logging -> loguru: final stage

* update welcome svg

* fix loading chatglm3 (#1937)

* update welcome svg

* update welcome message

* fix loading chatglm3

---------

Co-authored-by: binary-husky <qingxu.fu@outlook.com>
Co-authored-by: binary-husky <96192199+binary-husky@users.noreply.github.com>

* begin rag project with llama index

* rag version one

* rag beta release

* add social worker (proto)

* fix llamaindex version

---------

Co-authored-by: moetayuko <loli@yuko.moe>

.gitignore

@@ -131,6 +131,9 @@ dmypy.json
 # Pyre type checker
 .pyre/
 
+# macOS files
+.DS_Store
+
 .vscode
 .idea
 
@@ -153,4 +156,8 @@ media
 flagged
 request_llms/ChatGLM-6b-onnx-u8s8
 .pre-commit-config.yaml
-themes/common.js.min.*.js
+test.*
+temp.*
+objdump*
+*.min.*.js
+TODO

Dockerfile

@@ -12,11 +12,16 @@ RUN echo '[global]' > /etc/pip.conf && \
     echo 'trusted-host = mirrors.aliyun.com' >> /etc/pip.conf
 
 
+# 语音输出功能（以下两行，第一行更换阿里源，第二行安装ffmpeg，都可以删除）
+RUN UBUNTU_VERSION=$(awk -F= '/^VERSION_CODENAME=/{print $2}' /etc/os-release); echo "deb https://mirrors.aliyun.com/debian/ $UBUNTU_VERSION main non-free contrib" > /etc/apt/sources.list; apt-get update
+RUN apt-get install ffmpeg -y
+
+
 # 进入工作路径（必要）
 WORKDIR /gpt
 
 
-# 安装大部分依赖，利用Docker缓存加速以后的构建 （以下三行，可以删除）
+# 安装大部分依赖，利用Docker缓存加速以后的构建 （以下两行，可以删除）
 COPY requirements.txt ./
 RUN pip3 install -r requirements.txt
 

README.md

@@ -1,7 +1,7 @@
 > [!IMPORTANT]
+> 2024.6.1: 版本3.80加入插件二级菜单功能（详见wiki）  
 > 2024.5.1: 加入Doc2x翻译PDF论文的功能，[查看详情](https://github.com/binary-husky/gpt_academic/wiki/Doc2x)  
-> 2024.4.30: 3.75版本引入Edge-TTS和SoVits语音克隆模块，[查看详情](https://www.bilibili.com/video/BV1Rp421S7tF/)  
-> 2024.3.11: 恭迎Claude3和Moonshot，全力支持Qwen、GLM、DeepseekCoder等中文大语言模型！  
+> 2024.3.11: 全力支持Qwen、GLM、DeepseekCoder等中文大语言模型！ SoVits语音克隆模块，[查看详情](https://www.bilibili.com/video/BV1Rp421S7tF/) 
 > 2024.1.17: 安装依赖时，请选择`requirements.txt`中**指定的版本**。 安装命令：`pip install -r requirements.txt`。本项目完全开源免费，您可通过订阅[在线服务](https://github.com/binary-husky/gpt_academic/wiki/online)的方式鼓励本项目的发展。
 
 <br>
@@ -67,7 +67,7 @@ Read this in [English](docs/README.English.md) | [日本語](docs/README.Japanes
 读论文、[翻译](https://www.bilibili.com/video/BV1KT411x7Wn)论文 | [插件] 一键解读latex/pdf论文全文并生成摘要
 Latex全文[翻译](https://www.bilibili.com/video/BV1nk4y1Y7Js/)、[润色](https://www.bilibili.com/video/BV1FT411H7c5/) | [插件] 一键翻译或润色latex论文
 批量注释生成 | [插件] 一键批量生成函数注释
-Markdown[中英互译](https://www.bilibili.com/video/BV1yo4y157jV/) | [插件] 看到上面5种语言的[README](https://github.com/binary-husky/gpt_academic/blob/master/docs/README_EN.md)了吗？就是出自他的手笔
+Markdown[中英互译](https://www.bilibili.com/video/BV1yo4y157jV/) | [插件] 看到上面5种语言的[README](https://github.com/binary-husky/gpt_academic/blob/master/docs/README.English.md)了吗？就是出自他的手笔
 [PDF论文全文翻译功能](https://www.bilibili.com/video/BV1KT411x7Wn) | [插件] PDF论文提取题目&摘要+翻译全文（多线程）
 [Arxiv小助手](https://www.bilibili.com/video/BV1LM4y1279X) | [插件] 输入arxiv文章url即可一键翻译摘要+下载PDF
 Latex论文一键校对 | [插件] 仿Grammarly对Latex文章进行语法、拼写纠错+输出对照PDF

check_proxy.py

@@ -1,33 +1,45 @@
+from loguru import logger
 
-def check_proxy(proxies):
+def check_proxy(proxies, return_ip=False):
     import requests
     proxies_https = proxies['https'] if proxies is not None else '无'
+    ip = None
     try:
         response = requests.get("https://ipapi.co/json/", proxies=proxies, timeout=4)
         data = response.json()
         if 'country_name' in data:
             country = data['country_name']
             result = f"代理配置 {proxies_https}, 代理所在地：{country}"
+            if 'ip' in data: ip = data['ip']
         elif 'error' in data:
-            alternative = _check_with_backup_source(proxies)
+            alternative, ip = _check_with_backup_source(proxies)
             if alternative is None:
                 result = f"代理配置 {proxies_https}, 代理所在地：未知，IP查询频率受限"
             else:
                 result = f"代理配置 {proxies_https}, 代理所在地：{alternative}"
         else:
             result = f"代理配置 {proxies_https}, 代理数据解析失败：{data}"
-        print(result)
+        if not return_ip:
+            logger.warning(result)
             return result
+        else:
+            return ip
     except:
         result = f"代理配置 {proxies_https}, 代理所在地查询超时，代理可能无效"
-        print(result)
+        if not return_ip:
+            logger.warning(result)
             return result
+        else:
+            return ip
 
 def _check_with_backup_source(proxies):
     import random, string, requests
     random_string = ''.join(random.choices(string.ascii_letters + string.digits, k=32))
-    try: return requests.get(f"http://{random_string}.edns.ip-api.com/json", proxies=proxies, timeout=4).json()['dns']['geo']
-    except: return None
+    try:
+        res_json = requests.get(f"http://{random_string}.edns.ip-api.com/json", proxies=proxies, timeout=4).json()
+        return res_json['dns']['geo'], res_json['dns']['ip']
+    except:
+        return None, None
 
 def backup_and_download(current_version, remote_version):
     """
@@ -71,25 +83,25 @@ def patch_and_restart(path):
     import sys
     import time
     import glob
-    from colorful import print亮黄, print亮绿, print亮红
+    from shared_utils.colorful import log亮黄, log亮绿, log亮红
     # if not using config_private, move origin config.py as config_private.py
     if not os.path.exists('config_private.py'):
-        print亮黄('由于您没有设置config_private.py私密配置，现将您的现有配置移动至config_private.py以防止配置丢失，',
+        log亮黄('由于您没有设置config_private.py私密配置，现将您的现有配置移动至config_private.py以防止配置丢失，',
               '另外您可以随时在history子文件夹下找回旧版的程序。')
         shutil.copyfile('config.py', 'config_private.py')
     path_new_version = glob.glob(path + '/*-master')[0]
     dir_util.copy_tree(path_new_version, './')
-    print亮绿('代码已经更新，即将更新pip包依赖……')
-    for i in reversed(range(5)): time.sleep(1); print(i)
+    log亮绿('代码已经更新，即将更新pip包依赖……')
+    for i in reversed(range(5)): time.sleep(1); log亮绿(i)
     try:
         import subprocess
         subprocess.check_call([sys.executable, '-m', 'pip', 'install', '-r', 'requirements.txt'])
     except:
-        print亮红('pip包依赖安装出现问题，需要手动安装新增的依赖库 `python -m pip install -r requirements.txt`，然后在用常规的`python main.py`的方式启动。')
-    print亮绿('更新完成，您可以随时在history子文件夹下找回旧版的程序，5s之后重启')
-    print亮红('假如重启失败，您可能需要手动安装新增的依赖库 `python -m pip install -r requirements.txt`，然后在用常规的`python main.py`的方式启动。')
-    print(' ------------------------------ -----------------------------------')
-    for i in reversed(range(8)): time.sleep(1); print(i)
+        log亮红('pip包依赖安装出现问题，需要手动安装新增的依赖库 `python -m pip install -r requirements.txt`，然后在用常规的`python main.py`的方式启动。')
+    log亮绿('更新完成，您可以随时在history子文件夹下找回旧版的程序，5s之后重启')
+    log亮红('假如重启失败，您可能需要手动安装新增的依赖库 `python -m pip install -r requirements.txt`，然后在用常规的`python main.py`的方式启动。')
+    log亮绿(' ------------------------------ -----------------------------------')
+    for i in reversed(range(8)): time.sleep(1); log亮绿(i)
     os.execl(sys.executable, sys.executable, *sys.argv)
 
 
@@ -124,9 +136,9 @@ def auto_update(raise_error=False):
             current_version = f.read()
             current_version = json.loads(current_version)['version']
         if (remote_version - current_version) >= 0.01-1e-5:
-            from colorful import print亮黄
-            print亮黄(f'\n新版本可用。新版本:{remote_version}，当前版本:{current_version}。{new_feature}')
-            print('（1）Github更新地址:\nhttps://github.com/binary-husky/chatgpt_academic\n')
+            from shared_utils.colorful import log亮黄
+            log亮黄(f'\n新版本可用。新版本:{remote_version}，当前版本:{current_version}。{new_feature}')
+            logger.info('（1）Github更新地址:\nhttps://github.com/binary-husky/chatgpt_academic\n')
             user_instruction = input('（2）是否一键更新代码（Y+回车=确认，输入其他/无输入+回车=不更新）？')
             if user_instruction in ['Y', 'y']:
                 path = backup_and_download(current_version, remote_version)
@@ -137,9 +149,9 @@ def auto_update(raise_error=False):
                     if raise_error:
                         from toolbox import trimmed_format_exc
                         msg += trimmed_format_exc()
-                    print(msg)
+                    logger.warning(msg)
             else:
-                print('自动更新程序：已禁用')
+                logger.info('自动更新程序：已禁用')
                 return
         else:
             return
@@ -148,10 +160,10 @@ def auto_update(raise_error=False):
         if raise_error:
             from toolbox import trimmed_format_exc
             msg += trimmed_format_exc()
-        print(msg)
+        logger.info(msg)
 
 def warm_up_modules():
-    print('正在执行一些模块的预热 ...')
+    logger.info('正在执行一些模块的预热 ...')
     from toolbox import ProxyNetworkActivate
     from request_llms.bridge_all import model_info
     with ProxyNetworkActivate("Warmup_Modules"):
@@ -161,7 +173,7 @@ def warm_up_modules():
         enc.encode("模块预热", disallowed_special=())
 
 def warm_up_vectordb():
-    print('正在执行一些模块的预热 ...')
+    logger.info('正在执行一些模块的预热 ...')
     from toolbox import ProxyNetworkActivate
     with ProxyNetworkActivate("Warmup_Modules"):
         import nltk

config.py

@@ -32,22 +32,29 @@ else:
 
 # [step 3]>> 模型选择是 (注意: LLM_MODEL是默认选中的模型, 它*必须*被包含在AVAIL_LLM_MODELS列表中 )
 LLM_MODEL = "gpt-3.5-turbo-16k" # 可选 ↓↓↓
-AVAIL_LLM_MODELS = ["gpt-4-1106-preview", "gpt-4-turbo-preview", "gpt-4-vision-preview", "gpt-4-turbo", "gpt-4-turbo-2024-04-09",
+AVAIL_LLM_MODELS = ["gpt-4-1106-preview", "gpt-4-turbo-preview", "gpt-4-vision-preview",
+                    "gpt-4o", "gpt-4o-mini", "gpt-4-turbo", "gpt-4-turbo-2024-04-09",
                     "gpt-3.5-turbo-1106", "gpt-3.5-turbo-16k", "gpt-3.5-turbo", "azure-gpt-3.5",
                     "gpt-4", "gpt-4-32k", "azure-gpt-4", "glm-4", "glm-4v", "glm-3-turbo",
-                    "gemini-pro", "chatglm3"
+                    "gemini-1.5-pro", "chatglm3"
                     ]
+
+EMBEDDING_MODEL = "text-embedding-3-small"
+
 # --- --- --- ---
 # P.S. 其他可用的模型还包括
 # AVAIL_LLM_MODELS = [
+#   "glm-4-0520", "glm-4-air", "glm-4-airx", "glm-4-flash",
 #   "qianfan", "deepseekcoder",
-#   "spark", "sparkv2", "sparkv3", "sparkv3.5",
+#   "spark", "sparkv2", "sparkv3", "sparkv3.5", "sparkv4",
 #   "qwen-turbo", "qwen-plus", "qwen-max", "qwen-local",
 #   "moonshot-v1-128k", "moonshot-v1-32k", "moonshot-v1-8k",
-#   "gpt-3.5-turbo-0613", "gpt-3.5-turbo-16k-0613", "gpt-3.5-turbo-0125"
+#   "gpt-3.5-turbo-0613", "gpt-3.5-turbo-16k-0613", "gpt-3.5-turbo-0125", "gpt-4o-2024-05-13"
 #   "claude-3-haiku-20240307","claude-3-sonnet-20240229","claude-3-opus-20240229", "claude-2.1", "claude-instant-1.2",
 #   "moss", "llama2", "chatglm_onnx", "internlm", "jittorllms_pangualpha", "jittorllms_llama",
-#   "yi-34b-chat-0205", "yi-34b-chat-200k"
+#   "deepseek-chat" ,"deepseek-coder",
+#   "gemini-1.5-flash",
+#   "yi-34b-chat-0205","yi-34b-chat-200k","yi-large","yi-medium","yi-spark","yi-large-turbo","yi-large-preview",
 # ]
 # --- --- --- ---
 # 此外，您还可以在接入one-api/vllm/ollama时，
@@ -103,6 +110,10 @@ TIMEOUT_SECONDS = 30
 WEB_PORT = -1
 
 
+# 是否自动打开浏览器页面
+AUTO_OPEN_BROWSER = True
+
+
 # 如果OpenAI不响应（网络卡顿、代理失败、KEY失效），重试的次数限制
 MAX_RETRY = 2
 
@@ -128,7 +139,7 @@ DASHSCOPE_API_KEY = "" # 阿里灵积云API_KEY
 # 百度千帆（LLM_MODEL="qianfan"）
 BAIDU_CLOUD_API_KEY = ''
 BAIDU_CLOUD_SECRET_KEY = ''
-BAIDU_CLOUD_QIANFAN_MODEL = 'ERNIE-Bot'    # 可选 "ERNIE-Bot-4"(文心大模型4.0), "ERNIE-Bot"(文心一言), "ERNIE-Bot-turbo", "BLOOMZ-7B", "Llama-2-70B-Chat", "Llama-2-13B-Chat", "Llama-2-7B-Chat"
+BAIDU_CLOUD_QIANFAN_MODEL = 'ERNIE-Bot'    # 可选 "ERNIE-Bot-4"(文心大模型4.0), "ERNIE-Bot"(文心一言), "ERNIE-Bot-turbo", "BLOOMZ-7B", "Llama-2-70B-Chat", "Llama-2-13B-Chat", "Llama-2-7B-Chat", "ERNIE-Speed-128K", "ERNIE-Speed-8K", "ERNIE-Lite-8K"
 
 
 # 如果使用ChatGLM2微调模型，请把 LLM_MODEL="chatglmft"，并在此处指定模型路径
@@ -196,7 +207,7 @@ ALIYUN_SECRET=""    # （无需填写）
 
 
 # GPT-SOVITS 文本转语音服务的运行地址（将语言模型的生成文本朗读出来）
-TTS_TYPE = "DISABLE" # LOCAL / LOCAL_SOVITS_API / DISABLE
+TTS_TYPE = "EDGE_TTS" # EDGE_TTS / LOCAL_SOVITS_API / DISABLE
 GPT_SOVITS_URL = ""
 EDGE_TTS_VOICE = "zh-CN-XiaoxiaoNeural"
 
@@ -224,6 +235,14 @@ MOONSHOT_API_KEY = ""
 YIMODEL_API_KEY = ""
 
 
+# 深度求索(DeepSeek) API KEY，默认请求地址为"https://api.deepseek.com/v1/chat/completions"
+DEEPSEEK_API_KEY = ""
+
+
+# 紫东太初大模型 https://ai-maas.wair.ac.cn
+TAICHU_API_KEY = ""
+
+
 # Mathpix 拥有执行PDF的OCR功能，但是需要注册账号
 MATHPIX_APPID = ""
 MATHPIX_APPKEY = ""
@@ -254,6 +273,10 @@ GROBID_URLS = [
 ]
 
 
+# Searxng互联网检索服务
+SEARXNG_URL = "https://cloud-1.agent-matrix.com/"
+
+
 # 是否允许通过自然语言描述修改本页的配置，该功能具有一定的危险性，默认关闭
 ALLOW_RESET_CONFIG = False
 
@@ -262,21 +285,21 @@ ALLOW_RESET_CONFIG = False
 AUTOGEN_USE_DOCKER = False
 
 
-# 临时的上传文件夹位置，请勿修改
+# 临时的上传文件夹位置，请尽量不要修改
 PATH_PRIVATE_UPLOAD = "private_upload"
 
 
-# 日志文件夹的位置，请勿修改
+# 日志文件夹的位置，请尽量不要修改
 PATH_LOGGING = "gpt_log"
 
 
-# 除了连接OpenAI之外，还有哪些场合允许使用代理，请勿修改
+# 存储翻译好的arxiv论文的路径，请尽量不要修改
+ARXIV_CACHE_DIR = "gpt_log/arxiv_cache"
+
+
+# 除了连接OpenAI之外，还有哪些场合允许使用代理，请尽量不要修改
 WHEN_TO_USE_PROXY = ["Download_LLM", "Download_Gradio_Theme", "Connect_Grobid",
-                     "Warmup_Modules", "Nougat_Download", "AutoGen"]
-
-
-# *实验性功能*: 自动检测并屏蔽失效的KEY，请勿使用
-BLOCK_INVALID_APIKEY = False
+                     "Warmup_Modules", "Nougat_Download", "AutoGen", "Connect_OpenAI_Embedding"]
 
 
 # 启用插件热加载
@@ -375,6 +398,9 @@ NUM_CUSTOM_BASIC_BTN = 4
 
 插件在线服务配置依赖关系示意图
 │
+├── 互联网检索
+│   └── SEARXNG_URL
+│
 ├── 语音功能
 │   ├── ENABLE_AUDIO
 │   ├── ALIYUN_TOKEN

core_functional.py

@@ -33,6 +33,8 @@ def get_core_functions():
             "AutoClearHistory": False,
             # [6] 文本预处理 （可选参数，默认 None，举例：写个函数移除所有的换行符）
             "PreProcess": None,
+            # [7] 模型选择 （可选参数。如不设置，则使用当前全局模型；如设置，则用指定模型覆盖全局模型。）
+            # "ModelOverride": "gpt-3.5-turbo", # 主要用途：强制点击此基础功能按钮时，使用指定的模型。
         },
 
 

crazy_functional.py

@@ -1,46 +1,69 @@
 from toolbox import HotReload  # HotReload 的意思是热更新，修改函数插件后，不需要重启程序，代码直接生效
 from toolbox import trimmed_format_exc
+from loguru import logger
 
 
 def get_crazy_functions():
     from crazy_functions.读文章写摘要 import 读文章写摘要
     from crazy_functions.生成函数注释 import 批量生成函数注释
-    from crazy_functions.解析项目源代码 import 解析项目本身
-    from crazy_functions.解析项目源代码 import 解析一个Python项目
-    from crazy_functions.解析项目源代码 import 解析一个Matlab项目
-    from crazy_functions.解析项目源代码 import 解析一个C项目的头文件
-    from crazy_functions.解析项目源代码 import 解析一个C项目
-    from crazy_functions.解析项目源代码 import 解析一个Golang项目
-    from crazy_functions.解析项目源代码 import 解析一个Rust项目
-    from crazy_functions.解析项目源代码 import 解析一个Java项目
-    from crazy_functions.解析项目源代码 import 解析一个前端项目
+    from crazy_functions.Rag_Interface import Rag问答
+    from crazy_functions.SourceCode_Analyse import 解析项目本身
+    from crazy_functions.SourceCode_Analyse import 解析一个Python项目
+    from crazy_functions.SourceCode_Analyse import 解析一个Matlab项目
+    from crazy_functions.SourceCode_Analyse import 解析一个C项目的头文件
+    from crazy_functions.SourceCode_Analyse import 解析一个C项目
+    from crazy_functions.SourceCode_Analyse import 解析一个Golang项目
+    from crazy_functions.SourceCode_Analyse import 解析一个Rust项目
+    from crazy_functions.SourceCode_Analyse import 解析一个Java项目
+    from crazy_functions.SourceCode_Analyse import 解析一个前端项目
     from crazy_functions.高级功能函数模板 import 高阶功能模板函数
+    from crazy_functions.高级功能函数模板 import Demo_Wrap
     from crazy_functions.Latex全文润色 import Latex英文润色
     from crazy_functions.询问多个大语言模型 import 同时问询
-    from crazy_functions.解析项目源代码 import 解析一个Lua项目
-    from crazy_functions.解析项目源代码 import 解析一个CSharp项目
+    from crazy_functions.SourceCode_Analyse import 解析一个Lua项目
+    from crazy_functions.SourceCode_Analyse import 解析一个CSharp项目
     from crazy_functions.总结word文档 import 总结word文档
     from crazy_functions.解析JupyterNotebook import 解析ipynb文件
-    from crazy_functions.对话历史存档 import 对话历史存档
-    from crazy_functions.对话历史存档 import 载入对话历史存档
-    from crazy_functions.对话历史存档 import 删除所有本地对话历史记录
+    from crazy_functions.Conversation_To_File import 载入对话历史存档
+    from crazy_functions.Conversation_To_File import 对话历史存档
+    from crazy_functions.Conversation_To_File import Conversation_To_File_Wrap
+    from crazy_functions.Conversation_To_File import 删除所有本地对话历史记录
     from crazy_functions.辅助功能 import 清除缓存
-    from crazy_functions.批量Markdown翻译 import Markdown英译中
+    from crazy_functions.Markdown_Translate import Markdown英译中
     from crazy_functions.批量总结PDF文档 import 批量总结PDF文档
-    from crazy_functions.PDF批量翻译 import 批量翻译PDF文档
+    from crazy_functions.PDF_Translate import 批量翻译PDF文档
     from crazy_functions.谷歌检索小助手 import 谷歌检索小助手
     from crazy_functions.理解PDF文档内容 import 理解PDF文档内容标准文件输入
     from crazy_functions.Latex全文润色 import Latex中文润色
     from crazy_functions.Latex全文润色 import Latex英文纠错
-    from crazy_functions.批量Markdown翻译 import Markdown中译英
+    from crazy_functions.Markdown_Translate import Markdown中译英
     from crazy_functions.虚空终端 import 虚空终端
-    from crazy_functions.生成多种Mermaid图表 import 生成多种Mermaid图表
+    from crazy_functions.生成多种Mermaid图表 import Mermaid_Gen
+    from crazy_functions.PDF_Translate_Wrap import PDF_Tran
+    from crazy_functions.Latex_Function import Latex英文纠错加PDF对比
+    from crazy_functions.Latex_Function import Latex翻译中文并重新编译PDF
+    from crazy_functions.Latex_Function import PDF翻译中文并重新编译PDF
+    from crazy_functions.Latex_Function_Wrap import Arxiv_Localize
+    from crazy_functions.Latex_Function_Wrap import PDF_Localize
+    from crazy_functions.Internet_GPT import 连接网络回答问题
+    from crazy_functions.Internet_GPT_Wrap import NetworkGPT_Wrap
+    from crazy_functions.Image_Generate import 图片生成_DALLE2, 图片生成_DALLE3, 图片修改_DALLE2
+    from crazy_functions.Image_Generate_Wrap import ImageGen_Wrap
+    from crazy_functions.SourceCode_Comment import 注释Python项目
 
     function_plugins = {
+        "Rag智能召回": {
+            "Group": "对话",
+            "Color": "stop",
+            "AsButton": False,
+            "Info": "将问答数据记录到向量库中，作为长期参考。",
+            "Function": HotReload(Rag问答),
+        },
         "虚空终端": {
             "Group": "对话|编程|学术|智能体",
             "Color": "stop",
             "AsButton": True,
+            "Info": "使用自然语言实现您的想法",
             "Function": HotReload(虚空终端),
         },
         "解析整个Python项目": {
@@ -50,6 +73,13 @@ def get_crazy_functions():
             "Info": "解析一个Python项目的所有源文件(.py) | 输入参数为路径",
             "Function": HotReload(解析一个Python项目),
         },
+        "注释Python项目": {
+            "Group": "编程",
+            "Color": "stop",
+            "AsButton": False,
+            "Info": "上传一系列python源文件(或者压缩包), 为这些代码添加docstring | 输入参数为路径",
+            "Function": HotReload(注释Python项目),
+        },
         "载入对话历史存档（先上传存档或输入路径）": {
             "Group": "对话",
             "Color": "stop",
@@ -75,14 +105,21 @@ def get_crazy_functions():
             "Color": "stop",
             "AsButton": False,
             "Info" : "基于当前对话或文件生成多种Mermaid图表,图表类型由模型判断",
-            "Function": HotReload(生成多种Mermaid图表),
-            "AdvancedArgs": True,
-            "ArgsReminder": "请输入图类型对应的数字,不输入则为模型自行判断:1-流程图,2-序列图,3-类图,4-饼图,5-甘特图,6-状态图,7-实体关系图,8-象限提示图,9-思维导图",
+            "Function": None,
+            "Class": Mermaid_Gen
+        },
+        "Arxiv论文翻译": {
+            "Group": "学术",
+            "Color": "stop",
+            "AsButton": True,
+            "Info": "Arixv论文精细翻译 | 输入参数arxiv论文的ID，比如1812.10695",
+            "Function": HotReload(Latex翻译中文并重新编译PDF),  # 当注册Class后，Function旧接口仅会在“虚空终端”中起作用
+            "Class": Arxiv_Localize,    # 新一代插件需要注册Class
         },
         "批量总结Word文档": {
             "Group": "学术",
             "Color": "stop",
-            "AsButton": True,
+            "AsButton": False,
             "Info": "批量总结word文档 | 输入参数为路径",
             "Function": HotReload(总结word文档),
         },
@@ -188,28 +225,42 @@ def get_crazy_functions():
         },
         "保存当前的对话": {
             "Group": "对话",
+            "Color": "stop",
             "AsButton": True,
             "Info": "保存当前的对话 | 不需要输入参数",
-            "Function": HotReload(对话历史存档),
+            "Function": HotReload(对话历史存档),    # 当注册Class后，Function旧接口仅会在“虚空终端”中起作用
+            "Class": Conversation_To_File_Wrap     # 新一代插件需要注册Class
         },
         "[多线程Demo]解析此项目本身（源码自译解）": {
             "Group": "对话|编程",
+            "Color": "stop",
             "AsButton": False,  # 加入下拉菜单中
             "Info": "多线程解析并翻译此项目的源码 | 不需要输入参数",
             "Function": HotReload(解析项目本身),
         },
+        "查互联网后回答": {
+            "Group": "对话",
+            "Color": "stop",
+            "AsButton": True,  # 加入下拉菜单中
+            # "Info": "连接网络回答问题（需要访问谷歌）| 输入参数是一个问题",
+            "Function": HotReload(连接网络回答问题),
+            "Class": NetworkGPT_Wrap     # 新一代插件需要注册Class
+        },
         "历史上的今天": {
             "Group": "对话",
-            "AsButton": True,
+            "Color": "stop",
+            "AsButton": False,
             "Info": "查看历史上的今天事件 (这是一个面向开发者的插件Demo) | 不需要输入参数",
-            "Function": HotReload(高阶功能模板函数),
+            "Function": None,
+            "Class": Demo_Wrap, # 新一代插件需要注册Class
         },
         "精准翻译PDF论文": {
             "Group": "学术",
             "Color": "stop",
             "AsButton": True,
             "Info": "精准翻译PDF论文为中文 | 输入参数为路径",
-            "Function": HotReload(批量翻译PDF文档),
+            "Function": HotReload(批量翻译PDF文档), # 当注册Class后，Function旧接口仅会在“虚空终端”中起作用
+            "Class": PDF_Tran,  # 新一代插件需要注册Class
         },
         "询问多个GPT模型": {
             "Group": "对话",
@@ -284,260 +335,6 @@ def get_crazy_functions():
             "Info": "批量将Markdown文件中文翻译为英文 | 输入参数为路径或上传压缩包",
             "Function": HotReload(Markdown中译英),
         },
-    }
-
-    # -=--=- 尚未充分测试的实验性插件 & 需要额外依赖的插件 -=--=-
-    try:
-        from crazy_functions.下载arxiv论文翻译摘要 import 下载arxiv论文并翻译摘要
-
-        function_plugins.update(
-            {
-                "一键下载arxiv论文并翻译摘要（先在input输入编号，如1812.10695）": {
-                    "Group": "学术",
-                    "Color": "stop",
-                    "AsButton": False,  # 加入下拉菜单中
-                    # "Info": "下载arxiv论文并翻译摘要 | 输入参数为arxiv编号如1812.10695",
-                    "Function": HotReload(下载arxiv论文并翻译摘要),
-                }
-            }
-        )
-    except:
-        print(trimmed_format_exc())
-        print("Load function plugin failed")
-
-    try:
-        from crazy_functions.联网的ChatGPT import 连接网络回答问题
-
-        function_plugins.update(
-            {
-                "连接网络回答问题（输入问题后点击该插件，需要访问谷歌）": {
-                    "Group": "对话",
-                    "Color": "stop",
-                    "AsButton": False,  # 加入下拉菜单中
-                    # "Info": "连接网络回答问题（需要访问谷歌）| 输入参数是一个问题",
-                    "Function": HotReload(连接网络回答问题),
-                }
-            }
-        )
-        from crazy_functions.联网的ChatGPT_bing版 import 连接bing搜索回答问题
-
-        function_plugins.update(
-            {
-                "连接网络回答问题（中文Bing版，输入问题后点击该插件）": {
-                    "Group": "对话",
-                    "Color": "stop",
-                    "AsButton": False,  # 加入下拉菜单中
-                    "Info": "连接网络回答问题（需要访问中文Bing）| 输入参数是一个问题",
-                    "Function": HotReload(连接bing搜索回答问题),
-                }
-            }
-        )
-    except:
-        print(trimmed_format_exc())
-        print("Load function plugin failed")
-
-    try:
-        from crazy_functions.解析项目源代码 import 解析任意code项目
-
-        function_plugins.update(
-            {
-                "解析项目源代码（手动指定和筛选源代码文件类型）": {
-                    "Group": "编程",
-                    "Color": "stop",
-                    "AsButton": False,
-                    "AdvancedArgs": True,  # 调用时，唤起高级参数输入区（默认False）
-                    "ArgsReminder": '输入时用逗号隔开, *代表通配符, 加了^代表不匹配; 不输入代表全部匹配。例如: "*.c, ^*.cpp, config.toml, ^*.toml"',  # 高级参数输入区的显示提示
-                    "Function": HotReload(解析任意code项目),
-                },
-            }
-        )
-    except:
-        print(trimmed_format_exc())
-        print("Load function plugin failed")
-
-    try:
-        from crazy_functions.询问多个大语言模型 import 同时问询_指定模型
-
-        function_plugins.update(
-            {
-                "询问多个GPT模型（手动指定询问哪些模型）": {
-                    "Group": "对话",
-                    "Color": "stop",
-                    "AsButton": False,
-                    "AdvancedArgs": True,  # 调用时，唤起高级参数输入区（默认False）
-                    "ArgsReminder": "支持任意数量的llm接口，用&符号分隔。例如chatglm&gpt-3.5-turbo&gpt-4",  # 高级参数输入区的显示提示
-                    "Function": HotReload(同时问询_指定模型),
-                },
-            }
-        )
-    except:
-        print(trimmed_format_exc())
-        print("Load function plugin failed")
-
-    try:
-        from crazy_functions.图片生成 import 图片生成_DALLE2, 图片生成_DALLE3, 图片修改_DALLE2
-
-        function_plugins.update(
-            {
-                "图片生成_DALLE2 （先切换模型到gpt-*）": {
-                    "Group": "对话",
-                    "Color": "stop",
-                    "AsButton": False,
-                    "AdvancedArgs": True,  # 调用时，唤起高级参数输入区（默认False）
-                    "ArgsReminder": "在这里输入分辨率, 如1024x1024（默认），支持 256x256, 512x512, 1024x1024",  # 高级参数输入区的显示提示
-                    "Info": "使用DALLE2生成图片 | 输入参数字符串，提供图像的内容",
-                    "Function": HotReload(图片生成_DALLE2),
-                },
-            }
-        )
-        function_plugins.update(
-            {
-                "图片生成_DALLE3 （先切换模型到gpt-*）": {
-                    "Group": "对话",
-                    "Color": "stop",
-                    "AsButton": False,
-                    "AdvancedArgs": True,  # 调用时，唤起高级参数输入区（默认False）
-                    "ArgsReminder": "在这里输入自定义参数「分辨率-质量(可选)-风格(可选)」, 参数示例「1024x1024-hd-vivid」 || 分辨率支持 「1024x1024」(默认) /「1792x1024」/「1024x1792」 || 质量支持 「-standard」(默认) /「-hd」 || 风格支持 「-vivid」(默认) /「-natural」",  # 高级参数输入区的显示提示
-                    "Info": "使用DALLE3生成图片 | 输入参数字符串，提供图像的内容",
-                    "Function": HotReload(图片生成_DALLE3),
-                },
-            }
-        )
-        function_plugins.update(
-            {
-                "图片修改_DALLE2 （先切换模型到gpt-*）": {
-                    "Group": "对话",
-                    "Color": "stop",
-                    "AsButton": False,
-                    "AdvancedArgs": False,  # 调用时，唤起高级参数输入区（默认False）
-                    # "Info": "使用DALLE2修改图片 | 输入参数字符串，提供图像的内容",
-                    "Function": HotReload(图片修改_DALLE2),
-                },
-            }
-        )
-    except:
-        print(trimmed_format_exc())
-        print("Load function plugin failed")
-
-    try:
-        from crazy_functions.总结音视频 import 总结音视频
-
-        function_plugins.update(
-            {
-                "批量总结音视频（输入路径或上传压缩包）": {
-                    "Group": "对话",
-                    "Color": "stop",
-                    "AsButton": False,
-                    "AdvancedArgs": True,
-                    "ArgsReminder": "调用openai api 使用whisper-1模型, 目前支持的格式:mp4, m4a, wav, mpga, mpeg, mp3。此处可以输入解析提示，例如：解析为简体中文（默认）。",
-                    "Info": "批量总结音频或视频 | 输入参数为路径",
-                    "Function": HotReload(总结音视频),
-                }
-            }
-        )
-    except:
-        print(trimmed_format_exc())
-        print("Load function plugin failed")
-
-    try:
-        from crazy_functions.数学动画生成manim import 动画生成
-
-        function_plugins.update(
-            {
-                "数学动画生成（Manim）": {
-                    "Group": "对话",
-                    "Color": "stop",
-                    "AsButton": False,
-                    "Info": "按照自然语言描述生成一个动画 | 输入参数是一段话",
-                    "Function": HotReload(动画生成),
-                }
-            }
-        )
-    except:
-        print(trimmed_format_exc())
-        print("Load function plugin failed")
-
-    try:
-        from crazy_functions.批量Markdown翻译 import Markdown翻译指定语言
-
-        function_plugins.update(
-            {
-                "Markdown翻译（指定翻译成何种语言）": {
-                    "Group": "编程",
-                    "Color": "stop",
-                    "AsButton": False,
-                    "AdvancedArgs": True,
-                    "ArgsReminder": "请输入要翻译成哪种语言，默认为Chinese。",
-                    "Function": HotReload(Markdown翻译指定语言),
-                }
-            }
-        )
-    except:
-        print(trimmed_format_exc())
-        print("Load function plugin failed")
-
-    try:
-        from crazy_functions.知识库问答 import 知识库文件注入
-
-        function_plugins.update(
-            {
-                "构建知识库（先上传文件素材,再运行此插件）": {
-                    "Group": "对话",
-                    "Color": "stop",
-                    "AsButton": False,
-                    "AdvancedArgs": True,
-                    "ArgsReminder": "此处待注入的知识库名称id, 默认为default。文件进入知识库后可长期保存。可以通过再次调用本插件的方式，向知识库追加更多文档。",
-                    "Function": HotReload(知识库文件注入),
-                }
-            }
-        )
-    except:
-        print(trimmed_format_exc())
-        print("Load function plugin failed")
-
-    try:
-        from crazy_functions.知识库问答 import 读取知识库作答
-
-        function_plugins.update(
-            {
-                "知识库文件注入（构建知识库后,再运行此插件）": {
-                    "Group": "对话",
-                    "Color": "stop",
-                    "AsButton": False,
-                    "AdvancedArgs": True,
-                    "ArgsReminder": "待提取的知识库名称id, 默认为default, 您需要构建知识库后再运行此插件。",
-                    "Function": HotReload(读取知识库作答),
-                }
-            }
-        )
-    except:
-        print(trimmed_format_exc())
-        print("Load function plugin failed")
-
-    try:
-        from crazy_functions.交互功能函数模板 import 交互功能模板函数
-
-        function_plugins.update(
-            {
-                "交互功能模板Demo函数（查找wallhaven.cc的壁纸）": {
-                    "Group": "对话",
-                    "Color": "stop",
-                    "AsButton": False,
-                    "Function": HotReload(交互功能模板函数),
-                }
-            }
-        )
-    except:
-        print(trimmed_format_exc())
-        print("Load function plugin failed")
-
-    try:
-        from crazy_functions.Latex输出PDF import Latex英文纠错加PDF对比
-        from crazy_functions.Latex输出PDF import Latex翻译中文并重新编译PDF
-        from crazy_functions.Latex输出PDF import PDF翻译中文并重新编译PDF
-
-        function_plugins.update(
-            {
         "Latex英文纠错+高亮修正位置 [需Latex]": {
             "Group": "学术",
             "Color": "stop",
@@ -546,7 +343,7 @@ def get_crazy_functions():
             "ArgsReminder": "如果有必要, 请在此处追加更细致的矫错指令（使用英文）。",
             "Function": HotReload(Latex英文纠错加PDF对比),
         },
-                "Arxiv论文精细翻译（输入arxivID）[需Latex]": {
+        "📚Arxiv论文精细翻译（输入arxivID）[需Latex]": {
             "Group": "学术",
             "Color": "stop",
             "AsButton": False,
@@ -555,9 +352,10 @@ def get_crazy_functions():
                             r"例如当单词'agent'翻译不准确时, 请尝试把以下指令复制到高级参数区: "
                             r'If the term "agent" is used in this section, it should be translated to "智能体". ',
             "Info": "Arixv论文精细翻译 | 输入参数arxiv论文的ID，比如1812.10695",
-                    "Function": HotReload(Latex翻译中文并重新编译PDF),
+            "Function": HotReload(Latex翻译中文并重新编译PDF),  # 当注册Class后，Function旧接口仅会在“虚空终端”中起作用
+            "Class": Arxiv_Localize,    # 新一代插件需要注册Class
         },
-                "本地Latex论文精细翻译（上传Latex项目）[需Latex]": {
+        "📚本地Latex论文精细翻译（上传Latex项目）[需Latex]": {
             "Group": "学术",
             "Color": "stop",
             "AsButton": False,
@@ -577,13 +375,247 @@ def get_crazy_functions():
                             r"例如当单词'agent'翻译不准确时, 请尝试把以下指令复制到高级参数区: "
                             r'If the term "agent" is used in this section, it should be translated to "智能体". ',
             "Info": "PDF翻译中文，并重新编译PDF | 输入参数为路径",
-                    "Function": HotReload(PDF翻译中文并重新编译PDF)
+            "Function": HotReload(PDF翻译中文并重新编译PDF),   # 当注册Class后，Function旧接口仅会在“虚空终端”中起作用
+            "Class": PDF_Localize   # 新一代插件需要注册Class
+        }
+    }
+
+    function_plugins.update(
+        {
+            "🎨图片生成（DALLE2/DALLE3, 使用前切换到GPT系列模型）": {
+                "Group": "对话",
+                "Color": "stop",
+                "AsButton": False,
+                "Info": "使用 DALLE2/DALLE3 生成图片 | 输入参数字符串，提供图像的内容",
+                "Function": HotReload(图片生成_DALLE2),   # 当注册Class后，Function旧接口仅会在“虚空终端”中起作用
+                "Class": ImageGen_Wrap  # 新一代插件需要注册Class
+            },
+        }
+    )
+
+    function_plugins.update(
+        {
+            "🎨图片修改_DALLE2 （使用前请切换模型到GPT系列）": {
+                "Group": "对话",
+                "Color": "stop",
+                "AsButton": False,
+                "AdvancedArgs": False,  # 调用时，唤起高级参数输入区（默认False）
+                # "Info": "使用DALLE2修改图片 | 输入参数字符串，提供图像的内容",
+                "Function": HotReload(图片修改_DALLE2),
+            },
+        }
+    )
+
+
+
+
+
+
+
+
+
+    # -=--=- 尚未充分测试的实验性插件 & 需要额外依赖的插件 -=--=-
+    try:
+        from crazy_functions.下载arxiv论文翻译摘要 import 下载arxiv论文并翻译摘要
+
+        function_plugins.update(
+            {
+                "一键下载arxiv论文并翻译摘要（先在input输入编号，如1812.10695）": {
+                    "Group": "学术",
+                    "Color": "stop",
+                    "AsButton": False,  # 加入下拉菜单中
+                    # "Info": "下载arxiv论文并翻译摘要 | 输入参数为arxiv编号如1812.10695",
+                    "Function": HotReload(下载arxiv论文并翻译摘要),
                 }
             }
         )
     except:
-        print(trimmed_format_exc())
-        print("Load function plugin failed")
+        logger.error(trimmed_format_exc())
+        logger.error("Load function plugin failed")
+
+    # try:
+    #     from crazy_functions.联网的ChatGPT import 连接网络回答问题
+
+    #     function_plugins.update(
+    #         {
+    #             "连接网络回答问题（输入问题后点击该插件，需要访问谷歌）": {
+    #                 "Group": "对话",
+    #                 "Color": "stop",
+    #                 "AsButton": False,  # 加入下拉菜单中
+    #                 # "Info": "连接网络回答问题（需要访问谷歌）| 输入参数是一个问题",
+    #                 "Function": HotReload(连接网络回答问题),
+    #             }
+    #         }
+    #     )
+    #     from crazy_functions.联网的ChatGPT_bing版 import 连接bing搜索回答问题
+
+    #     function_plugins.update(
+    #         {
+    #             "连接网络回答问题（中文Bing版，输入问题后点击该插件）": {
+    #                 "Group": "对话",
+    #                 "Color": "stop",
+    #                 "AsButton": False,  # 加入下拉菜单中
+    #                 "Info": "连接网络回答问题（需要访问中文Bing）| 输入参数是一个问题",
+    #                 "Function": HotReload(连接bing搜索回答问题),
+    #             }
+    #         }
+    #     )
+    # except:
+    #     logger.error(trimmed_format_exc())
+    #     logger.error("Load function plugin failed")
+
+    try:
+        from crazy_functions.SourceCode_Analyse import 解析任意code项目
+
+        function_plugins.update(
+            {
+                "解析项目源代码（手动指定和筛选源代码文件类型）": {
+                    "Group": "编程",
+                    "Color": "stop",
+                    "AsButton": False,
+                    "AdvancedArgs": True,  # 调用时，唤起高级参数输入区（默认False）
+                    "ArgsReminder": '输入时用逗号隔开, *代表通配符, 加了^代表不匹配; 不输入代表全部匹配。例如: "*.c, ^*.cpp, config.toml, ^*.toml"',  # 高级参数输入区的显示提示
+                    "Function": HotReload(解析任意code项目),
+                },
+            }
+        )
+    except:
+        logger.error(trimmed_format_exc())
+        logger.error("Load function plugin failed")
+
+    try:
+        from crazy_functions.询问多个大语言模型 import 同时问询_指定模型
+
+        function_plugins.update(
+            {
+                "询问多个GPT模型（手动指定询问哪些模型）": {
+                    "Group": "对话",
+                    "Color": "stop",
+                    "AsButton": False,
+                    "AdvancedArgs": True,  # 调用时，唤起高级参数输入区（默认False）
+                    "ArgsReminder": "支持任意数量的llm接口，用&符号分隔。例如chatglm&gpt-3.5-turbo&gpt-4",  # 高级参数输入区的显示提示
+                    "Function": HotReload(同时问询_指定模型),
+                },
+            }
+        )
+    except:
+        logger.error(trimmed_format_exc())
+        logger.error("Load function plugin failed")
+
+
+
+    try:
+        from crazy_functions.总结音视频 import 总结音视频
+
+        function_plugins.update(
+            {
+                "批量总结音视频（输入路径或上传压缩包）": {
+                    "Group": "对话",
+                    "Color": "stop",
+                    "AsButton": False,
+                    "AdvancedArgs": True,
+                    "ArgsReminder": "调用openai api 使用whisper-1模型, 目前支持的格式:mp4, m4a, wav, mpga, mpeg, mp3。此处可以输入解析提示，例如：解析为简体中文（默认）。",
+                    "Info": "批量总结音频或视频 | 输入参数为路径",
+                    "Function": HotReload(总结音视频),
+                }
+            }
+        )
+    except:
+        logger.error(trimmed_format_exc())
+        logger.error("Load function plugin failed")
+
+    try:
+        from crazy_functions.数学动画生成manim import 动画生成
+
+        function_plugins.update(
+            {
+                "数学动画生成（Manim）": {
+                    "Group": "对话",
+                    "Color": "stop",
+                    "AsButton": False,
+                    "Info": "按照自然语言描述生成一个动画 | 输入参数是一段话",
+                    "Function": HotReload(动画生成),
+                }
+            }
+        )
+    except:
+        logger.error(trimmed_format_exc())
+        logger.error("Load function plugin failed")
+
+    try:
+        from crazy_functions.Markdown_Translate import Markdown翻译指定语言
+
+        function_plugins.update(
+            {
+                "Markdown翻译（指定翻译成何种语言）": {
+                    "Group": "编程",
+                    "Color": "stop",
+                    "AsButton": False,
+                    "AdvancedArgs": True,
+                    "ArgsReminder": "请输入要翻译成哪种语言，默认为Chinese。",
+                    "Function": HotReload(Markdown翻译指定语言),
+                }
+            }
+        )
+    except:
+        logger.error(trimmed_format_exc())
+        logger.error("Load function plugin failed")
+
+    try:
+        from crazy_functions.知识库问答 import 知识库文件注入
+
+        function_plugins.update(
+            {
+                "构建知识库（先上传文件素材,再运行此插件）": {
+                    "Group": "对话",
+                    "Color": "stop",
+                    "AsButton": False,
+                    "AdvancedArgs": True,
+                    "ArgsReminder": "此处待注入的知识库名称id, 默认为default。文件进入知识库后可长期保存。可以通过再次调用本插件的方式，向知识库追加更多文档。",
+                    "Function": HotReload(知识库文件注入),
+                }
+            }
+        )
+    except:
+        logger.error(trimmed_format_exc())
+        logger.error("Load function plugin failed")
+
+    try:
+        from crazy_functions.知识库问答 import 读取知识库作答
+
+        function_plugins.update(
+            {
+                "知识库文件注入（构建知识库后,再运行此插件）": {
+                    "Group": "对话",
+                    "Color": "stop",
+                    "AsButton": False,
+                    "AdvancedArgs": True,
+                    "ArgsReminder": "待提取的知识库名称id, 默认为default, 您需要构建知识库后再运行此插件。",
+                    "Function": HotReload(读取知识库作答),
+                }
+            }
+        )
+    except:
+        logger.error(trimmed_format_exc())
+        logger.error("Load function plugin failed")
+
+    try:
+        from crazy_functions.交互功能函数模板 import 交互功能模板函数
+
+        function_plugins.update(
+            {
+                "交互功能模板Demo函数（查找wallhaven.cc的壁纸）": {
+                    "Group": "对话",
+                    "Color": "stop",
+                    "AsButton": False,
+                    "Function": HotReload(交互功能模板函数),
+                }
+            }
+        )
+    except:
+        logger.error(trimmed_format_exc())
+        logger.error("Load function plugin failed")
+
 
