你是ChatGPT, 一个由OpenAI训练的大型语言模型, 你旨在回答并解决人们的任何问题，并且可以使用多种语言与人交流。'
       EXPIRES_IN_SECONDS: 3600

docker/entrypoint.sh

@@ -16,6 +16,7 @@ GROUP_CHAT_PREFIX=${GROUP_CHAT_PREFIX:-""}
 GROUP_NAME_WHITE_LIST=${GROUP_NAME_WHITE_LIST:-""}
 IMAGE_CREATE_PREFIX=${IMAGE_CREATE_PREFIX:-""}
 CONVERSATION_MAX_TOKENS=${CONVERSATION_MAX_TOKENS:-""}
+SPEECH_RECOGNITION=${SPEECH_RECOGNITION:-""}
 CHARACTER_DESC=${CHARACTER_DESC:-""}
 EXPIRES_IN_SECONDS=${EXPIRES_IN_SECONDS:-""}
 
@@ -36,50 +37,54 @@ fi
 
 # modify content in config.json
 if [ "$OPEN_AI_API_KEY" != "" ] ; then
-    sed -i "2c   \"open_ai_api_key\": \"$OPEN_AI_API_KEY\"," $CHATGPT_ON_WECHAT_CONFIG_PATH
+    sed -i "s/\"open_ai_api_key\".*,$/\"open_ai_api_key\": \"$OPEN_AI_API_KEY\",/" $CHATGPT_ON_WECHAT_CONFIG_PATH
 else
     echo -e "\033[31m[Warning] You need to set OPEN_AI_API_KEY before running!\033[0m"
 fi
 
 # use http_proxy as default
 if [ "$HTTP_PROXY" != "" ] ; then
-    sed -i "3c   \"proxy\": \"$HTTP_PROXY\"," $CHATGPT_ON_WECHAT_CONFIG_PATH
+    sed -i "s/\"proxy\".*,$/\"proxy\": \"$HTTP_PROXY\",/" $CHATGPT_ON_WECHAT_CONFIG_PATH
 fi
 
 if [ "$OPEN_AI_PROXY" != "" ] ; then
-    sed -i "3c   \"proxy\": \"$OPEN_AI_PROXY\"," $CHATGPT_ON_WECHAT_CONFIG_PATH
+    sed -i "s/\"proxy\".*,$/\"proxy\": \"$OPEN_AI_PROXY\",/" $CHATGPT_ON_WECHAT_CONFIG_PATH
 fi
 
 if [ "$SINGLE_CHAT_PREFIX" != "" ] ; then
-    sed -i "4c   \"single_chat_prefix\": $SINGLE_CHAT_PREFIX," $CHATGPT_ON_WECHAT_CONFIG_PATH
+    sed -i "s/\"single_chat_prefix\".*,$/\"single_chat_prefix\": $SINGLE_CHAT_PREFIX,/" $CHATGPT_ON_WECHAT_CONFIG_PATH
 fi
 
 if [ "$SINGLE_CHAT_REPLY_PREFIX" != "" ] ; then
-    sed -i "5c   \"single_chat_reply_prefix\": $SINGLE_CHAT_REPLY_PREFIX," $CHATGPT_ON_WECHAT_CONFIG_PATH
+    sed -i "s/\"single_chat_reply_prefix\".*,$/\"single_chat_reply_prefix\": $SINGLE_CHAT_REPLY_PREFIX,/" $CHATGPT_ON_WECHAT_CONFIG_PATH
 fi
 
 if [ "$GROUP_CHAT_PREFIX" != "" ] ; then
-    sed -i "6c   \"group_chat_prefix\": $GROUP_CHAT_PREFIX," $CHATGPT_ON_WECHAT_CONFIG_PATH
+    sed -i "s/\"group_chat_prefix\".*,$/\"group_chat_prefix\": $GROUP_CHAT_PREFIX,/" $CHATGPT_ON_WECHAT_CONFIG_PATH
 fi
 
 if [ "$GROUP_NAME_WHITE_LIST" != "" ] ; then
-    sed -i "7c   \"group_name_white_list\": $GROUP_NAME_WHITE_LIST," $CHATGPT_ON_WECHAT_CONFIG_PATH
+    sed -i "s/\"group_name_white_list\".*,$/\"group_name_white_list\": $GROUP_NAME_WHITE_LIST,/" $CHATGPT_ON_WECHAT_CONFIG_PATH
 fi
 
 if [ "$IMAGE_CREATE_PREFIX" != "" ] ; then
-    sed -i "8c   \"image_create_prefix\": $IMAGE_CREATE_PREFIX," $CHATGPT_ON_WECHAT_CONFIG_PATH
+    sed -i "s/\"image_create_prefix\".*,$/\"image_create_prefix\": $IMAGE_CREATE_PREFIX,/" $CHATGPT_ON_WECHAT_CONFIG_PATH
 fi
 
 if [ "$CONVERSATION_MAX_TOKENS" != "" ] ; then
-    sed -i "9c   \"conversation_max_tokens\": $CONVERSATION_MAX_TOKENS," $CHATGPT_ON_WECHAT_CONFIG_PATH
+    sed -i "s/\"conversation_max_tokens\".*,$/\"conversation_max_tokens\": $CONVERSATION_MAX_TOKENS,/" $CHATGPT_ON_WECHAT_CONFIG_PATH
+fi
+
+if [ "$SPEECH_RECOGNITION" != "" ] ; then
+    sed -i "s/\"speech_recognition\".*,$/\"speech_recognition\": $SPEECH_RECOGNITION,/" $CHATGPT_ON_WECHAT_CONFIG_PATH
 fi
 
 if [ "$CHARACTER_DESC" != "" ] ; then
-    sed -i "10c   \"character_desc\": \"$CHARACTER_DESC\"," $CHATGPT_ON_WECHAT_CONFIG_PATH
+    sed -i "s/\"character_desc\".*,$/\"character_desc\": \"$CHARACTER_DESC\",/" $CHATGPT_ON_WECHAT_CONFIG_PATH
 fi
 
 if [ "$EXPIRES_IN_SECONDS" != "" ] ; then
-    sed -i "11c   \"expires_in_seconds\": $EXPIRES_IN_SECONDS" $CHATGPT_ON_WECHAT_CONFIG_PATH
+    sed -i "s/\"expires_in_seconds\".*$/\"expires_in_seconds\": $EXPIRES_IN_SECONDS/" $CHATGPT_ON_WECHAT_CONFIG_PATH
 fi
 
 # go to prefix dir

docker/sample-chatgpt-on-wechat/.env

@@ -6,6 +6,7 @@ GROUP_CHAT_PREFIX=["@bot"]
 GROUP_NAME_WHITE_LIST=["ChatGPT测试群", "ChatGPT测试群2"]
 IMAGE_CREATE_PREFIX=["画", "看", "找"]
 CONVERSATION_MAX_TOKENS=1000
+SPEECH_RECOGNITION=false
 CHARACTER_DESC=你是ChatGPT, 一个由OpenAI训练的大型语言模型, 你旨在回答并解决人们的任何问题，并且可以使用多种语言与人交流。
 EXPIRES_IN_SECONDS=3600