feat: v1.6.0 verson update

fix openai voice_to_text whisper

README.md

@@ -1,11 +1,11 @@
 # 简介
 
-> 本项目是基于大模型的智能对话机器人，支持企业微信、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。
+> 本项目是基于大模型的智能对话机器人，支持企业微信、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/ChatGLM/KIMI，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，目前已支持微信生态下公众号、企业微信应用、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-3, Gemini, 文心一言, 讯飞星火, 通义千问，ChatGLM-4
+- [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-3, Gemini, 文心一言, 讯飞星火, 通义千问，ChatGLM-4，Kimi(月之暗面)
 - [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, 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
@@ -35,6 +35,8 @@ SaaS服务、私有化部署、稳定托管接入 等多种模式。
 
 # 更新日志
 
+>**2024.04.26：** [1.6.0版本](https://github.com/zhayujie/chatgpt-on-wechat/releases/tag/1.6.0)，新增 Kimi 接入、gpt-4-turbo版本升级、文件总结和语音识别问题修复
+
 >**2024.03.26：** [1.5.8版本](https://github.com/zhayujie/chatgpt-on-wechat/releases/tag/1.5.8) 和 [1.5.7版本](https://github.com/zhayujie/chatgpt-on-wechat/releases/tag/1.5.7)，新增 GLM-4、Claude-3 模型，edge-tts 语音支持
 
 >**2024.01.26：** [1.5.6版本](https://github.com/zhayujie/chatgpt-on-wechat/releases/tag/1.5.6) 和 [1.5.5版本](https://github.com/zhayujie/chatgpt-on-wechat/releases/tag/1.5.5)，钉钉接入，tool插件升级，4-turbo模型更新

bot/bot_factory.py

@@ -61,5 +61,9 @@ def create_bot(bot_type):
         from bot.zhipuai.zhipuai_bot import ZHIPUAIBot
         return ZHIPUAIBot()
 
+    elif bot_type == const.MOONSHOT:
+        from bot.moonshot.moonshot_bot import MoonshotBot
+        return MoonshotBot()
+
 
     raise RuntimeError

bot/chatgpt/chat_gpt_session.py

@@ -66,7 +66,7 @@ def num_tokens_from_messages(messages, model):
         return num_tokens_from_messages(messages, model="gpt-3.5-turbo")
     elif model in ["gpt-4-0314", "gpt-4-0613", "gpt-4-32k", "gpt-4-32k-0613", "gpt-3.5-turbo-0613",
                    "gpt-3.5-turbo-16k", "gpt-3.5-turbo-16k-0613", "gpt-35-turbo-16k", "gpt-4-turbo-preview",
-                   "gpt-4-1106-preview", const.GPT4_TURBO_PREVIEW, const.GPT4_VISION_PREVIEW]:
+                   "gpt-4-1106-preview", const.GPT4_TURBO_PREVIEW, const.GPT4_VISION_PREVIEW, const.GPT4_TURBO_01_25]:
         return num_tokens_from_messages(messages, model="gpt-4")
     elif model.startswith("claude-3"):
         return num_tokens_from_messages(messages, model="gpt-3.5-turbo")

bot/moonshot/moonshot_bot.py

@@ -0,0 +1,143 @@
+# encoding:utf-8
+
+import time
+
+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 .moonshot_session import MoonshotSession
+import requests
+
+
+# ZhipuAI对话模型API
+class MoonshotBot(Bot):
+    def __init__(self):
+        super().__init__()
+        self.sessions = SessionManager(MoonshotSession, model=conf().get("model") or "moonshot-v1-128k")
+        self.args = {
+            "model": conf().get("model") or "moonshot-v1-128k",  # 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("moonshot_api_key")
+        self.base_url = conf().get("moonshot_base_url", "https://api.moonshot.cn/v1/chat/completions")
+
+    def reply(self, query, context=None):
+        # acquire reply content
+        if context.type == ContextType.TEXT:
+            logger.info("[MOONSHOT_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("[MOONSHOT_AI] session query={}".format(session.messages))
+
+            model = context.get("moonshot_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(
+                "[MOONSHOT_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("[MOONSHOT_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: MoonshotSession, 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
+            # logger.debug("[MOONSHOT_AI] response={}".format(response))
+            # logger.info("[MOONSHOT_AI] reply={}, total_tokens={}".format(response.choices[0]['message']['content'], response["usage"]["total_tokens"]))
+            res = requests.post(
+                self.base_url,
+                headers=headers,
+                json=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()
+                error = response.get("error")
+                logger.error(f"[MOONSHOT_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"[MOONSHOT_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/moonshot/moonshot_session.py