     try:
         from toolbox import get_conf
@@ -604,8 +636,8 @@ def get_crazy_functions():
                 }
             )
     except:
-        print(trimmed_format_exc())
-        print("Load function plugin failed")
+        logger.error(trimmed_format_exc())
+        logger.error("Load function plugin failed")
 
     try:
         from crazy_functions.批量翻译PDF文档_NOUGAT import 批量翻译PDF文档
@@ -621,8 +653,8 @@ def get_crazy_functions():
             }
         )
     except:
-        print(trimmed_format_exc())
-        print("Load function plugin failed")
+        logger.error(trimmed_format_exc())
+        logger.error("Load function plugin failed")
 
     try:
         from crazy_functions.函数动态生成 import 函数动态生成
@@ -638,8 +670,8 @@ def get_crazy_functions():
             }
         )
     except:
-        print(trimmed_format_exc())
-        print("Load function plugin failed")
+        logger.error(trimmed_format_exc())
+        logger.error("Load function plugin failed")
 
     try:
         from crazy_functions.多智能体 import 多智能体终端
@@ -655,8 +687,8 @@ def get_crazy_functions():
             }
         )
     except:
-        print(trimmed_format_exc())
-        print("Load function plugin failed")
+        logger.error(trimmed_format_exc())
+        logger.error("Load function plugin failed")
 
     try:
         from crazy_functions.互动小游戏 import 随机小游戏
@@ -672,8 +704,8 @@ def get_crazy_functions():
             }
         )
     except:
-        print(trimmed_format_exc())
-        print("Load function plugin failed")
+        logger.error(trimmed_format_exc())
+        logger.error("Load function plugin failed")
 
     # try:
     #     from crazy_functions.高级功能函数模板 import 测试图表渲染
@@ -686,7 +718,7 @@ def get_crazy_functions():
     #         }
     #     })
     # except:
-    #     print(trimmed_format_exc())
+    #     logger.error(trimmed_format_exc())
     #     print('Load function plugin failed')
 
     # try:

crazy_functions/Conversation_To_File.py

@@ -1,4 +1,5 @@
 from toolbox import CatchException, update_ui, promote_file_to_downloadzone, get_log_folder, get_user
+from crazy_functions.plugin_template.plugin_class_template import GptAcademicPluginTemplate, ArgProperty
 import re
 
 f_prefix = 'GPT-Academic对话存档'
@@ -9,27 +10,61 @@ def write_chat_to_file(chatbot, history=None, file_name=None):
     """
     import os
     import time
+    from themes.theme import advanced_css
+
     if file_name is None:
         file_name = f_prefix + time.strftime("%Y-%m-%d-%H-%M-%S", time.localtime()) + '.html'
     fp = os.path.join(get_log_folder(get_user(chatbot), plugin_name='chat_history'), file_name)
+
     with open(fp, 'w', encoding='utf8') as f:
-        from themes.theme import advanced_css
-        f.write(f'<!DOCTYPE html><head><meta charset="utf-8"><title>对话历史</title><style>{advanced_css}</style></head>')
+        from textwrap import dedent
+        form = dedent("""
+        <!DOCTYPE html><head><meta charset="utf-8"><title>对话存档</title><style>{CSS}</style></head>
+        <body>
+        <div class="test_temp1" style="width:10%; height: 500px; float:left;"></div>
+        <div class="test_temp2" style="width:80%;padding: 40px;float:left;padding-left: 20px;padding-right: 20px;box-shadow: rgba(0, 0, 0, 0.2) 0px 0px 8px 8px;border-radius: 10px;">
+            <div class="chat-body" style="display: flex;justify-content: center;flex-direction: column;align-items: center;flex-wrap: nowrap;">
+                {CHAT_PREVIEW}
+                <div></div>
+                <div></div>
+                <div style="text-align: center;width:80%;padding: 0px;float:left;padding-left:20px;padding-right:20px;box-shadow: rgba(0, 0, 0, 0.05) 0px 0px 1px 2px;border-radius: 1px;">对话（原始数据）</div>
+                {HISTORY_PREVIEW}
+            </div>
+        </div>
+        <div class="test_temp3" style="width:10%; height: 500px; float:left;"></div>
+        </body>
+        """)
+
+        qa_from = dedent("""
+        <div class="QaBox" style="width:80%;padding: 20px;margin-bottom: 20px;box-shadow: rgb(0 255 159 / 50%) 0px 0px 1px 2px;border-radius: 4px;">
+            <div class="Question" style="border-radius: 2px;">{QUESTION}</div>
+            <hr color="blue" style="border-top: dotted 2px #ccc;">
+            <div class="Answer" style="border-radius: 2px;">{ANSWER}</div>
+        </div>
+        """)
+
+        history_from = dedent("""
+        <div class="historyBox" style="width:80%;padding: 0px;float:left;padding-left:20px;padding-right:20px;box-shadow: rgba(0, 0, 0, 0.05) 0px 0px 1px 2px;border-radius: 1px;">
+            <div class="entry" style="border-radius: 2px;">{ENTRY}</div>
+        </div>
+        """)
+        CHAT_PREVIEW_BUF = ""
         for i, contents in enumerate(chatbot):
-            for j, content in enumerate(contents):
-                try:    # 这个bug没找到触发条件，暂时先这样顶一下
-                    if type(content) != str: content = str(content)
-                except:
-                    continue
-                f.write(content)
-                if j == 0:
-                    f.write('<hr style="border-top: dotted 3px #ccc;">')
-            f.write('<hr color="red"> \n\n')
-        f.write('<hr color="blue"> \n\n raw chat context:\n')
-        f.write('<code>')
+            question, answer = contents[0], contents[1]
+            if question is None: question = ""
+            try: question = str(question)
+            except: question = ""
+            if answer is None: answer = ""
+            try: answer = str(answer)
+            except: answer = ""
+            CHAT_PREVIEW_BUF += qa_from.format(QUESTION=question, ANSWER=answer)
+
+        HISTORY_PREVIEW_BUF = ""
         for h in history:
-            f.write("\n>>>" + h)
-        f.write('</code>')
+            HISTORY_PREVIEW_BUF += history_from.format(ENTRY=h)
+        html_content = form.format(CHAT_PREVIEW=CHAT_PREVIEW_BUF, HISTORY_PREVIEW=HISTORY_PREVIEW_BUF, CSS=advanced_css)
+        f.write(html_content)
+
     promote_file_to_downloadzone(fp, rename_file=file_name, chatbot=chatbot)
     return '对话历史写入：' + fp
 
@@ -40,7 +75,7 @@ def gen_file_preview(file_name):
         # pattern to match the text between <head> and </head>
         pattern = re.compile(r'<head>.*?</head>', flags=re.DOTALL)
         file_content = re.sub(pattern, '', file_content)
-        html, history = file_content.split('<hr color="blue"> \n\n raw chat context:\n')
+        html, history = file_content.split('<hr color="blue"> \n\n 对话数据 (无渲染):\n')
         history = history.strip('<code>')
         history = history.strip('</code>')
         history = history.split("\n>>>")
@@ -51,21 +86,25 @@ def gen_file_preview(file_name):
 def read_file_to_chat(chatbot, history, file_name):
     with open(file_name, 'r', encoding='utf8') as f:
         file_content = f.read()
-    # pattern to match the text between <head> and </head>
-    pattern = re.compile(r'<head>.*?</head>', flags=re.DOTALL)
-    file_content = re.sub(pattern, '', file_content)
-    html, history = file_content.split('<hr color="blue"> \n\n raw chat context:\n')
-    history = history.strip('<code>')
-    history = history.strip('</code>')
-    history = history.split("\n>>>")
-    history = list(filter(lambda x:x!="", history))
-    html = html.split('<hr color="red"> \n\n')
-    html = list(filter(lambda x:x!="", html))
+    from bs4 import BeautifulSoup
+    soup = BeautifulSoup(file_content, 'lxml')
+    # 提取QaBox信息
     chatbot.clear()
-    for i, h in enumerate(html):
-        i_say, gpt_say = h.split('<hr style="border-top: dotted 3px #ccc;">')
-        chatbot.append([i_say, gpt_say])
-    chatbot.append([f"存档文件详情？", f"[Local Message] 载入对话{len(html)}条，上下文{len(history)}条。"])
+    qa_box_list = []
+    qa_boxes = soup.find_all("div", class_="QaBox")
+    for box in qa_boxes:
+        question = box.find("div", class_="Question").get_text(strip=False)
+        answer = box.find("div", class_="Answer").get_text(strip=False)
+        qa_box_list.append({"Question": question, "Answer": answer})
+        chatbot.append([question, answer])
+    # 提取historyBox信息
+    history_box_list = []
+    history_boxes = soup.find_all("div", class_="historyBox")
+    for box in history_boxes:
+        entry = box.find("div", class_="entry").get_text(strip=False)
+        history_box_list.append(entry)
+    history = history_box_list
+    chatbot.append([None, f"[Local Message] 载入对话{len(qa_box_list)}条，上下文{len(history)}条。"])
     return chatbot, history
 
 @CatchException
@@ -79,11 +118,42 @@ def 对话历史存档(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_
     system_prompt   给gpt的静默提醒
     user_request    当前用户的请求信息（IP地址等）
     """
+    file_name = plugin_kwargs.get("file_name", None)
+    if (file_name is not None) and (file_name != "") and (not file_name.endswith('.html')): file_name += '.html'
+    else: file_name = None
 
-    chatbot.append(("保存当前对话",
-        f"[Local Message] {write_chat_to_file(chatbot, history)}，您可以调用下拉菜单中的“载入对话历史存档”还原当下的对话。"))
+    chatbot.append((None, f"[Local Message] {write_chat_to_file(chatbot, history, file_name)}，您可以调用下拉菜单中的“载入对话历史存档”还原当下的对话。"))
     yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 由于请求gpt需要一段时间，我们先及时地做一次界面更新
 
+
+class Conversation_To_File_Wrap(GptAcademicPluginTemplate):
+    def __init__(self):
+        """
+        请注意`execute`会执行在不同的线程中，因此您在定义和使用类变量时，应当慎之又慎！
+        """
+        pass
+
+    def define_arg_selection_menu(self):
+        """
+        定义插件的二级选项菜单
+
+        第一个参数，名称`file_name`，参数`type`声明这是一个文本框，文本框上方显示`title`，文本框内部显示`description`，`default_value`为默认值；
+        """
+        gui_definition = {
+            "file_name": ArgProperty(title="保存文件名", description="输入对话存档文件名，留空则使用时间作为文件名", default_value="", type="string").model_dump_json(), # 主输入，自动从输入框同步
+        }
+        return gui_definition
+
+    def execute(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
+        """
+        执行插件
+        """
+        yield from 对话历史存档(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request)
+
+
+
+
+
 def hide_cwd(str):
     import os
     current_path = os.getcwd()
@@ -101,7 +171,7 @@ def 载入对话历史存档(txt, llm_kwargs, plugin_kwargs, chatbot, history, s
     system_prompt   给gpt的静默提醒
     user_request    当前用户的请求信息（IP地址等）
     """
-    from .crazy_utils import get_files_from_everything
+    from crazy_functions.crazy_utils import get_files_from_everything
     success, file_manifest, _ = get_files_from_everything(txt, type='.html')
 
     if not success:
@@ -148,5 +218,3 @@ def 删除所有本地对话历史记录(txt, llm_kwargs, plugin_kwargs, chatbot
     chatbot.append([f"删除所有历史对话文件", f"已删除<br/>{local_history}"])
     yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
     return
-
-

crazy_functions/Image_Generate.py

@@ -30,7 +30,7 @@ def gen_image(llm_kwargs, prompt, resolution="1024x1024", model="dall-e-2", qual
     if style is not None:
         data['style'] = style
     response = requests.post(url, headers=headers, json=data, proxies=proxies)
-    print(response.content)
+    # logger.info(response.content)
     try:
         image_url = json.loads(response.content.decode('utf8'))['data'][0]['url']
     except:
@@ -76,7 +76,7 @@ def edit_image(llm_kwargs, prompt, image_path, resolution="1024x1024", model="da
         }
 
     response = requests.post(url, headers=headers, files=files, proxies=proxies)
-    print(response.content)
+    # logger.info(response.content)
     try:
         image_url = json.loads(response.content.decode('utf8'))['data'][0]['url']
     except:
@@ -108,7 +108,7 @@ def 图片生成_DALLE2(prompt, llm_kwargs, plugin_kwargs, chatbot, history, sys
         chatbot.append((prompt, "[Local Message] 图像生成提示为空白，请在“输入区”输入图像生成提示。"))
         yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 界面更新
         return
-    chatbot.append(("您正在调用“图像生成”插件。", "[Local Message] 生成图像, 请先把模型切换至gpt-*。如果中文Prompt效果不理想, 请尝试英文Prompt。正在处理中 ....."))
+    chatbot.append(("您正在调用“图像生成”插件。", "[Local Message] 生成图像, 使用前请切换模型到GPT系列。如果中文Prompt效果不理想, 请尝试英文Prompt。正在处理中 ....."))
     yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 由于请求gpt需要一段时间,我们先及时地做一次界面更新
     if ("advanced_arg" in plugin_kwargs) and (plugin_kwargs["advanced_arg"] == ""): plugin_kwargs.pop("advanced_arg")
     resolution = plugin_kwargs.get("advanced_arg", '1024x1024')
@@ -129,7 +129,7 @@ def 图片生成_DALLE3(prompt, llm_kwargs, plugin_kwargs, chatbot, history, sys
         chatbot.append((prompt, "[Local Message] 图像生成提示为空白，请在“输入区”输入图像生成提示。"))
         yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 界面更新
         return
-    chatbot.append(("您正在调用“图像生成”插件。", "[Local Message] 生成图像, 请先把模型切换至gpt-*。如果中文Prompt效果不理想, 请尝试英文Prompt。正在处理中 ....."))
+    chatbot.append(("您正在调用“图像生成”插件。", "[Local Message] 生成图像, 使用前请切换模型到GPT系列。如果中文Prompt效果不理想, 请尝试英文Prompt。正在处理中 ....."))
     yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 由于请求gpt需要一段时间,我们先及时地做一次界面更新
     if ("advanced_arg" in plugin_kwargs) and (plugin_kwargs["advanced_arg"] == ""): plugin_kwargs.pop("advanced_arg")
     resolution_arg = plugin_kwargs.get("advanced_arg", '1024x1024-standard-vivid').lower()
@@ -166,7 +166,7 @@ class ImageEditState(GptAcademicState):
         return confirm, file
 
     def lock_plugin(self, chatbot):
-        chatbot._cookies['lock_plugin'] = 'crazy_functions.图片生成->图片修改_DALLE2'
+        chatbot._cookies['lock_plugin'] = 'crazy_functions.Image_Generate->图片修改_DALLE2'
         self.dump_state(chatbot)
 
     def unlock_plugin(self, chatbot):

crazy_functions/Image_Generate_Wrap.py

@@ -0,0 +1,56 @@
+
+from toolbox import get_conf, update_ui
+from crazy_functions.Image_Generate import 图片生成_DALLE2, 图片生成_DALLE3, 图片修改_DALLE2
+from crazy_functions.plugin_template.plugin_class_template import GptAcademicPluginTemplate, ArgProperty
+
+
+class ImageGen_Wrap(GptAcademicPluginTemplate):
+    def __init__(self):
+        """
+        请注意`execute`会执行在不同的线程中，因此您在定义和使用类变量时，应当慎之又慎！
+        """
+        pass
+
+    def define_arg_selection_menu(self):
+        """
+        定义插件的二级选项菜单
+
+        第一个参数，名称`main_input`，参数`type`声明这是一个文本框，文本框上方显示`title`，文本框内部显示`description`，`default_value`为默认值；
+        第二个参数，名称`advanced_arg`，参数`type`声明这是一个文本框，文本框上方显示`title`，文本框内部显示`description`，`default_value`为默认值；
+
+        """
+        gui_definition = {
+            "main_input":
+                ArgProperty(title="输入图片描述", description="需要生成图像的文本描述，尽量使用英文", default_value="", type="string").model_dump_json(), # 主输入，自动从输入框同步
+            "model_name":
+                ArgProperty(title="模型", options=["DALLE2", "DALLE3"], default_value="DALLE3", description="无", type="dropdown").model_dump_json(),
+            "resolution":
+                ArgProperty(title="分辨率", options=["256x256(限DALLE2)", "512x512(限DALLE2)", "1024x1024", "1792x1024(限DALLE3)", "1024x1792(限DALLE3)"], default_value="1024x1024", description="无", type="dropdown").model_dump_json(),
+            "quality (仅DALLE3生效)":
+                ArgProperty(title="质量", options=["standard", "hd"], default_value="standard", description="无", type="dropdown").model_dump_json(),
+            "style (仅DALLE3生效)":
+                ArgProperty(title="风格", options=["vivid", "natural"], default_value="vivid", description="无", type="dropdown").model_dump_json(),
+
+        }
+        return gui_definition
+
+    def execute(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
+        """
+        执行插件
+        """
+        # 分辨率
+        resolution = plugin_kwargs["resolution"].replace("(限DALLE2)", "").replace("(限DALLE3)", "")
+
+        if plugin_kwargs["model_name"] == "DALLE2":
+            plugin_kwargs["advanced_arg"] = resolution
+            yield from 图片生成_DALLE2(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request)
+
+        elif plugin_kwargs["model_name"] == "DALLE3":
+            quality = plugin_kwargs["quality (仅DALLE3生效)"]
+            style = plugin_kwargs["style (仅DALLE3生效)"]
+            plugin_kwargs["advanced_arg"] = f"{resolution}-{quality}-{style}"
+            yield from 图片生成_DALLE3(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request)
+
+        else:
+            chatbot.append([None, "抱歉，找不到该模型"])
+            yield from update_ui(chatbot=chatbot, history=history) # 刷新界面

crazy_functions/Internet_GPT.py

@@ -0,0 +1,278 @@
+import requests
+import random
+import time
+import re
+import json
+from bs4 import BeautifulSoup
+from functools import lru_cache
+from itertools import zip_longest
+from check_proxy import check_proxy
+from toolbox import CatchException, update_ui, get_conf
+from crazy_functions.crazy_utils import request_gpt_model_in_new_thread_with_ui_alive, input_clipping
+from request_llms.bridge_all import model_info
+from request_llms.bridge_all import predict_no_ui_long_connection
+from crazy_functions.prompts.internet import SearchOptimizerPrompt, SearchAcademicOptimizerPrompt
+
+def search_optimizer(
+    query,
+    proxies,
+    history,
+    llm_kwargs,
+    optimizer=1,
+    categories="general",
+    searxng_url=None,
+    engines=None,
+):
+    # ------------- < 第1步：尝试进行搜索优化 > -------------
+    # * 增强优化，会尝试结合历史记录进行搜索优化
+    if optimizer == 2:
+        his = " "
+        if len(history) == 0:
+            pass
+        else:
+            for i, h in enumerate(history):
+                if i % 2 == 0:
+                    his += f"Q: {h}\n"
+                else:
+                    his += f"A: {h}\n"
+        if categories == "general":
+            sys_prompt = SearchOptimizerPrompt.format(query=query, history=his, num=4)
+        elif categories == "science":
+            sys_prompt = SearchAcademicOptimizerPrompt.format(query=query, history=his, num=4)
+    else:
+        his = " "
+        if categories == "general":
+            sys_prompt = SearchOptimizerPrompt.format(query=query, history=his, num=3)
+        elif categories == "science":
+            sys_prompt = SearchAcademicOptimizerPrompt.format(query=query, history=his, num=3)
+    
+    mutable = ["", time.time(), ""]
+    llm_kwargs["temperature"] = 0.8
+    try:
+        querys_json = predict_no_ui_long_connection(
+            inputs=query,
+            llm_kwargs=llm_kwargs,
+            history=[],
+            sys_prompt=sys_prompt,
+            observe_window=mutable,
+        )
+    except Exception:
+        querys_json = "1234"
+    #* 尝试解码优化后的搜索结果
+    querys_json = re.sub(r"```json|```", "", querys_json)
+    try:
+        querys = json.loads(querys_json)
+    except Exception:
+        #* 如果解码失败,降低温度再试一次
+        try:
+            llm_kwargs["temperature"] = 0.4
+            querys_json = predict_no_ui_long_connection(
+                inputs=query,
+                llm_kwargs=llm_kwargs,
+                history=[],
+                sys_prompt=sys_prompt,
+                observe_window=mutable,
+            )
+            querys_json = re.sub(r"```json|```", "", querys_json)
+            querys = json.loads(querys_json)
+        except Exception:
+            #* 如果再次失败，直接返回原始问题
+            querys = [query]
+    links = []
+    success = 0
+    Exceptions = ""
+    for q in querys:
+        try:
+            link = searxng_request(q, proxies, categories, searxng_url, engines=engines)
+            if len(link) > 0:
+                links.append(link[:-5])
+                success += 1
+        except Exception:
+            Exceptions = Exception
+            pass
+    if success == 0:
+        raise ValueError(f"在线搜索失败！\n{Exceptions}")
+    # * 清洗搜索结果，依次放入每组第一，第二个搜索结果，并清洗重复的搜索结果
+    seen_links = set()
+    result = []
+    for tuple in zip_longest(*links, fillvalue=None):
+        for item in tuple:
+            if item is not None:
+                link = item["link"]
+                if link not in seen_links:
+                    seen_links.add(link)
+                    result.append(item)
+    return result
+
+
+@lru_cache
+def get_auth_ip():
+    ip = check_proxy(None, return_ip=True)
+    if ip is None:
+        return '114.114.114.' + str(random.randint(1, 10))
+    return ip
+
+
+def searxng_request(query, proxies, categories='general', searxng_url=None, engines=None):
+    if searxng_url is None:
+        url = get_conf("SEARXNG_URL")
+    else:
+        url = searxng_url
+
+    if engines == "Mixed":
+        engines = None
+
+    if categories == 'general':
+        params = {
+            'q': query,         # 搜索查询
+            'format': 'json',   # 输出格式为JSON
+            'language': 'zh',   # 搜索语言
+            'engines': engines,
+        }
+    elif categories == 'science':
+        params = {
+            'q': query,         # 搜索查询
+            'format': 'json',   # 输出格式为JSON
+            'language': 'zh',   # 搜索语言
+            'categories': 'science'
+        }
+    else:
+        raise ValueError('不支持的检索类型')
+
+    headers = {
+        'Accept-Language': 'zh-CN,zh;q=0.9',
+        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.36',
+        'X-Forwarded-For': get_auth_ip(),
+        'X-Real-IP': get_auth_ip()
+    }
+    results = []
+    response = requests.post(url, params=params, headers=headers, proxies=proxies, timeout=30)
+    if response.status_code == 200:
+        json_result = response.json()
+        for result in json_result['results']:
+            item = {
+                "title": result.get("title", ""),
+                "source": result.get("engines", "unknown"),
+                "content": result.get("content", ""),
+                "link": result["url"],
+            }
+            results.append(item)
+        return results
+    else:
+        if response.status_code == 429:
+            raise ValueError("Searxng（在线搜索服务）当前使用人数太多，请稍后。")
+        else:
+            raise ValueError("在线搜索失败，状态码: " + str(response.status_code) + '\t' + response.content.decode('utf-8'))
+
+
+def scrape_text(url, proxies) -> str:
+    """Scrape text from a webpage
+
+    Args:
+        url (str): The URL to scrape text from
+
+    Returns:
+        str: The scraped text
+    """
+    headers = {
+        'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/94.0.4606.61 Safari/537.36',
+        'Content-Type': 'text/plain',
+    }
+    try:
+        response = requests.get(url, headers=headers, proxies=proxies, timeout=8)
+        if response.encoding == "ISO-8859-1": response.encoding = response.apparent_encoding
+    except:
+        return "无法连接到该网页"
+    soup = BeautifulSoup(response.text, "html.parser")
+    for script in soup(["script", "style"]):
+        script.extract()
+    text = soup.get_text()
+    lines = (line.strip() for line in text.splitlines())
+    chunks = (phrase.strip() for line in lines for phrase in line.split("  "))
+    text = "\n".join(chunk for chunk in chunks if chunk)
+    return text
+
+
+@CatchException
+def 连接网络回答问题(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
+    optimizer_history = history[:-8]
+    history = []    # 清空历史，以免输入溢出
+    chatbot.append((f"请结合互联网信息回答以下问题：{txt}", "检索中..."))
+    yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+
+    # ------------- < 第1步：爬取搜索引擎的结果 > -------------
+    from toolbox import get_conf
+    proxies = get_conf('proxies')
+    categories = plugin_kwargs.get('categories', 'general')
+    searxng_url = plugin_kwargs.get('searxng_url', None)
+    engines = plugin_kwargs.get('engine', None)
+    optimizer = plugin_kwargs.get('optimizer', "关闭")
+    if optimizer == "关闭":
+        urls = searxng_request(txt, proxies, categories, searxng_url, engines=engines)
+    else:
+        urls = search_optimizer(txt, proxies, optimizer_history, llm_kwargs, optimizer, categories, searxng_url, engines)
+    history = []
+    if len(urls) == 0:
+        chatbot.append((f"结论：{txt}",
+                        "[Local Message] 受到限制，无法从searxng获取信息！请尝试更换搜索引擎。"))
+        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+        return
+
+    # ------------- < 第2步：依次访问网页 > -------------
+    max_search_result = 5   # 最多收纳多少个网页的结果
+    if optimizer == "开启(增强)":
+        max_search_result = 8
+    chatbot.append(["联网检索中 ...", None])
+    for index, url in enumerate(urls[:max_search_result]):
+        res = scrape_text(url['link'], proxies)
+        prefix = f"第{index}份搜索结果 [源自{url['source'][0]}搜索] （{url['title'][:25]}）："
+        history.extend([prefix, res])
+        res_squeeze = res.replace('\n', '...')
+        chatbot[-1] = [prefix + "\n\n" + res_squeeze[:500] + "......", None]
+        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+
+    # ------------- < 第3步：ChatGPT综合 > -------------
+    if (optimizer != "开启(增强)"):
+        i_say = f"从以上搜索结果中抽取信息，然后回答问题：{txt}"
+        i_say, history = input_clipping(    # 裁剪输入，从最长的条目开始裁剪，防止爆token
+            inputs=i_say,
+            history=history,
+            max_token_limit=min(model_info[llm_kwargs['llm_model']]['max_token']*3//4, 8192)
+        )
+        gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
+            inputs=i_say, inputs_show_user=i_say,
+            llm_kwargs=llm_kwargs, chatbot=chatbot, history=history,
+            sys_prompt="请从给定的若干条搜索结果中抽取信息，对最相关的两个搜索结果进行总结，然后回答问题。"
+        )
+        chatbot[-1] = (i_say, gpt_say)
+        history.append(i_say);history.append(gpt_say)
+        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 界面更新
+
+    #* 或者使用搜索优化器，这样可以保证后续问答能读取到有效的历史记录
+    else:
+        i_say = f"从以上搜索结果中抽取与问题：{txt} 相关的信息:"
+        i_say, history = input_clipping(    # 裁剪输入，从最长的条目开始裁剪，防止爆token
+            inputs=i_say,
+            history=history,
+            max_token_limit=min(model_info[llm_kwargs['llm_model']]['max_token']*3//4, 8192)
+        )
+        gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
+            inputs=i_say, inputs_show_user=i_say,
+            llm_kwargs=llm_kwargs, chatbot=chatbot, history=history,
+            sys_prompt="请从给定的若干条搜索结果中抽取信息，对最相关的三个搜索结果进行总结"
+        )
+        chatbot[-1] = (i_say, gpt_say)
+        history = []
+        history.append(i_say);history.append(gpt_say)
+        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 界面更新
+
+        # ------------- < 第4步：根据综合回答问题 > -------------
+        i_say = f"请根据以上搜索结果回答问题：{txt}"
+        gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
+            inputs=i_say, inputs_show_user=i_say,
+            llm_kwargs=llm_kwargs, chatbot=chatbot, history=history,
+            sys_prompt="请根据给定的若干条搜索结果回答问题"
+        )
+        chatbot[-1] = (i_say, gpt_say)
+        history.append(i_say);history.append(gpt_say)
+        yield from update_ui(chatbot=chatbot, history=history)

crazy_functions/Internet_GPT_Wrap.py

@@ -0,0 +1,45 @@
+
+from toolbox import get_conf
+from crazy_functions.Internet_GPT import 连接网络回答问题
+from crazy_functions.plugin_template.plugin_class_template import GptAcademicPluginTemplate, ArgProperty
+
+
+class NetworkGPT_Wrap(GptAcademicPluginTemplate):
+    def __init__(self):
+        """
+        请注意`execute`会执行在不同的线程中，因此您在定义和使用类变量时，应当慎之又慎！
+        """
+        pass
+
+    def define_arg_selection_menu(self):
+        """
+        定义插件的二级选项菜单
+
+        第一个参数，名称`main_input`，参数`type`声明这是一个文本框，文本框上方显示`title`，文本框内部显示`description`，`default_value`为默认值；
+        第二个参数，名称`advanced_arg`，参数`type`声明这是一个文本框，文本框上方显示`title`，文本框内部显示`description`，`default_value`为默认值；
+        第三个参数，名称`allow_cache`，参数`type`声明这是一个下拉菜单，下拉菜单上方显示`title`+`description`，下拉菜单的选项为`options`，`default_value`为下拉菜单默认值；
+
+        """
+        gui_definition = {
+            "main_input":
+                ArgProperty(title="输入问题", description="待通过互联网检索的问题，会自动读取输入框内容", default_value="", type="string").model_dump_json(), # 主输入，自动从输入框同步
+            "categories":
+                ArgProperty(title="搜索分类", options=["网页", "学术论文"], default_value="网页", description="无", type="dropdown").model_dump_json(),
+            "engine":
+                ArgProperty(title="选择搜索引擎", options=["Mixed", "bing", "google", "duckduckgo"], default_value="google", description="无", type="dropdown").model_dump_json(),
+            "optimizer":
+                ArgProperty(title="搜索优化", options=["关闭", "开启", "开启(增强)"], default_value="关闭", description="是否使用搜索增强。注意这可能会消耗较多token", type="dropdown").model_dump_json(),
+            "searxng_url":
+                ArgProperty(title="Searxng服务地址", description="输入Searxng的地址", default_value=get_conf("SEARXNG_URL"), type="string").model_dump_json(), # 主输入，自动从输入框同步
+
+        }
+        return gui_definition
+
+    def execute(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
+        """
+        执行插件
+        """
+        if plugin_kwargs["categories"] == "网页": plugin_kwargs["categories"] = "general"
+        if plugin_kwargs["categories"] == "学术论文": plugin_kwargs["categories"] = "science"
+        yield from 连接网络回答问题(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request)
+

crazy_functions/Latex_Function.py

@@ -1,10 +1,12 @@
 from toolbox import update_ui, trimmed_format_exc, get_conf, get_log_folder, promote_file_to_downloadzone, check_repeat_upload, map_file_to_sha256
 from toolbox import CatchException, report_exception, update_ui_lastest_msg, zip_result, gen_time_str
 from functools import partial
+from loguru import logger
+
 import glob, os, requests, time, json, tarfile
 
 pj = os.path.join
-ARXIV_CACHE_DIR = os.path.expanduser(f"~/arxiv_cache/")
+ARXIV_CACHE_DIR = get_conf("ARXIV_CACHE_DIR")
 
 
 # =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=- 工具函数 =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-
@@ -158,7 +160,8 @@ def arxiv_download(chatbot, history, txt, allow_cache=True):
     return extract_dst, arxiv_id
 
