Merge branch 'zhayujie:master' into master

README.md

@@ -6,14 +6,14 @@
   <a href="https://github.com/zhayujie/chatgpt-on-wechat"><img src="https://img.shields.io/github/stars/zhayujie/chatgpt-on-wechat?style=flat-square" alt="Stars"></a> <br/>
 </p>
 
-chatgpt-on-wechat（简称CoW）项目是基于大模型的智能对话机器人，支持微信公众号、企业微信应用、飞书、钉钉接入，可选择GPT3.5/GPT4.0/Claude/Gemini/LinkAI/ChatGLM/KIMI/文心一言/讯飞星火/通义千问/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。
+chatgpt-on-wechat（简称CoW）项目是基于大模型的智能对话机器人，支持微信公众号、企业微信应用、飞书、钉钉接入，可选择GPT3.5/GPT4.0/Claude/Gemini/LinkAI/ChatGLM/KIMI/文心一言/讯飞星火/通义千问/LinkAI/ModelScope，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。
 
 # 简介
 
 最新版本支持的功能如下：
 
 -  ✅   **多端部署：** 有多种部署方式可选择且功能完备，目前已支持微信公众号、企业微信应用、飞书、钉钉等部署方式
--  ✅   **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-4o-mini, GPT-4o,  GPT-4, Claude-3.5, Gemini, 文心一言, 讯飞星火, 通义千问，ChatGLM-4，Kimi(月之暗面), MiniMax, GiteeAI
+-  ✅   **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-4o-mini, GPT-4o,  GPT-4, Claude-3.5, Gemini, 文心一言, 讯飞星火, 通义千问，ChatGLM-4，Kimi(月之暗面), MiniMax, GiteeAI, ModelScope(魔搭社区)
 -  ✅   **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
 -  ✅   **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
 -  ✅   **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

bot/bot_factory.py

@@ -68,5 +68,9 @@ def create_bot(bot_type):
         from bot.minimax.minimax_bot import MinimaxBot
         return MinimaxBot()
 
+    elif bot_type == const.MODELSCOPE:
+        from bot.modelscope.modelscope_bot import ModelScopeBot
+        return ModelScopeBot()
+
 
     raise RuntimeError

bot/modelscope/modelscope_bot.py

@@ -0,0 +1,277 @@
+# encoding:utf-8
+
+import time
+import json
+import openai
+import openai.error
+from bot.bot import Bot
+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 .modelscope_session import ModelScopeSession
+import requests
+
+
+# ModelScope对话模型API
+class ModelScopeBot(Bot):
+    def __init__(self):
+        super().__init__()
+        self.sessions = SessionManager(ModelScopeSession, model=conf().get("model") or "Qwen/Qwen2.5-7B-Instruct")
+        model = conf().get("model") or "Qwen/Qwen2.5-7B-Instruct"
+        if model == "modelscope":
+            model = "Qwen/Qwen2.5-7B-Instruct"
+        self.args = {
+            "model": model,  # 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", 1.0),  # 使用默认值
+        }
+        self.api_key = conf().get("modelscope_api_key")
+        self.base_url = conf().get("modelscope_base_url", "https://api-inference.modelscope.cn/v1/chat/completions")
+        """
+        需要获取ModelScope支持API-inference的模型名称列表，请到魔搭社区官网模型中心查看 https://modelscope.cn/models?filter=inference_type&page=1。
+        或者使用命令 curl https://api-inference.modelscope.cn/v1/models 对模型列表和ID进行获取。查看commend/const.py文件也可以获取模型列表。
+        获取ModelScope的免费API Key，请到魔搭社区官网用户中心查看获取方式 https://modelscope.cn/docs/model-service/API-Inference/intro。
+        """
+    def reply(self, query, context=None):
+        # acquire reply content
+        if context.type == ContextType.TEXT:
+            logger.info("[MODELSCOPE_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("[MODELSCOPE_AI] session query={}".format(session.messages))
+
+            model = context.get("modelscope_model")
+            new_args = self.args.copy()
+            if model:
+                new_args["model"] = model
+
+            if new_args["model"] == "Qwen/QwQ-32B":
+                reply_content = self.reply_text_stream(session, args=new_args)
+            else:
+                reply_content = self.reply_text(session, args=new_args)
+
+            logger.debug(
+                "[MODELSCOPE_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:
+                # 只有当 content 为空且 completion_tokens 为 0 时才标记为错误
+                if len(reply_content["content"]) == 0:
+                    reply = Reply(ReplyType.ERROR, reply_content["content"])
+                else:
+                    reply = Reply(ReplyType.TEXT, 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("[MODELSCOPE_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: ModelScopeSession, 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
+            }
+            
+            body = args
+            body["messages"] = session.messages
+            res = requests.post(
+                self.base_url,
+                headers=headers,
+                data=json.dumps(body)
+            )
+
+            if res.status_code == 200:
+                response = res.json()
+                return {
+                    "total_tokens": response["usage"]["total_tokens"],
+                    "completion_tokens": response["usage"]["completion_tokens"],
+                    "content": response["choices"][0]["message"]["content"]
+                }
+            else:
+                response = res.json()
+                if "errors" in response:
+                    error = response.get("errors")
+                elif "error" in response:
+                    error = response.get("error")
+                else:
+                    error = "Unknown error"
+                logger.error(f"[MODELSCOPE_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"[MODELSCOPE_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
+
+    def reply_text_stream(self, session: ModelScopeSession, args=None, retry_count=0) -> dict:
+        """
+        call ModelScope's ChatCompletion to get the answer with stream response
+        :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
+            }
+            
+            body = args
+            body["messages"] = session.messages
+            body["stream"] = True  # 启用流式响应
+
+            res = requests.post(
+                self.base_url,
+                headers=headers,
+                data=json.dumps(body),
+                stream=True
+            )
+            if res.status_code == 200:
+                content = ""
+                for line in res.iter_lines():
+                    if line:
+                        decoded_line = line.decode('utf-8')
+                        if decoded_line.startswith("data: "):
+                            try:
+                                json_data = json.loads(decoded_line[6:])
+                                delta_content = json_data.get("choices", [{}])[0].get("delta", {}).get("content", "")
+                                if delta_content:
+                                    content += delta_content
+                            except json.JSONDecodeError as e:
+                                pass
+                return {
+                    "total_tokens": 1,  # 流式响应通常不返回token使用情况
+                    "completion_tokens": 1,
+                    "content": content
+                }
+            else:
+                response = res.json()
+                if "errors" in response:
+                    error = response.get("errors")
+                elif "error" in response:
+                    error = response.get("error")
+                else:
+                    error = "Unknown error"
+                logger.error(f"[MODELSCOPE_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"[MODELSCOPE_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_stream(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_stream(session, args, retry_count + 1)
+            else:
+                return result
+    def create_img(self, query, retry_count=0):
+        try:
+            logger.info("[ModelScopeImage] image_query={}".format(query))
+            headers = {
+                "Content-Type": "application/json; charset=utf-8",  # 明确指定编码
+                "Authorization": f"Bearer {self.api_key}"
+            }
+            payload = {
+                "prompt": query,  # required
+                "n": 1,
+                "model": conf().get("text_to_image"),
+            }
+            url = "https://api-inference.modelscope.cn/v1/images/generations"
+            
+            # 手动序列化并保留中文（禁用 ASCII 转义）
+            json_payload = json.dumps(payload, ensure_ascii=False).encode('utf-8')
+            
+            # 使用 data 参数发送原始字符串（requests 会自动处理编码）
+            res = requests.post(url, headers=headers, data=json_payload)
+            
+            response_data = res.json()
+            image_url = response_data['images'][0]['url']
+            logger.info("[ModelScopeImage] image_url={}".format(image_url))
+            return True, image_url
+
+        except Exception as e:
+            logger.error(format(e))
+            return False, "画图出现问题，请休息一下再问我吧"

