diff --git a/README.md b/README.md index bd6cd02..7f95674 100644 --- a/README.md +++ b/README.md @@ -112,7 +112,7 @@ pip3 install --upgrade tiktoken "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 "speech_recognition": false, # 是否开启语音识别 - "group_speech_recognition": false, # 是否开启群组语音识别 （目前仅支持wechaty） + "group_speech_recognition": false, # 是否开启群组语音识别 "use_azure_chatgpt": false, # 是否使用Azure ChatGPT service代替openai ChatGPT service. 当设置为true时需要设置 open_ai_api_base，如 https://xxx.openai.azure.com/ "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, } @@ -133,8 +133,8 @@ pip3 install --upgrade tiktoken **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，该参数仅支持私聊 (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 `"group_speech_recognition": true` 将开启群组语音识别，默认使用openai的whisper模型识别为文字，同时以文字回复，参数仅支持群聊 (可以匹配group_chat_prefix和group_chat_keyword，目前仅支持wechaty方案)； ++ 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，该参数仅支持私聊 (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，支持语音触发画图)； ++ 添加 `"group_speech_recognition": true` 将开启群组语音识别，默认使用openai的whisper模型识别为文字，同时以文字回复，参数仅支持群聊 (会匹配group_chat_prefix和group_chat_keyword, 支持语音触发画图)； + 添加 `"voice_reply_voice": true` 将开启语音回复语音（同时作用于私聊和群聊），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** diff --git a/channel/wechat/wechat_channel.py b/channel/wechat/wechat_channel.py index 05960ae..c7c660d 100644 --- a/channel/wechat/wechat_channel.py +++ b/channel/wechat/wechat_channel.py @@ -33,18 +33,20 @@ def handler_single_msg(msg): WechatChannel().handle_text(msg) return None - @itchat.msg_register(TEXT, isGroupChat=True) def handler_group_msg(msg): WechatChannel().handle_group(msg) return None - @itchat.msg_register(VOICE) def handler_single_voice(msg): WechatChannel().handle_voice(msg) return None - + +@itchat.msg_register(VOICE, isGroupChat=True) +def handler_group_voice(msg): + WechatChannel().handle_group_voice(msg) + return None class WechatChannel(Channel): def __init__(self): @@ -101,7 +103,6 @@ class WechatChannel(Channel): context.kwargs = {'isgroup': False, 'msg': msg, 'receiver': other_user_id, 'session_id': other_user_id} thread_pool.submit(self.handle, context).add_done_callback(thread_pool_callback) - @time_checker def handle_text(self, msg): logger.debug("[WX]receive text msg: " + json.dumps(msg, ensure_ascii=False)) @@ -188,6 +189,33 @@ class WechatChannel(Channel): thread_pool.submit(self.handle, context).add_done_callback(thread_pool_callback) + def handle_group_voice(self, msg): + if conf().get('group_speech_recognition', False) != True: + return + logger.debug("[WX]receive voice for group msg: " + msg['FileName']) + 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 voice skipped") + return + # 验证群名 + if not group_name: + return "" + if ('ALL_GROUP' in conf().get('group_name_white_list') or group_name in conf().get('group_name_white_list') or check_contain(group_name, conf().get('group_name_keyword_white_list'))): + context = Context(ContextType.VOICE,msg['FileName']) + context.kwargs = {'isgroup': True, 'msg': msg, 'receiver': group_id} + + group_chat_in_one_session = conf().get('group_chat_in_one_session', []) + if ('ALL_GROUP' in group_chat_in_one_session or + group_name in group_chat_in_one_session or + check_contain(group_name, group_chat_in_one_session)): + context['session_id'] = group_id + else: + context['session_id'] = msg['ActualUserName'] + + thread_pool.submit(self.handle, context).add_done_callback(thread_pool_callback) + # 统一的发送函数，每个Channel自行实现，根据reply的type字段发送不同类型的消息 def send(self, reply : Reply, receiver): if reply.type == ReplyType.TEXT: @@ -225,16 +253,33 @@ class WechatChannel(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 context.type == ContextType.TEXT or context.type == ContextType.IMAGE_CREATE: + if context.type == ContextType.TEXT or context.type == ContextType.IMAGE_CREATE: # 文字和图片消息 reply = super().build_reply_content(context.content, context) - elif context.type == ContextType.VOICE: + elif context.type == ContextType.VOICE: # 语音消息 msg = context['msg'] file_name = TmpDir().path() + context.content msg.download(file_name) reply = super().build_voice_to_text(file_name) - if reply.type != ReplyType.ERROR and reply.type != ReplyType.INFO: - context.content = reply.content # 语音转文字后，将文字内容作为新的context - context.type = ContextType.TEXT + if reply.type == ReplyType.TEXT: + content = reply.content # 语音转文字后，将文字内容作为新的context + # 如果是群消息，判断是否触发关键字 + if context['isgroup']: + match_prefix = check_prefix(content, conf().get('group_chat_prefix')) + match_contain = check_contain(content, conf().get('group_chat_keyword')) + logger.debug('[WX] group chat prefix match: {}'.format(match_prefix)) + if match_prefix is None and match_contain is None: + return + else: + if match_prefix: + content = content.replace(match_prefix, '', 1).strip() + + img_match_prefix = check_prefix(content, conf().get('image_create_prefix')) + if img_match_prefix: + content = content.replace(img_match_prefix, '', 1).strip() + context.type = ContextType.IMAGE_CREATE + else: + context.type = ContextType.TEXT + context.content = content reply = super().build_reply_content(context.content, context) if reply.type == ReplyType.TEXT: if conf().get('voice_reply_voice'): @@ -274,14 +319,12 @@ class WechatChannel(Channel): logger.debug('[WX] ready to send reply: {} to {}'.format(reply, context['receiver'])) self.send(reply, context['receiver']) - def check_prefix(content, prefix_list): for prefix in prefix_list: if content.startswith(prefix): return prefix return None - def check_contain(content, keyword_list): if not keyword_list: return None