 
-def pdf2tex_project(pdf_file_path):
+def pdf2tex_project(pdf_file_path, plugin_kwargs):
+    if plugin_kwargs["method"] == "MATHPIX":
         # Mathpix API credentials
         app_id, app_key = get_conf('MATHPIX_APPID', 'MATHPIX_APPKEY')
         headers = {"app_id": app_id, "app_key": app_key}
@@ -177,7 +180,7 @@ def pdf2tex_project(pdf_file_path):
 
         if response.ok:
             pdf_id = response.json()["pdf_id"]
-        print(f"PDF processing initiated. PDF ID: {pdf_id}")
+            logger.info(f"PDF processing initiated. PDF ID: {pdf_id}")
 
             # Step 2: Check processing status
             while True:
@@ -185,12 +188,12 @@ def pdf2tex_project(pdf_file_path):
                 conversion_data = conversion_response.json()
 
                 if conversion_data["status"] == "completed":
-                print("PDF processing completed.")
+                    logger.info("PDF processing completed.")
                     break
                 elif conversion_data["status"] == "error":
-                print("Error occurred during processing.")
+                    logger.info("Error occurred during processing.")
                 else:
-                print(f"Processing status: {conversion_data['status']}")
+                    logger.info(f"Processing status: {conversion_data['status']}")
                     time.sleep(5)  # wait for a few seconds before checking again
 
             # Step 3: Save results to local files
@@ -205,7 +208,7 @@ def pdf2tex_project(pdf_file_path):
             output_path = os.path.join(output_dir, output_name)
             with open(output_path, "wb") as output_file:
                 output_file.write(response.content)
-        print(f"tex.zip file saved at: {output_path}")
+            logger.info(f"tex.zip file saved at: {output_path}")
 
             import zipfile
             unzip_dir = os.path.join(output_dir, file_name_wo_dot)
@@ -215,8 +218,14 @@ def pdf2tex_project(pdf_file_path):
             return unzip_dir
 
         else:
-        print(f"Error sending PDF for processing. Status code: {response.status_code}")
+            logger.error(f"Error sending PDF for processing. Status code: {response.status_code}")
             return None
+    else:
+        from crazy_functions.pdf_fns.parse_pdf_via_doc2x import 解析PDF_DOC2X_转Latex
+        unzip_dir = 解析PDF_DOC2X_转Latex(pdf_file_path)
+        return unzip_dir
+
+
 
 
 # =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-= 插件主程序1 =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
@@ -226,7 +235,7 @@ def pdf2tex_project(pdf_file_path):
 def Latex英文纠错加PDF对比(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
     # <-------------- information about this plugin ------------->
     chatbot.append(["函数插件功能？",
-                    "对整个Latex项目进行纠错, 用latex编译为PDF对修正处做高亮。函数插件贡献者: Binary-Husky。注意事项: 目前仅支持GPT3.5/GPT4，其他模型转化效果未知。目前对机器学习类文献转化效果最好，其他类型文献转化效果未知。仅在Windows系统进行了测试，其他操作系统表现未知。"])
+                    "对整个Latex项目进行纠错, 用latex编译为PDF对修正处做高亮。函数插件贡献者: Binary-Husky。注意事项: 目前对机器学习类文献转化效果最好，其他类型文献转化效果未知。仅在Windows系统进行了测试，其他操作系统表现未知。"])
     yield from update_ui(chatbot=chatbot, history=history)  # 刷新界面
 
     # <-------------- more requirements ------------->
@@ -264,6 +273,8 @@ def Latex英文纠错加PDF对比(txt, llm_kwargs, plugin_kwargs, chatbot, histo
     project_folder = desend_to_extracted_folder_if_exist(project_folder)
 
     # <-------------- move latex project away from temp folder ------------->
+    from shared_utils.fastapi_server import validate_path_safety
+    validate_path_safety(project_folder, chatbot.get_user())
     project_folder = move_project(project_folder, arxiv_id=None)
 
     # <-------------- if merge_translate_zh is already generated, skip gpt req ------------->
@@ -287,7 +298,7 @@ def Latex英文纠错加PDF对比(txt, llm_kwargs, plugin_kwargs, chatbot, histo
         promote_file_to_downloadzone(file=zip_res, chatbot=chatbot)
     else:
         chatbot.append((f"失败了",
-                        '虽然PDF生成失败了, 但请查收结果（压缩包）, 内含已经翻译的Tex文档, 也是可读的, 您可以到Github Issue区, 用该压缩包+对话历史存档进行反馈 ...'))
+                        '虽然PDF生成失败了, 但请查收结果（压缩包）, 内含已经翻译的Tex文档, 也是可读的, 您可以到Github Issue区, 用该压缩包+Conversation_To_File进行反馈 ...'))
         yield from update_ui(chatbot=chatbot, history=history);
         time.sleep(1)  # 刷新界面
         promote_file_to_downloadzone(file=zip_res, chatbot=chatbot)
@@ -303,7 +314,7 @@ def Latex翻译中文并重新编译PDF(txt, llm_kwargs, plugin_kwargs, chatbot,
     # <-------------- information about this plugin ------------->
     chatbot.append([
         "函数插件功能？",
-        "对整个Latex项目进行翻译, 生成中文PDF。函数插件贡献者: Binary-Husky。注意事项: 此插件Windows支持最佳，Linux下必须使用Docker安装，详见项目主README.md。目前仅支持GPT3.5/GPT4，其他模型转化效果未知。目前对机器学习类文献转化效果最好，其他类型文献转化效果未知。"])
+        "对整个Latex项目进行翻译, 生成中文PDF。函数插件贡献者: Binary-Husky。注意事项: 此插件Windows支持最佳，Linux下必须使用Docker安装，详见项目主README.md。目前对机器学习类文献转化效果最好，其他类型文献转化效果未知。"])
     yield from update_ui(chatbot=chatbot, history=history)  # 刷新界面
 
     # <-------------- more requirements ------------->
@@ -358,6 +369,8 @@ def Latex翻译中文并重新编译PDF(txt, llm_kwargs, plugin_kwargs, chatbot,
     project_folder = desend_to_extracted_folder_if_exist(project_folder)
 
     # <-------------- move latex project away from temp folder ------------->
+    from shared_utils.fastapi_server import validate_path_safety
+    validate_path_safety(project_folder, chatbot.get_user())
     project_folder = move_project(project_folder, arxiv_id)
 
     # <-------------- if merge_translate_zh is already generated, skip gpt req ------------->
@@ -397,7 +410,7 @@ def PDF翻译中文并重新编译PDF(txt, llm_kwargs, plugin_kwargs, chatbot, h
     # <-------------- information about this plugin ------------->
     chatbot.append([
         "函数插件功能？",
-        "将PDF转换为Latex项目，翻译为中文后重新编译为PDF。函数插件贡献者: Marroh。注意事项: 此插件Windows支持最佳，Linux下必须使用Docker安装，详见项目主README.md。目前仅支持GPT3.5/GPT4，其他模型转化效果未知。目前对机器学习类文献转化效果最好，其他类型文献转化效果未知。"])
+        "将PDF转换为Latex项目，翻译为中文后重新编译为PDF。函数插件贡献者: Marroh。注意事项: 此插件Windows支持最佳，Linux下必须使用Docker安装，详见项目主README.md。目前对机器学习类文献转化效果最好，其他类型文献转化效果未知。"])
     yield from update_ui(chatbot=chatbot, history=history)  # 刷新界面
 
     # <-------------- more requirements ------------->
@@ -437,56 +450,48 @@ def PDF翻译中文并重新编译PDF(txt, llm_kwargs, plugin_kwargs, chatbot, h
         report_exception(chatbot, history, a=f"解析项目: {txt}", b=f"不支持同时处理多个pdf文件: {txt}")
         yield from update_ui(chatbot=chatbot, history=history)  # 刷新界面
         return
+
+    if plugin_kwargs.get("method", "") == 'MATHPIX':
         app_id, app_key = get_conf('MATHPIX_APPID', 'MATHPIX_APPKEY')
         if len(app_id) == 0 or len(app_key) == 0:
             report_exception(chatbot, history, a="缺失 MATHPIX_APPID 和 MATHPIX_APPKEY。", b=f"请配置 MATHPIX_APPID 和 MATHPIX_APPKEY")
             yield from update_ui(chatbot=chatbot, history=history)  # 刷新界面
             return
+    if plugin_kwargs.get("method", "") == 'DOC2X':
+        app_id, app_key = "", ""
+        DOC2X_API_KEY = get_conf('DOC2X_API_KEY')
+        if len(DOC2X_API_KEY) == 0:
+            report_exception(chatbot, history, a="缺失 DOC2X_API_KEY。", b=f"请配置 DOC2X_API_KEY")
+            yield from update_ui(chatbot=chatbot, history=history)  # 刷新界面
+            return
 
     hash_tag = map_file_to_sha256(file_manifest[0])
 
-    # <-------------- check repeated pdf ------------->
-    chatbot.append([f"检查PDF是否被重复上传", "正在检查..."])
-    yield from update_ui(chatbot=chatbot, history=history)
-    repeat, project_folder = check_repeat_upload(file_manifest[0], hash_tag)
+    # # <-------------- check repeated pdf ------------->
+    # chatbot.append([f"检查PDF是否被重复上传", "正在检查..."])
+    # yield from update_ui(chatbot=chatbot, history=history)
+    # repeat, project_folder = check_repeat_upload(file_manifest[0], hash_tag)
 
-    except_flag = False
-
-    if repeat:
-        yield from update_ui_lastest_msg(f"发现重复上传，请查收结果（压缩包）...", chatbot=chatbot, history=history)
-
-        try:
-            trans_html_file = [f for f in glob.glob(f'{project_folder}/**/*.trans.html', recursive=True)][0]
-            promote_file_to_downloadzone(trans_html_file, rename_file=None, chatbot=chatbot)
-
-            translate_pdf = [f for f in glob.glob(f'{project_folder}/**/merge_translate_zh.pdf', recursive=True)][0]
-            promote_file_to_downloadzone(translate_pdf, rename_file=None, chatbot=chatbot)
-
-            comparison_pdf = [f for f in glob.glob(f'{project_folder}/**/comparison.pdf', recursive=True)][0]
-            promote_file_to_downloadzone(comparison_pdf, rename_file=None, chatbot=chatbot)
-
-            zip_res = zip_result(project_folder)
-            promote_file_to_downloadzone(file=zip_res, chatbot=chatbot)
-
-            return True
-
-        except:
-            report_exception(chatbot, history, a=f"解析项目: {txt}", b=f"发现重复上传，但是无法找到相关文件")
-            yield from update_ui(chatbot=chatbot, history=history)
-
-            chatbot.append([f"没有相关文件", '尝试重新翻译PDF...'])
-            yield from update_ui(chatbot=chatbot, history=history)
-
-            except_flag = True
-
-
-    elif not repeat or except_flag:
-        yield from update_ui_lastest_msg(f"未发现重复上传", chatbot=chatbot, history=history)
+    # if repeat:
+    #     yield from update_ui_lastest_msg(f"发现重复上传，请查收结果（压缩包）...", chatbot=chatbot, history=history)
+    #     try:
+    #         translate_pdf = [f for f in glob.glob(f'{project_folder}/**/merge_translate_zh.pdf', recursive=True)][0]
+    #         promote_file_to_downloadzone(translate_pdf, rename_file=None, chatbot=chatbot)
+    #         comparison_pdf = [f for f in glob.glob(f'{project_folder}/**/comparison.pdf', recursive=True)][0]
+    #         promote_file_to_downloadzone(comparison_pdf, rename_file=None, chatbot=chatbot)
+    #         zip_res = zip_result(project_folder)
+    #         promote_file_to_downloadzone(file=zip_res, chatbot=chatbot)
+    #         return
+    #     except:
+    #         report_exception(chatbot, history, a=f"解析项目: {txt}", b=f"发现重复上传，但是无法找到相关文件")
+    #         yield from update_ui(chatbot=chatbot, history=history)
+    # else:
+    #     yield from update_ui_lastest_msg(f"未发现重复上传", chatbot=chatbot, history=history)
 
     # <-------------- convert pdf into tex ------------->
     chatbot.append([f"解析项目: {txt}", "正在将PDF转换为tex项目，请耐心等待..."])
     yield from update_ui(chatbot=chatbot, history=history)
-        project_folder = pdf2tex_project(file_manifest[0])
+    project_folder = pdf2tex_project(file_manifest[0], plugin_kwargs)
     if project_folder is None:
         report_exception(chatbot, history, a=f"解析项目: {txt}", b=f"PDF转换为tex项目失败")
         yield from update_ui(chatbot=chatbot, history=history)
@@ -504,6 +509,8 @@ def PDF翻译中文并重新编译PDF(txt, llm_kwargs, plugin_kwargs, chatbot, h
     project_folder = desend_to_extracted_folder_if_exist(project_folder)
 
     # <-------------- move latex project away from temp folder ------------->
+    from shared_utils.fastapi_server import validate_path_safety
+    validate_path_safety(project_folder, chatbot.get_user())
     project_folder = move_project(project_folder)
 
     # <-------------- set a hash tag for repeat-checking ------------->

crazy_functions/Latex_Function_Wrap.py

@@ -0,0 +1,78 @@
+
+from crazy_functions.Latex_Function import Latex翻译中文并重新编译PDF, PDF翻译中文并重新编译PDF
+from crazy_functions.plugin_template.plugin_class_template import GptAcademicPluginTemplate, ArgProperty
+
+
+class Arxiv_Localize(GptAcademicPluginTemplate):
+    def __init__(self):
+        """
+        请注意`execute`会执行在不同的线程中，因此您在定义和使用类变量时，应当慎之又慎！
+        """
+        pass
+
+    def define_arg_selection_menu(self):
+        """
+        定义插件的二级选项菜单
+
+        第一个参数，名称`main_input`，参数`type`声明这是一个文本框，文本框上方显示`title`，文本框内部显示`description`，`default_value`为默认值；
+        第二个参数，名称`advanced_arg`，参数`type`声明这是一个文本框，文本框上方显示`title`，文本框内部显示`description`，`default_value`为默认值；
+        第三个参数，名称`allow_cache`，参数`type`声明这是一个下拉菜单，下拉菜单上方显示`title`+`description`，下拉菜单的选项为`options`，`default_value`为下拉菜单默认值；
+
+        """
+        gui_definition = {
+            "main_input":
+                ArgProperty(title="ArxivID", description="输入Arxiv的ID或者网址", default_value="", type="string").model_dump_json(), # 主输入，自动从输入框同步
+            "advanced_arg":
+                ArgProperty(title="额外的翻译提示词",
+                            description=r"如果有必要, 请在此处给出自定义翻译命令, 解决部分词汇翻译不准确的问题。 "
+                                        r"例如当单词'agent'翻译不准确时, 请尝试把以下指令复制到高级参数区: "
+                                        r'If the term "agent" is used in this section, it should be translated to "智能体". ',
+                            default_value="", type="string").model_dump_json(), # 高级参数输入区，自动同步
+            "allow_cache":
+                ArgProperty(title="是否允许从缓存中调取结果", options=["允许缓存", "从头执行"], default_value="允许缓存", description="无", type="dropdown").model_dump_json(),
+        }
+        return gui_definition
+
+    def execute(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
+        """
+        执行插件
+        """
+        allow_cache = plugin_kwargs["allow_cache"]
+        advanced_arg = plugin_kwargs["advanced_arg"]
+
+        if allow_cache == "从头执行": plugin_kwargs["advanced_arg"] = "--no-cache " + plugin_kwargs["advanced_arg"]
+        yield from Latex翻译中文并重新编译PDF(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request)
+
+
+
+class PDF_Localize(GptAcademicPluginTemplate):
+    def __init__(self):
+        """
+        请注意`execute`会执行在不同的线程中，因此您在定义和使用类变量时，应当慎之又慎！
+        """
+        pass
+
+    def define_arg_selection_menu(self):
+        """
+        定义插件的二级选项菜单
+        """
+        gui_definition = {
+            "main_input":
+                ArgProperty(title="PDF文件路径", description="未指定路径，请上传文件后，再点击该插件", default_value="", type="string").model_dump_json(), # 主输入，自动从输入框同步
+            "advanced_arg":
+                ArgProperty(title="额外的翻译提示词",
+                            description=r"如果有必要, 请在此处给出自定义翻译命令, 解决部分词汇翻译不准确的问题。 "
+                                        r"例如当单词'agent'翻译不准确时, 请尝试把以下指令复制到高级参数区: "
+                                        r'If the term "agent" is used in this section, it should be translated to "智能体". ',
+                            default_value="", type="string").model_dump_json(), # 高级参数输入区，自动同步
+            "method":
+                ArgProperty(title="采用哪种方法执行转换", options=["MATHPIX", "DOC2X"], default_value="DOC2X", description="无", type="dropdown").model_dump_json(),
+
+        }
+        return gui_definition
+
+    def execute(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
+        """
+        执行插件
+        """
+        yield from PDF翻译中文并重新编译PDF(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request)

crazy_functions/Latex全文润色.py

@@ -1,6 +1,6 @@
 from toolbox import update_ui, trimmed_format_exc, promote_file_to_downloadzone, get_log_folder
 from toolbox import CatchException, report_exception, write_history_to_file, zip_folder
-
+from loguru import logger
 
 class PaperFileGroup():
     def __init__(self):
@@ -33,7 +33,7 @@ class PaperFileGroup():
                     self.sp_file_index.append(index)
                     self.sp_file_tag.append(self.file_paths[index] + f".part-{j}.tex")
 
-        print('Segmentation: done')
+        logger.info('Segmentation: done')
     def merge_result(self):
         self.file_result = ["" for _ in range(len(self.file_paths))]
         for r, k in zip(self.sp_file_result, self.sp_file_index):
@@ -56,7 +56,7 @@ class PaperFileGroup():
 
 def 多文件润色(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, language='en', mode='polish'):
     import time, os, re
-    from .crazy_utils import request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency
+    from crazy_functions.crazy_utils import request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency
 
 
     #  <-------- 读取Latex文件，删除其中的所有注释 ---------->
@@ -122,7 +122,7 @@ def 多文件润色(file_manifest, project_folder, llm_kwargs, plugin_kwargs, ch
         pfg.write_result()
         pfg.zip_result()
     except:
-        print(trimmed_format_exc())
+        logger.error(trimmed_format_exc())
 
     #  <-------- 整理结果，退出 ---------->
     create_report_file_name = time.strftime("%Y-%m-%d-%H-%M-%S", time.localtime()) + f"-chatgpt.polish.md"

crazy_functions/Latex全文翻译.py

@@ -1,6 +1,6 @@
 from toolbox import update_ui, promote_file_to_downloadzone
 from toolbox import CatchException, report_exception, write_history_to_file
-fast_debug = False
+from loguru import logger
 
 class PaperFileGroup():
     def __init__(self):
@@ -33,11 +33,11 @@ class PaperFileGroup():
                     self.sp_file_index.append(index)
                     self.sp_file_tag.append(self.file_paths[index] + f".part-{j}.tex")
 
-        print('Segmentation: done')
+        logger.info('Segmentation: done')
 
 def 多文件翻译(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, language='en'):
     import time, os, re
-    from .crazy_utils import request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency
+    from crazy_functions.crazy_utils import request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency
 
     #  <-------- 读取Latex文件，删除其中的所有注释 ---------->
     pfg = PaperFileGroup()

crazy_functions/Markdown_Translate.py

@@ -1,4 +1,5 @@
-import glob, shutil, os, re, logging
+import glob, shutil, os, re
+from loguru import logger
 from toolbox import update_ui, trimmed_format_exc, gen_time_str
 from toolbox import CatchException, report_exception, get_log_folder
 from toolbox import write_history_to_file, promote_file_to_downloadzone
@@ -34,7 +35,7 @@ class PaperFileGroup():
                     self.sp_file_contents.append(segment)
                     self.sp_file_index.append(index)
                     self.sp_file_tag.append(self.file_paths[index] + f".part-{j}.md")
-        logging.info('Segmentation: done')
+        logger.info('Segmentation: done')
 
     def merge_result(self):
         self.file_result = ["" for _ in range(len(self.file_paths))]
@@ -51,7 +52,7 @@ class PaperFileGroup():
         return manifest
 
 def 多文件翻译(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, language='en'):
-    from .crazy_utils import request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency
+    from crazy_functions.crazy_utils import request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency
 
     #  <-------- 读取Markdown文件，删除其中的所有注释 ---------->
     pfg = PaperFileGroup()
@@ -72,17 +73,17 @@ def 多文件翻译(file_manifest, project_folder, llm_kwargs, plugin_kwargs, ch
         inputs_array = ["This is a Markdown file, translate it into Chinese, do NOT modify any existing Markdown commands, do NOT use code wrapper (```), ONLY answer me with translated results:" +
                         f"\n\n{frag}" for frag in pfg.sp_file_contents]
         inputs_show_user_array = [f"翻译 {f}" for f in pfg.sp_file_tag]
-        sys_prompt_array = ["You are a professional academic paper translator." for _ in range(n_split)]
+        sys_prompt_array = ["You are a professional academic paper translator." + plugin_kwargs.get("additional_prompt", "") for _ in range(n_split)]
     elif language == 'zh->en':
         inputs_array = [f"This is a Markdown file, translate it into English, do NOT modify any existing Markdown commands, do NOT use code wrapper (```), ONLY answer me with translated results:" +
                         f"\n\n{frag}" for frag in pfg.sp_file_contents]
         inputs_show_user_array = [f"翻译 {f}" for f in pfg.sp_file_tag]
-        sys_prompt_array = ["You are a professional academic paper translator." for _ in range(n_split)]
+        sys_prompt_array = ["You are a professional academic paper translator." + plugin_kwargs.get("additional_prompt", "") for _ in range(n_split)]
     else:
         inputs_array = [f"This is a Markdown file, translate it into {language}, do NOT modify any existing Markdown commands, do NOT use code wrapper (```), ONLY answer me with translated results:" +
                         f"\n\n{frag}" for frag in pfg.sp_file_contents]
         inputs_show_user_array = [f"翻译 {f}" for f in pfg.sp_file_tag]
-        sys_prompt_array = ["You are a professional academic paper translator." for _ in range(n_split)]
+        sys_prompt_array = ["You are a professional academic paper translator." + plugin_kwargs.get("additional_prompt", "") for _ in range(n_split)]
 
     gpt_response_collection = yield from request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
         inputs_array=inputs_array,
@@ -106,7 +107,7 @@ def 多文件翻译(file_manifest, project_folder, llm_kwargs, plugin_kwargs, ch
                 expected_f_name = plugin_kwargs['markdown_expected_output_path']
                 shutil.copyfile(output_file, expected_f_name)
     except:
-        logging.error(trimmed_format_exc())
+        logger.error(trimmed_format_exc())
 
     #  <-------- 整理结果，退出 ---------->
     create_report_file_name = gen_time_str() + f"-chatgpt.md"
@@ -126,7 +127,7 @@ def get_files_from_everything(txt, preference=''):
         proxies = get_conf('proxies')
         # 网络的远程文件
         if preference == 'Github':
-            logging.info('正在从github下载资源 ...')
+            logger.info('正在从github下载资源 ...')
             if not txt.endswith('.md'):
                 # Make a request to the GitHub API to retrieve the repository information
                 url = txt.replace("https://github.com/", "https://api.github.com/repos/") + '/readme'

crazy_functions/PDF_Translate.py

@@ -0,0 +1,83 @@
+from toolbox import CatchException, check_packages, get_conf
+from toolbox import update_ui, update_ui_lastest_msg, disable_auto_promotion
+from toolbox import trimmed_format_exc_markdown
+from crazy_functions.crazy_utils import get_files_from_everything
+from crazy_functions.pdf_fns.parse_pdf import get_avail_grobid_url
+from crazy_functions.pdf_fns.parse_pdf_via_doc2x import 解析PDF_基于DOC2X
+from crazy_functions.pdf_fns.parse_pdf_legacy import 解析PDF_简单拆解
+from crazy_functions.pdf_fns.parse_pdf_grobid import 解析PDF_基于GROBID
+from shared_utils.colorful import *
+
+@CatchException
+def 批量翻译PDF文档(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
+
+    disable_auto_promotion(chatbot)
+    # 基本信息：功能、贡献者
+    chatbot.append([None, "插件功能：批量翻译PDF文档。函数插件贡献者: Binary-Husky"])
+    yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+
+    # 尝试导入依赖，如果缺少依赖，则给出安装建议
+    try:
+        check_packages(["fitz", "tiktoken", "scipdf"])
+    except:
+        chatbot.append([None, f"导入软件依赖失败。使用该模块需要额外依赖，安装方法```pip install --upgrade pymupdf tiktoken scipdf_parser```。"])
+        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+        return
+
+    # 清空历史，以免输入溢出
+    history = []
+    success, file_manifest, project_folder = get_files_from_everything(txt, type='.pdf')
+
+    # 检测输入参数，如没有给定输入参数，直接退出
+    if (not success) and txt == "": txt = '空空如也的输入栏。提示：请先上传文件（把PDF文件拖入对话）。'
+
+    # 如果没找到任何文件
+    if len(file_manifest) == 0:
+        chatbot.append([None, f"找不到任何.pdf拓展名的文件: {txt}"])
+        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+        return
+
+    # 开始正式执行任务
+    method = plugin_kwargs.get("pdf_parse_method", None)
+    if method == "DOC2X":
+        # ------- 第一种方法，效果最好，但是需要DOC2X服务 -------
+        DOC2X_API_KEY = get_conf("DOC2X_API_KEY")
+        if len(DOC2X_API_KEY) != 0:
+            try:
+                yield from 解析PDF_基于DOC2X(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, DOC2X_API_KEY, user_request)
+                return
+            except:
+                chatbot.append([None, f"DOC2X服务不可用，现在将执行效果稍差的旧版代码。{trimmed_format_exc_markdown()}"])
+                yield from update_ui(chatbot=chatbot, history=history)
+
+    if method == "GROBID":
+        # ------- 第二种方法，效果次优 -------
+        grobid_url = get_avail_grobid_url()
+        if grobid_url is not None:
+            yield from 解析PDF_基于GROBID(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, grobid_url)
+            return
+
+    if method == "ClASSIC":
+        # ------- 第三种方法，早期代码，效果不理想 -------
+        yield from update_ui_lastest_msg("GROBID服务不可用，请检查config中的GROBID_URL。作为替代，现在将执行效果稍差的旧版代码。", chatbot, history, delay=3)
+        yield from 解析PDF_简单拆解(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt)
+        return
+
+    if method is None:
+        # ------- 以上三种方法都试一遍 -------
+        DOC2X_API_KEY = get_conf("DOC2X_API_KEY")
+        if len(DOC2X_API_KEY) != 0:
+            try:
+                yield from 解析PDF_基于DOC2X(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, DOC2X_API_KEY, user_request)
+                return
+            except:
+                chatbot.append([None, f"DOC2X服务不可用，正在尝试GROBID。{trimmed_format_exc_markdown()}"])
+                yield from update_ui(chatbot=chatbot, history=history)
+        grobid_url = get_avail_grobid_url()
+        if grobid_url is not None:
+            yield from 解析PDF_基于GROBID(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, grobid_url)
+            return
+        yield from update_ui_lastest_msg("GROBID服务不可用，请检查config中的GROBID_URL。作为替代，现在将执行效果稍差的旧版代码。", chatbot, history, delay=3)
+        yield from 解析PDF_简单拆解(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt)
+        return
+

crazy_functions/PDF_Translate_Wrap.py

@@ -0,0 +1,33 @@
+from crazy_functions.plugin_template.plugin_class_template import GptAcademicPluginTemplate, ArgProperty
+from .PDF_Translate import 批量翻译PDF文档
+
+
+class PDF_Tran(GptAcademicPluginTemplate):
+    def __init__(self):
+        """
+        请注意`execute`会执行在不同的线程中，因此您在定义和使用类变量时，应当慎之又慎！
+        """
+        pass
+
+    def define_arg_selection_menu(self):
+        """
+        定义插件的二级选项菜单
+        """
+        gui_definition = {
+            "main_input":
+                ArgProperty(title="PDF文件路径", description="未指定路径，请上传文件后，再点击该插件", default_value="", type="string").model_dump_json(), # 主输入，自动从输入框同步
+            "additional_prompt":
+                ArgProperty(title="额外提示词", description="例如：对专有名词、翻译语气等方面的要求", default_value="", type="string").model_dump_json(), # 高级参数输入区，自动同步
+            "pdf_parse_method":
+                ArgProperty(title="PDF解析方法", options=["DOC2X", "GROBID", "ClASSIC"], description="无", default_value="GROBID", type="dropdown").model_dump_json(),
+        }
+        return gui_definition
+
+    def execute(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
+        """
+        执行插件
+        """
+        main_input = plugin_kwargs["main_input"]
+        additional_prompt = plugin_kwargs["additional_prompt"]
+        pdf_parse_method = plugin_kwargs["pdf_parse_method"]
+        yield from 批量翻译PDF文档(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request)

crazy_functions/PDF批量翻译.py

@@ -1,324 +0,0 @@
-from toolbox import CatchException, report_exception, get_log_folder, gen_time_str, check_packages
-from toolbox import update_ui, promote_file_to_downloadzone, update_ui_lastest_msg, disable_auto_promotion
-from toolbox import write_history_to_file, promote_file_to_downloadzone, get_conf, extract_archive
-from toolbox import generate_file_link, zip_folder, trimmed_format_exc, trimmed_format_exc_markdown
-from .crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
-from .crazy_utils import request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency
-from .crazy_utils import read_and_clean_pdf_text
-from .crazy_utils import get_files_from_everything
-from .pdf_fns.parse_pdf import parse_pdf, get_avail_grobid_url, translate_pdf
-from colorful import *
-import os
-
-
-@CatchException
-def 批量翻译PDF文档(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
-
-    disable_auto_promotion(chatbot)
-    # 基本信息：功能、贡献者
-    chatbot.append([None, "插件功能：批量翻译PDF文档。函数插件贡献者: Binary-Husky"])
-    yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
-
-    # 尝试导入依赖，如果缺少依赖，则给出安装建议
-    try:
-        check_packages(["fitz", "tiktoken", "scipdf"])
-    except:
-        report_exception(chatbot, history,
-                         a=f"解析项目: {txt}",
-                         b=f"导入软件依赖失败。使用该模块需要额外依赖，安装方法```pip install --upgrade pymupdf tiktoken scipdf_parser```。")
-        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
-        return
-
-    # 清空历史，以免输入溢出
-    history = []
-
-    success, file_manifest, project_folder = get_files_from_everything(txt, type='.pdf')
-    # 检测输入参数，如没有给定输入参数，直接退出
-    if not success:
-        if txt == "": txt = '空空如也的输入栏'
-
-    # 如果没找到任何文件
-    if len(file_manifest) == 0:
-        report_exception(chatbot, history,
-                         a=f"解析项目: {txt}", b=f"找不到任何.pdf拓展名的文件: {txt}")
-        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
-        return
-
-    # 开始正式执行任务
-    DOC2X_API_KEY = get_conf("DOC2X_API_KEY")
-    # ------- 第一种方法，效果最好，但是需要DOC2X服务 -------
-    if len(DOC2X_API_KEY) != 0:
-        try:
-            yield from 解析PDF_DOC2X(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, DOC2X_API_KEY, user_request)
-            return
-        except:
-            chatbot.append([None, f"DOC2X服务不可用，现在将执行效果稍差的旧版代码。{trimmed_format_exc_markdown()}"])
-            yield from update_ui(chatbot=chatbot, history=history)
-
-    # ------- 第二种方法，效果次优 -------
-    grobid_url = get_avail_grobid_url()
-    if grobid_url is not None:
-        yield from 解析PDF_基于GROBID(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, grobid_url)
-        return
-
-    # ------- 第三种方法，早期代码，效果不理想 -------
-    yield from update_ui_lastest_msg("GROBID服务不可用，请检查config中的GROBID_URL。作为替代，现在将执行效果稍差的旧版代码。", chatbot, history, delay=3)
-    yield from 解析PDF(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt)
-    return
-
-
-
-def 解析PDF_DOC2X_单文件(fp, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, DOC2X_API_KEY, user_request):
-
-    def pdf2markdown(filepath):
-        import requests, json, os
-        markdown_dir = get_log_folder(plugin_name="pdf_ocr")
-        doc2x_api_key = DOC2X_API_KEY
-        if doc2x_api_key.startswith('sk-'):
-            url = "https://api.doc2x.noedgeai.com/api/v1/pdf"
-        else:
-            url = "https://api.doc2x.noedgeai.com/api/platform/pdf"
-
-        chatbot.append((None, "加载PDF文件，发送至DOC2X解析..."))
-        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
-
-        res = requests.post(
-            url,
-            files={"file": open(filepath, "rb")},
-            data={"ocr": "1"},
-            headers={"Authorization": "Bearer " + doc2x_api_key}
-        )
-        res_json = []
-        if res.status_code == 200:
-            decoded = res.content.decode("utf-8")
-            for z_decoded in decoded.split('\n'):
-                if len(z_decoded) == 0: continue
-                assert z_decoded.startswith("data: ")
-                z_decoded = z_decoded[len("data: "):]
-                decoded_json = json.loads(z_decoded)
-                res_json.append(decoded_json)
-        else:
-            raise RuntimeError(format("[ERROR] status code: %d, body: %s" % (res.status_code, res.text)))
-        uuid = res_json[0]['uuid']
-        to = "md" # latex, md, docx
-        url = "https://api.doc2x.noedgeai.com/api/export"+"?request_id="+uuid+"&to="+to
-
-        chatbot.append((None, f"读取解析: {url} ..."))
-        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
-
-        res = requests.get(url, headers={"Authorization": "Bearer " + doc2x_api_key})
-        md_zip_path = os.path.join(markdown_dir, gen_time_str() + '.zip')
-        if res.status_code == 200:
-            with open(md_zip_path, "wb") as f: f.write(res.content)
-        else:
-            raise RuntimeError(format("[ERROR] status code: %d, body: %s" % (res.status_code, res.text)))
-        promote_file_to_downloadzone(md_zip_path, chatbot=chatbot)
-        chatbot.append((None, f"完成解析 {md_zip_path} ..."))
-        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
-        return md_zip_path
-
-    def deliver_to_markdown_plugin(md_zip_path, user_request):
-        from crazy_functions.批量Markdown翻译 import Markdown英译中
-        import shutil, re
-
-        time_tag = gen_time_str()
-        target_path_base = get_log_folder(chatbot.get_user())
-        file_origin_name = os.path.basename(md_zip_path)
-        this_file_path = os.path.join(target_path_base, file_origin_name)
-        os.makedirs(target_path_base, exist_ok=True)
-        shutil.copyfile(md_zip_path, this_file_path)
-        ex_folder = this_file_path + ".extract"
-        extract_archive(
-            file_path=this_file_path, dest_dir=ex_folder
-        )
-
-        # edit markdown files
-        success, file_manifest, project_folder = get_files_from_everything(ex_folder, type='.md')
-        for generated_fp in file_manifest:
-            # 修正一些公式问题
-            with open(generated_fp, 'r', encoding='utf8') as f:
-                content = f.read()
-            # 将公式中的\[ \]替换成$$
-            content = content.replace(r'\[', r'$$').replace(r'\]', r'$$')
-            # 将公式中的\( \)替换成$
-            content = content.replace(r'\(', r'$').replace(r'\)', r'$')
-            content = content.replace('```markdown', '\n').replace('```', '\n')
-            with open(generated_fp, 'w', encoding='utf8') as f:
-                f.write(content)
-            promote_file_to_downloadzone(generated_fp, chatbot=chatbot)
-            yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
-
-            # 生成在线预览html
-            file_name = '在线预览翻译（原文）' + gen_time_str() + '.html'
-            preview_fp = os.path.join(ex_folder, file_name)
-            from shared_utils.advanced_markdown_format import markdown_convertion_for_file
-            with open(generated_fp, "r", encoding="utf-8") as f:
-                md = f.read()
-                # Markdown中使用不标准的表格，需要在表格前加上一个emoji，以便公式渲染
-                md = re.sub(r'^<table>', r'😃<table>', md, flags=re.MULTILINE)
-            html = markdown_convertion_for_file(md)
-            with open(preview_fp, "w", encoding="utf-8") as f: f.write(html)
-            chatbot.append([None, f"生成在线预览：{generate_file_link([preview_fp])}"])
-            promote_file_to_downloadzone(preview_fp, chatbot=chatbot)
-
-
-
-        chatbot.append((None, f"调用Markdown插件 {ex_folder} ..."))
-        plugin_kwargs['markdown_expected_output_dir'] = ex_folder
-
-        translated_f_name = 'translated_markdown.md'
-        generated_fp = plugin_kwargs['markdown_expected_output_path'] = os.path.join(ex_folder, translated_f_name)
-        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
-        yield from Markdown英译中(ex_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request)
-        if os.path.exists(generated_fp):
-            # 修正一些公式问题
-            with open(generated_fp, 'r', encoding='utf8') as f: content = f.read()
-            content = content.replace('```markdown', '\n').replace('```', '\n')
-            # Markdown中使用不标准的表格，需要在表格前加上一个emoji，以便公式渲染
-            content = re.sub(r'^<table>', r'😃<table>', content, flags=re.MULTILINE)
-            with open(generated_fp, 'w', encoding='utf8') as f: f.write(content)
-            # 生成在线预览html
-            file_name = '在线预览翻译' + gen_time_str() + '.html'
-            preview_fp = os.path.join(ex_folder, file_name)
-            from shared_utils.advanced_markdown_format import markdown_convertion_for_file
-            with open(generated_fp, "r", encoding="utf-8") as f:
-                md = f.read()
-            html = markdown_convertion_for_file(md)
-            with open(preview_fp, "w", encoding="utf-8") as f: f.write(html)
-            promote_file_to_downloadzone(preview_fp, chatbot=chatbot)
-            # 生成包含图片的压缩包
-            dest_folder = get_log_folder(chatbot.get_user())
-            zip_name = '翻译后的带图文档.zip'
-            zip_folder(source_folder=ex_folder, dest_folder=dest_folder, zip_name=zip_name)
-            zip_fp = os.path.join(dest_folder, zip_name)
-            promote_file_to_downloadzone(zip_fp, chatbot=chatbot)
-            yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
-    md_zip_path = yield from pdf2markdown(fp)
-    yield from deliver_to_markdown_plugin(md_zip_path, user_request)
-
-def 解析PDF_DOC2X(file_manifest, *args):
-    for index, fp in enumerate(file_manifest):
-        yield from 解析PDF_DOC2X_单文件(fp, *args)
-    return
-
-def 解析PDF_基于GROBID(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, grobid_url):
-    import copy, json
-    TOKEN_LIMIT_PER_FRAGMENT = 1024
-    generated_conclusion_files = []
-    generated_html_files = []
-    DST_LANG = "中文"
-    from crazy_functions.pdf_fns.report_gen_html import construct_html
-    for index, fp in enumerate(file_manifest):
-        chatbot.append(["当前进度：", f"正在连接GROBID服务，请稍候: {grobid_url}\n如果等待时间过长，请修改config中的GROBID_URL，可修改成本地GROBID服务。"]); yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
-        article_dict = parse_pdf(fp, grobid_url)
-        grobid_json_res = os.path.join(get_log_folder(), gen_time_str() + "grobid.json")
-        with open(grobid_json_res, 'w+', encoding='utf8') as f:
-            f.write(json.dumps(article_dict, indent=4, ensure_ascii=False))
-        promote_file_to_downloadzone(grobid_json_res, chatbot=chatbot)
-
-        if article_dict is None: raise RuntimeError("解析PDF失败，请检查PDF是否损坏。")
-        yield from translate_pdf(article_dict, llm_kwargs, chatbot, fp, generated_conclusion_files, TOKEN_LIMIT_PER_FRAGMENT, DST_LANG)
-    chatbot.append(("给出输出文件清单", str(generated_conclusion_files + generated_html_files)))
-    yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
-
-
-def 解析PDF(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt):
-    """
-    此函数已经弃用
-    """
-    import copy
-    TOKEN_LIMIT_PER_FRAGMENT = 1024
-    generated_conclusion_files = []
-    generated_html_files = []
-    from crazy_functions.pdf_fns.report_gen_html import construct_html
-    for index, fp in enumerate(file_manifest):
-        # 读取PDF文件
-        file_content, page_one = read_and_clean_pdf_text(fp)
-        file_content = file_content.encode('utf-8', 'ignore').decode()   # avoid reading non-utf8 chars
-        page_one = str(page_one).encode('utf-8', 'ignore').decode()      # avoid reading non-utf8 chars
-
-        # 递归地切割PDF文件
-        from crazy_functions.pdf_fns.breakdown_txt import breakdown_text_to_satisfy_token_limit
-        paper_fragments = breakdown_text_to_satisfy_token_limit(txt=file_content, limit=TOKEN_LIMIT_PER_FRAGMENT, llm_model=llm_kwargs['llm_model'])
-        page_one_fragments = breakdown_text_to_satisfy_token_limit(txt=page_one, limit=TOKEN_LIMIT_PER_FRAGMENT//4, llm_model=llm_kwargs['llm_model'])
-
-        # 为了更好的效果，我们剥离Introduction之后的部分（如果有）
-        paper_meta = page_one_fragments[0].split('introduction')[0].split('Introduction')[0].split('INTRODUCTION')[0]
-
-        # 单线，获取文章meta信息
-        paper_meta_info = yield from request_gpt_model_in_new_thread_with_ui_alive(
-            inputs=f"以下是一篇学术论文的基础信息，请从中提取出“标题”、“收录会议或期刊”、“作者”、“摘要”、“编号”、“作者邮箱”这六个部分。请用markdown格式输出，最后用中文翻译摘要部分。请提取：{paper_meta}",
-            inputs_show_user=f"请从{fp}中提取出“标题”、“收录会议或期刊”等基本信息。",
-            llm_kwargs=llm_kwargs,
-            chatbot=chatbot, history=[],
-            sys_prompt="Your job is to collect information from materials。",
-        )
-
-        # 多线，翻译
-        gpt_response_collection = yield from request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
-            inputs_array=[
-                f"你需要翻译以下内容：\n{frag}" for frag in paper_fragments],
-            inputs_show_user_array=[f"\n---\n 原文： \n\n {frag.replace('#', '')}  \n---\n 翻译：\n " for frag in paper_fragments],
-            llm_kwargs=llm_kwargs,
-            chatbot=chatbot,
-            history_array=[[paper_meta] for _ in paper_fragments],
-            sys_prompt_array=[
-                "请你作为一个学术翻译，负责把学术论文准确翻译成中文。注意文章中的每一句话都要翻译。" for _ in paper_fragments],
-            # max_workers=5  # OpenAI所允许的最大并行过载
-        )
-        gpt_response_collection_md = copy.deepcopy(gpt_response_collection)
-        # 整理报告的格式
-        for i,k in enumerate(gpt_response_collection_md):
-            if i%2==0:
-                gpt_response_collection_md[i] = f"\n\n---\n\n ## 原文[{i//2}/{len(gpt_response_collection_md)//2}]： \n\n {paper_fragments[i//2].replace('#', '')}  \n\n---\n\n ## 翻译[{i//2}/{len(gpt_response_collection_md)//2}]：\n "
-            else:
-                gpt_response_collection_md[i] = gpt_response_collection_md[i]
-        final = ["一、论文概况\n\n---\n\n", paper_meta_info.replace('# ', '### ') + '\n\n---\n\n', "二、论文翻译", ""]
-        final.extend(gpt_response_collection_md)
-        create_report_file_name = f"{os.path.basename(fp)}.trans.md"
-        res = write_history_to_file(final, create_report_file_name)
-        promote_file_to_downloadzone(res, chatbot=chatbot)
-
-        # 更新UI
-        generated_conclusion_files.append(f'{get_log_folder()}/{create_report_file_name}')
-        chatbot.append((f"{fp}完成了吗？", res))
-        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
-
-        # write html
-        try:
-            ch = construct_html()
-            orig = ""
-            trans = ""
-            gpt_response_collection_html = copy.deepcopy(gpt_response_collection)
-            for i,k in enumerate(gpt_response_collection_html):
-                if i%2==0:
-                    gpt_response_collection_html[i] = paper_fragments[i//2].replace('#', '')
-                else:
-                    gpt_response_collection_html[i] = gpt_response_collection_html[i]
-            final = ["论文概况", paper_meta_info.replace('# ', '### '),  "二、论文翻译",  ""]
-            final.extend(gpt_response_collection_html)
-            for i, k in enumerate(final):
-                if i%2==0:
-                    orig = k
-                if i%2==1:
-                    trans = k
-                    ch.add_row(a=orig, b=trans)
-            create_report_file_name = f"{os.path.basename(fp)}.trans.html"
-            generated_html_files.append(ch.save_file(create_report_file_name))
-        except:
-            from toolbox import trimmed_format_exc
-            print('writing html result failed:', trimmed_format_exc())
-
-    # 准备文件的下载
-    for pdf_path in generated_conclusion_files:
-        # 重命名文件
-        rename_file = f'翻译-{os.path.basename(pdf_path)}'
-        promote_file_to_downloadzone(pdf_path, rename_file=rename_file, chatbot=chatbot)
-    for html_path in generated_html_files:
-        # 重命名文件
-        rename_file = f'翻译-{os.path.basename(html_path)}'
-        promote_file_to_downloadzone(html_path, rename_file=rename_file, chatbot=chatbot)
-    chatbot.append(("给出输出文件清单", str(generated_conclusion_files + generated_html_files)))
-    yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
-
-