bot/modelscope/modelscope_session.py

@@ -0,0 +1,51 @@
+from bot.session_manager import Session
+from common.log import logger
+
+
+class ModelScopeSession(Session):
+    def __init__(self, session_id, system_prompt=None, model="Qwen/Qwen2.5-7B-Instruct"):
+        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

bridge/bridge.py

@@ -49,6 +49,9 @@ class Bridge(object):
             if model_type in [const.MOONSHOT, "moonshot-v1-8k", "moonshot-v1-32k", "moonshot-v1-128k"]:
                 self.btype["chat"] = const.MOONSHOT
 
+            if model_type in [const.MODELSCOPE]:
+                self.btype["chat"] = const.MODELSCOPE
+            
             if model_type in ["abab6.5-chat"]:
                 self.btype["chat"] = const.MiniMax
 

common/const.py

@@ -15,7 +15,7 @@ GEMINI = "gemini"  # gemini-1.0-pro
 ZHIPU_AI = "glm-4"
 MOONSHOT = "moonshot"
 MiniMax = "minimax"
-
+MODELSCOPE = "modelscope"
 
 # model
 CLAUDE3 = "claude-3-opus-20240229"
@@ -85,6 +85,12 @@ DEEPSEEK_REASONER = "deepseek-reasoner"  # DeepSeek-R1模型
 
 GITEE_AI_MODEL_LIST = ["Yi-34B-Chat", "InternVL2-8B", "deepseek-coder-33B-instruct", "InternVL2.5-26B", "Qwen2-VL-72B", "Qwen2.5-32B-Instruct", "glm-4-9b-chat", "codegeex4-all-9b", "Qwen2.5-Coder-32B-Instruct", "Qwen2.5-72B-Instruct", "Qwen2.5-7B-Instruct", "Qwen2-72B-Instruct", "Qwen2-7B-Instruct", "code-raccoon-v1", "Qwen2.5-14B-Instruct"]
 
+MODELSCOPE_MODEL_LIST = ["LLM-Research/c4ai-command-r-plus-08-2024","mistralai/Mistral-Small-Instruct-2409","mistralai/Ministral-8B-Instruct-2410","mistralai/Mistral-Large-Instruct-2407",
+                          "Qwen/Qwen2.5-Coder-32B-Instruct","Qwen/Qwen2.5-Coder-14B-Instruct","Qwen/Qwen2.5-Coder-7B-Instruct","Qwen/Qwen2.5-72B-Instruct","Qwen/Qwen2.5-32B-Instruct","Qwen/Qwen2.5-14B-Instruct","Qwen/Qwen2.5-7B-Instruct","Qwen/QwQ-32B-Preview",
+                          "LLM-Research/Llama-3.3-70B-Instruct","opencompass/CompassJudger-1-32B-Instruct","Qwen/QVQ-72B-Preview","LLM-Research/Meta-Llama-3.1-405B-Instruct","LLM-Research/Meta-Llama-3.1-8B-Instruct","Qwen/Qwen2-VL-7B-Instruct","LLM-Research/Meta-Llama-3.1-70B-Instruct",
+                          "Qwen/Qwen2.5-14B-Instruct-1M","Qwen/Qwen2.5-7B-Instruct-1M","Qwen/Qwen2.5-VL-3B-Instruct","Qwen/Qwen2.5-VL-7B-Instruct","Qwen/Qwen2.5-VL-72B-Instruct","deepseek-ai/DeepSeek-R1-Distill-Llama-70B","deepseek-ai/DeepSeek-R1-Distill-Llama-8B","deepseek-ai/DeepSeek-R1-Distill-Qwen-32B",
+                          "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B","deepseek-ai/DeepSeek-R1-Distill-Qwen-7B","deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B","deepseek-ai/DeepSeek-R1","deepseek-ai/DeepSeek-V3","Qwen/QwQ-32B"]
+
 MODEL_LIST = [
               GPT35, GPT35_0125, GPT35_1106, "gpt-3.5-turbo-16k",
               O1, O1_MINI, GPT_4o, GPT_4O_0806, GPT_4o_MINI, GPT4_TURBO, GPT4_TURBO_PREVIEW, GPT4_TURBO_01_25, GPT4_TURBO_11_06, GPT4, GPT4_32k, GPT4_06_13, GPT4_32k_06_13,
@@ -97,10 +103,11 @@ MODEL_LIST = [
               "moonshot-v1-8k", "moonshot-v1-32k", "moonshot-v1-128k",
               QWEN, QWEN_TURBO, QWEN_PLUS, QWEN_MAX,
               LINKAI_35, LINKAI_4_TURBO, LINKAI_4o,
-              DEEPSEEK_CHAT, DEEPSEEK_REASONER
+              DEEPSEEK_CHAT, DEEPSEEK_REASONER,
+              MODELSCOPE
             ]
 
-MODEL_LIST = MODEL_LIST + GITEE_AI_MODEL_LIST
+MODEL_LIST = MODEL_LIST + GITEE_AI_MODEL_LIST + MODELSCOPE_MODEL_LIST
 # channel
 FEISHU = "feishu"
 DINGTALK = "dingtalk"

config.py

@@ -171,6 +171,9 @@ available_setting = {
     "zhipu_ai_api_base": "https://open.bigmodel.cn/api/paas/v4",
     "moonshot_api_key": "",
     "moonshot_base_url": "https://api.moonshot.cn/v1/chat/completions",
+    #魔搭社区 平台配置
+    "modelscope_api_key": "",
+    "modelscope_base_url": "https://api-inference.modelscope.cn/v1/chat/completions",
     # LinkAI平台配置
     "use_linkai": False,
     "linkai_api_key": "",

plugins/godcmd/godcmd.py

@@ -339,7 +339,8 @@ class Godcmd(Plugin):
                             ok, result = True, "配置已重载"
                         elif cmd == "resetall":
                             if bottype in [const.OPEN_AI, const.CHATGPT, const.CHATGPTONAZURE, const.LINKAI,
-                                           const.BAIDU, const.XUNFEI, const.QWEN, const.GEMINI, const.ZHIPU_AI, const.MOONSHOT]:
+                                           const.BAIDU, const.XUNFEI, const.QWEN, const.GEMINI, const.ZHIPU_AI, const.MOONSHOT,
+                                           const.MODELSCOPE]:
                                 channel.cancel_all_session()
                                 bot.sessions.clear_all_session()
                                 ok, result = True, "重置所有会话成功"

plugins/role/role.py

@@ -99,7 +99,7 @@ class Role(Plugin):
         if e_context["context"].type != ContextType.TEXT:
             return
         btype = Bridge().get_bot_type("chat")
-        if btype not in [const.OPEN_AI, const.CHATGPT, const.CHATGPTONAZURE, const.QWEN_DASHSCOPE, const.XUNFEI, const.BAIDU, const.ZHIPU_AI, const.MOONSHOT, const.MiniMax, const.LINKAI]:
+        if btype not in [const.OPEN_AI, const.CHATGPT, const.CHATGPTONAZURE, const.QWEN_DASHSCOPE, const.XUNFEI, const.BAIDU, const.ZHIPU_AI, const.MOONSHOT, const.MiniMax, const.LINKAI,const.MODELSCOPE]:
             logger.debug(f'不支持的bot: {btype}')
             return
         bot = Bridge().get_bot("chat")