Merge pull request #1723 from zRzRzRzRzRzRzR/master

支持ZhipuAI GLM系列模型和画图代码

README.md

@@ -1,13 +1,13 @@
 # 简介
 
-> 本项目是基于大模型的智能对话机器人，支持微信、企业微信、公众号、飞书、钉钉接入，可选择GPT3.5/GPT4.0/Claude/文心一言/讯飞星火/通义千问/Gemini/LinkAI，能处理文本、语音和图片，通过插件访问操作系统和互联网等外部资源，支持基于自有知识库定制企业AI应用。
+> 本项目是基于大模型的智能对话机器人，支持微信、企业微信、公众号、飞书、钉钉接入，可选择GPT3.5/GPT4.0/Claude/文心一言/讯飞星火/通义千问/Gemini/LinkAI/ZhipuAI，能处理文本、语音和图片，通过插件访问操作系统和互联网等外部资源，支持基于自有知识库定制企业AI应用。
 
 最新版本支持的功能如下：
 
 - [x] **多端部署：** 有多种部署方式可选择且功能完备，目前已支持个人微信、微信公众号和、企业微信、飞书、钉钉等部署方式
-- [x] **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, claude, Gemini, 文心一言, 讯飞星火, 通义千问
+- [x] **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, claude, Gemini, 文心一言, 讯飞星火, 通义千问，ChatGLM
 - [x] **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
-- [x] **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, vision模型
+- [x] **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
 - [x] **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
 - [x] **知识库：** 通过上传知识库文件自定义专属机器人，可作为数字分身、智能客服、私域助手使用，基于 [LinkAI](https://link-ai.tech) 实现
 

bot/bot_factory.py

@@ -52,8 +52,9 @@ def create_bot(bot_type):
         from bot.gemini.google_gemini_bot import GoogleGeminiBot
         return GoogleGeminiBot()
 
-    elif bot_type == const.CHATGLM:
-        from bot.zhipu.chat_glm_bot import ChatGLMBot
-        return ChatGLMBot()
+    elif bot_type == const.ZHIPU_AI:
+        from bot.zhipuai.zhipuai_bot import ZHIPUAIBot
+        return ZHIPUAIBot()
+
 
     raise RuntimeError

bot/zhipuai/zhipu_ai_image.py

@@ -0,0 +1,29 @@
+from common.log import logger
+from config import conf
+
+
+# ZhipuAI提供的画图接口
+
+class ZhipuAIImage(object):
+    def __init__(self):
+        from zhipuai import ZhipuAI
+        self.client = ZhipuAI(api_key=conf().get("zhipu_ai_api_key"))
+
+    def create_img(self, query, retry_count=0, api_key=None, api_base=None):
+        try:
+            if conf().get("rate_limit_dalle"):
+                return False, "请求太快了，请休息一下再问我吧"
+            logger.info("[ZHIPU_AI] image_query={}".format(query))
+            response = self.client.images.generations(
+                prompt=query,
+                n=1,  # 每次生成图片的数量
+                model=conf().get("text_to_image") or "cogview-3",
+                size=conf().get("image_create_size", "1024x1024"),  # 图片大小,可选有 256x256, 512x512, 1024x1024
+                quality="standard",
+            )
+            image_url = response.data[0].url
+            logger.info("[ZHIPU_AI] image_url={}".format(image_url))
+            return True, image_url
+        except Exception as e:
+            logger.exception(e)
+            return False, "画图出现问题，请休息一下再问我吧"

bot/zhipuai/zhipu_ai_session.py

@@ -0,0 +1,51 @@
+from bot.session_manager import Session
+from common.log import logger
+
+
+class ZhipuAISession(Session):
+    def __init__(self, session_id, system_prompt=None, model="glm-4"):
+        super().__init__(session_id, system_prompt)
+        self.model = model
+        self.reset()
+
+    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]["role"] == "assistant":
+                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]["role"] == "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):
+    tokens = 0
+    for msg in messages:
+        tokens += len(msg["content"])
+    return tokens

bot/zhipuai/zhipuai_bot.py

@@ -0,0 +1,149 @@
+# encoding:utf-8
+
+import time
+
+import openai
+import openai.error
+from bot.bot import Bot
+from bot.zhipuai.zhipu_ai_session import ZhipuAISession
+from bot.zhipuai.zhipu_ai_image import ZhipuAIImage
+from bot.session_manager import SessionManager
+from bridge.context import ContextType
+from bridge.reply import Reply, ReplyType
+from common.log import logger
+from config import conf, load_config
+from zhipuai import ZhipuAI
+
+
+# ZhipuAI对话模型API
+class ZHIPUAIBot(Bot, ZhipuAIImage):
+    def __init__(self):
+        super().__init__()
+        self.sessions = SessionManager(ZhipuAISession, model=conf().get("model") or "ZHIPU_AI")
+        self.args = {
+            "model": conf().get("model") or "glm-4",  # 对话模型的名称
+            "temperature": conf().get("temperature", 0.9),  # 值在(0,1)之间(智谱AI 的温度不能取 0 或者 1)
+            "top_p": conf().get("top_p", 0.7),  # 值在(0,1)之间(智谱AI 的 top_p 不能取 0 或者 1)
+        }
+        self.client = ZhipuAI(api_key=conf().get("zhipu_ai_api_key"))
+
+    def reply(self, query, context=None):
+        # acquire reply content
+        if context.type == ContextType.TEXT:
+            logger.info("[ZHIPU_AI] query={}".format(query))
+
+            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("[ZHIPU_AI] session query={}".format(session.messages))
+
+            api_key = context.get("openai_api_key") or openai.api_key
+            model = context.get("gpt_model")
+            new_args = None
+            if model:
+                new_args = self.args.copy()
+                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, api_key, args=new_args)
+            logger.debug(
+                "[ZHIPU_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("[ZHIPU_AI] reply {} used 0 tokens.".format(reply_content))
+            return reply
+        elif context.type == ContextType.IMAGE_CREATE:
+            ok, retstring = self.create_img(query, 0)
+            reply = None
+            if ok:
+                reply = Reply(ReplyType.IMAGE_URL, retstring)
+            else:
+                reply = Reply(ReplyType.ERROR, retstring)
+            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: ZhipuAISession, api_key=None, 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:
+            # if conf().get("rate_limit_chatgpt") and not self.tb4chatgpt.get_token():
+            #     raise openai.error.RateLimitError("RateLimitError: rate limit exceeded")
+            # if api_key == None, the default openai.api_key will be used
+            if args is None:
+                args = self.args
+            # response = openai.ChatCompletion.create(api_key=api_key, messages=session.messages, **args)
+            response = self.client.chat.completions.create(messages=session.messages, **args)
+            # logger.debug("[ZHIPU_AI] response={}".format(response))
+            # logger.info("[ZHIPU_AI] reply={}, total_tokens={}".format(response.choices[0]['message']['content'], response["usage"]["total_tokens"]))
+
+            return {
+                "total_tokens": response.usage.total_tokens,
+                "completion_tokens": response.usage.completion_tokens,
+                "content": response.choices[0].message.content,
+            }
+        except Exception as e:
+            need_retry = retry_count < 2
+            result = {"completion_tokens": 0, "content": "我现在有点累了，等会再来吧"}
+            if isinstance(e, openai.error.RateLimitError):
+                logger.warn("[ZHIPU_AI] RateLimitError: {}".format(e))
+                result["content"] = "提问太快啦，请休息一下再问我吧"
+                if need_retry:
+                    time.sleep(20)
+            elif isinstance(e, openai.error.Timeout):
+                logger.warn("[ZHIPU_AI] Timeout: {}".format(e))
+                result["content"] = "我没有收到你的消息"
+                if need_retry:
+                    time.sleep(5)
+            elif isinstance(e, openai.error.APIError):
+                logger.warn("[ZHIPU_AI] Bad Gateway: {}".format(e))
+                result["content"] = "请再问我一次"
+                if need_retry:
+                    time.sleep(10)
+            elif isinstance(e, openai.error.APIConnectionError):
+                logger.warn("[ZHIPU_AI] APIConnectionError: {}".format(e))
+                result["content"] = "我连接不到你的网络"
+                if need_retry:
+                    time.sleep(5)
+            else:
+                logger.exception("[ZHIPU_AI] Exception: {}".format(e), e)
+                need_retry = False
+                self.sessions.clear_session(session.session_id)
+
+            if need_retry:
+                logger.warn("[ZHIPU_AI] 第{}次重试".format(retry_count + 1))
+                return self.reply_text(session, api_key, args, retry_count + 1)
+            else:
+                return result

bridge/bridge.py

@@ -31,8 +31,8 @@ class Bridge(object):
             self.btype["chat"] = const.QWEN
         if model_type in [const.GEMINI]:
             self.btype["chat"] = const.GEMINI
-        if model_type in [const.CHATGLM]:
-            self.btype["chat"] = const.CHATGLM
+        if model_type in [const.ZHIPU_AI]:
+            self.btype["chat"] = const.ZHIPU_AI
 
         if conf().get("use_linkai") and conf().get("linkai_api_key"):
             self.btype["chat"] = const.LINKAI

common/const.py

@@ -8,7 +8,8 @@ LINKAI = "linkai"
 CLAUDEAI = "claude"
 QWEN = "qwen"
 GEMINI = "gemini"
-CHATGLM = "chatglm"
+ZHIPU_AI = "glm-4"
+
 
 # model
 GPT35 = "gpt-3.5-turbo"
@@ -20,7 +21,7 @@ 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", "gpt-4-turbo",
-              "gpt-4-turbo-preview", "gpt-4-1106-preview", GPT4_TURBO_PREVIEW, QWEN, GEMINI, CHATGLM]
+              "gpt-4-turbo-preview", "gpt-4-1106-preview", GPT4_TURBO_PREVIEW, QWEN, GEMINI, ZHIPU_AI]
 
 # channel
 FEISHU = "feishu"

config.py

@@ -150,15 +150,14 @@ available_setting = {
     "use_global_plugin_config": False,
     "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",
     # LinkAI平台配置
     "use_linkai": False,
     "linkai_api_key": "",
     "linkai_app_code": "",
     "linkai_api_base": "https://api.link-ai.chat",  # linkAI服务地址，若国内无法访问或延迟较高可改为 https://api.link-ai.tech
-
-#   # 智谱AI
-    "zhipu_ai_api_key": "",
-    "zhipu_ai_api_base": "https://open.bigmodel.cn/api/paas/v4",
 }
 
 

requirements-optional.txt

@@ -38,5 +38,5 @@ linkai
 # dingtalk
 dingtalk_stream
 
-# zhipu
-zhipuai
+# zhipuai
+zhipuai>=2.0.1