crazy_functions/Rag_Interface.py

@@ -0,0 +1,95 @@
+from toolbox import CatchException, update_ui, get_conf, get_log_folder, update_ui_lastest_msg
+from crazy_functions.crazy_utils import input_clipping
+from crazy_functions.crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
+
+VECTOR_STORE_TYPE = "Milvus"
+
+if VECTOR_STORE_TYPE == "Milvus":
+    try:
+        from crazy_functions.rag_fns.milvus_worker import MilvusRagWorker as LlamaIndexRagWorker
+    except:
+        VECTOR_STORE_TYPE = "Simple"
+
+if VECTOR_STORE_TYPE == "Simple":
+    from crazy_functions.rag_fns.llama_index_worker import LlamaIndexRagWorker
+
+
+RAG_WORKER_REGISTER = {}
+
+MAX_HISTORY_ROUND = 5
+MAX_CONTEXT_TOKEN_LIMIT = 4096
+REMEMBER_PREVIEW = 1000
+
+@CatchException
+def Rag问答(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
+
+    # 1. we retrieve rag worker from global context
+    user_name = chatbot.get_user()
+    checkpoint_dir = get_log_folder(user_name, plugin_name='experimental_rag')
+    if user_name in RAG_WORKER_REGISTER:
+        rag_worker = RAG_WORKER_REGISTER[user_name]
+    else:
+        rag_worker = RAG_WORKER_REGISTER[user_name] = LlamaIndexRagWorker(
+            user_name, 
+            llm_kwargs, 
+            checkpoint_dir=checkpoint_dir, 
+            auto_load_checkpoint=True)
+    current_context = f"{VECTOR_STORE_TYPE} @ {checkpoint_dir}"
+    tip = "提示：输入“清空向量数据库”可以清空RAG向量数据库"
+    if txt == "清空向量数据库":
+        chatbot.append([txt, f'正在清空 ({current_context}) ...'])
+        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+        rag_worker.purge()
+        yield from update_ui_lastest_msg('已清空', chatbot, history, delay=0) # 刷新界面
+        return
+
+    chatbot.append([txt, f'正在召回知识 ({current_context}) ...'])
+    yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+
+    # 2. clip history to reduce token consumption
+    #   2-1. reduce chat round
+    txt_origin = txt
+
+    if len(history) > MAX_HISTORY_ROUND * 2:
+        history = history[-(MAX_HISTORY_ROUND * 2):]
+    txt_clip, history, flags = input_clipping(txt, history, max_token_limit=MAX_CONTEXT_TOKEN_LIMIT, return_clip_flags=True)
+    input_is_clipped_flag = (flags["original_input_len"] != flags["clipped_input_len"])
+
+    #   2-2. if input is clipped, add input to vector store before retrieve
+    if input_is_clipped_flag:
+        yield from update_ui_lastest_msg('检测到长输入, 正在向量化 ...', chatbot, history, delay=0) # 刷新界面
+        # save input to vector store
+        rag_worker.add_text_to_vector_store(txt_origin)
+        yield from update_ui_lastest_msg('向量化完成 ...', chatbot, history, delay=0) # 刷新界面
+        if len(txt_origin) > REMEMBER_PREVIEW:
+            HALF = REMEMBER_PREVIEW//2
+            i_say_to_remember = txt[:HALF] + f" ...\n...(省略{len(txt_origin)-REMEMBER_PREVIEW}字)...\n... " + txt[-HALF:]
+            if (flags["original_input_len"] - flags["clipped_input_len"]) > HALF:
+                txt_clip = txt_clip  + f" ...\n...(省略{len(txt_origin)-len(txt_clip)-HALF}字)...\n... " + txt[-HALF:]
+            else:
+                pass
+            i_say = txt_clip
+        else:
+            i_say_to_remember = i_say = txt_clip
+    else:
+        i_say_to_remember = i_say = txt_clip
+
+    # 3. we search vector store and build prompts
+    nodes = rag_worker.retrieve_from_store_with_query(i_say)
+    prompt = rag_worker.build_prompt(query=i_say, nodes=nodes)
+
+    # 4. it is time to query llms
+    if len(chatbot) != 0: chatbot.pop(-1) # pop temp chat, because we are going to add them again inside `request_gpt_model_in_new_thread_with_ui_alive`
+    model_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
+        inputs=prompt, inputs_show_user=i_say,
+        llm_kwargs=llm_kwargs, chatbot=chatbot, history=history,
+        sys_prompt=system_prompt,
+        retry_times_at_unknown_error=0
+    )
+
+    # 5. remember what has been asked / answered
+    yield from update_ui_lastest_msg(model_say + '</br></br>' + f'对话记忆中, 请稍等 ({current_context}) ...', chatbot, history, delay=0.5) # 刷新界面
+    rag_worker.remember_qa(i_say_to_remember, model_say)
+    history.extend([i_say, model_say])
+
+    yield from update_ui_lastest_msg(model_say, chatbot, history, delay=0, msg=tip) # 刷新界面

crazy_functions/Social_Helper.py

@@ -0,0 +1,65 @@
+from toolbox import CatchException, update_ui, get_conf, get_log_folder, update_ui_lastest_msg
+from crazy_functions.crazy_utils import input_clipping
+from crazy_functions.crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
+import pickle, os
+
+SOCIAL_NETWOK_WORKER_REGISTER = {}
+
+class SocialNetwork():
+    def __init__(self):
+        self.people = []
+
+class SocialNetworkWorker():
+    def __init__(self, user_name, llm_kwargs, auto_load_checkpoint=True, checkpoint_dir=None) -> None:
+        self.user_name = user_name
+        self.checkpoint_dir = checkpoint_dir
+        if auto_load_checkpoint:
+            self.social_network = self.load_from_checkpoint(checkpoint_dir)
+        else:
+            self.social_network = SocialNetwork()
+
+    def does_checkpoint_exist(self, checkpoint_dir=None):
+        import os, glob
+        if checkpoint_dir is None: checkpoint_dir = self.checkpoint_dir
+        if not os.path.exists(checkpoint_dir): return False
+        if len(glob.glob(os.path.join(checkpoint_dir, "social_network.pkl"))) == 0: return False
+        return True
+
+    def save_to_checkpoint(self, checkpoint_dir=None):
+        if checkpoint_dir is None: checkpoint_dir = self.checkpoint_dir
+        with open(os.path.join(checkpoint_dir, 'social_network.pkl'), "wb+") as f:
+            pickle.dump(self.social_network, f)
+        return
+
+    def load_from_checkpoint(self, checkpoint_dir=None):
+        if checkpoint_dir is None: checkpoint_dir = self.checkpoint_dir
+        if self.does_checkpoint_exist(checkpoint_dir=checkpoint_dir):
+            with open(os.path.join(checkpoint_dir, 'social_network.pkl'), "rb") as f:
+                social_network = pickle.load(f)
+                return social_network
+        else:
+            return SocialNetwork()
+
+
+@CatchException
+def I人助手(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request, num_day=5):
+
+    # 1. we retrieve worker from global context
+    user_name = chatbot.get_user()
+    checkpoint_dir=get_log_folder(user_name, plugin_name='experimental_rag')
+    if user_name in SOCIAL_NETWOK_WORKER_REGISTER:
+        social_network_worker = SOCIAL_NETWOK_WORKER_REGISTER[user_name]
+    else:
+        social_network_worker = SOCIAL_NETWOK_WORKER_REGISTER[user_name] = SocialNetworkWorker(
+            user_name, 
+            llm_kwargs, 
+            checkpoint_dir=checkpoint_dir, 
+            auto_load_checkpoint=True
+        )
+
+    # 2. save
+    social_network_worker.social_network.people.append("张三")
+    social_network_worker.save_to_checkpoint(checkpoint_dir)
+    chatbot.append(["good", "work"])
+    yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+

crazy_functions/SourceCode_Analyse.py

@@ -1,12 +1,12 @@
-from toolbox import update_ui, promote_file_to_downloadzone, disable_auto_promotion
+from toolbox import update_ui, promote_file_to_downloadzone
 from toolbox import CatchException, report_exception, write_history_to_file
-from .crazy_utils import input_clipping
+from shared_utils.fastapi_server import validate_path_safety
+from crazy_functions.crazy_utils import input_clipping
 
 def 解析源代码新(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt):
     import os, copy
-    from .crazy_utils import request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency
-    from .crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
-    disable_auto_promotion(chatbot=chatbot)
+    from crazy_functions.crazy_utils import request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency
+    from crazy_functions.crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
 
     summary_batch_isolation = True
     inputs_array = []
@@ -23,7 +23,7 @@ def 解析源代码新(file_manifest, project_folder, llm_kwargs, plugin_kwargs,
             file_content = f.read()
         prefix = "接下来请你逐文件分析下面的工程" if index==0 else ""
         i_say = prefix + f'请对下面的程序文件做一个概述文件名是{os.path.relpath(fp, project_folder)}，文件代码是 ```{file_content}```'
-        i_say_show_user = prefix + f'[{index}/{len(file_manifest)}] 请对下面的程序文件做一个概述: {fp}'
+        i_say_show_user = prefix + f'[{index+1}/{len(file_manifest)}] 请对下面的程序文件做一个概述: {fp}'
         # 装载请求内容
         inputs_array.append(i_say)
         inputs_show_user_array.append(i_say_show_user)
@@ -128,6 +128,7 @@ def 解析一个Python项目(txt, llm_kwargs, plugin_kwargs, chatbot, history, s
     import glob, os
     if os.path.exists(txt):
         project_folder = txt
+        validate_path_safety(project_folder, chatbot.get_user())
     else:
         if txt == "": txt = '空空如也的输入栏'
         report_exception(chatbot, history, a = f"解析项目: {txt}", b = f"找不到本地项目或无权访问: {txt}")
@@ -146,6 +147,7 @@ def 解析一个Matlab项目(txt, llm_kwargs, plugin_kwargs, chatbot, history, s
     import glob, os
     if os.path.exists(txt):
         project_folder = txt
+        validate_path_safety(project_folder, chatbot.get_user())
     else:
         if txt == "": txt = '空空如也的输入栏'
         report_exception(chatbot, history, a = f"解析Matlab项目: {txt}", b = f"找不到本地项目或无权访问: {txt}")
@@ -164,6 +166,7 @@ def 解析一个C项目的头文件(txt, llm_kwargs, plugin_kwargs, chatbot, his
     import glob, os
     if os.path.exists(txt):
         project_folder = txt
+        validate_path_safety(project_folder, chatbot.get_user())
     else:
         if txt == "": txt = '空空如也的输入栏'
         report_exception(chatbot, history, a = f"解析项目: {txt}", b = f"找不到本地项目或无权访问: {txt}")
@@ -184,6 +187,7 @@ def 解析一个C项目(txt, llm_kwargs, plugin_kwargs, chatbot, history, system
     import glob, os
     if os.path.exists(txt):
         project_folder = txt
+        validate_path_safety(project_folder, chatbot.get_user())
     else:
         if txt == "": txt = '空空如也的输入栏'
         report_exception(chatbot, history, a = f"解析项目: {txt}", b = f"找不到本地项目或无权访问: {txt}")
@@ -206,6 +210,7 @@ def 解析一个Java项目(txt, llm_kwargs, plugin_kwargs, chatbot, history, sys
     import glob, os
     if os.path.exists(txt):
         project_folder = txt
+        validate_path_safety(project_folder, chatbot.get_user())
     else:
         if txt == "": txt = '空空如也的输入栏'
         report_exception(chatbot, history, a=f"解析项目: {txt}", b=f"找不到本地项目或无权访问: {txt}")
@@ -228,6 +233,7 @@ def 解析一个前端项目(txt, llm_kwargs, plugin_kwargs, chatbot, history, s
     import glob, os
     if os.path.exists(txt):
         project_folder = txt
+        validate_path_safety(project_folder, chatbot.get_user())
     else:
         if txt == "": txt = '空空如也的输入栏'
         report_exception(chatbot, history, a=f"解析项目: {txt}", b=f"找不到本地项目或无权访问: {txt}")
@@ -257,6 +263,7 @@ def 解析一个Golang项目(txt, llm_kwargs, plugin_kwargs, chatbot, history, s
     import glob, os
     if os.path.exists(txt):
         project_folder = txt
+        validate_path_safety(project_folder, chatbot.get_user())
     else:
         if txt == "": txt = '空空如也的输入栏'
         report_exception(chatbot, history, a=f"解析项目: {txt}", b=f"找不到本地项目或无权访问: {txt}")
@@ -278,6 +285,7 @@ def 解析一个Rust项目(txt, llm_kwargs, plugin_kwargs, chatbot, history, sys
     import glob, os
     if os.path.exists(txt):
         project_folder = txt
+        validate_path_safety(project_folder, chatbot.get_user())
     else:
         if txt == "": txt = '空空如也的输入栏'
         report_exception(chatbot, history, a=f"解析项目: {txt}", b=f"找不到本地项目或无权访问: {txt}")
@@ -298,6 +306,7 @@ def 解析一个Lua项目(txt, llm_kwargs, plugin_kwargs, chatbot, history, syst
     import glob, os
     if os.path.exists(txt):
         project_folder = txt
+        validate_path_safety(project_folder, chatbot.get_user())
     else:
         if txt == "": txt = '空空如也的输入栏'
         report_exception(chatbot, history, a = f"解析项目: {txt}", b = f"找不到本地项目或无权访问: {txt}")
@@ -320,6 +329,7 @@ def 解析一个CSharp项目(txt, llm_kwargs, plugin_kwargs, chatbot, history, s
     import glob, os
     if os.path.exists(txt):
         project_folder = txt
+        validate_path_safety(project_folder, chatbot.get_user())
     else:
         if txt == "": txt = '空空如也的输入栏'
         report_exception(chatbot, history, a = f"解析项目: {txt}", b = f"找不到本地项目或无权访问: {txt}")
@@ -357,6 +367,7 @@ def 解析任意code项目(txt, llm_kwargs, plugin_kwargs, chatbot, history, sys
     import glob, os, re
     if os.path.exists(txt):
         project_folder = txt
+        validate_path_safety(project_folder, chatbot.get_user())
     else:
         if txt == "": txt = '空空如也的输入栏'
         report_exception(chatbot, history, a = f"解析项目: {txt}", b = f"找不到本地项目或无权访问: {txt}")

crazy_functions/SourceCode_Comment.py

@@ -0,0 +1,138 @@
+import os, copy, time
+from toolbox import CatchException, report_exception, update_ui, zip_result, promote_file_to_downloadzone, update_ui_lastest_msg, get_conf, generate_file_link
+from shared_utils.fastapi_server import validate_path_safety
+from crazy_functions.crazy_utils import input_clipping
+from crazy_functions.crazy_utils import request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency
+from crazy_functions.crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
+from crazy_functions.agent_fns.python_comment_agent import PythonCodeComment
+from crazy_functions.diagram_fns.file_tree import FileNode
+from shared_utils.advanced_markdown_format import markdown_convertion_for_file
+
+def 注释源代码(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt):
+
+    summary_batch_isolation = True
+    inputs_array = []
+    inputs_show_user_array = []
+    history_array = []
+    sys_prompt_array = []
+
+    assert len(file_manifest) <= 512, "源文件太多（超过512个）, 请缩减输入文件的数量。或者，您也可以选择删除此行警告，并修改代码拆分file_manifest列表，从而实现分批次处理。"
+
+    # 建立文件树
+    file_tree_struct = FileNode("root", build_manifest=True)
+    for file_path in file_manifest:
+        file_tree_struct.add_file(file_path, file_path)
+
+    # <第一步，逐个文件分析，多线程>
+    for index, fp in enumerate(file_manifest):
+        # 读取文件
+        with open(fp, 'r', encoding='utf-8', errors='replace') as f:
+            file_content = f.read()
+        prefix = ""
+        i_say = prefix + f'Please conclude the following source code at {os.path.relpath(fp, project_folder)} with only one sentence, the code is:\n```{file_content}```'
+        i_say_show_user = prefix + f'[{index+1}/{len(file_manifest)}] 请用一句话对下面的程序文件做一个整体概述: {fp}'
+        # 装载请求内容
+        MAX_TOKEN_SINGLE_FILE = 2560
+        i_say, _ = input_clipping(inputs=i_say, history=[], max_token_limit=MAX_TOKEN_SINGLE_FILE)
+        inputs_array.append(i_say)
+        inputs_show_user_array.append(i_say_show_user)
+        history_array.append([])
+        sys_prompt_array.append("You are a software architecture analyst analyzing a source code project. Do not dig into details, tell me what the code is doing in general. Your answer must be short, simple and clear.")
+    # 文件读取完成，对每一个源代码文件，生成一个请求线程，发送到大模型进行分析
+    gpt_response_collection = yield from request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
+        inputs_array = inputs_array,
+        inputs_show_user_array = inputs_show_user_array,
+        history_array = history_array,
+        sys_prompt_array = sys_prompt_array,
+        llm_kwargs = llm_kwargs,
+        chatbot = chatbot,
+        show_user_at_complete = True
+    )
+
+    # <第二步，逐个文件分析，生成带注释文件>
+    from concurrent.futures import ThreadPoolExecutor
+    executor = ThreadPoolExecutor(max_workers=get_conf('DEFAULT_WORKER_NUM'))
+    def _task_multi_threading(i_say, gpt_say, fp, file_tree_struct):
+        pcc = PythonCodeComment(llm_kwargs, language='English')
+        pcc.read_file(path=fp, brief=gpt_say)
+        revised_path, revised_content = pcc.begin_comment_source_code(None, None)
+        file_tree_struct.manifest[fp].revised_path = revised_path
+        file_tree_struct.manifest[fp].revised_content = revised_content
+        # <将结果写回源文件>
+        with open(fp, 'w', encoding='utf-8') as f:
+            f.write(file_tree_struct.manifest[fp].revised_content)
+        # <生成对比html>
+        with open("crazy_functions/agent_fns/python_comment_compare.html", 'r', encoding='utf-8') as f:
+            html_template = f.read()
+        warp = lambda x: "```python\n\n" + x + "\n\n```"
+        from themes.theme import advanced_css
+        html_template = html_template.replace("ADVANCED_CSS", advanced_css)
+        html_template = html_template.replace("REPLACE_CODE_FILE_LEFT", pcc.get_markdown_block_in_html(markdown_convertion_for_file(warp(pcc.original_content))))
+        html_template = html_template.replace("REPLACE_CODE_FILE_RIGHT", pcc.get_markdown_block_in_html(markdown_convertion_for_file(warp(revised_content))))
+        compare_html_path = fp + '.compare.html'
+        file_tree_struct.manifest[fp].compare_html = compare_html_path
+        with open(compare_html_path, 'w', encoding='utf-8') as f:
+            f.write(html_template)
+        # print('done 1')
+
+    chatbot.append([None, f"正在处理:"])
+    futures = []
+    for i_say, gpt_say, fp in zip(gpt_response_collection[0::2], gpt_response_collection[1::2], file_manifest):
+        future = executor.submit(_task_multi_threading, i_say, gpt_say, fp, file_tree_struct)
+        futures.append(future)
+
+    cnt = 0
+    while True:
+        cnt += 1
+        time.sleep(3)
+        worker_done = [h.done() for h in futures]
+        remain = len(worker_done) - sum(worker_done)
+
+        # <展示已经完成的部分>
+        preview_html_list = []
+        for done, fp in zip(worker_done, file_manifest):
+            if not done: continue
+            preview_html_list.append(file_tree_struct.manifest[fp].compare_html)
+        file_links = generate_file_link(preview_html_list)
+
+        yield from update_ui_lastest_msg(
+            f"剩余源文件数量: {remain}.\n\n" + 
+            f"已完成的文件: {sum(worker_done)}.\n\n" + 
+            file_links +
+            "\n\n" +
+            ''.join(['.']*(cnt % 10 + 1)
+        ), chatbot=chatbot, history=history, delay=0)
+        yield from update_ui(chatbot=chatbot, history=[]) # 刷新界面
+        if all(worker_done):
+            executor.shutdown()
+            break
+
+    # <第四步，压缩结果>
+    zip_res = zip_result(project_folder)
+    promote_file_to_downloadzone(file=zip_res, chatbot=chatbot)
+
+    # <END>
+    chatbot.append((None, "所有源文件均已处理完毕。"))
+    yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+
+
+
+@CatchException
+def 注释Python项目(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
+    history = []    # 清空历史，以免输入溢出
+    import glob, os
+    if os.path.exists(txt):
+        project_folder = txt
+        validate_path_safety(project_folder, chatbot.get_user())
+    else:
+        if txt == "": txt = '空空如也的输入栏'
+        report_exception(chatbot, history, a = f"解析项目: {txt}", b = f"找不到本地项目或无权访问: {txt}")
+        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+        return
+    file_manifest = [f for f in glob.glob(f'{project_folder}/**/*.py', recursive=True)]
+    if len(file_manifest) == 0:
+        report_exception(chatbot, history, a = f"解析项目: {txt}", b = f"找不到任何python文件: {txt}")
+        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+        return
+
+    yield from 注释源代码(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt)

crazy_functions/agent_fns/echo_agent.py

@@ -1,4 +1,5 @@
 from crazy_functions.agent_fns.pipe import PluginMultiprocessManager, PipeCom
+from loguru import logger
 
 class EchoDemo(PluginMultiprocessManager):
     def subprocess_worker(self, child_conn):
@@ -16,4 +17,4 @@ class EchoDemo(PluginMultiprocessManager):
             elif msg.cmd == "terminate":
                 self.child_conn.send(PipeCom("done", ""))
                 break
-        print('[debug] subprocess_worker terminated')
+        logger.info('[debug] subprocess_worker terminated')

crazy_functions/agent_fns/pipe.py

@@ -1,5 +1,6 @@
 from toolbox import get_log_folder, update_ui, gen_time_str, get_conf, promote_file_to_downloadzone
 from crazy_functions.agent_fns.watchdog import WatchDog
+from loguru import logger
 import time, os
 
 class PipeCom:
@@ -47,7 +48,7 @@ class PluginMultiprocessManager:
     def terminate(self):
         self.p.terminate()
         self.alive = False
-        print("[debug] instance terminated")
+        logger.info("[debug] instance terminated")
 
     def subprocess_worker(self, child_conn):
         # ⭐⭐ run in subprocess

crazy_functions/agent_fns/python_comment_agent.py

@@ -0,0 +1,393 @@
+import datetime
+import re
+import os
+from loguru import logger
+from textwrap import dedent
+from toolbox import CatchException, update_ui
+from request_llms.bridge_all import predict_no_ui_long_connection
+from crazy_functions.crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
+
+# TODO: 解决缩进问题
+
+find_function_end_prompt = '''
+Below is a page of code that you need to read. This page may not yet complete, you job is to split this page to sperate functions, class functions etc.
+- Provide the line number where the first visible function ends.
+- Provide the line number where the next visible function begins.
+- If there are no other functions in this page, you should simply return the line number of the last line.
+- Only focus on functions declared by `def` keyword. Ignore inline functions. Ignore function calls.
+
+------------------ Example ------------------
+INPUT:
+
+    ```
+    L0000 |import sys
+    L0001 |import re
+    L0002 |
+    L0003 |def trimmed_format_exc():
+    L0004 |    import os
+    L0005 |    import traceback
+    L0006 |    str = traceback.format_exc()
+    L0007 |    current_path = os.getcwd()
+    L0008 |    replace_path = "."
+    L0009 |    return str.replace(current_path, replace_path)
+    L0010 |
+    L0011 |
+    L0012 |def trimmed_format_exc_markdown():
+    L0013 |    ...
+    L0014 |    ...
+    ```
+
+OUTPUT:
+
+    ```
+    <first_function_end_at>L0009</first_function_end_at>
+    <next_function_begin_from>L0012</next_function_begin_from>
+    ```
+
+------------------ End of Example ------------------
+
+
+------------------ the real INPUT you need to process NOW ------------------
+```
+{THE_TAGGED_CODE}
+```
+'''
+
+
+
+
+
+
+
+revise_funtion_prompt = '''
+You need to read the following code, and revise the source code ({FILE_BASENAME}) according to following instructions:
+1. You should analyze the purpose of the functions (if there are any).
+2. You need to add docstring for the provided functions (if there are any).
+
+Be aware:
+1. You must NOT modify the indent of code.
+2. You are NOT authorized to change or translate non-comment code, and you are NOT authorized to add empty lines either, toggle qu.
+3. Use {LANG} to add comments and docstrings. Do NOT translate Chinese that is already in the code.
+
+------------------ Example ------------------
+INPUT:
+```
+L0000 |
+L0001 |def zip_result(folder):
+L0002 |    t = gen_time_str()
+L0003 |    zip_folder(folder, get_log_folder(), f"result.zip")
+L0004 |    return os.path.join(get_log_folder(), f"result.zip")
+L0005 |
+L0006 |
+```
+
+OUTPUT:
+
+<instruction_1_purpose>
+This function compresses a given folder, and return the path of the resulting `zip` file.
+</instruction_1_purpose>
+<instruction_2_revised_code>
+```
+def zip_result(folder):
+    """
+    Compresses the specified folder into a zip file and stores it in the log folder.
+
+    Args:
+        folder (str): The path to the folder that needs to be compressed.
+
+    Returns:
+        str: The path to the created zip file in the log folder.
+    """
+    t = gen_time_str()
+    zip_folder(folder, get_log_folder(), f"result.zip")  # ⭐ Execute the zipping of folder
+    return os.path.join(get_log_folder(), f"result.zip")
+```
+</instruction_2_revised_code>
+------------------ End of Example ------------------
+
+
+------------------ the real INPUT you need to process NOW ({FILE_BASENAME}) ------------------
+```
+{THE_CODE}
+```
+{INDENT_REMINDER}
+{BRIEF_REMINDER}
+{HINT_REMINDER}
+'''
+
+
+
+class PythonCodeComment():
+
+    def __init__(self, llm_kwargs, language) -> None:
+        self.original_content = ""
+        self.full_context = []
+        self.full_context_with_line_no = []
+        self.current_page_start = 0
+        self.page_limit = 100 # 100 lines of code each page
+        self.ignore_limit = 20
+        self.llm_kwargs = llm_kwargs
+        self.language = language
+        self.path = None
+        self.file_basename = None
+        self.file_brief = ""
+
+    def generate_tagged_code_from_full_context(self):
+        for i, code in enumerate(self.full_context):
+            number = i
+            padded_number = f"{number:04}"
+            result = f"L{padded_number}"
+            self.full_context_with_line_no.append(f"{result} | {code}")
+        return self.full_context_with_line_no
+
+    def read_file(self, path, brief):
+        with open(path, 'r', encoding='utf8') as f:
+            self.full_context = f.readlines()
+        self.original_content = ''.join(self.full_context)
+        self.file_basename = os.path.basename(path)
+        self.file_brief = brief
+        self.full_context_with_line_no = self.generate_tagged_code_from_full_context()
+        self.path = path
+
+    def find_next_function_begin(self, tagged_code:list, begin_and_end):
+        begin, end = begin_and_end
+        THE_TAGGED_CODE = ''.join(tagged_code)
+        self.llm_kwargs['temperature'] = 0
+        result = predict_no_ui_long_connection(
+            inputs=find_function_end_prompt.format(THE_TAGGED_CODE=THE_TAGGED_CODE),
+            llm_kwargs=self.llm_kwargs,
+            history=[],
+            sys_prompt="",
+            observe_window=[],
+            console_slience=True
+        )
+
+        def extract_number(text):
+            # 使用正则表达式匹配模式
+            match = re.search(r'<next_function_begin_from>L(\d+)</next_function_begin_from>', text)
+            if match:
+                # 提取匹配的数字部分并转换为整数
+                return int(match.group(1))
+            return None
+
+        line_no = extract_number(result)
+        if line_no is not None:
+            return line_no
+        else:
+            return end
+
+    def _get_next_window(self):
+        #
+        current_page_start = self.current_page_start
+
+        if self.current_page_start == len(self.full_context) + 1:
+            raise StopIteration
+
+        # 如果剩余的行数非常少，一鼓作气处理掉
+        if len(self.full_context) - self.current_page_start < self.ignore_limit:
+            future_page_start = len(self.full_context) + 1
+            self.current_page_start = future_page_start
+            return current_page_start, future_page_start
+
+
+        tagged_code = self.full_context_with_line_no[ self.current_page_start: self.current_page_start + self.page_limit]
+        line_no = self.find_next_function_begin(tagged_code, [self.current_page_start, self.current_page_start + self.page_limit])
+
+        if line_no > len(self.full_context) - 5:
+            line_no = len(self.full_context) + 1
+
+        future_page_start = line_no
+        self.current_page_start = future_page_start
+
+        # ! consider eof
+        return current_page_start, future_page_start
+
+    def dedent(self, text):
+        """Remove any common leading whitespace from every line in `text`.
+        """
+        # Look for the longest leading string of spaces and tabs common to
+        # all lines.
+        margin = None
+        _whitespace_only_re = re.compile('^[ \t]+$', re.MULTILINE)
+        _leading_whitespace_re = re.compile('(^[ \t]*)(?:[^ \t\n])', re.MULTILINE)
+        text = _whitespace_only_re.sub('', text)
+        indents = _leading_whitespace_re.findall(text)
+        for indent in indents:
+            if margin is None:
+                margin = indent
+
+            # Current line more deeply indented than previous winner:
+            # no change (previous winner is still on top).
+            elif indent.startswith(margin):
+                pass
+
+            # Current line consistent with and no deeper than previous winner:
+            # it's the new winner.
+            elif margin.startswith(indent):
+                margin = indent
+
+            # Find the largest common whitespace between current line and previous
+            # winner.
+            else:
+                for i, (x, y) in enumerate(zip(margin, indent)):
+                    if x != y:
+                        margin = margin[:i]
+                        break
+
+        # sanity check (testing/debugging only)
+        if 0 and margin:
+            for line in text.split("\n"):
+                assert not line or line.startswith(margin), \
+                    "line = %r, margin = %r" % (line, margin)
+
+        if margin:
+            text = re.sub(r'(?m)^' + margin, '', text)
+            return text, len(margin)
+        else:
+            return text, 0
+
+    def get_next_batch(self):
+        current_page_start, future_page_start = self._get_next_window()
+        return ''.join(self.full_context[current_page_start: future_page_start]), current_page_start, future_page_start
+
+    def tag_code(self, fn, hint):
+        code = fn
+        _, n_indent = self.dedent(code)
+        indent_reminder = "" if n_indent == 0 else "(Reminder: as you can see, this piece of code has indent made up with {n_indent} whitespace, please preseve them in the OUTPUT.)"
+        brief_reminder = "" if self.file_brief == "" else f"({self.file_basename} abstract: {self.file_brief})"
+        hint_reminder = "" if hint is None else f"(Reminder: do not ignore or modify code such as `{hint}`, provide complete code in the OUTPUT.)"
+        self.llm_kwargs['temperature'] = 0
+        result = predict_no_ui_long_connection(
+            inputs=revise_funtion_prompt.format(
+                LANG=self.language, 
+                FILE_BASENAME=self.file_basename, 
+                THE_CODE=code, 
+                INDENT_REMINDER=indent_reminder, 
+                BRIEF_REMINDER=brief_reminder,
+                HINT_REMINDER=hint_reminder
+            ),
+            llm_kwargs=self.llm_kwargs,
+            history=[],
+            sys_prompt="",
+            observe_window=[],
+            console_slience=True
+        )
+
+        def get_code_block(reply):
+            import re
+            pattern = r"```([\s\S]*?)```" # regex pattern to match code blocks
+            matches = re.findall(pattern, reply) # find all code blocks in text
+            if len(matches) == 1:
+                return matches[0].strip('python') #  code block
+            return None
+
+        code_block = get_code_block(result)
+        if code_block is not None:
+            code_block = self.sync_and_patch(original=code, revised=code_block)
+            return code_block
+        else:
+            return code
+        
+    def get_markdown_block_in_html(self, html):
+        from bs4 import BeautifulSoup
+        soup = BeautifulSoup(html, 'lxml')
+        found_list = soup.find_all("div", class_="markdown-body")
+        if found_list:
+            res = found_list[0]
+            return res.prettify()
+        else:
+            return None
+
+
+    def sync_and_patch(self, original, revised):
+        """Ensure the number of pre-string empty lines in revised matches those in original."""
+
+        def count_leading_empty_lines(s, reverse=False):
+            """Count the number of leading empty lines in a string."""
+            lines = s.split('\n')
+            if reverse: lines = list(reversed(lines))
+            count = 0
+            for line in lines:
+                if line.strip() == '':
+                    count += 1
+                else:
+                    break
+            return count
+
+        original_empty_lines = count_leading_empty_lines(original)
+        revised_empty_lines = count_leading_empty_lines(revised)
+
+        if original_empty_lines > revised_empty_lines:
+            additional_lines = '\n' * (original_empty_lines - revised_empty_lines)
+            revised = additional_lines + revised
+        elif original_empty_lines < revised_empty_lines:
+            lines = revised.split('\n')
+            revised = '\n'.join(lines[revised_empty_lines - original_empty_lines:])
+
+        original_empty_lines = count_leading_empty_lines(original, reverse=True)
+        revised_empty_lines = count_leading_empty_lines(revised, reverse=True)
+
+        if original_empty_lines > revised_empty_lines:
+            additional_lines = '\n' * (original_empty_lines - revised_empty_lines)
+            revised =  revised + additional_lines
+        elif original_empty_lines < revised_empty_lines:
+            lines = revised.split('\n')
+            revised = '\n'.join(lines[:-(revised_empty_lines - original_empty_lines)])
+
+        return revised
+
+    def begin_comment_source_code(self, chatbot=None, history=None):
+        # from toolbox import update_ui_lastest_msg
+        assert self.path is not None
+        assert '.py' in self.path   # must be python source code
+        # write_target = self.path + '.revised.py'
+
+        write_content = ""
+        # with open(self.path + '.revised.py', 'w+', encoding='utf8') as f:
+        while True:
+            try:
+                # yield from update_ui_lastest_msg(f"({self.file_basename}) 正在读取下一段代码片段:\n", chatbot=chatbot, history=history, delay=0)
+                next_batch, line_no_start, line_no_end = self.get_next_batch()
+                # yield from update_ui_lastest_msg(f"({self.file_basename}) 处理代码片段:\n\n{next_batch}", chatbot=chatbot, history=history, delay=0)
+                
+                hint = None
+                MAX_ATTEMPT = 2
+                for attempt in range(MAX_ATTEMPT):
+                    result = self.tag_code(next_batch, hint)
+                    try:
+                        successful, hint = self.verify_successful(next_batch, result)
+                    except Exception as e:
+                        logger.error('ignored exception:\n' + str(e))
+                        break
+                    if successful:
+                        break
+                    if attempt == MAX_ATTEMPT - 1:
+                        # cannot deal with this, give up
+                        result = next_batch
+                        break
+
+                # f.write(result)
+                write_content += result
+            except StopIteration:
+                next_batch, line_no_start, line_no_end = [], -1, -1
+                return None, write_content
+
+    def verify_successful(self, original, revised):
+        """ Determine whether the revised code contains every line that already exists
+        """
+        from crazy_functions.ast_fns.comment_remove import remove_python_comments
+        original = remove_python_comments(original)
+        original_lines = original.split('\n')
+        revised_lines = revised.split('\n')
+
+        for l in original_lines:
+            l = l.strip()
+            if '\'' in l or '\"' in l: continue  # ast sometimes toggle " to '
+            found = False
+            for lt in revised_lines:
+                if l in lt:
+                    found = True
+                    break
+            if not found:
+                return False, l
+        return True, None

crazy_functions/agent_fns/python_comment_compare.html

@@ -0,0 +1,45 @@
+<!DOCTYPE html>
+<html lang="zh-CN">
+<head>
+    <style>ADVANCED_CSS</style>
+    <meta charset="UTF-8">
+    <title>源文件对比</title>
+    <style>
+        body {
+            font-family: Arial, sans-serif;
+            display: flex;
+            justify-content: center;
+            align-items: center;
+            height: 100vh;
+            margin: 0;
+        }
+        .container {
+            display: flex;
+            width: 95%;
+            height: -webkit-fill-available;
+        }
+        .code-container {
+            flex: 1;
+            margin: 0px;
+            padding: 0px;
+            border: 1px solid #ccc;
+            background-color: #f9f9f9;
+            overflow: auto;
+        }
+        pre {
+            white-space: pre-wrap;
+            word-wrap: break-word;
+        }
+    </style>
+</head>
+<body>
+<div class="container">
+<div class="code-container">
+REPLACE_CODE_FILE_LEFT
+</div>
+<div class="code-container">
+REPLACE_CODE_FILE_RIGHT
+</div>
+</div>
+</body>
+</html>

crazy_functions/agent_fns/watchdog.py

@@ -1,4 +1,5 @@
 import threading, time
+from loguru import logger
 
 class WatchDog():
     def __init__(self, timeout, bark_fn, interval=3, msg="") -> None:
@@ -13,7 +14,7 @@ class WatchDog():
         while True:
             if self.kill_dog: break
             if time.time() - self.last_feed > self.timeout:
-                if len(self.msg) > 0: print(self.msg)
+                if len(self.msg) > 0: logger.info(self.msg)
                 self.bark_fn()
                 break
             time.sleep(self.interval)

crazy_functions/ast_fns/comment_remove.py

@@ -0,0 +1,46 @@
+import ast
+
+class CommentRemover(ast.NodeTransformer):
+    def visit_FunctionDef(self, node):
+        # 移除函数的文档字符串
+        if (node.body and isinstance(node.body[0], ast.Expr) and
+                isinstance(node.body[0].value, ast.Str)):
+            node.body = node.body[1:]
+        self.generic_visit(node)
+        return node
+
+    def visit_ClassDef(self, node):
+        # 移除类的文档字符串
+        if (node.body and isinstance(node.body[0], ast.Expr) and
+                isinstance(node.body[0].value, ast.Str)):
+            node.body = node.body[1:]
+        self.generic_visit(node)
+        return node
+
+    def visit_Module(self, node):
+        # 移除模块的文档字符串
+        if (node.body and isinstance(node.body[0], ast.Expr) and
+                isinstance(node.body[0].value, ast.Str)):
+            node.body = node.body[1:]
+        self.generic_visit(node)
+        return node
+    
+
+def remove_python_comments(source_code):
+    # 解析源代码为 AST
+    tree = ast.parse(source_code)
+    # 移除注释
+    transformer = CommentRemover()
+    tree = transformer.visit(tree)
+    # 将处理后的 AST 转换回源代码
+    return ast.unparse(tree)
+
+# 示例使用
+if __name__ == "__main__":
+    with open("source.py", "r", encoding="utf-8") as f:
+        source_code = f.read()
+
+    cleaned_code = remove_python_comments(source_code)
+
+    with open("cleaned_source.py", "w", encoding="utf-8") as f:
+        f.write(cleaned_code)

crazy_functions/chatglm微调工具.py

@@ -1,5 +1,5 @@
 from toolbox import CatchException, update_ui, promote_file_to_downloadzone
-from .crazy_utils import request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency
+from crazy_functions.crazy_utils import request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency
 import datetime, json
 
 def fetch_items(list_of_items, batch_size):

crazy_functions/crazy_utils.py

@@ -1,25 +1,39 @@
-from toolbox import update_ui, get_conf, trimmed_format_exc, get_max_token, Singleton
-import threading
 import os
-import logging
+import threading
+from loguru import logger
+from shared_utils.char_visual_effect import scolling_visual_effect
+from toolbox import update_ui, get_conf, trimmed_format_exc, get_max_token, Singleton
 
-def input_clipping(inputs, history, max_token_limit):
+def input_clipping(inputs, history, max_token_limit, return_clip_flags=False):
+    """
+    当输入文本 + 历史文本超出最大限制时，采取措施丢弃一部分文本。
+    输入：
+        - inputs 本次请求
+        - history 历史上下文
+        - max_token_limit 最大token限制
+    输出:
+        - inputs 本次请求（经过clip）
+        - history 历史上下文（经过clip）
+    """
     import numpy as np
     from request_llms.bridge_all import model_info
     enc = model_info["gpt-3.5-turbo"]['tokenizer']
     def get_token_num(txt): return len(enc.encode(txt, disallowed_special=()))
 
+
     mode = 'input-and-history'
     # 当 输入部分的token占比 小于 全文的一半时，只裁剪历史
     input_token_num = get_token_num(inputs)
+    original_input_len = len(inputs)
     if input_token_num < max_token_limit//2:
         mode = 'only-history'
         max_token_limit = max_token_limit - input_token_num
 
     everything = [inputs] if mode == 'input-and-history' else ['']
     everything.extend(history)
-    n_token = get_token_num('\n'.join(everything))
+    full_token_num = n_token = get_token_num('\n'.join(everything))
     everything_token = [get_token_num(e) for e in everything]
+    everything_token_num = sum(everything_token)
     delta = max(everything_token) // 16 # 截断时的颗粒度
 
     while n_token > max_token_limit:
@@ -32,10 +46,24 @@ def input_clipping(inputs, history, max_token_limit):
 
     if mode == 'input-and-history':
         inputs = everything[0]
+        full_token_num = everything_token_num
     else:
-        pass
+        full_token_num = everything_token_num + input_token_num
+
     history = everything[1:]
+
+    flags = {
+        "mode": mode,
+        "original_input_token_num": input_token_num,
+        "original_full_token_num": full_token_num,
+        "original_input_len": original_input_len,
+        "clipped_input_len": len(inputs),
+    }
+
+    if not return_clip_flags:
         return inputs, history
+    else:
+        return inputs, history, flags
 
 def request_gpt_model_in_new_thread_with_ui_alive(
         inputs, inputs_show_user, llm_kwargs,
@@ -105,7 +133,7 @@ def request_gpt_model_in_new_thread_with_ui_alive(
             except:
                 # 【第三种情况】：其他错误：重试几次
                 tb_str = '```\n' + trimmed_format_exc() + '```'
-                print(tb_str)
+                logger.error(tb_str)
                 mutable[0] += f"[Local Message] 警告，在执行过程中遭遇问题, Traceback：\n\n{tb_str}\n\n"
                 if retry_op > 0:
                     retry_op -= 1
@@ -158,7 +186,7 @@ def can_multi_process(llm) -> bool:
 def request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
         inputs_array, inputs_show_user_array, llm_kwargs,
         chatbot, history_array, sys_prompt_array,
-        refresh_interval=0.2, max_workers=-1, scroller_max_len=30,
+        refresh_interval=0.2, max_workers=-1, scroller_max_len=75,
         handle_token_exceed=True, show_user_at_complete=False,
         retry_times_at_unknown_error=2,
         ):
@@ -255,7 +283,7 @@ def request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
                 # 【第三种情况】：其他错误
                 if detect_timeout(): raise RuntimeError("检测到程序终止。")
                 tb_str = '```\n' + trimmed_format_exc() + '```'
-                print(tb_str)
+                logger.error(tb_str)
                 gpt_say += f"[Local Message] 警告，线程{index}在执行过程中遭遇问题, Traceback：\n\n{tb_str}\n\n"
                 if len(mutable[index][0]) > 0: gpt_say += "此线程失败前收到的回答：\n\n" + mutable[index][0]
                 if retry_op > 0:
@@ -283,6 +311,8 @@ def request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
     futures = [executor.submit(_req_gpt, index, inputs, history, sys_prompt) for index, inputs, history, sys_prompt in zip(
         range(len(inputs_array)), inputs_array, history_array, sys_prompt_array)]
     cnt = 0
+
+
     while True:
         # yield一次以刷新前端页面
         time.sleep(refresh_interval)
@@ -295,8 +325,7 @@ def request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
             mutable[thread_index][1] = time.time()
         # 在前端打印些好玩的东西
         for thread_index, _ in enumerate(worker_done):
-            print_something_really_funny = "[ ...`"+mutable[thread_index][0][-scroller_max_len:].\
-                replace('\n', '').replace('`', '.').replace(' ', '.').replace('<br/>', '.....').replace('$', '.')+"`... ]"
+            print_something_really_funny = f"[ ...`{scolling_visual_effect(mutable[thread_index][0], scroller_max_len)}`... ]"
             observe_win.append(print_something_really_funny)
         # 在前端打印些好玩的东西
         stat_str = ''.join([f'`{mutable[thread_index][2]}`: {obs}\n\n'
@@ -349,7 +378,7 @@ def read_and_clean_pdf_text(fp):
     import fitz, copy
     import re
     import numpy as np
-    from colorful import print亮黄, print亮绿
+    # from shared_utils.colorful import print亮黄, print亮绿
     fc = 0  # Index 0 文本
     fs = 1  # Index 1 字体
     fb = 2  # Index 2 框框
@@ -566,7 +595,7 @@ class nougat_interface():
     def nougat_with_timeout(self, command, cwd, timeout=3600):
         import subprocess
         from toolbox import ProxyNetworkActivate
-        logging.info(f'正在执行命令 {command}')
+        logger.info(f'正在执行命令 {command}')
         with ProxyNetworkActivate("Nougat_Download"):
             process = subprocess.Popen(command, shell=False, cwd=cwd, env=os.environ)
         try:
@@ -574,7 +603,7 @@ class nougat_interface():
         except subprocess.TimeoutExpired:
             process.kill()
             stdout, stderr = process.communicate()
-            print("Process timed out!")
+            logger.error("Process timed out!")
             return False
         return True
 

crazy_functions/diagram_fns/file_tree.py

@@ -1,8 +1,9 @@
 import os
 from textwrap import indent
+from loguru import logger
 
 class FileNode:
-    def __init__(self, name):
+    def __init__(self, name, build_manifest=False):
         self.name = name
         self.children = []
         self.is_leaf = False
@@ -10,6 +11,8 @@ class FileNode:
         self.parenting_ship = []
         self.comment = ""
         self.comment_maxlen_show = 50
+        self.build_manifest = build_manifest
+        self.manifest = {}
 
     @staticmethod
     def add_linebreaks_at_spaces(string, interval=10):
@@ -29,6 +32,7 @@ class FileNode:
         level = 1
         if directory_names == "":
             new_node = FileNode(file_name)
+            self.manifest[file_path] = new_node
             current_node.children.append(new_node)
             new_node.is_leaf = True
             new_node.comment = self.sanitize_comment(file_comment)
@@ -50,13 +54,14 @@ class FileNode:
                     new_node.level = level - 1
                     current_node = new_node
             term = FileNode(file_name)
+            self.manifest[file_path] = term
             term.level = level
             term.comment = self.sanitize_comment(file_comment)
             term.is_leaf = True
             current_node.children.append(term)
 
     def print_files_recursively(self, level=0, code="R0"):
-        print('    '*level + self.name + ' ' + str(self.is_leaf) + ' ' + str(self.level))
+        logger.info('    '*level + self.name + ' ' + str(self.is_leaf) + ' ' + str(self.level))
         for j, child in enumerate(self.children):
             child.print_files_recursively(level=level+1, code=code+str(j))
             self.parenting_ship.extend(child.parenting_ship)
@@ -119,4 +124,4 @@ if __name__ == "__main__":
         "用于加载和分割文件中的文本的通用文件加载器用于加载和分割文件中的文本的通用文件加载器用于加载和分割文件中的文本的通用文件加载器",
         "包含了用于构建和管理向量数据库的函数和类包含了用于构建和管理向量数据库的函数和类包含了用于构建和管理向量数据库的函数和类",
     ]
-    print(build_file_tree_mermaid_diagram(file_manifest, file_comments, "项目文件树"))
+    logger.info(build_file_tree_mermaid_diagram(file_manifest, file_comments, "项目文件树"))

crazy_functions/game_fns/game_interactive_story.py

@@ -92,7 +92,7 @@ class MiniGame_ResumeStory(GptAcademicGameBaseState):
 
     def generate_story_image(self, story_paragraph):
         try:
-            from crazy_functions.图片生成 import gen_image
+            from crazy_functions.Image_Generate import gen_image
             prompt_ = predict_no_ui_long_connection(inputs=story_paragraph, llm_kwargs=self.llm_kwargs, history=[], sys_prompt='你需要根据用户给出的小说段落，进行简短的环境描写。要求：80字以内。')
             image_url, image_path = gen_image(self.llm_kwargs, prompt_, '512x512', model="dall-e-2", quality='standard', style='natural')
             return f'<br/><div align="center"><img src="file={image_path}"></div>'

crazy_functions/json_fns/pydantic_io.py

@@ -24,8 +24,8 @@ class Actor(BaseModel):
     film_names: List[str] = Field(description="list of names of films they starred in")
 """
 
-import json, re, logging
-
+import json, re
+from loguru import logger as logging
 
 PYDANTIC_FORMAT_INSTRUCTIONS = """The output should be formatted as a JSON instance that conforms to the JSON schema below.
 

crazy_functions/latex_fns/latex_actions.py

@@ -1,15 +1,17 @@
+import os
+import re
+import shutil
+import numpy as np
+from loguru import logger
 from toolbox import update_ui, update_ui_lastest_msg, get_log_folder
 from toolbox import get_conf, promote_file_to_downloadzone
-from .latex_toolbox import PRESERVE, TRANSFORM
-from .latex_toolbox import set_forbidden_text, set_forbidden_text_begin_end, set_forbidden_text_careful_brace
-from .latex_toolbox import reverse_forbidden_text_careful_brace, reverse_forbidden_text, convert_to_linklist, post_process
-from .latex_toolbox import fix_content, find_main_tex_file, merge_tex_files, compile_latex_with_timeout
-from .latex_toolbox import find_title_and_abs
-from .latex_pickle_io import objdump, objload
+from crazy_functions.latex_fns.latex_toolbox import PRESERVE, TRANSFORM
+from crazy_functions.latex_fns.latex_toolbox import set_forbidden_text, set_forbidden_text_begin_end, set_forbidden_text_careful_brace
+from crazy_functions.latex_fns.latex_toolbox import reverse_forbidden_text_careful_brace, reverse_forbidden_text, convert_to_linklist, post_process
+from crazy_functions.latex_fns.latex_toolbox import fix_content, find_main_tex_file, merge_tex_files, compile_latex_with_timeout
+from crazy_functions.latex_fns.latex_toolbox import find_title_and_abs
+from crazy_functions.latex_fns.latex_pickle_io import objdump, objload
 
-import os, shutil
-import re
-import numpy as np
 
 pj = os.path.join
 
@@ -323,7 +325,7 @@ def remove_buggy_lines(file_path, log_path, tex_name, tex_name_pure, n_fix, work
         buggy_lines = [int(l) for l in buggy_lines]
         buggy_lines = sorted(buggy_lines)
         buggy_line = buggy_lines[0]-1
-        print("reversing tex line that has errors", buggy_line)
+        logger.warning("reversing tex line that has errors", buggy_line)
 
         # 重组，逆转出错的段落
         if buggy_line not in fixed_line:
@@ -337,7 +339,7 @@ def remove_buggy_lines(file_path, log_path, tex_name, tex_name_pure, n_fix, work
 
         return True, f"{tex_name_pure}_fix_{n_fix}", buggy_lines
     except:
-        print("Fatal error occurred, but we cannot identify error, please download zip, read latex log, and compile manually.")
+        logger.error("Fatal error occurred, but we cannot identify error, please download zip, read latex log, and compile manually.")
         return False, -1, [-1]
 
 
@@ -380,7 +382,7 @@ def 编译Latex(chatbot, history, main_file_original, main_file_modified, work_f
 
             if mode!='translate_zh':
                 yield from update_ui_lastest_msg(f'尝试第 {n_fix}/{max_try} 次编译, 使用latexdiff生成论文转化前后对比 ...', chatbot, history) # 刷新Gradio前端界面
-                print(    f'latexdiff --encoding=utf8 --append-safecmd=subfile {work_folder_original}/{main_file_original}.tex  {work_folder_modified}/{main_file_modified}.tex --flatten > {work_folder}/merge_diff.tex')
+                logger.info(    f'latexdiff --encoding=utf8 --append-safecmd=subfile {work_folder_original}/{main_file_original}.tex  {work_folder_modified}/{main_file_modified}.tex --flatten > {work_folder}/merge_diff.tex')
                 ok = compile_latex_with_timeout(f'latexdiff --encoding=utf8 --append-safecmd=subfile {work_folder_original}/{main_file_original}.tex  {work_folder_modified}/{main_file_modified}.tex --flatten > {work_folder}/merge_diff.tex', os.getcwd())
 
                 yield from update_ui_lastest_msg(f'尝试第 {n_fix}/{max_try} 次编译, 正在编译对比PDF ...', chatbot, history)   # 刷新Gradio前端界面
@@ -419,7 +421,7 @@ def 编译Latex(chatbot, history, main_file_original, main_file_modified, work_f
                         shutil.copyfile(concat_pdf, pj(work_folder, '..', 'translation', 'comparison.pdf'))
                     promote_file_to_downloadzone(concat_pdf, rename_file=None, chatbot=chatbot)  # promote file to web UI
                 except Exception as e:
-                    print(e)
+                    logger.error(e)
                     pass
             return True # 成功啦
         else:
@@ -465,4 +467,4 @@ def write_html(sp_file_contents, sp_file_result, chatbot, project_folder):
         promote_file_to_downloadzone(file=res, chatbot=chatbot)
     except:
         from toolbox import trimmed_format_exc
-        print('writing html result failed:', trimmed_format_exc())
+        logger.error('writing html result failed:', trimmed_format_exc())

crazy_functions/latex_fns/latex_pickle_io.py

@@ -4,20 +4,28 @@ import pickle
 class SafeUnpickler(pickle.Unpickler):
 
     def get_safe_classes(self):
-        from .latex_actions import LatexPaperFileGroup, LatexPaperSplit
+        from crazy_functions.latex_fns.latex_actions import LatexPaperFileGroup, LatexPaperSplit
+        from crazy_functions.latex_fns.latex_toolbox import LinkedListNode
         # 定义允许的安全类
         safe_classes = {
             # 在这里添加其他安全的类
             'LatexPaperFileGroup': LatexPaperFileGroup,
             'LatexPaperSplit': LatexPaperSplit,
+            'LinkedListNode': LinkedListNode,
         }
         return safe_classes
 
     def find_class(self, module, name):
         # 只允许特定的类进行反序列化
         self.safe_classes = self.get_safe_classes()
-        if f'{module}.{name}' in self.safe_classes:
-            return self.safe_classes[f'{module}.{name}']
+        match_class_name = None
+        for class_name in self.safe_classes.keys():
+            if (class_name in f'{module}.{name}'):
+                match_class_name = class_name
+        if module == 'numpy' or module.startswith('numpy.'):
+            return super().find_class(module, name)
+        if match_class_name is not None:
+            return self.safe_classes[match_class_name]
         # 如果尝试加载未授权的类，则抛出异常
         raise pickle.UnpicklingError(f"Attempted to deserialize unauthorized class '{name}' from module '{module}'")
 

crazy_functions/latex_fns/latex_toolbox.py

@@ -1,6 +1,8 @@
-import os, shutil
+import os
 import re
+import shutil
 import numpy as np
+from loguru import logger
 
 PRESERVE = 0
 TRANSFORM = 1
@@ -55,7 +57,7 @@ def post_process(root):
                     str_stack.append("{")
                 elif c == "}":
                     if len(str_stack) == 1:
-                        print("stack fix")
+                        logger.warning("fixing brace error")
                         return i
                     str_stack.pop(-1)
                 else:
@@ -601,7 +603,7 @@ def compile_latex_with_timeout(command, cwd, timeout=60):
     except subprocess.TimeoutExpired:
         process.kill()
         stdout, stderr = process.communicate()
-        print("Process timed out!")
+        logger.error("Process timed out (compile_latex_with_timeout)!")
         return False
     return True
 

crazy_functions/live_audio/aliyunASR.py

@@ -1,5 +1,6 @@
-import time, logging, json, sys, struct
+import time, json, sys, struct
 import numpy as np
+from loguru import logger as logging
 from scipy.io.wavfile import WAVE_FORMAT
 
 def write_numpy_to_wave(filename, rate, data, add_header=False):
@@ -106,18 +107,14 @@ def is_speaker_speaking(vad, data, sample_rate):
 class AliyunASR():
 
     def test_on_sentence_begin(self, message, *args):
-        # print("test_on_sentence_begin:{}".format(message))
         pass
 
     def test_on_sentence_end(self, message, *args):
-        # print("test_on_sentence_end:{}".format(message))
         message = json.loads(message)
         self.parsed_sentence = message['payload']['result']
         self.event_on_entence_end.set()
-        # print(self.parsed_sentence)
 
     def test_on_start(self, message, *args):
-        # print("test_on_start:{}".format(message))
         pass
 
     def test_on_error(self, message, *args):
@@ -129,13 +126,11 @@ class AliyunASR():
         pass
 
     def test_on_result_chg(self, message, *args):
-        # print("test_on_chg:{}".format(message))
         message = json.loads(message)
         self.parsed_text = message['payload']['result']
         self.event_on_result_chg.set()
 
     def test_on_completed(self, message, *args):
-        # print("on_completed:args=>{} message=>{}".format(args, message))
         pass
 
     def audio_convertion_thread(self, uuid):
@@ -248,14 +243,14 @@ class AliyunASR():
 
         try:
             response = client.do_action_with_exception(request)
-            print(response)
+            logging.info(response)
             jss = json.loads(response)
             if 'Token' in jss and 'Id' in jss['Token']:
                 token = jss['Token']['Id']
                 expireTime = jss['Token']['ExpireTime']
-                print("token = " + token)
-                print("expireTime = " + str(expireTime))
+                logging.info("token = " + token)
+                logging.info("expireTime = " + str(expireTime))
         except Exception as e:
-            print(e)
+            logging.error(e)
 
         return token

crazy_functions/pdf_fns/breakdown_txt.py

@@ -1,4 +1,5 @@
 from crazy_functions.ipc_fns.mp import run_in_subprocess_with_timeout
+from loguru import logger
 
 def force_breakdown(txt, limit, get_token_fn):
     """ 当无法用标点、空行分割时，我们用最暴力的方法切割
@@ -76,7 +77,7 @@ def cut(limit, get_token_fn, txt_tocut, must_break_at_empty_line, break_anyway=F
             remain_txt_to_cut = post
             remain_txt_to_cut, remain_txt_to_cut_storage = maintain_storage(remain_txt_to_cut, remain_txt_to_cut_storage)
             process = fin_len/total_len
-            print(f'正在文本切分 {int(process*100)}%')
+            logger.info(f'正在文本切分 {int(process*100)}%')
             if len(remain_txt_to_cut.strip()) == 0:
                 break
     return res
@@ -119,7 +120,7 @@ if __name__ == '__main__':
     for i in range(5):
         file_content += file_content
 
-    print(len(file_content))
+    logger.info(len(file_content))
     TOKEN_LIMIT_PER_FRAGMENT = 2500
     res = breakdown_text_to_satisfy_token_limit(file_content, TOKEN_LIMIT_PER_FRAGMENT)
 

crazy_functions/pdf_fns/parse_pdf.py

@@ -4,7 +4,7 @@ from toolbox import promote_file_to_downloadzone
 from toolbox import write_history_to_file, promote_file_to_downloadzone
 from toolbox import get_conf
 from toolbox import ProxyNetworkActivate
-from colorful import *
+from shared_utils.colorful import *
 import requests
 import random
 import copy
@@ -72,7 +72,7 @@ def produce_report_markdown(gpt_response_collection, meta, paper_meta_info, chat
     generated_conclusion_files.append(res_path)
     return res_path
 
-def translate_pdf(article_dict, llm_kwargs, chatbot, fp, generated_conclusion_files, TOKEN_LIMIT_PER_FRAGMENT, DST_LANG):
+def translate_pdf(article_dict, llm_kwargs, chatbot, fp, generated_conclusion_files, TOKEN_LIMIT_PER_FRAGMENT, DST_LANG, plugin_kwargs={}):
     from crazy_functions.pdf_fns.report_gen_html import construct_html
     from crazy_functions.pdf_fns.breakdown_txt import breakdown_text_to_satisfy_token_limit
     from crazy_functions.crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
@@ -138,7 +138,7 @@ def translate_pdf(article_dict, llm_kwargs, chatbot, fp, generated_conclusion_fi
         chatbot=chatbot,
         history_array=[meta for _ in inputs_array],
         sys_prompt_array=[
-            "请你作为一个学术翻译，负责把学术论文准确翻译成中文。注意文章中的每一句话都要翻译。" for _ in inputs_array],
+            "请你作为一个学术翻译，负责把学术论文准确翻译成中文。注意文章中的每一句话都要翻译。" + plugin_kwargs.get("additional_prompt", "") for _ in inputs_array],
     )
     # -=-=-=-=-=-=-=-= 写出Markdown文件 -=-=-=-=-=-=-=-=
     produce_report_markdown(gpt_response_collection, meta, paper_meta_info, chatbot, fp, generated_conclusion_files)

crazy_functions/pdf_fns/parse_pdf_grobid.py

@@ -0,0 +1,26 @@
+import os
+from toolbox import CatchException, report_exception, get_log_folder, gen_time_str, check_packages
+from toolbox import update_ui, promote_file_to_downloadzone, update_ui_lastest_msg, disable_auto_promotion
+from toolbox import write_history_to_file, promote_file_to_downloadzone, get_conf, extract_archive
+from crazy_functions.pdf_fns.parse_pdf import parse_pdf, translate_pdf
+
+def 解析PDF_基于GROBID(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, grobid_url):
+    import copy, json
+    TOKEN_LIMIT_PER_FRAGMENT = 1024
+    generated_conclusion_files = []
+    generated_html_files = []
+    DST_LANG = "中文"
+    from crazy_functions.pdf_fns.report_gen_html import construct_html
+    for index, fp in enumerate(file_manifest):
+        chatbot.append(["当前进度：", f"正在连接GROBID服务，请稍候: {grobid_url}\n如果等待时间过长，请修改config中的GROBID_URL，可修改成本地GROBID服务。"]); yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+        article_dict = parse_pdf(fp, grobid_url)
+        grobid_json_res = os.path.join(get_log_folder(), gen_time_str() + "grobid.json")
+        with open(grobid_json_res, 'w+', encoding='utf8') as f:
+            f.write(json.dumps(article_dict, indent=4, ensure_ascii=False))
+        promote_file_to_downloadzone(grobid_json_res, chatbot=chatbot)
+        if article_dict is None: raise RuntimeError("解析PDF失败，请检查PDF是否损坏。")
+        yield from translate_pdf(article_dict, llm_kwargs, chatbot, fp, generated_conclusion_files, TOKEN_LIMIT_PER_FRAGMENT, DST_LANG, plugin_kwargs=plugin_kwargs)
+    chatbot.append(("给出输出文件清单", str(generated_conclusion_files + generated_html_files)))
+    yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+
+

crazy_functions/pdf_fns/parse_pdf_legacy.py

@@ -0,0 +1,111 @@
+from toolbox import get_log_folder
+from toolbox import update_ui, promote_file_to_downloadzone
+from toolbox import write_history_to_file, promote_file_to_downloadzone
+from crazy_functions.crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
+from crazy_functions.crazy_utils import request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency
+from crazy_functions.crazy_utils import read_and_clean_pdf_text
+from shared_utils.colorful import *
+from loguru import logger
+import os
+
+def 解析PDF_简单拆解(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt):
+    """
+    注意：此函数已经弃用！！新函数位于：crazy_functions/pdf_fns/parse_pdf.py
+    """
+    import copy
+    TOKEN_LIMIT_PER_FRAGMENT = 1024
+    generated_conclusion_files = []
+    generated_html_files = []
+    from crazy_functions.pdf_fns.report_gen_html import construct_html
+    for index, fp in enumerate(file_manifest):
+        # 读取PDF文件
+        file_content, page_one = read_and_clean_pdf_text(fp)
+        file_content = file_content.encode('utf-8', 'ignore').decode()   # avoid reading non-utf8 chars
+        page_one = str(page_one).encode('utf-8', 'ignore').decode()      # avoid reading non-utf8 chars
+
+        # 递归地切割PDF文件
+        from crazy_functions.pdf_fns.breakdown_txt import breakdown_text_to_satisfy_token_limit
+        paper_fragments = breakdown_text_to_satisfy_token_limit(txt=file_content, limit=TOKEN_LIMIT_PER_FRAGMENT, llm_model=llm_kwargs['llm_model'])
+        page_one_fragments = breakdown_text_to_satisfy_token_limit(txt=page_one, limit=TOKEN_LIMIT_PER_FRAGMENT//4, llm_model=llm_kwargs['llm_model'])
+
+        # 为了更好的效果，我们剥离Introduction之后的部分（如果有）
+        paper_meta = page_one_fragments[0].split('introduction')[0].split('Introduction')[0].split('INTRODUCTION')[0]
+
+        # 单线，获取文章meta信息
+        paper_meta_info = yield from request_gpt_model_in_new_thread_with_ui_alive(
+            inputs=f"以下是一篇学术论文的基础信息，请从中提取出“标题”、“收录会议或期刊”、“作者”、“摘要”、“编号”、“作者邮箱”这六个部分。请用markdown格式输出，最后用中文翻译摘要部分。请提取：{paper_meta}",
+            inputs_show_user=f"请从{fp}中提取出“标题”、“收录会议或期刊”等基本信息。",
+            llm_kwargs=llm_kwargs,
+            chatbot=chatbot, history=[],
+            sys_prompt="Your job is to collect information from materials。",
+        )
+
+        # 多线，翻译
+        gpt_response_collection = yield from request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
+            inputs_array=[
+                f"你需要翻译以下内容：\n{frag}" for frag in paper_fragments],
+            inputs_show_user_array=[f"\n---\n 原文： \n\n {frag.replace('#', '')}  \n---\n 翻译：\n " for frag in paper_fragments],
+            llm_kwargs=llm_kwargs,
+            chatbot=chatbot,
+            history_array=[[paper_meta] for _ in paper_fragments],
+            sys_prompt_array=[
+                "请你作为一个学术翻译，负责把学术论文准确翻译成中文。注意文章中的每一句话都要翻译。" + plugin_kwargs.get("additional_prompt", "")
+                for _ in paper_fragments],
+            # max_workers=5  # OpenAI所允许的最大并行过载
+        )
+        gpt_response_collection_md = copy.deepcopy(gpt_response_collection)
+        # 整理报告的格式
+        for i,k in enumerate(gpt_response_collection_md):
+            if i%2==0:
+                gpt_response_collection_md[i] = f"\n\n---\n\n ## 原文[{i//2}/{len(gpt_response_collection_md)//2}]： \n\n {paper_fragments[i//2].replace('#', '')}  \n\n---\n\n ## 翻译[{i//2}/{len(gpt_response_collection_md)//2}]：\n "
+            else:
+                gpt_response_collection_md[i] = gpt_response_collection_md[i]
+        final = ["一、论文概况\n\n---\n\n", paper_meta_info.replace('# ', '### ') + '\n\n---\n\n', "二、论文翻译", ""]
+        final.extend(gpt_response_collection_md)
+        create_report_file_name = f"{os.path.basename(fp)}.trans.md"
+        res = write_history_to_file(final, create_report_file_name)
+        promote_file_to_downloadzone(res, chatbot=chatbot)
+
+        # 更新UI
+        generated_conclusion_files.append(f'{get_log_folder()}/{create_report_file_name}')
+        chatbot.append((f"{fp}完成了吗？", res))
+        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+
+        # write html
+        try:
+            ch = construct_html()
+            orig = ""
+            trans = ""
+            gpt_response_collection_html = copy.deepcopy(gpt_response_collection)
+            for i,k in enumerate(gpt_response_collection_html):
+                if i%2==0:
+                    gpt_response_collection_html[i] = paper_fragments[i//2].replace('#', '')
+                else:
+                    gpt_response_collection_html[i] = gpt_response_collection_html[i]
+            final = ["论文概况", paper_meta_info.replace('# ', '### '),  "二、论文翻译",  ""]
+            final.extend(gpt_response_collection_html)
+            for i, k in enumerate(final):
+                if i%2==0:
+                    orig = k
+                if i%2==1:
+                    trans = k
+                    ch.add_row(a=orig, b=trans)
+            create_report_file_name = f"{os.path.basename(fp)}.trans.html"
+            generated_html_files.append(ch.save_file(create_report_file_name))
+        except:
+            from toolbox import trimmed_format_exc
+            logger.error('writing html result failed:', trimmed_format_exc())
+
+    # 准备文件的下载
+    for pdf_path in generated_conclusion_files:
+        # 重命名文件
+        rename_file = f'翻译-{os.path.basename(pdf_path)}'
+        promote_file_to_downloadzone(pdf_path, rename_file=rename_file, chatbot=chatbot)
+    for html_path in generated_html_files:
+        # 重命名文件
+        rename_file = f'翻译-{os.path.basename(html_path)}'
+        promote_file_to_downloadzone(html_path, rename_file=rename_file, chatbot=chatbot)
+    chatbot.append(("给出输出文件清单", str(generated_conclusion_files + generated_html_files)))
+    yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+
+

crazy_functions/pdf_fns/parse_pdf_via_doc2x.py

@@ -0,0 +1,213 @@
+from toolbox import get_log_folder, gen_time_str, get_conf
+from toolbox import update_ui, promote_file_to_downloadzone
+from toolbox import promote_file_to_downloadzone, extract_archive
+from toolbox import generate_file_link, zip_folder
+from crazy_functions.crazy_utils import get_files_from_everything
+from shared_utils.colorful import *
+import os
+
+def refresh_key(doc2x_api_key):
+    import requests, json
+    url = "https://api.doc2x.noedgeai.com/api/token/refresh"
+    res = requests.post(
+        url,
+        headers={"Authorization": "Bearer " + doc2x_api_key}
+    )
+    res_json = []
+    if res.status_code == 200:
+        decoded = res.content.decode("utf-8")
+        res_json = json.loads(decoded)
+        doc2x_api_key = res_json['data']['token']
+    else:
+        raise RuntimeError(format("[ERROR] status code: %d, body: %s" % (res.status_code, res.text)))
+    return doc2x_api_key
+
+def 解析PDF_DOC2X_转Latex(pdf_file_path):
+    import requests, json, os
+    DOC2X_API_KEY = get_conf('DOC2X_API_KEY')
+    latex_dir = get_log_folder(plugin_name="pdf_ocr_latex")
+    doc2x_api_key = DOC2X_API_KEY
+    if doc2x_api_key.startswith('sk-'):
+        url = "https://api.doc2x.noedgeai.com/api/v1/pdf"
+    else:
+        doc2x_api_key = refresh_key(doc2x_api_key)
+        url = "https://api.doc2x.noedgeai.com/api/platform/pdf"
+
+    res = requests.post(
+        url,
+        files={"file": open(pdf_file_path, "rb")},
+        data={"ocr": "1"},
+        headers={"Authorization": "Bearer " + doc2x_api_key}
+    )
+    res_json = []
+    if res.status_code == 200:
+        decoded = res.content.decode("utf-8")
+        for z_decoded in decoded.split('\n'):
+            if len(z_decoded) == 0: continue
+            assert z_decoded.startswith("data: ")
+            z_decoded = z_decoded[len("data: "):]
+            decoded_json = json.loads(z_decoded)
+            res_json.append(decoded_json)
+    else:
+        raise RuntimeError(format("[ERROR] status code: %d, body: %s" % (res.status_code, res.text)))
+
+    uuid = res_json[0]['uuid']
+    to = "latex" # latex, md, docx
+    url = "https://api.doc2x.noedgeai.com/api/export"+"?request_id="+uuid+"&to="+to
+
+    res = requests.get(url, headers={"Authorization": "Bearer " + doc2x_api_key})
+    latex_zip_path = os.path.join(latex_dir, gen_time_str() + '.zip')
+    latex_unzip_path = os.path.join(latex_dir, gen_time_str())
+    if res.status_code == 200:
+        with open(latex_zip_path, "wb") as f: f.write(res.content)
+    else:
+        raise RuntimeError(format("[ERROR] status code: %d, body: %s" % (res.status_code, res.text)))
+
+    import zipfile
+    with zipfile.ZipFile(latex_zip_path, 'r') as zip_ref:
+        zip_ref.extractall(latex_unzip_path)
+
+
+    return latex_unzip_path
+
+
+
+
+def 解析PDF_DOC2X_单文件(fp, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, DOC2X_API_KEY, user_request):
+
+
+    def pdf2markdown(filepath):
+        import requests, json, os
+        markdown_dir = get_log_folder(plugin_name="pdf_ocr")
+        doc2x_api_key = DOC2X_API_KEY
+        if doc2x_api_key.startswith('sk-'):
+            url = "https://api.doc2x.noedgeai.com/api/v1/pdf"
+        else:
+            doc2x_api_key = refresh_key(doc2x_api_key)
+            url = "https://api.doc2x.noedgeai.com/api/platform/pdf"
+
+        chatbot.append((None, "加载PDF文件，发送至DOC2X解析..."))
+        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+
+        res = requests.post(
+            url,
+            files={"file": open(filepath, "rb")},
+            data={"ocr": "1"},
+            headers={"Authorization": "Bearer " + doc2x_api_key}
+        )
+        res_json = []
+        if res.status_code == 200:
+            decoded = res.content.decode("utf-8")
+            for z_decoded in decoded.split('\n'):
+                if len(z_decoded) == 0: continue
+                assert z_decoded.startswith("data: ")
+                z_decoded = z_decoded[len("data: "):]
+                decoded_json = json.loads(z_decoded)
+                res_json.append(decoded_json)
+            if 'limit exceeded' in decoded_json.get('status', ''):
+                raise RuntimeError("Doc2x API 页数受限，请联系 Doc2x 方面，并更换新的 API 秘钥。")
+        else:
+            raise RuntimeError(format("[ERROR] status code: %d, body: %s" % (res.status_code, res.text)))
+        uuid = res_json[0]['uuid']
+        to = "md" # latex, md, docx
+        url = "https://api.doc2x.noedgeai.com/api/export"+"?request_id="+uuid+"&to="+to
+
+        chatbot.append((None, f"读取解析: {url} ..."))
+        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+
+        res = requests.get(url, headers={"Authorization": "Bearer " + doc2x_api_key})
+        md_zip_path = os.path.join(markdown_dir, gen_time_str() + '.zip')
+        if res.status_code == 200:
+            with open(md_zip_path, "wb") as f: f.write(res.content)
+        else:
+            raise RuntimeError(format("[ERROR] status code: %d, body: %s" % (res.status_code, res.text)))
+        promote_file_to_downloadzone(md_zip_path, chatbot=chatbot)
+        chatbot.append((None, f"完成解析 {md_zip_path} ..."))
+        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+        return md_zip_path
+
+    def deliver_to_markdown_plugin(md_zip_path, user_request):
+        from crazy_functions.Markdown_Translate import Markdown英译中
+        import shutil, re
+
+        time_tag = gen_time_str()
+        target_path_base = get_log_folder(chatbot.get_user())
+        file_origin_name = os.path.basename(md_zip_path)
+        this_file_path = os.path.join(target_path_base, file_origin_name)
+        os.makedirs(target_path_base, exist_ok=True)
+        shutil.copyfile(md_zip_path, this_file_path)
+        ex_folder = this_file_path + ".extract"
+        extract_archive(
+            file_path=this_file_path, dest_dir=ex_folder
+        )
+
+        # edit markdown files
+        success, file_manifest, project_folder = get_files_from_everything(ex_folder, type='.md')
+        for generated_fp in file_manifest:
+            # 修正一些公式问题
+            with open(generated_fp, 'r', encoding='utf8') as f:
+                content = f.read()
+            # 将公式中的\[ \]替换成$$
+            content = content.replace(r'\[', r'$$').replace(r'\]', r'$$')
+            # 将公式中的\( \)替换成$
+            content = content.replace(r'\(', r'$').replace(r'\)', r'$')
+            content = content.replace('```markdown', '\n').replace('```', '\n')
+            with open(generated_fp, 'w', encoding='utf8') as f:
+                f.write(content)
+            promote_file_to_downloadzone(generated_fp, chatbot=chatbot)
+            yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+
+            # 生成在线预览html
+            file_name = '在线预览翻译（原文）' + gen_time_str() + '.html'
+            preview_fp = os.path.join(ex_folder, file_name)
+            from shared_utils.advanced_markdown_format import markdown_convertion_for_file
+            with open(generated_fp, "r", encoding="utf-8") as f:
+                md = f.read()
+            #     # Markdown中使用不标准的表格，需要在表格前加上一个emoji，以便公式渲染
+            #     md = re.sub(r'^<table>', r'.<table>', md, flags=re.MULTILINE)
+            html = markdown_convertion_for_file(md)
+            with open(preview_fp, "w", encoding="utf-8") as f: f.write(html)
+            chatbot.append([None, f"生成在线预览：{generate_file_link([preview_fp])}"])
+            promote_file_to_downloadzone(preview_fp, chatbot=chatbot)
+
+
+
+        chatbot.append((None, f"调用Markdown插件 {ex_folder} ..."))
+        plugin_kwargs['markdown_expected_output_dir'] = ex_folder
+
+        translated_f_name = 'translated_markdown.md'
+        generated_fp = plugin_kwargs['markdown_expected_output_path'] = os.path.join(ex_folder, translated_f_name)
+        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+        yield from Markdown英译中(ex_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request)
+        if os.path.exists(generated_fp):
+            # 修正一些公式问题
+            with open(generated_fp, 'r', encoding='utf8') as f: content = f.read()
+            content = content.replace('```markdown', '\n').replace('```', '\n')
+            # Markdown中使用不标准的表格，需要在表格前加上一个emoji，以便公式渲染
+            # content = re.sub(r'^<table>', r'.<table>', content, flags=re.MULTILINE)
+            with open(generated_fp, 'w', encoding='utf8') as f: f.write(content)
+            # 生成在线预览html
+            file_name = '在线预览翻译' + gen_time_str() + '.html'
+            preview_fp = os.path.join(ex_folder, file_name)
+            from shared_utils.advanced_markdown_format import markdown_convertion_for_file
+            with open(generated_fp, "r", encoding="utf-8") as f:
+                md = f.read()
+            html = markdown_convertion_for_file(md)
+            with open(preview_fp, "w", encoding="utf-8") as f: f.write(html)
+            promote_file_to_downloadzone(preview_fp, chatbot=chatbot)
+            # 生成包含图片的压缩包
+            dest_folder = get_log_folder(chatbot.get_user())
+            zip_name = '翻译后的带图文档.zip'
+            zip_folder(source_folder=ex_folder, dest_folder=dest_folder, zip_name=zip_name)
+            zip_fp = os.path.join(dest_folder, zip_name)
+            promote_file_to_downloadzone(zip_fp, chatbot=chatbot)
+            yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+    md_zip_path = yield from pdf2markdown(fp)
+    yield from deliver_to_markdown_plugin(md_zip_path, user_request)
+
+def 解析PDF_基于DOC2X(file_manifest, *args):
+    for index, fp in enumerate(file_manifest):
+        yield from 解析PDF_DOC2X_单文件(fp, *args)
+    return
+
+