@@ -0,0 +1,51 @@
+from bot.session_manager import Session
+from common.log import logger
+
+
+class MoonshotSession(Session):
+    def __init__(self, session_id, system_prompt=None, model="moonshot-v1-128k"):
+        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

@@ -48,6 +48,9 @@ class Bridge(object):
         if model_type in ["claude"]:
             self.btype["chat"] = const.CLAUDEAI
 
+        if model_type in ["moonshot-v1-8k", "moonshot-v1-32k", "moonshot-v1-128k"]:
+            self.btype["chat"] = const.MOONSHOT
+
         self.bots = {}
         self.chat_bots = {}
     # 模型对应的接口

common/const.py

@@ -23,14 +23,16 @@ MOONSHOT = "moonshot"
 CLAUDE3 = "claude-3-opus-20240229"
 GPT35 = "gpt-3.5-turbo"
 GPT4 = "gpt-4"
-GPT4_TURBO_PREVIEW = "gpt-4-0125-preview"
+GPT4_TURBO_PREVIEW = "gpt-4-turbo-2024-04-09"
+GPT4_TURBO_04_09 = "gpt-4-turbo-2024-04-09"
+GPT4_TURBO_01_25 = "gpt-4-0125-preview"
 GPT4_VISION_PREVIEW = "gpt-4-vision-preview"
 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, QWEN, GEMINI, ZHIPU_AI, MOONSHOT,
+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, QWEN, GEMINI, ZHIPU_AI, MOONSHOT,
               QWEN_TURBO, QWEN_PLUS, QWEN_MAX]
 
 # channel

config.py

@@ -157,6 +157,8 @@ available_setting = {
     # 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",
     # LinkAI平台配置
     "use_linkai": False,
     "linkai_api_key": "",

plugins/linkai/summary.py

@@ -2,6 +2,7 @@ import requests
 from config import conf
 from common.log import logger
 import os
+import html
 
 
 class LinkSummary:
@@ -18,6 +19,7 @@ class LinkSummary:
         return self._parse_summary_res(res)
 
     def summary_url(self, url: str):
+        url = html.unescape(url)
         body = {
             "url": url
         }

voice/openai/openai_voice.py

@@ -21,8 +21,21 @@ class OpenaiVoice(Voice):
         logger.debug("[Openai] voice file name={}".format(voice_file))
         try:
             file = open(voice_file, "rb")
-            result = openai.Audio.transcribe("whisper-1", file)
-            text = result["text"]
+            api_base = conf().get("open_ai_api_base") or "https://api.openai.com/v1"
+            url = f'{api_base}/audio/transcriptions'
+            headers = {
+                'Authorization': 'Bearer ' + conf().get("open_ai_api_key"),
+                # 'Content-Type': 'multipart/form-data' # 加了会报错，不知道什么原因
+            }
+            files = {
+                "file": file,
+            }
+            data = {
+                "model": "whisper-1",
+            }
+            response = requests.post(url, headers=headers, files=files, data=data)
+            response_data = response.json()
+            text = response_data['text']
             reply = Reply(ReplyType.TEXT, text)
             logger.info("[Openai] voiceToText text={} voice file name={}".format(text, voice_file))
         except Exception as e: