Merge pull request #2071 from lmy668/master

feat#add minmax model

bot/bot_factory.py

@@ -63,6 +63,10 @@ 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

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

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

bridge/bridge.py

@@ -49,6 +49,9 @@ 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"]:

common/const.py

@@ -8,13 +8,13 @@ LINKAI = "linkai"
 CLAUDEAI = "claude"  # 使用cookie的历史模型
 CLAUDEAPI= "claudeAPI"  # 通过Claude api调用模型
 QWEN = "qwen"  # 旧版通义模型
-
 QWEN_DASHSCOPE = "dashscope"  # 通义新版sdk和api key
 
 
 GEMINI = "gemini"
 ZHIPU_AI = "glm-4"
 MOONSHOT = "moonshot"
+MINIMAX = "minimax"
 
 
 # model
@@ -59,10 +59,11 @@ MODEL_LIST = [
               XUNFEI, GEMINI, ZHIPU_AI, MOONSHOT,
               "claude", "claude-3-haiku", "claude-3-sonnet", "claude-3-opus", "claude-3-opus-20240229",
               "moonshot-v1-8k", "moonshot-v1-32k", "moonshot-v1-128k",
-              LINKAI_35, LINKAI_4_TURBO, LINKAI_4o,
-              QWEN, QWEN_TURBO, QWEN_PLUS, QWEN_MAX
+              QWEN, QWEN_TURBO, QWEN_PLUS, QWEN_MAX,
+              MINIMAX,
+              LINKAI_35, LINKAI_4_TURBO, LINKAI_4o
             ]
 
 # channel
 FEISHU = "feishu"
-DINGTALK = "dingtalk"   
+DINGTALK = "dingtalk"

config.py

@@ -35,7 +35,7 @@ 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
@@ -49,7 +49,7 @@ 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
@@ -77,7 +77,7 @@ 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": "",
@@ -109,8 +109,8 @@ 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
@@ -138,14 +138,12 @@ 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
@@ -162,18 +160,21 @@ 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": "",
 }
 
 
@@ -347,6 +348,4 @@ 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": []}