crazy_functions/plugin_template/plugin_class_template.py

@@ -0,0 +1,52 @@
+import os, json, base64
+from pydantic import BaseModel, Field
+from textwrap import dedent
+from typing import List
+
+class ArgProperty(BaseModel): # PLUGIN_ARG_MENU
+    title: str = Field(description="The title", default="")
+    description: str = Field(description="The description", default="")
+    default_value: str = Field(description="The default value", default="")
+    type: str = Field(description="The type", default="")   # currently we support ['string', 'dropdown']
+    options: List[str] = Field(default=[], description="List of options available for the argument") # only used when type is 'dropdown'
+
+class GptAcademicPluginTemplate():
+    def __init__(self):
+        # please note that `execute` method may run in different threads,
+        # thus you should not store any state in the plugin instance,
+        # which may be accessed by multiple threads
+        pass
+
+
+    def define_arg_selection_menu(self):
+        """
+        An example as below:
+            ```
+            def define_arg_selection_menu(self):
+                gui_definition = {
+                    "main_input":
+                        ArgProperty(title="main input", description="description", default_value="default_value", type="string").model_dump_json(),
+                    "advanced_arg":
+                        ArgProperty(title="advanced arguments", description="description", default_value="default_value", type="string").model_dump_json(),
+                    "additional_arg_01":
+                        ArgProperty(title="additional", description="description", default_value="default_value", type="string").model_dump_json(),
+                }
+                return gui_definition
+            ```
+        """
+        raise NotImplementedError("You need to implement this method in your plugin class")
+
+
+    def get_js_code_for_generating_menu(self, btnName):
+        define_arg_selection = self.define_arg_selection_menu()
+
+        if len(define_arg_selection.keys()) > 8:
+            raise ValueError("You can only have up to 8 arguments in the define_arg_selection")
+        # if "main_input" not in define_arg_selection:
+        #     raise ValueError("You must have a 'main_input' in the define_arg_selection")
+
+        DEFINE_ARG_INPUT_INTERFACE = json.dumps(define_arg_selection)
+        return base64.b64encode(DEFINE_ARG_INPUT_INTERFACE.encode('utf-8')).decode('utf-8')
+
+    def execute(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
+        raise NotImplementedError("You need to implement this method in your plugin class")

crazy_functions/prompts/internet.py

@@ -0,0 +1,87 @@
+SearchOptimizerPrompt="""作为一个网页搜索助手，你的任务是结合历史记录，从不同角度，为“原问题”生成个不同版本的“检索词”，从而提高网页检索的精度。生成的问题要求指向对象清晰明确，并与“原问题语言相同”。例如：
+历史记录: 
+"
+Q: 对话背景。
+A: 当前对话是关于 Nginx 的介绍和在Ubuntu上的使用等。
+"
+原问题: 怎么下载
+检索词: ["Nginx 下载","Ubuntu Nginx","Ubuntu安装Nginx"]
+----------------
+历史记录: 
+"
+Q: 对话背景。
+A: 当前对话是关于 Nginx 的介绍和使用等。
+Q: 报错 "no connection"
+A: 报错"no connection"可能是因为……
+"
+原问题: 怎么解决
+检索词: ["Nginx报错"no connection" 解决","Nginx'no connection'报错 原因","Nginx提示'no connection'"]
+----------------
+历史记录:
+"
+
+"
+原问题: 你知道 Python 么？
+检索词: ["Python","Python 使用教程。","Python 特点和优势"]
+----------------
+历史记录:
+"
+Q: 列出Java的三种特点？
+A: 1. Java 是一种编译型语言。
+   2. Java 是一种面向对象的编程语言。
+   3. Java 是一种跨平台的编程语言。
+"
+原问题: 介绍下第2点。
+检索词: ["Java 面向对象特点","Java 面向对象编程优势。","Java 面向对象编程"]
+----------------
+现在有历史记录:
+"
+{history}
+"
+有其原问题: {query}
+直接给出最多{num}个检索词，必须以json形式给出，不得有多余字符:
+"""
+
+SearchAcademicOptimizerPrompt="""作为一个学术论文搜索助手，你的任务是结合历史记录，从不同角度，为“原问题”生成个不同版本的“检索词”，从而提高学术论文检索的精度。生成的问题要求指向对象清晰明确，并与“原问题语言相同”。例如：
+历史记录: 
+"
+Q: 对话背景。
+A: 当前对话是关于深度学习的介绍和在图像识别中的应用等。
+"
+原问题: 怎么下载相关论文
+检索词: ["深度学习 图像识别 论文下载","图像识别 深度学习 研究论文","深度学习 图像识别 论文资源","Deep Learning Image Recognition Paper Download","Image Recognition Deep Learning Research Paper"]
+----------------
+历史记录: 
+"
+Q: 对话背景。
+A: 当前对话是关于深度学习的介绍和应用等。
+Q: 报错 "模型不收敛"
+A: 报错"模型不收敛"可能是因为……
+"
+原问题: 怎么解决
+检索词: ["深度学习 模型不收敛 解决方案 论文","深度学习 模型不收敛 原因 研究","深度学习 模型不收敛 论文","Deep Learning Model Convergence Issue Solution Paper","Deep Learning Model Convergence Problem Research"]
+----------------
+历史记录:
+"
+
+"
+原问题: 你知道 GAN 么？
+检索词: ["生成对抗网络 论文","GAN 使用教程 论文","GAN 特点和优势 研究","Generative Adversarial Network Paper","GAN Usage Tutorial Paper"]
+----------------
+历史记录:
+"
+Q: 列出机器学习的三种应用？
+A: 1. 机器学习在图像识别中的应用。
+   2. 机器学习在自然语言处理中的应用。
+   3. 机器学习在推荐系统中的应用。
+"
+原问题: 介绍下第2点。
+检索词: ["机器学习 自然语言处理 应用 论文","机器学习 自然语言处理 研究","机器学习 NLP 应用 论文","Machine Learning Natural Language Processing Application Paper","Machine Learning NLP Research"]
+----------------
+现在有历史记录:
+"
+{history}
+"
+有其原问题: {query}
+直接给出最多{num}个检索词，必须以json形式给出，不得有多余字符:
+"""

crazy_functions/rag_fns/llama_index_worker.py

@@ -0,0 +1,130 @@
+import llama_index
+import os
+import atexit
+from loguru import logger
+from typing import List
+from llama_index.core import Document
+from llama_index.core.schema import TextNode
+from request_llms.embed_models.openai_embed import OpenAiEmbeddingModel
+from shared_utils.connect_void_terminal import get_chat_default_kwargs
+from llama_index.core import VectorStoreIndex, SimpleDirectoryReader
+from crazy_functions.rag_fns.vector_store_index import GptacVectorStoreIndex
+from llama_index.core.ingestion import run_transformations
+from llama_index.core import PromptTemplate
+from llama_index.core.response_synthesizers import TreeSummarize
+
+DEFAULT_QUERY_GENERATION_PROMPT = """\
+Now, you have context information as below:
+---------------------
+{context_str}
+---------------------
+Answer the user request below (use the context information if necessary, otherwise you can ignore them):
+---------------------
+{query_str}
+"""
+
+QUESTION_ANSWER_RECORD = """\
+{{
+    "type": "This is a previous conversation with the user",
+    "question": "{question}",
+    "answer": "{answer}",
+}}
+"""
+
+
+class SaveLoad():
+
+    def does_checkpoint_exist(self, checkpoint_dir=None):
+        import os, glob
+        if checkpoint_dir is None: checkpoint_dir = self.checkpoint_dir
+        if not os.path.exists(checkpoint_dir): return False
+        if len(glob.glob(os.path.join(checkpoint_dir, "*.json"))) == 0: return False
+        return True
+
+    def save_to_checkpoint(self, checkpoint_dir=None):
+        logger.info(f'saving vector store to: {checkpoint_dir}')
+        if checkpoint_dir is None: checkpoint_dir = self.checkpoint_dir
+        self.vs_index.storage_context.persist(persist_dir=checkpoint_dir)
+
+    def load_from_checkpoint(self, checkpoint_dir=None):
+        if checkpoint_dir is None: checkpoint_dir = self.checkpoint_dir
+        if self.does_checkpoint_exist(checkpoint_dir=checkpoint_dir):
+            logger.info('loading checkpoint from disk')
+            from llama_index.core import StorageContext, load_index_from_storage
+            storage_context = StorageContext.from_defaults(persist_dir=checkpoint_dir)
+            self.vs_index = load_index_from_storage(storage_context, embed_model=self.embed_model)
+            return self.vs_index
+        else:
+            return self.create_new_vs()
+
+    def create_new_vs(self):
+        return GptacVectorStoreIndex.default_vector_store(embed_model=self.embed_model)
+
+    def purge(self):
+        import shutil
+        shutil.rmtree(self.checkpoint_dir, ignore_errors=True)
+        self.vs_index = self.create_new_vs()
+
+
+class LlamaIndexRagWorker(SaveLoad):
+    def __init__(self, user_name, llm_kwargs, auto_load_checkpoint=True, checkpoint_dir=None) -> None:
+        self.debug_mode = True
+        self.embed_model = OpenAiEmbeddingModel(llm_kwargs)
+        self.user_name = user_name
+        self.checkpoint_dir = checkpoint_dir
+        if auto_load_checkpoint:
+            self.vs_index = self.load_from_checkpoint(checkpoint_dir)
+        else:
+            self.vs_index = self.create_new_vs(checkpoint_dir)
+        atexit.register(lambda: self.save_to_checkpoint(checkpoint_dir))
+
+    def assign_embedding_model(self):
+        pass
+
+    def inspect_vector_store(self):
+        # This function is for debugging
+        self.vs_index.storage_context.index_store.to_dict()
+        docstore = self.vs_index.storage_context.docstore.docs
+        vector_store_preview = "\n".join([ f"{_id} | {tn.text}" for _id, tn in docstore.items() ])
+        logger.info('\n++ --------inspect_vector_store begin--------')
+        logger.info(vector_store_preview)
+        logger.info('oo --------inspect_vector_store end--------')
+        return vector_store_preview
+
+    def add_documents_to_vector_store(self, document_list):
+        documents = [Document(text=t) for t in document_list]
+        documents_nodes = run_transformations(
+                        documents,  # type: ignore
+                        self.vs_index._transformations,
+                        show_progress=True
+                    )
+        self.vs_index.insert_nodes(documents_nodes)
+        if self.debug_mode: self.inspect_vector_store()
+
+    def add_text_to_vector_store(self, text):
+        node = TextNode(text=text)
+        documents_nodes = run_transformations(
+                        [node],
+                        self.vs_index._transformations,
+                        show_progress=True
+                    )
+        self.vs_index.insert_nodes(documents_nodes)
+        if self.debug_mode: self.inspect_vector_store()
+
+    def remember_qa(self, question, answer):
+        formatted_str = QUESTION_ANSWER_RECORD.format(question=question, answer=answer)
+        self.add_text_to_vector_store(formatted_str)
+
+    def retrieve_from_store_with_query(self, query):
+        if self.debug_mode: self.inspect_vector_store()
+        retriever = self.vs_index.as_retriever()
+        return retriever.retrieve(query)
+
+    def build_prompt(self, query, nodes):
+        context_str = self.generate_node_array_preview(nodes)
+        return DEFAULT_QUERY_GENERATION_PROMPT.format(context_str=context_str, query_str=query)
+        
+    def generate_node_array_preview(self, nodes):
+        buf = "\n".join(([f"(No.{i+1} | score {n.score:.3f}): {n.text}" for i, n in enumerate(nodes)]))
+        if self.debug_mode: logger.info(buf)
+        return buf

crazy_functions/rag_fns/milvus_worker.py

@@ -0,0 +1,108 @@
+import llama_index
+import os
+import atexit
+from typing import List
+from loguru import logger
+from llama_index.core import Document
+from llama_index.core.schema import TextNode
+from request_llms.embed_models.openai_embed import OpenAiEmbeddingModel
+from shared_utils.connect_void_terminal import get_chat_default_kwargs
+from llama_index.core import VectorStoreIndex, SimpleDirectoryReader
+from crazy_functions.rag_fns.vector_store_index import GptacVectorStoreIndex
+from llama_index.core.ingestion import run_transformations
+from llama_index.core import PromptTemplate
+from llama_index.core.response_synthesizers import TreeSummarize
+from llama_index.core import StorageContext
+from llama_index.vector_stores.milvus import MilvusVectorStore
+from crazy_functions.rag_fns.llama_index_worker import LlamaIndexRagWorker
+
+DEFAULT_QUERY_GENERATION_PROMPT = """\
+Now, you have context information as below:
+---------------------
+{context_str}
+---------------------
+Answer the user request below (use the context information if necessary, otherwise you can ignore them):
+---------------------
+{query_str}
+"""
+
+QUESTION_ANSWER_RECORD = """\
+{{
+    "type": "This is a previous conversation with the user",
+    "question": "{question}",
+    "answer": "{answer}",
+}}
+"""
+
+
+class MilvusSaveLoad():
+
+    def does_checkpoint_exist(self, checkpoint_dir=None):
+        import os, glob
+        if checkpoint_dir is None: checkpoint_dir = self.checkpoint_dir
+        if not os.path.exists(checkpoint_dir): return False
+        if len(glob.glob(os.path.join(checkpoint_dir, "*.json"))) == 0: return False
+        return True
+
+    def save_to_checkpoint(self, checkpoint_dir=None):
+        logger.info(f'saving vector store to: {checkpoint_dir}')
+        # if checkpoint_dir is None: checkpoint_dir = self.checkpoint_dir
+        # self.vs_index.storage_context.persist(persist_dir=checkpoint_dir)
+
+    def load_from_checkpoint(self, checkpoint_dir=None):
+        if checkpoint_dir is None: checkpoint_dir = self.checkpoint_dir
+        if self.does_checkpoint_exist(checkpoint_dir=checkpoint_dir):
+            logger.info('loading checkpoint from disk')
+            from llama_index.core import StorageContext, load_index_from_storage
+            storage_context = StorageContext.from_defaults(persist_dir=checkpoint_dir)
+            try:
+                self.vs_index = load_index_from_storage(storage_context, embed_model=self.embed_model)
+                return self.vs_index
+            except:
+                return self.create_new_vs(checkpoint_dir)
+        else:
+            return self.create_new_vs(checkpoint_dir)
+
+    def create_new_vs(self, checkpoint_dir, overwrite=False):
+        vector_store = MilvusVectorStore(
+            uri=os.path.join(checkpoint_dir, "milvus_demo.db"), 
+            dim=self.embed_model.embedding_dimension(),
+            overwrite=overwrite
+        )
+        storage_context = StorageContext.from_defaults(vector_store=vector_store)
+        index = GptacVectorStoreIndex.default_vector_store(storage_context=storage_context, embed_model=self.embed_model)
+        return index
+
+    def purge(self):
+        self.vs_index = self.create_new_vs(self.checkpoint_dir, overwrite=True)
+
+class MilvusRagWorker(MilvusSaveLoad, LlamaIndexRagWorker):
+
+    def __init__(self, user_name, llm_kwargs, auto_load_checkpoint=True, checkpoint_dir=None) -> None:
+        self.debug_mode = True
+        self.embed_model = OpenAiEmbeddingModel(llm_kwargs)
+        self.user_name = user_name
+        self.checkpoint_dir = checkpoint_dir
+        if auto_load_checkpoint:
+            self.vs_index = self.load_from_checkpoint(checkpoint_dir)
+        else:
+            self.vs_index = self.create_new_vs(checkpoint_dir)
+        atexit.register(lambda: self.save_to_checkpoint(checkpoint_dir))
+
+    def inspect_vector_store(self):
+        # This function is for debugging
+        try:
+            self.vs_index.storage_context.index_store.to_dict()
+            docstore = self.vs_index.storage_context.docstore.docs
+            if not docstore.items():
+                raise ValueError("cannot inspect")
+            vector_store_preview = "\n".join([ f"{_id} | {tn.text}" for _id, tn in docstore.items() ])
+        except:
+            dummy_retrieve_res: List["NodeWithScore"] = self.vs_index.as_retriever().retrieve(' ')
+            vector_store_preview = "\n".join(
+                [f"{node.id_} | {node.text}" for node in dummy_retrieve_res]
+            )
+        logger.info('\n++ --------inspect_vector_store begin--------')
+        logger.info(vector_store_preview)
+        logger.info('oo --------inspect_vector_store end--------')
+        return vector_store_preview

crazy_functions/rag_fns/vector_store_index.py

@@ -0,0 +1,58 @@
+from llama_index.core import VectorStoreIndex
+from typing import Any,  List, Optional
+
+from llama_index.core.callbacks.base import CallbackManager
+from llama_index.core.schema import TransformComponent
+from llama_index.core.service_context import ServiceContext
+from llama_index.core.settings import (
+    Settings,
+    callback_manager_from_settings_or_context,
+    transformations_from_settings_or_context,
+)
+from llama_index.core.storage.storage_context import StorageContext
+
+
+class GptacVectorStoreIndex(VectorStoreIndex):
+    
+    @classmethod
+    def default_vector_store(
+        cls,
+        storage_context: Optional[StorageContext] = None,
+        show_progress: bool = False,
+        callback_manager: Optional[CallbackManager] = None,
+        transformations: Optional[List[TransformComponent]] = None,
+        # deprecated
+        service_context: Optional[ServiceContext] = None,
+        embed_model = None,
+        **kwargs: Any,
+    ):
+        """Create index from documents.
+
+        Args:
+            documents (Optional[Sequence[BaseDocument]]): List of documents to
+                build the index from.
+
+        """
+        storage_context = storage_context or StorageContext.from_defaults()
+        docstore = storage_context.docstore
+        callback_manager = (
+            callback_manager
+            or callback_manager_from_settings_or_context(Settings, service_context)
+        )
+        transformations = transformations or transformations_from_settings_or_context(
+            Settings, service_context
+        )
+
+        with callback_manager.as_trace("index_construction"):
+
+            return cls(
+                nodes=[],
+                storage_context=storage_context,
+                callback_manager=callback_manager,
+                show_progress=show_progress,
+                transformations=transformations,
+                service_context=service_context,
+                embed_model=embed_model,
+                **kwargs,
+            )
+

crazy_functions/vector_fns/vector_database.py

@@ -1,16 +1,17 @@
 # From project chatglm-langchain
 
-import threading
-from toolbox import Singleton
 import os
-import shutil
 import os
 import uuid
 import tqdm
+import shutil
+import threading
+import numpy as np
+from toolbox import Singleton
+from loguru import logger
 from langchain.vectorstores import FAISS
 from langchain.docstore.document import Document
 from typing import List, Tuple
-import numpy as np
 from crazy_functions.vector_fns.general_file_loader import load_file
 
 embedding_model_dict = {
@@ -150,17 +151,17 @@ class LocalDocQA:
         failed_files = []
         if isinstance(filepath, str):
             if not os.path.exists(filepath):
-                print("路径不存在")
+                logger.error("路径不存在")
                 return None
             elif os.path.isfile(filepath):
                 file = os.path.split(filepath)[-1]
                 try:
                     docs = load_file(filepath, SENTENCE_SIZE)
-                    print(f"{file} 已成功加载")
+                    logger.info(f"{file} 已成功加载")
                     loaded_files.append(filepath)
                 except Exception as e:
-                    print(e)
-                    print(f"{file} 未能成功加载")
+                    logger.error(e)
+                    logger.error(f"{file} 未能成功加载")
                     return None
             elif os.path.isdir(filepath):
                 docs = []
@@ -170,23 +171,23 @@ class LocalDocQA:
                         docs += load_file(fullfilepath, SENTENCE_SIZE)
                         loaded_files.append(fullfilepath)
                     except Exception as e:
-                        print(e)
+                        logger.error(e)
                         failed_files.append(file)
 
                 if len(failed_files) > 0:
-                    print("以下文件未能成功加载：")
+                    logger.error("以下文件未能成功加载：")
                     for file in failed_files:
-                        print(f"{file}\n")
+                        logger.error(f"{file}\n")
 
         else:
             docs = []
             for file in filepath:
                 docs += load_file(file, SENTENCE_SIZE)
-                print(f"{file} 已成功加载")
+                logger.info(f"{file} 已成功加载")
                 loaded_files.append(file)
 
         if len(docs) > 0:
-            print("文件加载完毕，正在生成向量库")
+            logger.info("文件加载完毕，正在生成向量库")
             if vs_path and os.path.isdir(vs_path):
                 try:
                     self.vector_store = FAISS.load_local(vs_path, text2vec)
@@ -233,7 +234,7 @@ class LocalDocQA:
         prompt += "\n\n".join([f"({k}): " + doc.page_content for k, doc in enumerate(related_docs_with_score)])
         prompt += "\n\n---\n\n"
         prompt = prompt.encode('utf-8', 'ignore').decode()   # avoid reading non-utf8 chars
-        # print(prompt)
+        # logger.info(prompt)
         response = {"query": query, "source_documents": related_docs_with_score}
         return response, prompt
 
@@ -262,7 +263,7 @@ def construct_vector_store(vs_id, vs_path, files, sentence_size, history, one_co
     else:
         pass
         # file_status = "文件未成功加载，请重新上传文件"
-    # print(file_status)
+    # logger.info(file_status)
     return local_doc_qa, vs_path
 
 @Singleton
@@ -278,7 +279,7 @@ class knowledge_archive_interface():
         if self.text2vec_large_chinese is None:
             # < -------------------预热文本向量化模组--------------- >
             from toolbox import ProxyNetworkActivate
-            print('Checking Text2vec ...')
+            logger.info('Checking Text2vec ...')
             from langchain.embeddings.huggingface import HuggingFaceEmbeddings
             with ProxyNetworkActivate('Download_LLM'):    # 临时地激活代理网络
                 self.text2vec_large_chinese = HuggingFaceEmbeddings(model_name="GanymedeNil/text2vec-large-chinese")

crazy_functions/vt_fns/vt_call_plugin.py

@@ -10,7 +10,7 @@ def read_avail_plugin_enum():
     from crazy_functional import get_crazy_functions
     plugin_arr = get_crazy_functions()
     # remove plugins with out explaination
-    plugin_arr = {k:v for k, v in plugin_arr.items() if 'Info' in v}
+    plugin_arr = {k:v for k, v in plugin_arr.items() if ('Info' in v) and ('Function' in v)}
     plugin_arr_info = {"F_{:04d}".format(i):v["Info"] for i, v in enumerate(plugin_arr.values(), start=1)}
     plugin_arr_dict = {"F_{:04d}".format(i):v for i, v in enumerate(plugin_arr.values(), start=1)}
     plugin_arr_dict_parse = {"F_{:04d}".format(i):v for i, v in enumerate(plugin_arr.values(), start=1)}

crazy_functions/下载arxiv论文翻译摘要.py

@@ -1,17 +1,19 @@
+import re, requests, unicodedata, os
 from toolbox import update_ui, get_log_folder
 from toolbox import write_history_to_file, promote_file_to_downloadzone
 from toolbox import CatchException, report_exception, get_conf
-import re, requests, unicodedata, os
-from .crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
+from crazy_functions.crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
+from loguru import logger
+
 def download_arxiv_(url_pdf):
     if 'arxiv.org' not in url_pdf:
         if ('.' in url_pdf) and ('/' not in url_pdf):
             new_url = 'https://arxiv.org/abs/'+url_pdf
-            print('下载编号：', url_pdf, '自动定位：', new_url)
+            logger.info('下载编号：', url_pdf, '自动定位：', new_url)
             # download_arxiv_(new_url)
             return download_arxiv_(new_url)
         else:
-            print('不能识别的URL！')
+            logger.info('不能识别的URL！')
             return None
     if 'abs' in url_pdf:
         url_pdf = url_pdf.replace('abs', 'pdf')
@@ -42,15 +44,12 @@ def download_arxiv_(url_pdf):
     requests_pdf_url = url_pdf
     file_path = download_dir+title_str
 
-    print('下载中')
+    logger.info('下载中')
     proxies = get_conf('proxies')
     r = requests.get(requests_pdf_url, proxies=proxies)
     with open(file_path, 'wb+') as f:
         f.write(r.content)
-    print('下载完成')
-
-    # print('输出下载命令：','aria2c -o \"%s\" %s'%(title_str,url_pdf))
-    # subprocess.call('aria2c --all-proxy=\"172.18.116.150:11084\" -o \"%s\" %s'%(download_dir+title_str,url_pdf), shell=True)
+    logger.info('下载完成')
 
     x = "%s  %s %s.bib" % (paper_id, other_info['year'], other_info['authors'])
     x = x.replace('?', '？')\
@@ -63,19 +62,9 @@ def download_arxiv_(url_pdf):
 
 
 def get_name(_url_):
-    import os
     from bs4 import BeautifulSoup
-    print('正在获取文献名！')
-    print(_url_)
-
-    # arxiv_recall = {}
-    # if os.path.exists('./arxiv_recall.pkl'):
-    #     with open('./arxiv_recall.pkl', 'rb') as f:
-    #         arxiv_recall = pickle.load(f)
-
-    # if _url_ in arxiv_recall:
-    #     print('在缓存中')
-    #     return arxiv_recall[_url_]
+    logger.info('正在获取文献名！')
+    logger.info(_url_)
 
     proxies = get_conf('proxies')
     res = requests.get(_url_, proxies=proxies)
@@ -92,7 +81,7 @@ def get_name(_url_):
         other_details['abstract'] = abstract
     except:
         other_details['year'] = ''
-        print('年份获取失败')
+        logger.info('年份获取失败')
 
     # get author
     try:
@@ -101,7 +90,7 @@ def get_name(_url_):
         other_details['authors'] = authors
     except:
         other_details['authors'] = ''
-        print('authors获取失败')
+        logger.info('authors获取失败')
 
     # get comment
     try:
@@ -116,11 +105,11 @@ def get_name(_url_):
             other_details['comment'] = ''
     except:
         other_details['comment'] = ''
-        print('年份获取失败')
+        logger.info('年份获取失败')
 
     title_str = BeautifulSoup(
         res.text, 'html.parser').find('title').contents[0]
-    print('获取成功：', title_str)
+    logger.info('获取成功：', title_str)
     # arxiv_recall[_url_] = (title_str+'.pdf', other_details)
     # with open('./arxiv_recall.pkl', 'wb') as f:
     #     pickle.dump(arxiv_recall, f)

crazy_functions/交互功能函数模板.py

@@ -1,6 +1,5 @@
 from toolbox import CatchException, update_ui
-from .crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
-
+from crazy_functions.crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
 
 @CatchException
 def 交互功能模板函数(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):

crazy_functions/函数动态生成.py

@@ -16,8 +16,8 @@ Testing:
 
 from toolbox import CatchException, update_ui, gen_time_str, trimmed_format_exc, is_the_upload_folder
 from toolbox import promote_file_to_downloadzone, get_log_folder, update_ui_lastest_msg
-from .crazy_utils import request_gpt_model_in_new_thread_with_ui_alive, get_plugin_arg
-from .crazy_utils import input_clipping, try_install_deps
+from crazy_functions.crazy_utils import request_gpt_model_in_new_thread_with_ui_alive, get_plugin_arg
+from crazy_functions.crazy_utils import input_clipping, try_install_deps
 from crazy_functions.gen_fns.gen_fns_shared import is_function_successfully_generated
 from crazy_functions.gen_fns.gen_fns_shared import get_class_name
 from crazy_functions.gen_fns.gen_fns_shared import subprocess_worker

crazy_functions/命令行助手.py

@@ -1,6 +1,6 @@
 from toolbox import CatchException, update_ui, gen_time_str
-from .crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
-from .crazy_utils import input_clipping
+from crazy_functions.crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
+from crazy_functions.crazy_utils import input_clipping
 import copy, json
 
 @CatchException

crazy_functions/多智能体.py

@@ -6,13 +6,14 @@
 """
 
 
+import time
 from toolbox import CatchException, update_ui, gen_time_str, trimmed_format_exc, ProxyNetworkActivate
 from toolbox import get_conf, select_api_key, update_ui_lastest_msg, Singleton
 from crazy_functions.crazy_utils import request_gpt_model_in_new_thread_with_ui_alive, get_plugin_arg
 from crazy_functions.crazy_utils import input_clipping, try_install_deps
 from crazy_functions.agent_fns.persistent import GradioMultiuserManagerForPersistentClasses
 from crazy_functions.agent_fns.auto_agent import AutoGenMath
-import time
+from loguru import logger
 
 def remove_model_prefix(llm):
     if llm.startswith('api2d-'): llm = llm.replace('api2d-', '')
@@ -80,12 +81,12 @@ def 多智能体终端(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_
     persistent_key = f"{user_uuid}->多智能体终端"
     if persistent_class_multi_user_manager.already_alive(persistent_key):
         # 当已经存在一个正在运行的多智能体终端时，直接将用户输入传递给它，而不是再次启动一个新的多智能体终端
-        print('[debug] feed new user input')
+        logger.info('[debug] feed new user input')
         executor = persistent_class_multi_user_manager.get(persistent_key)
         exit_reason = yield from executor.main_process_ui_control(txt, create_or_resume="resume")
     else:
         # 运行多智能体终端 (首次)
-        print('[debug] create new executor instance')
+        logger.info('[debug] create new executor instance')
         history = []
         chatbot.append(["正在启动: 多智能体终端", "插件动态生成, 执行开始, 作者 Microsoft & Binary-Husky."])
         yield from update_ui(chatbot=chatbot, history=history) # 刷新界面

crazy_functions/总结word文档.py

@@ -1,7 +1,7 @@
 from toolbox import update_ui
 from toolbox import CatchException, report_exception
 from toolbox import write_history_to_file, promote_file_to_downloadzone
-from .crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
+from crazy_functions.crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
 fast_debug = False
 
 

crazy_functions/总结音视频.py

@@ -1,5 +1,5 @@
 from toolbox import CatchException, report_exception, select_api_key, update_ui, get_conf
-from .crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
+from crazy_functions.crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
 from toolbox import write_history_to_file, promote_file_to_downloadzone, get_log_folder
 
 def split_audio_file(filename, split_duration=1000):

crazy_functions/批量总结PDF文档.py

@@ -1,16 +1,18 @@
+from loguru import logger
+
 from toolbox import update_ui, promote_file_to_downloadzone, gen_time_str
 from toolbox import CatchException, report_exception
 from toolbox import write_history_to_file, promote_file_to_downloadzone
-from .crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
-from .crazy_utils import read_and_clean_pdf_text
-from .crazy_utils import input_clipping
+from crazy_functions.crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
+from crazy_functions.crazy_utils import read_and_clean_pdf_text
+from crazy_functions.crazy_utils import input_clipping
 
 
 
 def 解析PDF(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt):
     file_write_buffer = []
     for file_name in file_manifest:
-        print('begin analysis on:', file_name)
+        logger.info('begin analysis on:', file_name)
         ############################## <第 0 步，切割PDF> ##################################
         # 递归地切割PDF文件，每一块（尽量是完整的一个section，比如introduction，experiment等，必要时再进行切割）
         # 的长度必须小于 2500 个 Token
@@ -38,7 +40,7 @@ def 解析PDF(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot,
         last_iteration_result = paper_meta  # 初始值是摘要
         MAX_WORD_TOTAL = 4096 * 0.7
         n_fragment = len(paper_fragments)
-        if n_fragment >= 20: print('文章极长，不能达到预期效果')
+        if n_fragment >= 20: logger.warning('文章极长，不能达到预期效果')
         for i in range(n_fragment):
             NUM_OF_WORD = MAX_WORD_TOTAL // n_fragment
             i_say = f"Read this section, recapitulate the content of this section with less than {NUM_OF_WORD} Chinese characters: {paper_fragments[i]}"

crazy_functions/批量总结PDF文档pdfminer.py

@@ -1,6 +1,7 @@
+from loguru import logger
 from toolbox import update_ui
 from toolbox import CatchException, report_exception
-from .crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
+from crazy_functions.crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
 from toolbox import write_history_to_file, promote_file_to_downloadzone
 
 fast_debug = False
@@ -57,7 +58,6 @@ def readPdf(pdfPath):
         layout = device.get_result()
         for obj in layout._objs:
             if isinstance(obj, pdfminer.layout.LTTextBoxHorizontal):
-                # print(obj.get_text())
                 outTextList.append(obj.get_text())
 
     return outTextList
@@ -66,7 +66,7 @@ def readPdf(pdfPath):
 def 解析Paper(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt):
     import time, glob, os
     from bs4 import BeautifulSoup
-    print('begin analysis on:', file_manifest)
+    logger.info('begin analysis on:', file_manifest)
     for index, fp in enumerate(file_manifest):
         if ".tex" in fp:
             with open(fp, 'r', encoding='utf-8', errors='replace') as f:
@@ -77,7 +77,7 @@ def 解析Paper(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbo
 
         prefix = "接下来请你逐文件分析下面的论文文件，概括其内容" if index==0 else ""
         i_say = prefix + f'请对下面的文章片段用中文做一个概述，文件名是{os.path.relpath(fp, project_folder)}，文章内容是 ```{file_content}```'
-        i_say_show_user = prefix + f'[{index}/{len(file_manifest)}] 请对下面的文章片段做一个概述: {os.path.abspath(fp)}'
+        i_say_show_user = prefix + f'[{index+1}/{len(file_manifest)}] 请对下面的文章片段做一个概述: {os.path.abspath(fp)}'
         chatbot.append((i_say_show_user, "[Local Message] waiting gpt response."))
         yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
 

crazy_functions/批量翻译PDF文档_NOUGAT.py

@@ -1,11 +1,11 @@
 from toolbox import CatchException, report_exception, get_log_folder, gen_time_str
 from toolbox import update_ui, promote_file_to_downloadzone, update_ui_lastest_msg, disable_auto_promotion
 from toolbox import write_history_to_file, promote_file_to_downloadzone
-from .crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
-from .crazy_utils import request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency
-from .crazy_utils import read_and_clean_pdf_text
+from crazy_functions.crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
+from crazy_functions.crazy_utils import request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency
+from crazy_functions.crazy_utils import read_and_clean_pdf_text
 from .pdf_fns.parse_pdf import parse_pdf, get_avail_grobid_url, translate_pdf
-from colorful import *
+from shared_utils.colorful import *
 import copy
 import os
 import math
@@ -60,7 +60,7 @@ def 批量翻译PDF文档(txt, llm_kwargs, plugin_kwargs, chatbot, history, syst
     # 清空历史，以免输入溢出
     history = []
 
-    from .crazy_utils import get_files_from_everything
+    from crazy_functions.crazy_utils import get_files_from_everything
     success, file_manifest, project_folder = get_files_from_everything(txt, type='.pdf')
     if len(file_manifest) > 0:
         # 尝试导入依赖，如果缺少依赖，则给出安装建议

crazy_functions/数学动画生成manim.py

@@ -1,4 +1,5 @@
 import os
+from loguru import logger
 from toolbox import CatchException, update_ui, gen_time_str, promote_file_to_downloadzone
 from crazy_functions.crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
 from crazy_functions.crazy_utils import input_clipping
@@ -34,10 +35,10 @@ def eval_manim(code):
         return f'gpt_log/{time_str}.mp4'
     except subprocess.CalledProcessError as e:
         output = e.output.decode()
-        print(f"Command returned non-zero exit status {e.returncode}: {output}.")
+        logger.error(f"Command returned non-zero exit status {e.returncode}: {output}.")
         return f"Evaluating python script failed: {e.output}."
     except:
-        print('generating mp4 failed')
+        logger.error('generating mp4 failed')
         return "Generating mp4 failed."
 
