diff --git a/bot/bot_factory.py b/bot/bot_factory.py index 3b31af0..6cb0e49 100644 --- a/bot/bot_factory.py +++ b/bot/bot_factory.py @@ -64,6 +64,10 @@ def create_bot(bot_type): elif bot_type == const.MOONSHOT: from bot.moonshot.moonshot_bot import MoonshotBot return MoonshotBot() + + elif bot_type == const.MiniMax: + from bot.minimax.minimax_bot import MinimaxBot + return MinimaxBot() raise RuntimeError diff --git a/bot/minimax/minimax_bot.py b/bot/minimax/minimax_bot.py new file mode 100644 index 0000000..40112d8 --- /dev/null +++ b/bot/minimax/minimax_bot.py @@ -0,0 +1,151 @@ +# encoding:utf-8 + +import time + +import openai +import openai.error +from bot.bot import Bot +from bot.minimax.minimax_session import MinimaxSession +from bot.session_manager import SessionManager +from bridge.context import Context, ContextType +from bridge.reply import Reply, ReplyType +from common.log import logger +from config import conf, load_config +from bot.chatgpt.chat_gpt_session import ChatGPTSession +import requests +from common import const + + +# ZhipuAI对话模型API +class MinimaxBot(Bot): + def __init__(self): + super().__init__() + self.args = { + "model": conf().get("model") or "abab6.5", # 对话模型的名称 + "temperature": conf().get("temperature", 0.3), # 如果设置，值域须为 [0, 1] 我们推荐 0.3，以达到较合适的效果。 + "top_p": conf().get("top_p", 0.95), # 使用默认值 + } + self.api_key = conf().get("Minimax_api_key") + self.group_id = conf().get("Minimax_group_id") + self.base_url = conf().get("Minimax_base_url", f"https://api.minimax.chat/v1/text/chatcompletion_pro?GroupId={self.group_id}") + # tokens_to_generate/bot_setting/reply_constraints可自行修改 + self.request_body = { + "model": self.args["model"], + "tokens_to_generate": 2048, + "reply_constraints": {"sender_type": "BOT", "sender_name": "MM智能助理"}, + "messages": [], + "bot_setting": [ + { + "bot_name": "MM智能助理", + "content": "MM智能助理是一款由MiniMax自研的，没有调用其他产品的接口的大型语言模型。MiniMax是一家中国科技公司，一直致力于进行大模型相关的研究。", + } + ], + } + self.sessions = SessionManager(MinimaxSession, model=const.MiniMax) + + def reply(self, query, context: Context = None) -> Reply: + # acquire reply content + logger.info("[Minimax_AI] query={}".format(query)) + if context.type == ContextType.TEXT: + 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("[Minimax_AI] session query={}".format(session)) + + model = context.get("Minimax_model") + new_args = self.args.copy() + if model: + new_args["model"] = model + # if context.get('stream'): + # # reply in stream + # return self.reply_text_stream(query, new_query, session_id) + + reply_content = self.reply_text(session, args=new_args) + logger.debug( + "[Minimax_AI] 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("[Minimax_AI] 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: MinimaxSession, args=None, retry_count=0) -> dict: + """ + call openai's ChatCompletion to get the answer + :param session: a conversation session + :param session_id: session id + :param retry_count: retry count + :return: {} + """ + try: + headers = {"Content-Type": "application/json", "Authorization": "Bearer " + self.api_key} + self.request_body["messages"].extend(session.messages) + logger.info("[Minimax_AI] request_body={}".format(self.request_body)) + # logger.info("[Minimax_AI] reply={}, total_tokens={}".format(response.choices[0]['message']['content'], response["usage"]["total_tokens"])) + res = requests.post(self.base_url, headers=headers, json=self.request_body) + + # self.request_body["messages"].extend(response.json()["choices"][0]["messages"]) + if res.status_code == 200: + response = res.json() + return { + "total_tokens": response["usage"]["total_tokens"], + "completion_tokens": response["usage"]["total_tokens"], + "content": response["reply"], + } + else: + response = res.json() + error = response.get("error") + logger.error(f"[Minimax_AI] chat failed, status_code={res.status_code}, " f"msg={error.get('message')}, type={error.get('type')}") + + result = {"completion_tokens": 0, "content": "提问太快啦，请休息一下再问我吧"} + need_retry = False + if res.status_code >= 500: + # server error, need retry + logger.warn(f"[Minimax_AI] do retry, times={retry_count}") + need_retry = retry_count < 2 + elif res.status_code == 401: + result["content"] = "授权失败，请检查API Key是否正确" + elif res.status_code == 429: + result["content"] = "请求过于频繁，请稍后再试" + need_retry = retry_count < 2 + else: + need_retry = False + + if need_retry: + time.sleep(3) + return self.reply_text(session, args, retry_count + 1) + else: + return result + except Exception as e: + logger.exception(e) + need_retry = retry_count < 2 + result = {"completion_tokens": 0, "content": "我现在有点累了，等会再来吧"} + if need_retry: + return self.reply_text(session, args, retry_count + 1) + else: + return result diff --git a/bot/minimax/minimax_session.py b/bot/minimax/minimax_session.py new file mode 100644 index 0000000..1925b4b --- /dev/null +++ b/bot/minimax/minimax_session.py @@ -0,0 +1,72 @@ +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 MinimaxSession(Session): + def __init__(self, session_id, system_prompt=None, model="minimax"): + super().__init__(session_id, system_prompt) + self.model = model + # self.reset() + + def add_query(self, query): + user_item = {"sender_type": "USER", "sender_name": self.session_id, "text": query} + self.messages.append(user_item) + + def add_reply(self, reply): + assistant_item = {"sender_type": "BOT", "sender_name": "MM智能助理", "text": reply} + self.messages.append(assistant_item) + + 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]["sender_type"] == "BOT": + 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]["sender_type"] == "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["text"]) + return tokens diff --git a/bridge/bridge.py b/bridge/bridge.py index 6733701..cc24198 100644 --- a/bridge/bridge.py +++ b/bridge/bridge.py @@ -45,6 +45,9 @@ class Bridge(object): if model_type in ["moonshot-v1-8k", "moonshot-v1-32k", "moonshot-v1-128k"]: self.btype["chat"] = const.MOONSHOT + if model_type in ["abab6.5-chat"]: + self.btype["chat"] = const.MiniMax + 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"]: diff --git a/common/const.py b/common/const.py index 2c8d01e..1c4c2e1 100644 --- a/common/const.py +++ b/common/const.py @@ -6,7 +6,7 @@ XUNFEI = "xunfei" CHATGPTONAZURE = "chatGPTOnAzure" LINKAI = "linkai" CLAUDEAI = "claude" -CLAUDEAPI= "claudeAPI" +CLAUDEAPI = "claudeAPI" QWEN = "qwen" QWEN_DASHSCOPE = "dashscope" @@ -17,6 +17,7 @@ QWEN_MAX = "qwen-max" GEMINI = "gemini" ZHIPU_AI = "glm-4" MOONSHOT = "moonshot" +MiniMax = "minimax" # model @@ -35,10 +36,34 @@ 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", "claude-3-opus-20240229", "gpt-4-turbo", - "gpt-4-turbo-preview", "gpt-4-1106-preview", GPT4_TURBO_PREVIEW, GPT4_TURBO_01_25, GPT_4o, QWEN, GEMINI, ZHIPU_AI, MOONSHOT, - QWEN_TURBO, QWEN_PLUS, QWEN_MAX, LINKAI_35, LINKAI_4_TURBO, LINKAI_4o] +MODEL_LIST = [ + "gpt-3.5-turbo", + "gpt-3.5-turbo-16k", + "gpt-4", + "wenxin", + "wenxin-4", + "xunfei", + "claude", + "claude-3-opus-20240229", + "gpt-4-turbo", + "gpt-4-turbo-preview", + "gpt-4-1106-preview", + GPT4_TURBO_PREVIEW, + GPT4_TURBO_01_25, + GPT_4o, + QWEN, + GEMINI, + ZHIPU_AI, + MOONSHOT, + QWEN_TURBO, + QWEN_PLUS, + QWEN_MAX, + LINKAI_35, + LINKAI_4_TURBO, + LINKAI_4o, + MiniMax, +] # channel FEISHU = "feishu" -DINGTALK = "dingtalk" +DINGTALK = "dingtalk" diff --git a/config.py b/config.py index 6556203..cd43a2c 100644 --- a/config.py +++ b/config.py @@ -34,7 +34,7 @@ available_setting = { "group_name_keyword_white_list": [], # 开启自动回复的群名称关键词列表 "group_chat_in_one_session": ["ChatGPT测试群"], # 支持会话上下文共享的群名称 "nick_name_black_list": [], # 用户昵称黑名单 - "group_welcome_msg": "", # 配置新人进群固定欢迎语，不配置则使用随机风格欢迎 + "group_welcome_msg": "", # 配置新人进群固定欢迎语，不配置则使用随机风格欢迎 "trigger_by_self": False, # 是否允许机器人触发 "text_to_image": "dall-e-2", # 图片生成模型，可选 dall-e-2, dall-e-3 # Azure OpenAI dall-e-3 配置 @@ -48,7 +48,7 @@ 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, + "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 @@ -76,7 +76,7 @@ available_setting = { "claude_api_cookie": "", "claude_uuid": "", # claude api key - "claude_api_key":"", + "claude_api_key": "", # 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": "", @@ -108,8 +108,8 @@ available_setting = { "azure_voice_api_key": "", "azure_voice_region": "japaneast", # elevenlabs 语音api配置 - "xi_api_key": "", #获取ap的方法可以参考https://docs.elevenlabs.io/api-reference/quick-start/authentication - "xi_voice_id": "", #ElevenLabs提供了9种英式、美式等英语发音id，分别是“Adam/Antoni/Arnold/Bella/Domi/Elli/Josh/Rachel/Sam” + "xi_api_key": "", # 获取ap的方法可以参考https://docs.elevenlabs.io/api-reference/quick-start/authentication + "xi_voice_id": "", # ElevenLabs提供了9种英式、美式等英语发音id，分别是“Adam/Antoni/Arnold/Bella/Domi/Elli/Josh/Rachel/Sam” # 服务时间限制，目前支持itchat "chat_time_module": False, # 是否开启服务时间限制 "chat_start_time": "00:00", # 服务开始时间 @@ -137,14 +137,12 @@ available_setting = { "wechatcomapp_secret": "", # 企业微信app的secret "wechatcomapp_agent_id": "", # 企业微信app的agent_id "wechatcomapp_aes_key": "", # 企业微信app的aes_key - # 飞书配置 "feishu_port": 80, # 飞书bot监听端口 "feishu_app_id": "", # 飞书机器人应用APP Id "feishu_app_secret": "", # 飞书机器人APP secret "feishu_token": "", # 飞书 verification token "feishu_bot_name": "", # 飞书机器人的名字 - # 钉钉配置 "dingtalk_client_id": "", # 钉钉机器人Client ID "dingtalk_client_secret": "", # 钉钉机器人Client Secret @@ -161,18 +159,21 @@ available_setting = { "plugin_trigger_prefix": "$", # 规范插件提供聊天相关指令的前缀，建议不要和管理员指令前缀"#"冲突 # 是否使用全局插件配置 "use_global_plugin_config": False, - "max_media_send_count": 3, # 单次最大发送媒体资源的个数 + "max_media_send_count": 3, # 单次最大发送媒体资源的个数 "media_send_interval": 1, # 发送图片的事件间隔，单位秒 # 智谱AI 平台配置 "zhipu_ai_api_key": "", "zhipu_ai_api_base": "https://open.bigmodel.cn/api/paas/v4", "moonshot_api_key": "", - "moonshot_base_url":"https://api.moonshot.cn/v1/chat/completions", + "moonshot_base_url": "https://api.moonshot.cn/v1/chat/completions", # LinkAI平台配置 "use_linkai": False, "linkai_api_key": "", "linkai_app_code": "", "linkai_api_base": "https://api.link-ai.tech", # linkAI服务地址 + "Minimax_api_key": "", + "Minimax_group_id": "", + "Minimax_base_url": "", } @@ -346,6 +347,4 @@ def pconf(plugin_name: str) -> dict: # 全局配置，用于存放全局生效的状态 -global_config = { - "admin_users": [] -} +global_config = {"admin_users": []}