 

crazy_functions/理解PDF文档内容.py

@@ -1,13 +1,12 @@
+from loguru import logger
 from toolbox import update_ui
 from toolbox import CatchException, report_exception
-from .crazy_utils import read_and_clean_pdf_text
-from .crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
-fast_debug = False
+from crazy_functions.crazy_utils import read_and_clean_pdf_text
+from crazy_functions.crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
 
 
 def 解析PDF(file_name, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt):
-    import tiktoken
-    print('begin analysis on:', file_name)
+    logger.info('begin analysis on:', file_name)
 
     ############################## <第 0 步，切割PDF> ##################################
     # 递归地切割PDF文件，每一块（尽量是完整的一个section，比如introduction，experiment等，必要时再进行切割）
@@ -36,7 +35,7 @@ def 解析PDF(file_name, llm_kwargs, plugin_kwargs, chatbot, history, system_pro
     last_iteration_result = paper_meta  # 初始值是摘要
     MAX_WORD_TOTAL = 4096
     n_fragment = len(paper_fragments)
-    if n_fragment >= 20: print('文章极长，不能达到预期效果')
+    if n_fragment >= 20: logger.warning('文章极长，不能达到预期效果')
     for i in range(n_fragment):
         NUM_OF_WORD = MAX_WORD_TOTAL // n_fragment
         i_say = f"Read this section, recapitulate the content of this section with less than {NUM_OF_WORD} words: {paper_fragments[i]}"
@@ -57,7 +56,7 @@ def 解析PDF(file_name, llm_kwargs, plugin_kwargs, chatbot, history, system_pro
     chatbot.append([i_say_show_user, gpt_say])
 
     ############################## <第 4 步，设置一个token上限，防止回答时Token溢出> ##################################
-    from .crazy_utils import input_clipping
+    from crazy_functions.crazy_utils import input_clipping
     _, final_results = input_clipping("", final_results, max_token_limit=3200)
     yield from update_ui(chatbot=chatbot, history=final_results) # 注意这里的历史记录被替代了
 

crazy_functions/生成函数注释.py

@@ -1,22 +1,21 @@
+from loguru import logger
 from toolbox import update_ui
 from toolbox import CatchException, report_exception
 from toolbox import write_history_to_file, promote_file_to_downloadzone
-from .crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
-fast_debug = False
+from crazy_functions.crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
 
 def 生成函数注释(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt):
     import time, os
-    print('begin analysis on:', file_manifest)
+    logger.info('begin analysis on:', file_manifest)
     for index, fp in enumerate(file_manifest):
         with open(fp, 'r', encoding='utf-8', errors='replace') as f:
             file_content = f.read()
 
         i_say = f'请对下面的程序文件做一个概述，并对文件中的所有函数生成注释，使用markdown表格输出结果，文件名是{os.path.relpath(fp, project_folder)}，文件内容是 ```{file_content}```'
-        i_say_show_user = f'[{index}/{len(file_manifest)}] 请对下面的程序文件做一个概述，并对文件中的所有函数生成注释: {os.path.abspath(fp)}'
+        i_say_show_user = f'[{index+1}/{len(file_manifest)}] 请对下面的程序文件做一个概述，并对文件中的所有函数生成注释: {os.path.abspath(fp)}'
         chatbot.append((i_say_show_user, "[Local Message] waiting gpt response."))
         yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
 
-        if not fast_debug:
         msg = '正常'
         # ** gpt request **
         gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
@@ -25,9 +24,8 @@ def 生成函数注释(file_manifest, project_folder, llm_kwargs, plugin_kwargs,
         chatbot[-1] = (i_say_show_user, gpt_say)
         history.append(i_say_show_user); history.append(gpt_say)
         yield from update_ui(chatbot=chatbot, history=history, msg=msg) # 刷新界面
-            if not fast_debug: time.sleep(2)
+        time.sleep(2)
 
-    if not fast_debug:
     res = write_history_to_file(history)
     promote_file_to_downloadzone(res, chatbot=chatbot)
     chatbot.append(("完成了吗？", res))

crazy_functions/生成多种Mermaid图表.py

@@ -1,6 +1,9 @@
 from toolbox import CatchException, update_ui, report_exception
-from .crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
-import datetime
+from crazy_functions.crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
+from crazy_functions.plugin_template.plugin_class_template import (
+    GptAcademicPluginTemplate,
+)
+from crazy_functions.plugin_template.plugin_class_template import ArgProperty
 
 # 以下是每类图表的PROMPT
 SELECT_PROMPT = """
@@ -20,19 +23,21 @@ SELECT_PROMPT = """
 # 没有思维导图!!!测试发现模型始终会优先选择思维导图
 # 流程图
 PROMPT_1 = """
-请你给出围绕“{subject}”的逻辑关系图，使用mermaid语法，mermaid语法举例：
+请你给出围绕“{subject}”的逻辑关系图，使用mermaid语法，注意需要使用双引号将内容括起来。
+mermaid语法举例：
 ```mermaid
 graph TD
-    P(编程) --> L1(Python)
-    P(编程) --> L2(C)
-    P(编程) --> L3(C++)
-    P(编程) --> L4(Javascipt)
-    P(编程) --> L5(PHP)
+    P("编程") --> L1("Python")
+    P("编程") --> L2("C")
+    P("编程") --> L3("C++")
+    P("编程") --> L4("Javascipt")
+    P("编程") --> L5("PHP")
 ```
 """
 # 序列图
 PROMPT_2 = """
-请你给出围绕“{subject}”的序列图，使用mermaid语法，mermaid语法举例：
+请你给出围绕“{subject}”的序列图，使用mermaid语法。
+mermaid语法举例：
 ```mermaid
 sequenceDiagram
     participant A as 用户
@@ -45,7 +50,8 @@ sequenceDiagram
 """
 # 类图
 PROMPT_3 = """
-请你给出围绕“{subject}”的类图，使用mermaid语法，mermaid语法举例：
+请你给出围绕“{subject}”的类图，使用mermaid语法。
+mermaid语法举例：
 ```mermaid
 classDiagram
     Class01 <|-- AveryLongClass : Cool
@@ -65,7 +71,8 @@ classDiagram
 """
 # 饼图
 PROMPT_4 = """
-请你给出围绕“{subject}”的饼图，使用mermaid语法，mermaid语法举例：
+请你给出围绕“{subject}”的饼图，使用mermaid语法，注意需要使用双引号将内容括起来。
+mermaid语法举例：
 ```mermaid
 pie title Pets adopted by volunteers
     "狗" : 386
@@ -75,36 +82,39 @@ pie title Pets adopted by volunteers
 """
 # 甘特图
 PROMPT_5 = """
-请你给出围绕“{subject}”的甘特图，使用mermaid语法，mermaid语法举例：
+请你给出围绕“{subject}”的甘特图，使用mermaid语法，注意需要使用双引号将内容括起来。
+mermaid语法举例：
 ```mermaid
 gantt
-    title 项目开发流程
+    title "项目开发流程"
     dateFormat  YYYY-MM-DD
-    section 设计
-    需求分析 :done, des1, 2024-01-06,2024-01-08
-    原型设计 :active, des2, 2024-01-09, 3d
-    UI设计 : des3, after des2, 5d
-    section 开发
-    前端开发 :2024-01-20, 10d
-    后端开发 :2024-01-20, 10d
+    section "设计"
+    "需求分析" :done, des1, 2024-01-06,2024-01-08
+    "原型设计" :active, des2, 2024-01-09, 3d
+    "UI设计" : des3, after des2, 5d
+    section "开发"
+    "前端开发" :2024-01-20, 10d
+    "后端开发" :2024-01-20, 10d
 ```
 """
 # 状态图
 PROMPT_6 = """
-请你给出围绕“{subject}”的状态图，使用mermaid语法，mermaid语法举例：
+请你给出围绕“{subject}”的状态图，使用mermaid语法，注意需要使用双引号将内容括起来。
+mermaid语法举例：
 ```mermaid
 stateDiagram-v2
-   [*] --> Still
-    Still --> [*]
-    Still --> Moving
-    Moving --> Still
-    Moving --> Crash
-    Crash --> [*]
+   [*] --> "Still"
+    "Still" --> [*]
+    "Still" --> "Moving"
+    "Moving" --> "Still"
+    "Moving" --> "Crash"
+    "Crash" --> [*]
 ```
 """
 # 实体关系图
 PROMPT_7 = """
-请你给出围绕“{subject}”的实体关系图，使用mermaid语法，mermaid语法举例：
+请你给出围绕“{subject}”的实体关系图，使用mermaid语法。
+mermaid语法举例：
 ```mermaid
 erDiagram
     CUSTOMER ||--o{ ORDER : places
@@ -126,116 +136,170 @@ erDiagram
 """
 # 象限提示图
 PROMPT_8 = """
-请你给出围绕“{subject}”的象限图，使用mermaid语法，mermaid语法举例：
+请你给出围绕“{subject}”的象限图，使用mermaid语法，注意需要使用双引号将内容括起来。
+mermaid语法举例：
 ```mermaid
 graph LR
-    A[Hard skill] --> B(Programming)
-    A[Hard skill] --> C(Design)
-    D[Soft skill] --> E(Coordination)
-    D[Soft skill] --> F(Communication)
+    A["Hard skill"] --> B("Programming")
+    A["Hard skill"] --> C("Design")
+    D["Soft skill"] --> E("Coordination")
+    D["Soft skill"] --> F("Communication")
 ```
 """
 # 思维导图
 PROMPT_9 = """
 {subject}
 ==========
-请给出上方内容的思维导图，充分考虑其之间的逻辑，使用mermaid语法，mermaid语法举例：
+请给出上方内容的思维导图，充分考虑其之间的逻辑，使用mermaid语法，注意需要使用双引号将内容括起来。
+mermaid语法举例：
 ```mermaid
 mindmap
   root((mindmap))
-    Origins
-      Long history
+    ("Origins")
+      ("Long history")
       ::icon(fa fa-book)
-      Popularisation
-        British popular psychology author Tony Buzan
-    Research
-      On effectiveness<br/>and features
-      On Automatic creation
-        Uses
-            Creative techniques
-            Strategic planning
-            Argument mapping
-    Tools
-      Pen and paper
-      Mermaid
+      ("Popularisation")
+        ("British popular psychology author Tony Buzan")
+        ::icon(fa fa-user)
+    ("Research")
+      ("On effectiveness<br/>and features")
+      ::icon(fa fa-search)
+      ("On Automatic creation")
+      ::icon(fa fa-robot)
+        ("Uses")
+            ("Creative techniques")
+            ::icon(fa fa-lightbulb-o)
+            ("Strategic planning")
+            ::icon(fa fa-flag)
+            ("Argument mapping")
+            ::icon(fa fa-comments)
+    ("Tools")
+      ("Pen and paper")
+      ::icon(fa fa-pencil)
+      ("Mermaid")
+      ::icon(fa fa-code)
 ```
 """
 
+
 def 解析历史输入(history, llm_kwargs, file_manifest, chatbot, plugin_kwargs):
     ############################## <第 0 步，切割输入> ##################################
     # 借用PDF切割中的函数对文本进行切割
     TOKEN_LIMIT_PER_FRAGMENT = 2500
-    txt = str(history).encode('utf-8', 'ignore').decode()   # avoid reading non-utf8 chars
-    from crazy_functions.pdf_fns.breakdown_txt import breakdown_text_to_satisfy_token_limit
-    txt = breakdown_text_to_satisfy_token_limit(txt=txt, limit=TOKEN_LIMIT_PER_FRAGMENT, llm_model=llm_kwargs['llm_model'])
+    txt = (
+        str(history).encode("utf-8", "ignore").decode()
+    )  # avoid reading non-utf8 chars
+    from crazy_functions.pdf_fns.breakdown_txt import (
+        breakdown_text_to_satisfy_token_limit,
+    )
+
+    txt = breakdown_text_to_satisfy_token_limit(
+        txt=txt, limit=TOKEN_LIMIT_PER_FRAGMENT, llm_model=llm_kwargs["llm_model"]
+    )
     ############################## <第 1 步，迭代地历遍整个文章，提取精炼信息> ##################################
     results = []
     MAX_WORD_TOTAL = 4096
     n_txt = len(txt)
     last_iteration_result = "从以下文本中提取摘要。"
-    if n_txt >= 20: print('文章极长，不能达到预期效果')
+
     for i in range(n_txt):
         NUM_OF_WORD = MAX_WORD_TOTAL // n_txt
         i_say = f"Read this section, recapitulate the content of this section with less than {NUM_OF_WORD} words in Chinese: {txt[i]}"
         i_say_show_user = f"[{i+1}/{n_txt}] Read this section, recapitulate the content of this section with less than {NUM_OF_WORD} words: {txt[i][:200]} ...."
-        gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(i_say, i_say_show_user,  # i_say=真正给chatgpt的提问， i_say_show_user=给用户看的提问
-                                                                           llm_kwargs, chatbot,
-                                                                           history=["The main content of the previous section is?", last_iteration_result], # 迭代上一次的结果
-                                                                           sys_prompt="Extracts the main content from the text section where it is located for graphing purposes, answer me with Chinese."  # 提示
+        gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
+            i_say,
+            i_say_show_user,  # i_say=真正给chatgpt的提问， i_say_show_user=给用户看的提问
+            llm_kwargs,
+            chatbot,
+            history=[
+                "The main content of the previous section is?",
+                last_iteration_result,
+            ],  # 迭代上一次的结果
+            sys_prompt="Extracts the main content from the text section where it is located for graphing purposes, answer me with Chinese.",  # 提示
         )
         results.append(gpt_say)
         last_iteration_result = gpt_say
     ############################## <第 2 步，根据整理的摘要选择图表类型> ##################################
-    if ("advanced_arg" in plugin_kwargs) and (plugin_kwargs["advanced_arg"] == ""): plugin_kwargs.pop("advanced_arg")
-    gpt_say = plugin_kwargs.get("advanced_arg", "")     #将图表类型参数赋值为插件参数
-    results_txt = '\n'.join(results)    #合并摘要
-    if gpt_say not in ['1','2','3','4','5','6','7','8','9']:    #如插件参数不正确则使用对话模型判断
-        i_say_show_user = f'接下来将判断适合的图表类型,如连续3次判断失败将会使用流程图进行绘制'; gpt_say = "[Local Message] 收到。"   # 用户提示
-        chatbot.append([i_say_show_user, gpt_say]); yield from update_ui(chatbot=chatbot, history=[])    # 更新UI
+    gpt_say = str(plugin_kwargs)  # 将图表类型参数赋值为插件参数
+    results_txt = "\n".join(results)  # 合并摘要
+    if gpt_say not in [
+        "1",
+        "2",
+        "3",
+        "4",
+        "5",
+        "6",
+        "7",
+        "8",
+        "9",
+    ]:  # 如插件参数不正确则使用对话模型判断
+        i_say_show_user = (
+            f"接下来将判断适合的图表类型,如连续3次判断失败将会使用流程图进行绘制"
+        )
+        gpt_say = "[Local Message] 收到。"  # 用户提示
+        chatbot.append([i_say_show_user, gpt_say])
+        yield from update_ui(chatbot=chatbot, history=[])  # 更新UI
         i_say = SELECT_PROMPT.format(subject=results_txt)
         i_say_show_user = f'请判断适合使用的流程图类型,其中数字对应关系为:1-流程图,2-序列图,3-类图,4-饼图,5-甘特图,6-状态图,7-实体关系图,8-象限提示图。由于不管提供文本是什么,模型大概率认为"思维导图"最合适,因此思维导图仅能通过参数调用。'
         for i in range(3):
             gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
                 inputs=i_say,
                 inputs_show_user=i_say_show_user,
-                llm_kwargs=llm_kwargs, chatbot=chatbot, history=[],
-                sys_prompt=""
+                llm_kwargs=llm_kwargs,
+                chatbot=chatbot,
+                history=[],
+                sys_prompt="",
             )
-            if gpt_say in ['1','2','3','4','5','6','7','8','9']:     #判断返回是否正确
+            if gpt_say in [
+                "1",
+                "2",
+                "3",
+                "4",
+                "5",
+                "6",
+                "7",
+                "8",
+                "9",
+            ]:  # 判断返回是否正确
                 break
-        if gpt_say not in ['1','2','3','4','5','6','7','8','9']:
-            gpt_say = '1'
+        if gpt_say not in ["1", "2", "3", "4", "5", "6", "7", "8", "9"]:
+            gpt_say = "1"
     ############################## <第 3 步，根据选择的图表类型绘制图表> ##################################
-    if gpt_say == '1':
+    if gpt_say == "1":
         i_say = PROMPT_1.format(subject=results_txt)
-    elif gpt_say == '2':
+    elif gpt_say == "2":
         i_say = PROMPT_2.format(subject=results_txt)
-    elif gpt_say == '3':
+    elif gpt_say == "3":
         i_say = PROMPT_3.format(subject=results_txt)
-    elif gpt_say == '4':
+    elif gpt_say == "4":
         i_say = PROMPT_4.format(subject=results_txt)
-    elif gpt_say == '5':
+    elif gpt_say == "5":
         i_say = PROMPT_5.format(subject=results_txt)
-    elif gpt_say == '6':
+    elif gpt_say == "6":
         i_say = PROMPT_6.format(subject=results_txt)
-    elif gpt_say == '7':
+    elif gpt_say == "7":
         i_say = PROMPT_7.replace("{subject}", results_txt)  # 由于实体关系图用到了{}符号
-    elif gpt_say == '8':
+    elif gpt_say == "8":
         i_say = PROMPT_8.format(subject=results_txt)
-    elif gpt_say == '9':
+    elif gpt_say == "9":
         i_say = PROMPT_9.format(subject=results_txt)
-    i_say_show_user = f'请根据判断结果绘制相应的图表。如需绘制思维导图请使用参数调用,同时过大的图表可能需要复制到在线编辑器中进行渲染。'
+    i_say_show_user = f"请根据判断结果绘制相应的图表。如需绘制思维导图请使用参数调用,同时过大的图表可能需要复制到在线编辑器中进行渲染。"
     gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
         inputs=i_say,
         inputs_show_user=i_say_show_user,
-        llm_kwargs=llm_kwargs, chatbot=chatbot, history=[],
-        sys_prompt=""
+        llm_kwargs=llm_kwargs,
+        chatbot=chatbot,
+        history=[],
+        sys_prompt="",
     )
     history.append(gpt_say)
     yield from update_ui(chatbot=chatbot, history=history)  # 刷新界面 # 界面更新
 
+
 @CatchException
-def 生成多种Mermaid图表(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
+def 生成多种Mermaid图表(
+    txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port
+):
     """
     txt             输入栏用户输入的文本，例如需要翻译的一段话，再例如一个包含了待处理文件的路径
     llm_kwargs      gpt模型参数，如温度和top_p等，一般原样传递下去就行
@@ -248,15 +312,21 @@ def 生成多种Mermaid图表(txt, llm_kwargs, plugin_kwargs, chatbot, history,
     import os
 
     # 基本信息：功能、贡献者
-    chatbot.append([
+    chatbot.append(
+        [
             "函数插件功能？",
             "根据当前聊天历史或指定的路径文件(文件内容优先)绘制多种mermaid图表，将会由对话模型首先判断适合的图表类型，随后绘制图表。\
-        \n您也可以使用插件参数指定绘制的图表类型,函数插件贡献者: Menghuan1918"])
+        \n您也可以使用插件参数指定绘制的图表类型,函数插件贡献者: Menghuan1918",
+        ]
+    )
     yield from update_ui(chatbot=chatbot, history=history)  # 刷新界面
 
     if os.path.exists(txt):  # 如输入区无内容则直接解析历史记录
         from crazy_functions.pdf_fns.parse_word import extract_text_from_files
-        file_exist, final_result, page_one, file_manifest, excption = extract_text_from_files(txt, chatbot, history)
+
+        file_exist, final_result, page_one, file_manifest, excption = (
+            extract_text_from_files(txt, chatbot, history)
+        )
     else:
         file_exist = False
         excption = ""
@@ -264,33 +334,104 @@ def 生成多种Mermaid图表(txt, llm_kwargs, plugin_kwargs, chatbot, history,
 
     if excption != "":
         if excption == "word":
-            report_exception(chatbot, history,
+            report_exception(
+                chatbot,
+                history,
                 a=f"解析项目: {txt}",
-                b = f"找到了.doc文件，但是该文件格式不被支持，请先转化为.docx格式。")
+                b=f"找到了.doc文件，但是该文件格式不被支持，请先转化为.docx格式。",
+            )
 
         elif excption == "pdf":
-            report_exception(chatbot, history,
+            report_exception(
+                chatbot,
+                history,
                 a=f"解析项目: {txt}",
-                b = f"导入软件依赖失败。使用该模块需要额外依赖，安装方法```pip install --upgrade pymupdf```。")
+                b=f"导入软件依赖失败。使用该模块需要额外依赖，安装方法```pip install --upgrade pymupdf```。",
+            )
 
         elif excption == "word_pip":
-                report_exception(chatbot, history,
+            report_exception(
+                chatbot,
+                history,
                 a=f"解析项目: {txt}",
-                    b=f"导入软件依赖失败。使用该模块需要额外依赖，安装方法```pip install --upgrade python-docx pywin32```。")
+                b=f"导入软件依赖失败。使用该模块需要额外依赖，安装方法```pip install --upgrade python-docx pywin32```。",
+            )
 
         yield from update_ui(chatbot=chatbot, history=history)  # 刷新界面
 
     else:
         if not file_exist:
             history.append(txt)  # 如输入区不是文件则将输入区内容加入历史记录
-            i_say_show_user = f'首先你从历史记录中提取摘要。'; gpt_say = "[Local Message] 收到。"   # 用户提示
-            chatbot.append([i_say_show_user, gpt_say]); yield from update_ui(chatbot=chatbot, history=history)    # 更新UI
-            yield from 解析历史输入(history,llm_kwargs,file_manifest,chatbot,plugin_kwargs)
+            i_say_show_user = f"首先你从历史记录中提取摘要。"
+            gpt_say = "[Local Message] 收到。"  # 用户提示
+            chatbot.append([i_say_show_user, gpt_say])
+            yield from update_ui(chatbot=chatbot, history=history)  # 更新UI
+            yield from 解析历史输入(
+                history, llm_kwargs, file_manifest, chatbot, plugin_kwargs
+            )
         else:
             file_num = len(file_manifest)
             for i in range(file_num):  # 依次处理文件
-                i_say_show_user = f"[{i+1}/{file_num}]处理文件{file_manifest[i]}"; gpt_say = "[Local Message] 收到。"   # 用户提示
-                chatbot.append([i_say_show_user, gpt_say]); yield from update_ui(chatbot=chatbot, history=history)    # 更新UI
+                i_say_show_user = f"[{i+1}/{file_num}]处理文件{file_manifest[i]}"
+                gpt_say = "[Local Message] 收到。"  # 用户提示
+                chatbot.append([i_say_show_user, gpt_say])
+                yield from update_ui(chatbot=chatbot, history=history)  # 更新UI
                 history = []  # 如输入区内容为文件则清空历史记录
                 history.append(final_result[i])
-                yield from 解析历史输入(history,llm_kwargs,file_manifest,chatbot,plugin_kwargs)
+                yield from 解析历史输入(
+                    history, llm_kwargs, file_manifest, chatbot, plugin_kwargs
+                )
+
+
+class Mermaid_Gen(GptAcademicPluginTemplate):
+    def __init__(self):
+        pass
+
+    def define_arg_selection_menu(self):
+        gui_definition = {
+            "Type_of_Mermaid": ArgProperty(
+                title="绘制的Mermaid图表类型",
+                options=[
+                    "由LLM决定",
+                    "流程图",
+                    "序列图",
+                    "类图",
+                    "饼图",
+                    "甘特图",
+                    "状态图",
+                    "实体关系图",
+                    "象限提示图",
+                    "思维导图",
+                ],
+                default_value="由LLM决定",
+                description="选择'由LLM决定'时将由对话模型判断适合的图表类型(不包括思维导图)，选择其他类型时将直接绘制指定的图表类型。",
+                type="dropdown",
+            ).model_dump_json(),
+        }
+        return gui_definition
+
+    def execute(
+        txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request
+    ):
+        options = [
+            "由LLM决定",
+            "流程图",
+            "序列图",
+            "类图",
+            "饼图",
+            "甘特图",
+            "状态图",
+            "实体关系图",
+            "象限提示图",
+            "思维导图",
+        ]
+        plugin_kwargs = options.index(plugin_kwargs['Type_of_Mermaid'])
+        yield from 生成多种Mermaid图表(
+            txt,
+            llm_kwargs,
+            plugin_kwargs,
+            chatbot,
+            history,
+            system_prompt,
+            user_request,
+        )

crazy_functions/知识库问答.py

@@ -1,6 +1,6 @@
 from toolbox import CatchException, update_ui, ProxyNetworkActivate, update_ui_lastest_msg, get_log_folder, get_user
-from .crazy_utils import request_gpt_model_in_new_thread_with_ui_alive, get_files_from_everything
-
+from crazy_functions.crazy_utils import request_gpt_model_in_new_thread_with_ui_alive, get_files_from_everything
+from loguru import logger
 install_msg ="""
 
 1. python -m pip install torch --index-url https://download.pytorch.org/whl/cpu
@@ -40,7 +40,7 @@ def 知识库文件注入(txt, llm_kwargs, plugin_kwargs, chatbot, history, syst
     except Exception as e:
         chatbot.append(["依赖不足", f"{str(e)}\n\n导入依赖失败。请用以下命令安装" + install_msg])
         yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
-        # from .crazy_utils import try_install_deps
+        # from crazy_functions.crazy_utils import try_install_deps
         # try_install_deps(['zh_langchain==0.2.1', 'pypinyin'], reload_m=['pypinyin', 'zh_langchain'])
         # yield from update_ui_lastest_msg("安装完成，您可以再次重试。", chatbot, history)
         return
@@ -60,7 +60,7 @@ def 知识库文件注入(txt, llm_kwargs, plugin_kwargs, chatbot, history, syst
     # < -------------------预热文本向量化模组--------------- >
     chatbot.append(['<br/>'.join(file_manifest), "正在预热文本向量化模组, 如果是第一次运行, 将消耗较长时间下载中文向量化模型..."])
     yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
-    print('Checking Text2vec ...')
+    logger.info('Checking Text2vec ...')
     from langchain.embeddings.huggingface import HuggingFaceEmbeddings
     with ProxyNetworkActivate('Download_LLM'):    # 临时地激活代理网络
         HuggingFaceEmbeddings(model_name="GanymedeNil/text2vec-large-chinese")
@@ -68,7 +68,7 @@ def 知识库文件注入(txt, llm_kwargs, plugin_kwargs, chatbot, history, syst
     # < -------------------构建知识库--------------- >
     chatbot.append(['<br/>'.join(file_manifest), "正在构建知识库..."])
     yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
-    print('Establishing knowledge archive ...')
+    logger.info('Establishing knowledge archive ...')
     with ProxyNetworkActivate('Download_LLM'):    # 临时地激活代理网络
         kai = knowledge_archive_interface()
         vs_path = get_log_folder(user=get_user(chatbot), plugin_name='vec_store')
@@ -93,7 +93,7 @@ def 读取知识库作答(txt, llm_kwargs, plugin_kwargs, chatbot, history, syst
     except Exception as e:
         chatbot.append(["依赖不足", f"{str(e)}\n\n导入依赖失败。请用以下命令安装" + install_msg])
         yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
-        # from .crazy_utils import try_install_deps
+        # from crazy_functions.crazy_utils import try_install_deps
         # try_install_deps(['zh_langchain==0.2.1', 'pypinyin'], reload_m=['pypinyin', 'zh_langchain'])
         # yield from update_ui_lastest_msg("安装完成，您可以再次重试。", chatbot, history)
         return

crazy_functions/联网的ChatGPT.py

@@ -1,5 +1,5 @@
 from toolbox import CatchException, update_ui
-from .crazy_utils import request_gpt_model_in_new_thread_with_ui_alive, input_clipping
+from crazy_functions.crazy_utils import request_gpt_model_in_new_thread_with_ui_alive, input_clipping
 import requests
 from bs4 import BeautifulSoup
 from request_llms.bridge_all import model_info
@@ -23,8 +23,8 @@ def google(query, proxies):
             item = {'title': title, 'link': link}
             results.append(item)
 
-    for r in results:
-        print(r['link'])
+    # for r in results:
+    #     print(r['link'])
     return results
 
 def scrape_text(url, proxies) -> str:

crazy_functions/联网的ChatGPT_bing版.py

@@ -1,5 +1,5 @@
 from toolbox import CatchException, update_ui
-from .crazy_utils import request_gpt_model_in_new_thread_with_ui_alive, input_clipping
+from crazy_functions.crazy_utils import request_gpt_model_in_new_thread_with_ui_alive, input_clipping
 import requests
 from bs4 import BeautifulSoup
 from request_llms.bridge_all import model_info
@@ -22,8 +22,8 @@ def bing_search(query, proxies=None):
             item = {'title': title, 'link': link}
             results.append(item)
 
-    for r in results:
-        print(r['link'])
+    # for r in results:
+    #     print(r['link'])
     return results
 
 

crazy_functions/解析JupyterNotebook.py

@@ -64,7 +64,7 @@ def parseNotebook(filename, enable_markdown=1):
 
 
 def ipynb解释(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt):
-    from .crazy_utils import request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency
+    from crazy_functions.crazy_utils import request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency
 
     if ("advanced_arg" in plugin_kwargs) and (plugin_kwargs["advanced_arg"] == ""): plugin_kwargs.pop("advanced_arg")
     enable_markdown = plugin_kwargs.get("advanced_arg", "1")

crazy_functions/询问多个大语言模型.py

@@ -1,5 +1,5 @@
 from toolbox import CatchException, update_ui, get_conf
-from .crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
+from crazy_functions.crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
 import datetime
 @CatchException
 def 同时问询(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):

crazy_functions/语音助手.py

@@ -1,11 +1,13 @@
 from toolbox import update_ui
 from toolbox import CatchException, get_conf, markdown_convertion
+from request_llms.bridge_all import predict_no_ui_long_connection
 from crazy_functions.crazy_utils import input_clipping
 from crazy_functions.agent_fns.watchdog import WatchDog
-from request_llms.bridge_all import predict_no_ui_long_connection
+from crazy_functions.live_audio.aliyunASR import AliyunASR
+from loguru import logger
+
 import threading, time
 import numpy as np
-from .live_audio.aliyunASR import AliyunASR
 import json
 import re
 
@@ -42,9 +44,9 @@ class AsyncGptTask():
             gpt_say_partial = predict_no_ui_long_connection(inputs=i_say, llm_kwargs=llm_kwargs, history=history, sys_prompt=sys_prompt,
                                                             observe_window=observe_window[index], console_slience=True)
         except ConnectionAbortedError as token_exceed_err:
-            print('至少一个线程任务Token溢出而失败', e)
+            logger.error('至少一个线程任务Token溢出而失败', e)
         except Exception as e:
-            print('至少一个线程任务意外失败', e)
+            logger.error('至少一个线程任务意外失败', e)
 
     def add_async_gpt_task(self, i_say, chatbot_index, llm_kwargs, history, system_prompt):
         self.observe_future.append([""])

crazy_functions/读文章写摘要.py

@@ -1,19 +1,18 @@
 from toolbox import update_ui
 from toolbox import CatchException, report_exception
 from toolbox import write_history_to_file, promote_file_to_downloadzone
-from .crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
+from crazy_functions.crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
 
 
 def 解析Paper(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt):
     import time, glob, os
-    print('begin analysis on:', file_manifest)
     for index, fp in enumerate(file_manifest):
         with open(fp, 'r', encoding='utf-8', errors='replace') as f:
             file_content = f.read()
 
         prefix = "接下来请你逐文件分析下面的论文文件，概括其内容" if index==0 else ""
         i_say = prefix + f'请对下面的文章片段用中文做一个概述，文件名是{os.path.relpath(fp, project_folder)}，文章内容是 ```{file_content}```'
-        i_say_show_user = prefix + f'[{index}/{len(file_manifest)}] 请对下面的文章片段做一个概述: {os.path.abspath(fp)}'
+        i_say_show_user = prefix + f'[{index+1}/{len(file_manifest)}] 请对下面的文章片段做一个概述: {os.path.abspath(fp)}'
         chatbot.append((i_say_show_user, "[Local Message] waiting gpt response."))
         yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
 

crazy_functions/谷歌检索小助手.py

@@ -1,4 +1,4 @@
-from .crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
+from crazy_functions.crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
 from toolbox import CatchException, report_exception, promote_file_to_downloadzone
 from toolbox import update_ui, update_ui_lastest_msg, disable_auto_promotion, write_history_to_file
 import logging

crazy_functions/高级功能函数模板.py

@@ -2,6 +2,10 @@ from toolbox import CatchException, update_ui
 from crazy_functions.crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
 import datetime
 
+####################################################################################################################
+# Demo 1: 一个非常简单的插件 #########################################################################################
+####################################################################################################################
+
 高阶功能模板函数示意图 = f"""
 ```mermaid
 flowchart TD
@@ -26,7 +30,7 @@ flowchart TD
 """
 
 @CatchException
-def 高阶功能模板函数(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
+def 高阶功能模板函数(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request, num_day=5):
     """
     # 高阶功能模板函数示意图：https://mermaid.live/edit#pako:eNptk1tvEkEYhv8KmattQpvlvOyFCcdeeaVXuoYssBwie8gyhCIlqVoLhrbbtAWNUpEGUkyMEDW2Fmn_DDOL_8LZHdOwxrnamX3f7_3mmZk6yKhZCfAgV1KrmYKoQ9fDuKC4yChX0nld1Aou1JzjznQ5fWmejh8LYHW6vG2a47YAnlCLNSIRolnenKBXI_zRIBrcuqRT890u7jZx7zMDt-AaMbnW1--5olGiz2sQjwfoQxsZL0hxplSSU0-rop4vrzmKR6O2JxYjHmwcL2Y_HDatVMkXlf86YzHbGY9bO5j8XE7O8Nsbc3iNB3ukL2SMcH-XIQBgWoVOZzxuOxOJOyc63EPGV6ZQLENVrznViYStTiaJ2vw2M2d9bByRnOXkgCnXylCSU5quyto_IcmkbdvctELmJ-j1ASW3uB3g5xOmKqVTmqr_Na3AtuS_dtBFm8H90XJyHkDDT7S9xXWb4HGmRChx64AOL5HRpUm411rM5uh4H78Z4V7fCZzytjZz2seto9XaNPFue07clLaVZF8UNLygJ-VES8lah_n-O-5Ozc7-77NzJ0-K0yr0ZYrmHdqAk50t2RbA4qq9uNohBASw7YpSgaRkLWCCAtxAlnRZLGbJba9bPwUAC5IsCYAnn1kpJ1ZKUACC0iBSsQLVBzUlA3ioVyQ3qGhZEUrxokiehAz4nFgqk1VNVABfB1uAD_g2_AGPl-W8nMcbCvsDblADfNCz4feyobDPy3rYEMtxwYYbPFNVUoHdCPmDHBv2cP4AMfrCbiBli-Q-3afv0X6WdsIjW2-10fgDy1SAig
 
@@ -43,7 +47,7 @@ def 高阶功能模板函数(txt, llm_kwargs, plugin_kwargs, chatbot, history, s
         "您正在调用插件：历史上的今天",
         "[Local Message] 请注意，您正在调用一个[函数插件]的模板，该函数面向希望实现更多有趣功能的开发者，它可以作为创建新功能函数的模板（该函数只有20多行代码）。此外我们也提供可同步处理大量文件的多线程Demo供您参考。您若希望分享新的功能模组，请不吝PR！" + 高阶功能模板函数示意图))
     yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 由于请求gpt需要一段时间，我们先及时地做一次界面更新
-    for i in range(5):
+    for i in range(int(num_day)):
         currentMonth = (datetime.date.today() + datetime.timedelta(days=i)).month
         currentDay = (datetime.date.today() + datetime.timedelta(days=i)).day
         i_say = f'历史中哪些事件发生在{currentMonth}月{currentDay}日？列举两条并发送相关图片。发送图片时，请使用Markdown，将Unsplash API中的PUT_YOUR_QUERY_HERE替换成描述该事件的一个最重要的单词。'
@@ -59,6 +63,56 @@ def 高阶功能模板函数(txt, llm_kwargs, plugin_kwargs, chatbot, history, s
 
 
 
+
+
+
+####################################################################################################################
+# Demo 2: 一个带二级菜单的插件 #######################################################################################
+####################################################################################################################
+
+from crazy_functions.plugin_template.plugin_class_template import GptAcademicPluginTemplate, ArgProperty
+class Demo_Wrap(GptAcademicPluginTemplate):
+    def __init__(self):
+        """
+        请注意`execute`会执行在不同的线程中，因此您在定义和使用类变量时，应当慎之又慎！
+        """
+        pass
+
+    def define_arg_selection_menu(self):
+        """
+        定义插件的二级选项菜单
+        """
+        gui_definition = {
+            "num_day":
+                ArgProperty(title="日期选择", options=["仅今天", "未来3天", "未来5天"], default_value="未来3天", description="无", type="dropdown").model_dump_json(),
+        }
+        return gui_definition
+
+    def execute(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
+        """
+        执行插件
+        """
+        num_day = plugin_kwargs["num_day"]
+        if num_day == "仅今天": num_day = 1
+        if num_day == "未来3天": num_day = 3
+        if num_day == "未来5天": num_day = 5
+        yield from 高阶功能模板函数(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request, num_day=num_day)
+
+
+
+
+
+
+
+
+
+
+
+
+####################################################################################################################
+# Demo 3: 绘制脑图的Demo ############################################################################################
+####################################################################################################################
+
 PROMPT = """
 请你给出围绕“{subject}”的逻辑关系图，使用mermaid语法，mermaid语法举例：
 ```mermaid

docs/GithubAction+AllCapacity

@@ -3,6 +3,9 @@
 # 从NVIDIA源，从而支持显卡（检查宿主的nvidia-smi中的cuda版本必须>=11.3）
 FROM fuqingxu/11.3.1-runtime-ubuntu20.04-with-texlive:latest
 
+# edge-tts需要的依赖，某些pip包所需的依赖
+RUN apt update && apt install ffmpeg build-essential -y
+
 # use python3 as the system default python
 WORKDIR /gpt
 RUN curl -sS https://bootstrap.pypa.io/get-pip.py | python3.8

docs/GithubAction+AllCapacityBeta

@@ -5,6 +5,9 @@
 # 从NVIDIA源，从而支持显卡（检查宿主的nvidia-smi中的cuda版本必须>=11.3）
 FROM fuqingxu/11.3.1-runtime-ubuntu20.04-with-texlive:latest
 
+# edge-tts需要的依赖，某些pip包所需的依赖
+RUN apt update && apt install ffmpeg build-essential -y
+
 # use python3 as the system default python
 WORKDIR /gpt
 RUN curl -sS https://bootstrap.pypa.io/get-pip.py | python3.8
@@ -36,6 +39,7 @@ RUN python3 -m pip install -r request_llms/requirements_chatglm.txt
 RUN python3 -m pip install -r request_llms/requirements_newbing.txt
 RUN python3 -m pip install nougat-ocr
 
+
 # 预热Tiktoken模块
 RUN python3  -c 'from check_proxy import warm_up_modules; warm_up_modules()'
 

docs/GithubAction+ChatGLM+Moss

@@ -5,6 +5,8 @@ RUN apt-get update
 RUN apt-get install -y curl proxychains curl gcc
 RUN apt-get install -y git python python3 python-dev python3-dev --fix-missing
 
+# edge-tts需要的依赖，某些pip包所需的依赖
+RUN apt update && apt install ffmpeg build-essential -y
 
 # use python3 as the system default python
 RUN curl -sS https://bootstrap.pypa.io/get-pip.py | python3.8
@@ -22,7 +24,6 @@ RUN python3 -m pip install -r request_llms/requirements_chatglm.txt
 RUN python3 -m pip install -r request_llms/requirements_newbing.txt
 
 
-
 # 预热Tiktoken模块
 RUN python3  -c 'from check_proxy import warm_up_modules; warm_up_modules()'
 

docs/GithubAction+JittorLLMs

@@ -23,6 +23,9 @@ RUN python3 -m pip install -r request_llms/requirements_jittorllms.txt -i https:
 # 下载JittorLLMs
 RUN git clone https://github.com/binary-husky/JittorLLMs.git --depth 1 request_llms/jittorllms
 
+# edge-tts需要的依赖
+RUN apt update && apt install ffmpeg -y
+
 # 禁用缓存，确保更新代码
 ADD "https://www.random.org/cgi-bin/randbyte?nbytes=10&format=h" skipcache
 RUN git pull

docs/GithubAction+NoLocal

@@ -12,6 +12,8 @@ COPY . .
 # 安装依赖
 RUN pip3 install -r requirements.txt
 
+# edge-tts需要的依赖
+RUN apt update && apt install ffmpeg -y
 
 # 可选步骤，用于预热模块
 RUN python3  -c 'from check_proxy import warm_up_modules; warm_up_modules()'

docs/GithubAction+NoLocal+AudioAssistant

@@ -15,6 +15,9 @@ RUN pip3 install -r requirements.txt
 # 安装语音插件的额外依赖
 RUN pip3 install aliyun-python-sdk-core==2.13.3 pyOpenSSL webrtcvad scipy git+https://github.com/aliyun/alibabacloud-nls-python-sdk.git
 
+# edge-tts需要的依赖
+RUN apt update && apt install ffmpeg -y
+
 # 可选步骤，用于预热模块
 RUN python3  -c 'from check_proxy import warm_up_modules; warm_up_modules()'
 

docs/GithubAction+NoLocal+Latex

@@ -25,6 +25,9 @@ COPY . .
 # 安装依赖
 RUN pip3 install -r requirements.txt
 
+# edge-tts需要的依赖
+RUN apt update && apt install ffmpeg -y
+
 # 可选步骤，用于预热模块
 RUN python3  -c 'from check_proxy import warm_up_modules; warm_up_modules()'
 

docs/GithubAction+NoLocal+Vectordb

@@ -19,6 +19,9 @@ RUN pip3 install transformers protobuf langchain sentence-transformers  faiss-cp
 RUN pip3 install unstructured[all-docs] --upgrade
 RUN python3  -c 'from check_proxy import warm_up_vectordb; warm_up_vectordb()'
 
+# edge-tts需要的依赖
+RUN apt update && apt install ffmpeg -y
+
 # 可选步骤，用于预热模块
 RUN python3  -c 'from check_proxy import warm_up_modules; warm_up_modules()'
 

docs/plugin_with_secondary_menu.md

@@ -0,0 +1,189 @@
+# 实现带二级菜单的插件
+
+## 一、如何写带有二级菜单的插件
+
+1. 声明一个 `Class`，继承父类 `GptAcademicPluginTemplate`
+
+    ```python
+    from crazy_functions.plugin_template.plugin_class_template import GptAcademicPluginTemplate
+    from crazy_functions.plugin_template.plugin_class_template import ArgProperty
+
+    class Demo_Wrap(GptAcademicPluginTemplate):
+        def __init__(self): ...
+    ```
+
+2. 声明二级菜单中需要的变量，覆盖父类的`define_arg_selection_menu`函数。
+
+    ```python
+    class Demo_Wrap(GptAcademicPluginTemplate):
+        ...
+
+        def define_arg_selection_menu(self):
+            """
+            定义插件的二级选项菜单
+
+            第一个参数，名称`main_input`，参数`type`声明这是一个文本框，文本框上方显示`title`，文本框内部显示`description`，`default_value`为默认值；
+            第二个参数，名称`advanced_arg`，参数`type`声明这是一个文本框，文本框上方显示`title`，文本框内部显示`description`，`default_value`为默认值；
+            第三个参数，名称`allow_cache`，参数`type`声明这是一个下拉菜单，下拉菜单上方显示`title`+`description`，下拉菜单的选项为`options`，`default_value`为下拉菜单默认值；
+            """
+            gui_definition = {
+                "main_input":
+                    ArgProperty(title="ArxivID", description="输入Arxiv的ID或者网址", default_value="", type="string").model_dump_json(),
+                "advanced_arg":
+                    ArgProperty(title="额外的翻译提示词",
+                                description=r"如果有必要, 请在此处给出自定义翻译命令",
+                                default_value="", type="string").model_dump_json(),
+                "allow_cache":
+                    ArgProperty(title="是否允许从缓存中调取结果", options=["允许缓存", "从头执行"], default_value="允许缓存", description="无", type="dropdown").model_dump_json(),
+            }
+            return gui_definition
+        ...
+    ```
+
+
+    > [!IMPORTANT]
+    >
+    > ArgProperty 中每个条目对应一个参数，`type == "string"`时，使用文本块，`type == dropdown`时，使用下拉菜单。
+    >
+    > 注意：`main_input` 和 `advanced_arg`是两个特殊的参数。`main_input`会自动与界面右上角的`输入区`进行同步，而`advanced_arg`会自动与界面右下角的`高级参数输入区`同步。除此之外，参数名称可以任意选取。其他细节详见`crazy_functions/plugin_template/plugin_class_template.py`。
+
+
+
+
+3. 编写插件程序，覆盖父类的`execute`函数。
+
+    例如：
+
+    ```python
+    class Demo_Wrap(GptAcademicPluginTemplate):
+        ...
+        ...
+
+        def execute(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
+            """
+            执行插件
+
+            plugin_kwargs字典中会包含用户的选择，与上述 `define_arg_selection_menu` 一一对应
+            """
+            allow_cache = plugin_kwargs["allow_cache"]
+            advanced_arg = plugin_kwargs["advanced_arg"]
+
+            if allow_cache == "从头执行": plugin_kwargs["advanced_arg"] = "--no-cache " + plugin_kwargs["advanced_arg"]
+            yield from Latex翻译中文并重新编译PDF(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request)
+
+    ```
+
+
+
+4. 注册插件
+
+    将以下条目插入`crazy_functional.py`即可。注意，与旧插件不同的是，`Function`键值应该为None，而`Class`键值为上述插件的类名称（`Demo_Wrap`）。
+    ```
+        "新插件": {
+            "Group": "学术",
+            "Color": "stop",
+            "AsButton": True,
+            "Info": "插件说明",
+            "Function": None,
+            "Class": Demo_Wrap,
+        },
+    ```
+
+5. 已经结束了，启动程序测试吧~！
+
+
+
+## 二、背后的原理（需要JavaScript的前置知识）
+
+
+### (I) 首先介绍三个Gradio官方没有的重要前端函数
+
+主javascript程序`common.js`中有三个Gradio官方没有的重要API
+
+1. `get_data_from_gradio_component`
+    这个函数可以获取任意gradio组件的当前值，例如textbox中的字符，dropdown中的当前选项，chatbot当前的对话等等。调用方法举例：
+    ```javascript
+    // 获取当前的对话
+    let chatbot = await get_data_from_gradio_component('gpt-chatbot');
+    ```
+
+2. `get_gradio_component`
+    有时候我们不仅需要gradio组件的当前值，还需要它的label值、是否隐藏、下拉菜单其他可选选项等等，而通过这个函数可以直接获取这个组件的句柄。举例：
+    ```javascript
+    // 获取下拉菜单组件的句柄
+    var model_sel = await get_gradio_component("elem_model_sel");
+    // 获取它的所有属性，包括其所有可选选项
+    console.log(model_sel.props)
+    ```
+
+
+3. `push_data_to_gradio_component`
+    这个函数可以将数据推回gradio组件，例如textbox中的字符，dropdown中的当前选项等等。调用方法举例：
+
+    ```javascript
+    // 修改一个按钮上面的文本
+    push_data_to_gradio_component("btnName", "gradio_element_id", "string");
+
+    // 隐藏一个组件
+    push_data_to_gradio_component({ visible: false, __type__: 'update' }, "plugin_arg_menu", "obj");
+
+    // 修改组件label
+    push_data_to_gradio_component({ label: '新label的值', __type__: 'update' }, "gpt-chatbot", "obj")
+
+    // 第一个参数是value，
+    //     - 可以是字符串（调整textbox的文本，按钮的文本）；
+    //     - 还可以是 { visible: false, __type__: 'update' }  这样的字典（调整visible, label, choices）
+    // 第二个参数是elem_id
+    // 第三个参数是"string" 或者 "obj"
+    ```
+
+
+### (II) 从点击插件到执行插件的逻辑过程
+
+简述：程序启动时把每个插件的二级菜单编码为BASE64，存储在用户的浏览器前端，用户调用对应功能时，会按照插件的BASE64编码，将平时隐藏的菜单（有选择性地）显示出来。
+
+1. 启动阶段（主函数 `main.py` 中），遍历每个插件，生成二级菜单的BASE64编码，存入变量`register_advanced_plugin_init_code_arr`。
+    ```python
+    def get_js_code_for_generating_menu(self, btnName):
+        define_arg_selection = self.define_arg_selection_menu()
+        DEFINE_ARG_INPUT_INTERFACE = json.dumps(define_arg_selection)
+        return base64.b64encode(DEFINE_ARG_INPUT_INTERFACE.encode('utf-8')).decode('utf-8')
+    ```
+
+
+2. 用户加载阶段（主javascript程序`common.js`中），浏览器加载`register_advanced_plugin_init_code_arr`，存入本地的字典`advanced_plugin_init_code_lib`：
+
+    ```javascript
+    advanced_plugin_init_code_lib = {}
+    function register_advanced_plugin_init_code(key, code){
+        advanced_plugin_init_code_lib[key] = code;
+    }
+    ```
+
+3. 用户点击插件按钮（主函数 `main.py` 中）时，仅执行以下javascript代码，唤醒隐藏的二级菜单（生成菜单的代码在`common.js`中的`generate_menu`函数上）：
+
+
+    ```javascript
+    // 生成高级插件的选择菜单
+    function run_advanced_plugin_launch_code(key){
+        generate_menu(advanced_plugin_init_code_lib[key], key);
+    }
+    function on_flex_button_click(key){
+        run_advanced_plugin_launch_code(key);
+    }
+    ```
+
+    ```python
+    click_handle = plugins[k]["Button"].click(None, inputs=[], outputs=None, _js=f"""()=>run_advanced_plugin_launch_code("{k}")""")
+    ```
+
+4. 当用户点击二级菜单的执行键时，通过javascript脚本模拟点击一个隐藏按钮，触发后续程序（`common.js`中的`execute_current_pop_up_plugin`，会把二级菜单中的参数缓存到`invisible_current_pop_up_plugin_arg_final`，然后模拟点击`invisible_callback_btn_for_plugin_exe`按钮）。隐藏按钮的定义在（主函数 `main.py` ），该隐藏按钮会最终触发`route_switchy_bt_with_arg`函数（定义于`themes/gui_advanced_plugin_class.py`）：
+
+    ```python
+    click_handle_ng = new_plugin_callback.click(route_switchy_bt_with_arg, [
+            gr.State(["new_plugin_callback", "usr_confirmed_arg"] + input_combo_order),
+            new_plugin_callback, usr_confirmed_arg, *input_combo
+        ], output_combo)
+    ```
+
+5. 最后，`route_switchy_bt_with_arg`中，会搜集所有用户参数，统一集中到`plugin_kwargs`参数中，并执行对应插件的`execute`函数。

docs/self_analysis.md

@@ -22,13 +22,13 @@
 | crazy_functions\下载arxiv论文翻译摘要.py | 下载 `arxiv` 论文的 PDF 文件，并提取摘要和翻译 |
 | crazy_functions\代码重写为全英文_多线程.py | 将Python源代码文件中的中文内容转化为英文 |
 | crazy_functions\图片生成.py | 根据激励文本使用GPT模型生成相应的图像 |
-| crazy_functions\对话历史存档.py | 将每次对话记录写入Markdown格式的文件中 |
+| crazy_functions\Conversation_To_File.py | 将每次对话记录写入Markdown格式的文件中 |
 | crazy_functions\总结word文档.py | 对输入的word文档进行摘要生成 |
 | crazy_functions\总结音视频.py | 对输入的音视频文件进行摘要生成 |
-| crazy_functions\批量Markdown翻译.py | 将指定目录下的Markdown文件进行中英文翻译 |
+| crazy_functions\Markdown_Translate.py | 将指定目录下的Markdown文件进行中英文翻译 |
 | crazy_functions\批量总结PDF文档.py | 对PDF文件进行切割和摘要生成 |
 | crazy_functions\批量总结PDF文档pdfminer.py | 对PDF文件进行文本内容的提取和摘要生成 |
-| crazy_functions\PDF批量翻译.py | 将指定目录下的PDF文件进行中英文翻译 |
+| crazy_functions\PDF_Translate.py | 将指定目录下的PDF文件进行中英文翻译 |
 | crazy_functions\理解PDF文档内容.py | 对PDF文件进行摘要生成和问题解答 |
 | crazy_functions\生成函数注释.py | 自动生成Python函数的注释 |
 | crazy_functions\联网的ChatGPT.py | 使用网络爬虫和ChatGPT模型进行聊天回答 |
@@ -155,9 +155,9 @@ toolbox.py是一个工具类库，其中主要包含了一些函数装饰器和
 
 该程序文件提供了一个用于生成图像的函数`图片生成`。函数实现的过程中，会调用`gen_image`函数来生成图像，并返回图像生成的网址和本地文件地址。函数有多个参数，包括`prompt`(激励文本)、`llm_kwargs`(GPT模型的参数)、`plugin_kwargs`(插件模型的参数)等。函数核心代码使用了`requests`库向OpenAI API请求图像，并做了简单的处理和保存。函数还更新了交互界面，清空聊天历史并显示正在生成图像的消息和最终的图像网址和预览。
 
-## [18/48] 请对下面的程序文件做一个概述: crazy_functions\对话历史存档.py
+## [18/48] 请对下面的程序文件做一个概述: crazy_functions\Conversation_To_File.py
 
-这个文件是名为crazy_functions\对话历史存档.py的Python程序文件，包含了4个函数：
+这个文件是名为crazy_functions\Conversation_To_File.py的Python程序文件，包含了4个函数：
 
 1. write_chat_to_file(chatbot, history=None, file_name=None)：用来将对话记录以Markdown格式写入文件中，并且生成文件名，如果没指定文件名则用当前时间。写入完成后将文件路径打印出来。
 
@@ -165,7 +165,7 @@ toolbox.py是一个工具类库，其中主要包含了一些函数装饰器和
 
 3. read_file_to_chat(chatbot, history, file_name)：从传入的文件中读取内容，解析出对话历史记录并更新聊天显示框。
 
-4. 对话历史存档(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request)：一个主要函数，用于保存当前对话记录并提醒用户。如果用户希望加载历史记录，则调用read_file_to_chat()来更新聊天显示框。如果用户希望删除历史记录，调用删除所有本地对话历史记录()函数完成删除操作。
+4. Conversation_To_File(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request)：一个主要函数，用于保存当前对话记录并提醒用户。如果用户希望加载历史记录，则调用read_file_to_chat()来更新聊天显示框。如果用户希望删除历史记录，调用删除所有本地对话历史记录()函数完成删除操作。
 
 ## [19/48] 请对下面的程序文件做一个概述: crazy_functions\总结word文档.py
 
@@ -175,9 +175,9 @@ toolbox.py是一个工具类库，其中主要包含了一些函数装饰器和
 
 该程序文件包括两个函数：split_audio_file()和AnalyAudio()，并且导入了一些必要的库并定义了一些工具函数。split_audio_file用于将音频文件分割成多个时长相等的片段，返回一个包含所有切割音频片段文件路径的列表，而AnalyAudio用来分析音频文件，通过调用whisper模型进行音频转文字并使用GPT模型对音频内容进行概述，最终将所有总结结果写入结果文件中。
 
-## [21/48] 请对下面的程序文件做一个概述: crazy_functions\批量Markdown翻译.py
+## [21/48] 请对下面的程序文件做一个概述: crazy_functions\Markdown_Translate.py
 
-该程序文件名为`批量Markdown翻译.py`，包含了以下功能：读取Markdown文件，将长文本分离开来，将Markdown文件进行翻译（英译中和中译英），整理结果并退出。程序使用了多线程以提高效率。程序使用了`tiktoken`依赖库，可能需要额外安装。文件中还有一些其他的函数和类，但与文件名所描述的功能无关。
+该程序文件名为`Markdown_Translate.py`，包含了以下功能：读取Markdown文件，将长文本分离开来，将Markdown文件进行翻译（英译中和中译英），整理结果并退出。程序使用了多线程以提高效率。程序使用了`tiktoken`依赖库，可能需要额外安装。文件中还有一些其他的函数和类，但与文件名所描述的功能无关。
 
 ## [22/48] 请对下面的程序文件做一个概述: crazy_functions\批量总结PDF文档.py
 
@@ -187,9 +187,9 @@ toolbox.py是一个工具类库，其中主要包含了一些函数装饰器和
 
 该程序文件是一个用于批量总结PDF文档的函数插件，使用了pdfminer插件和BeautifulSoup库来提取PDF文档的文本内容，对每个PDF文件分别进行处理并生成中英文摘要。同时，该程序文件还包括一些辅助工具函数和处理异常的装饰器。
 
-## [24/48] 请对下面的程序文件做一个概述: crazy_functions\PDF批量翻译.py
+## [24/48] 请对下面的程序文件做一个概述: crazy_functions\PDF_Translate.py
 
-这个程序文件是一个Python脚本，文件名为“PDF批量翻译.py”。它主要使用了“toolbox”、“request_gpt_model_in_new_thread_with_ui_alive”、“request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency”、“colorful”等Python库和自定义的模块“crazy_utils”的一些函数。程序实现了一个批量翻译PDF文档的功能，可以自动解析PDF文件中的基础信息，递归地切割PDF文件，翻译和处理PDF论文中的所有内容，并生成相应的翻译结果文件（包括md文件和html文件）。功能比较复杂，其中需要调用多个函数和依赖库，涉及到多线程操作和UI更新。文件中有详细的注释和变量命名，代码比较清晰易读。
+这个程序文件是一个Python脚本，文件名为“PDF_Translate.py”。它主要使用了“toolbox”、“request_gpt_model_in_new_thread_with_ui_alive”、“request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency”、“colorful”等Python库和自定义的模块“crazy_utils”的一些函数。程序实现了一个批量翻译PDF文档的功能，可以自动解析PDF文件中的基础信息，递归地切割PDF文件，翻译和处理PDF论文中的所有内容，并生成相应的翻译结果文件（包括md文件和html文件）。功能比较复杂，其中需要调用多个函数和依赖库，涉及到多线程操作和UI更新。文件中有详细的注释和变量命名，代码比较清晰易读。
 
 ## [25/48] 请对下面的程序文件做一个概述: crazy_functions\理解PDF文档内容.py
 
@@ -331,19 +331,19 @@ check_proxy.py, colorful.py, config.py, config_private.py, core_functional.py, c
 这些程序源文件提供了基础的文本和语言处理功能、工具函数和高级插件，使 Chatbot 能够处理各种复杂的学术文本问题，包括润色、翻译、搜索、下载、解析等。
 
 ## 用一张Markdown表格简要描述以下文件的功能：
-crazy_functions\代码重写为全英文_多线程.py, crazy_functions\图片生成.py, crazy_functions\对话历史存档.py, crazy_functions\总结word文档.py, crazy_functions\总结音视频.py, crazy_functions\批量Markdown翻译.py, crazy_functions\批量总结PDF文档.py, crazy_functions\批量总结PDF文档pdfminer.py, crazy_functions\PDF批量翻译.py, crazy_functions\理解PDF文档内容.py, crazy_functions\生成函数注释.py, crazy_functions\联网的ChatGPT.py, crazy_functions\解析JupyterNotebook.py, crazy_functions\解析项目源代码.py, crazy_functions\询问多个大语言模型.py, crazy_functions\读文章写摘要.py。根据以上分析，用一句话概括程序的整体功能。
+crazy_functions\代码重写为全英文_多线程.py, crazy_functions\图片生成.py, crazy_functions\Conversation_To_File.py, crazy_functions\总结word文档.py, crazy_functions\总结音视频.py, crazy_functions\Markdown_Translate.py, crazy_functions\批量总结PDF文档.py, crazy_functions\批量总结PDF文档pdfminer.py, crazy_functions\PDF_Translate.py, crazy_functions\理解PDF文档内容.py, crazy_functions\生成函数注释.py, crazy_functions\联网的ChatGPT.py, crazy_functions\解析JupyterNotebook.py, crazy_functions\解析项目源代码.py, crazy_functions\询问多个大语言模型.py, crazy_functions\读文章写摘要.py。根据以上分析，用一句话概括程序的整体功能。
 
 | 文件名 | 功能简述 |
 | --- | --- |
 | 代码重写为全英文_多线程.py | 将Python源代码文件中的中文内容转化为英文 |
 | 图片生成.py | 根据激励文本使用GPT模型生成相应的图像 |
-| 对话历史存档.py | 将每次对话记录写入Markdown格式的文件中 |
+| Conversation_To_File.py | 将每次对话记录写入Markdown格式的文件中 |
 | 总结word文档.py | 对输入的word文档进行摘要生成 |
 | 总结音视频.py | 对输入的音视频文件进行摘要生成 |
-| 批量Markdown翻译.py | 将指定目录下的Markdown文件进行中英文翻译 |
+| Markdown_Translate.py | 将指定目录下的Markdown文件进行中英文翻译 |
 | 批量总结PDF文档.py | 对PDF文件进行切割和摘要生成 |
 | 批量总结PDF文档pdfminer.py | 对PDF文件进行文本内容的提取和摘要生成 |
-| PDF批量翻译.py | 将指定目录下的PDF文件进行中英文翻译 |
+| PDF_Translate.py | 将指定目录下的PDF文件进行中英文翻译 |
 | 理解PDF文档内容.py | 对PDF文件进行摘要生成和问题解答 |
 | 生成函数注释.py | 自动生成Python函数的注释 |
 | 联网的ChatGPT.py | 使用网络爬虫和ChatGPT模型进行聊天回答 |

docs/translate_english.json

@@ -36,15 +36,12 @@
     "总结word文档": "SummarizingWordDocuments",
     "解析ipynb文件": "ParsingIpynbFiles",
     "解析JupyterNotebook": "ParsingJupyterNotebook",
-    "对话历史存档": "ConversationHistoryArchive",
-    "载入对话历史存档": "LoadConversationHistoryArchive",
+    "载入Conversation_To_File": "LoadConversationHistoryArchive",
     "删除所有本地对话历史记录": "DeleteAllLocalConversationHistoryRecords",
     "Markdown英译中": "TranslateMarkdownFromEnglishToChinese",
-    "批量Markdown翻译": "BatchTranslateMarkdown",
     "批量总结PDF文档": "BatchSummarizePDFDocuments",
     "批量总结PDF文档pdfminer": "BatchSummarizePDFDocumentsUsingPdfminer",
     "批量翻译PDF文档": "BatchTranslatePDFDocuments",
-    "PDF批量翻译": "BatchTranslatePDFDocuments_MultiThreaded",
     "谷歌检索小助手": "GoogleSearchAssistant",
     "理解PDF文档内容标准文件输入": "UnderstandPdfDocumentContentStandardFileInput",
     "理解PDF文档内容": "UnderstandPdfDocumentContent",
@@ -294,7 +291,7 @@
     "gradio的inbrowser触发不太稳定": "In-browser triggering of gradio is not very stable",
     "回滚代码到原始的浏览器打开函数": "Roll back code to the original browser open function",
     "打开浏览器": "Open browser",
-    "ChatGPT 学术优化": "ChatGPT academic optimization",
+    "ChatGPT 学术优化": "GPT Academic",
     "代码开源和更新": "Code open source and updates",
     "地址🚀": "Address 🚀",
     "感谢热情的": "Thanks to the enthusiastic",
@@ -313,7 +310,7 @@
     "注意": "Attention",
     "以下“红颜色”标识的函数插件需从输入区读取路径作为参数": "The function plugins marked in 'red' below need to read the path from the input area as a parameter",
     "更多函数插件": "More function plugins",
-    "打开插件列表": "Open plugin list",
+    "点击这里搜索插件列表": "Click Here to Search the Plugin List",
     "高级参数输入区": "Advanced parameter input area",
     "这里是特殊函数插件的高级参数输入区": "Here is the advanced parameter input area for special function plugins",
     "请先从插件列表中选择": "Please select from the plugin list first",
@@ -1668,7 +1665,6 @@
     "Markdown翻译指定语言": "TranslateMarkdownToSpecifiedLanguage",
     "Langchain知识库": "LangchainKnowledgeBase",
     "Latex英文纠错加PDF对比": "CorrectEnglishInLatexWithPDFComparison",
-    "Latex输出PDF": "OutputPDFFromLatex",
     "Latex翻译中文并重新编译PDF": "TranslateChineseToEnglishInLatexAndRecompilePDF",
     "sprint亮靛": "SprintIndigo",
     "寻找Latex主文件": "FindLatexMainFile",
@@ -3748,5 +3744,466 @@
     "中文省略号": "Chinese Ellipsis",
     "则不生效": "Will not take effect",
     "目前是两位小数": "Currently is two decimal places",
-    "Incorrect API key. Cohere以提供了不正确的API_KEY为由": "Incorrect API key. Cohere reports an incorrect API_KEY."
+    "Incorrect API key. Cohere以提供了不正确的API_KEY为由": "Incorrect API key. Cohere reports an incorrect API_KEY.",
+    "应当慎之又慎！": "Should be extremely cautious!",
+    "、后端setter": "backend setter",
+    "对于 Run1 的数据": "data for Run1",
+    "另一种更简单的setter方法": "another simpler setter method",
+    "完成解析": "complete parsing",
+    "自动同步": "automatic synchronization",
+    "**表8**": "**Table 8**",
+    "安装方法见": "Installation method see",
+    "通过更严格的 PID 选择对π介子和 K 介子进行过滤以减少主要鉴别为 π 介子的 K 介子等峰背景的污染": "Filtering π mesons and K mesons with a stricter PID to reduce contamination of K mesons mainly identified as π mesons",
+    "并且占据高质量边带的候选体会被拒绝": "And candidates occupying high-quality sidebands are rejected",
+    "GPT-SOVITS 文本转语音服务的运行地址": "Operating address of GPT-SOVITS text-to-speech service",
+    "PDF文件路径": "PDF file path",
+    "注意图片大约占用1": "Note that the image takes up about 1",
+    "以便可以研究BDT输入": "So that BDT inputs can be studied",
+    "是否自动打开浏览器页面": "Whether to automatically open the browser page",
+    "中此模型的APIKEY的名字": "The name of the APIKEY for this model",
+    "{0.8} $ 和 $ \\operatorname{ProbNNk}\\left": "{0.8} $ and $ \\operatorname{ProbNNk}\\left",
+    "请检测终端输出": "Please check the terminal output",
+    "注册账号并获取API KEY": "Register an account and get an API KEY",
+    "-=-=-=-=-=-=-= 👇 以下是多模型路由切换函数 -=-=-=-=-=-=-=": "-=-=-=-=-=-=-= 👇 The following is a multi-model route switching function -=-=-=-=-=-=-=",
+    "如不设置": "If not set",
+    "如果只询问“一个”大语言模型": "If only asking about 'one' large language model",
+    "并非为了计算权重而专门施加了附加选择": "Not specifically applying additional selection for weight calculation",
+    "DOC2X的PDF解析服务": "PDF parsing service of DOC2X",
+    "两兄弟": "Two brothers",
+    "相同的切割也用于Run2和Run1数据": "The same segmentation is also used for Run2 and Run1 data",
+    "返回的数据流第一次为空": "The returned data stream is empty for the first time",
+    "对于光子 PID": "For photon PID",
+    "例如chatglm&gpt-3.5-turbo&gpt-4": "For example chatglm&gpt-3.5-turbo&gpt-4",
+    "第二种方法": "The second method",
+    "BDT 模型的系统性误差使用通过拟合通过和未通过所选 BDT 截断值的 $ B $ 候选体质量分布的异构同位旋对称模式进行评估": "The systematic error of the BDT model is evaluated using the heterogeneous isospin symmetry mode of the candidate body mass distribution of $ B $ selected by fitting through and not through the selected BDT truncation value",
+    "通过比较模拟和真实的 $ {B}^{ + } \\rightarrow  J/\\psi {K}^{* + } $ 衰变样本来计算权重": "Calculate weights by comparing simulated and real $ {B}^{ + } \\rightarrow  J/\\psi {K}^{* + } $ decay samples",
+    "上下文长度超过glm-4v上限2000tokens": "The context length exceeds the upper limit of 2000 tokens for glm-4v",
+    "通过为每个模拟信号候选分配权重来校正模拟和碰撞数据之间的一些差异": "Correct some differences between simulated and collision data by assigning weights to each simulated signal candidate",
+    "2016 年上磁场数据集中通过松散选择": "Loose selection in the 2016 upper magnetic field data set",
+    "定义history的一个孪生的前端存储区": "Define a twin front-end storage area for history",
+    "为默认值；": "For the default value;",
+    "一个带二级菜单的插件": "A plugin with a secondary menu",
+    "用于": "Used for",
+    "每次请求的最大token数量": "Maximum token count for each request",
+    "输入Arxiv的ID或者网址": "Enter the Arxiv ID or URL",
+    "采用哪种方法执行转换": "Which method to use for transformation",
+    "定义history_cache-": "Define history_cache-",
+    "再点击该插件": "Click the plugin again",
+    "隐藏": "Hide",
+    "第三个参数": "The third parameter",
+    "声明这是一个文本框": "Declare this as a text box",
+    "其准则为拒绝已知 $ {B}^{ + } $ 质量内 $  \\pm  {50}\\mathrm{{MeV}}/{c}^{2} $ 范围内的候选体": "Its criterion is to reject candidates within $  \\pm  {50}\\mathrm{{MeV}}/{c}^{2} $ of the known $ {B}^{ + } $ mass",
+    "第一种方法": "The first method",
+    "正在尝试GROBID": "Trying GROBID",
+    "定义新一代插件的高级参数区": "Define the advanced parameter area for the new generation of plugins",
+    "047个tokens": "47 tokens",
+    "PDF解析方法": "PDF parsing method",
+    "缺失 DOC2X_API_KEY": "Missing DOC2X_API_KEY",
+    "第二个参数": "The second parameter",
+    "将只取第一张图片进行处理": "Only the first image will be processed",
+    "请检查配置文件的": "Please check the configuration file",
+    "此函数已经弃用！！新函数位于": "This function has been deprecated!! The new function is located at",
+    "同样地": "Similarly",
+    "的 $ J/\\psi {K}^{ + }{\\pi }^{0} $ 和 $ J/\\psi {K}^{ + } $ 质量的分布": "The distribution of the masses of $ J/\\psi {K}^{ + }{\\pi }^{0} $ and $ J/\\psi {K}^{ + } $",
+    "取消": "Cancel",
+    "3.8 对 BDT 系统误差的严格 PID 选择": "Strict PID selection for BDT system errors at 3.8",
+    "发送至DOC2X解析": "Send to DOC2X for parsing",
+    "在触发这个按钮时": "When triggering this button",
+    "例如对于01万物的yi-34b-chat-200k": "For example, for 010,000 items yi-34b-chat-200k",
+    "继续等待": "Continue waiting",
+    "留空则使用时间作为文件名": "Leave blank to use time as the file name",
+    "获得以下报错信息": "Get the following error message",
+    "ollama模型": "Ollama model",
+    "要求如下": "Requirements are as follows",
+    "不包括思维导图": "Excluding mind maps",
+    "则用指定模型覆盖全局模型": "Then override the global model with the specified model",
+    "DOC2X服务不可用": "DOC2X service is not available",
+    "则抛出异常": "Then throw an exception",
+    "幻方-深度求索大模型在线API -=-=-=-=-=-=-": "Magic Square - Deep Quest Large Model Online API -=-=-=-=-=-=-",
+    "详见 themes/common.js": "See themes/common.js",
+    "如果尝试加载未授权的类": "If trying to load unauthorized class",
+    "因此真实样本包含一定比例的背景": "Therefore, real samples contain a certain proportion of background",
+    "热更新Prompt & ModelOverride": "Hot update Prompt & ModelOverride",
+    "可能的原因是": "Possible reasons are",
+    "因此仅BDT进入相应的选择": "So only BDT enters the corresponding selection",
+    "⚠️请不要与模型的最大token数量相混淆": "⚠️ Do not confuse with the maximum token number of the model",
+    "为openai格式的API生成响应函数": "Generate response function for OpenAI format API",
+    "API异常": "API exception",
+    "调用Markdown插件": "Call Markdown plugin",
+    "报告已经添加到右侧“文件下载区”": "The report has been added to the right 'File Download Area'",
+    "把PDF文件拖入对话": "Drag the PDF file into the dialogue",
+    "根据基础功能区 ModelOverride 参数调整模型类型": "Adjust the model type according to the ModelOverride parameter in the basic function area",
+    "vllm 对齐支持 -=-=-=-=-=-=-": "VLLM alignment support -=-=-=-=-=-=-",
+    "强制点击此基础功能按钮时": "When forcing to click this basic function button",
+    "请上传文件后": "Please upload the file first",
+    "解析错误": "Parsing error",
+    "APIKEY为空": "APIKEY is empty",
+    "效果最好": "Best effect",
+    "未来5天": "Next 5 days",
+    "会先执行js代码更新history_cache": "Will first execute js code to update history_cache",
+    "下拉菜单的选项为": "The options in the dropdown menu are",
+    "额外的翻译提示词": "Additional translation prompts",
+    "这三个切割也用于选择 $ {B}^{ + } \\rightarrow  J/\\psi {K}^{* + } $ 衰变": "These three cuts are also used to select $ {B}^{ + } \\rightarrow  J/\\psi {K}^{* + } $ decay",
+    "借鉴自同目录下的bridge_chatgpt.py": "Inspired by bridge_chatgpt.py in the same directory",
+    "其中质量从 DTF 四维向量重新计算以改善测量的线形": "Recalculate the mass from the DTF four-vector to improve the linearity of the measurement",
+    "移除任何不安全的元素": "Remove any unsafe elements",
+    "默认返回原参数": "Return the original parameters by default",
+    "三兄弟": "Three brothers",
+    "为下拉菜单默认值；": "As the default value for the dropdown menu;",
+    "翻译后的带图文档.zip": "Translated document with images.zip",
+    "是否使用代理": "Whether to use a proxy",
+    "新一代插件的高级参数区确认按钮": "Confirmation button for the advanced parameter area of the new generation plugin",
+    "声明这是一个下拉菜单": "Declare that this is a dropdown menu",
+    "ffmpeg未安装": "FFmpeg not installed",
+    "围绕 $ {K}^{* + } $ 的质量窗口从 $  \\pm  {100} $ 缩小至 $  \\pm  {75}\\mathrm{{MeV}}/{c}^{2} $": "Narrow the mass window around $ {K}^{* + } $ from $  \\pm  {100} $ to $  \\pm  {75}\\mathrm{{MeV}}/{c}^{2} $",
+    "保存文件名": "Save file name",
+    "第三种方法": "The third method",
+    "$ 缩减到 $ \\left\\lbrack  {{75}": "$ Reduced to $ \\left\\lbrack  {{75}",
+    "清理提取路径": "Clean up the extraction path",
+    "history的更新方法": "Method to update the history",
+    "定义history的后端state": "Define the backend state of the history",
+    "生成包含图片的压缩包": "Generate a compressed package containing images",
+    "执行插件": "Execute the plugin",
+    "使用指定的模型": "Use the specified model",
+    "只允许特定的类进行反序列化": "Only allow specific classes to be deserialized",
+    "是否允许从缓存中调取结果": "Whether to allow fetching results from the cache",
+    "效果不理想": "The effect is not ideal",
+    "这计算是在不需要BDT要求的情况下进行的": "This calculation is done without the need for BDT requirements",
+    "生成在线预览": "Generate online preview",
+    "主输入": "Primary input",
+    "定义允许的安全类": "Define allowed security classes",
+    "其最大请求数为4096": "Its maximum request number is 4096",
+    "在线预览翻译": "Online preview translation",
+    "其中传入参数": "Among the incoming parameters",
+    "下载Gradio主题时出现异常": "An exception occurred when downloading the Gradio theme",
+    "修正一些公式问题": "Correcting some formula issues",
+    "对专有名词、翻译语气等方面的要求": "Requirements for proper nouns, translation tone, etc.",
+    "替换成$$": "Replace with $$",
+    "主要用途": "Main purpose",
+    "允许 $ {\\pi }^{0} $ 候选体的质量范围从 $ \\left\\lbrack  {0": "Allow the mass range of the $ {\\pi }^{0} $ candidate from $ \\left\\lbrack  {0",
+    "$ {B}^{ + } $ 衰变到 $ J/\\psi {K}^{ + } $": "$ {B}^{ + } $ decays to $ J/\\psi {K}^{ + } $",
+    "未指定路径": "Path not specified",
+    "True为不使用": "True means not in use",
+    "尝试获取完整的错误信息": "Attempt to get the complete error message",
+    "仅今天": "Only today",
+    "图 12": "Figure 12",
+    "效果次优": "Effect is suboptimal",
+    "绘制的Mermaid图表类型": "Types of Mermaid charts drawn",
+    "vllm模型": "VLLM model",
+    "文本框上方显示": "Displayed above the text box",
+    "未来3天": "Next 3 days",
+    "在这里添加其他安全的类": "Add other secure classes here",
+    "额外提示词": "Additional prompt words",
+    "由于在等离子体共轭模式中没有光子": "Due to no photons in the plasma conjugate mode",
+    "将公式中的\\": "Escape the backslash in the formula",
+    "插件功能": "Plugin function",
+    "设置5秒不准咬人": "Disallow biting for 5 seconds",
+    "定义cookies的后端state": "Define the backend state of cookies",
+    "选择其他类型时将直接绘制指定的图表类型": "Directly draw the specified chart type when selecting another type",
+    "替换成$": "Replace with $",
+    "自动从输入框同步": "Automatically sync from the input box",
+    "第一个参数": "The first parameter",
+    "注意需要使用双引号将内容括起来": "Note that you need to enclose the content in double quotes",
+    "下拉菜单上方显示": "Display above the dropdown menu",
+    "把history转存history_cache备用": "Transfer history to history_cache for backup",
+    "从头执行": "Execute from the beginning",
+    "选择插件参数": "Select plugin parameters",
+    "您还可以在接入one-api/vllm/ollama时": "You can also access one-api/vllm/ollama",
+    "输入对话存档文件名": "Enter the dialogue archive file name",
+    "但是需要DOC2X服务": "But DOC2X service is required",
+    "相反": "On the contrary",
+    "你好👋": "Hello👋",
+    "生成在线预览html": "Generate online preview HTML",
+    "为简化拟合模型": "To simplify the fitting model",
+    "、前端": "Front end",
+    "定义插件的二级选项菜单": "Define the secondary option menu of the plugin",
+    "未选定任何插件": "No plugin selected",
+    "以上三种方法都试一遍": "Try all three methods above once",
+    "一个非常简单的插件": "A very simple plugin",
+    "为了更灵活地接入ollama多模型管理界面": "In order to more flexibly access the ollama multi-model management interface",
+    "文本框内部显示": "Text box internal display",
+    "☝️ 以上是模型路由 -=-=-=-=-=-=-=-=-=": "☝️ The above is the model route -=-=-=-=-=-=-=-=-=",
+    "则使用当前全局模型；如设置": "Then use the current global model; if set",
+    "由LLM决定": "Decided by LLM",
+    "4 对模拟的修正": "4 corrections to the simulation",
+    "glm-4v只支持一张图片": "glm-4v only supports one image",
+    "这个并发量稍微大一点": "This concurrency is slightly larger",
+    "无法处理EdgeTTS音频": "Unable to handle EdgeTTS audio",
+    "早期代码": "Early code",
+    "您可以调用下拉菜单中的“LoadChatHistoryArchive”还原当下的对话": "You can use the 'LoadChatHistoryArchive' in the drop-down menu to restore the current conversation",
+    "因此您在定义和使用类变量时": "So when you define and use class variables",
+    "这将通过sPlot方法进行减除": "This will be subtracted through the sPlot method",
+    "然后再执行python代码更新history": "Then execute python code to update history",
+    "新一代插件需要注册Class": "The new generation plugin needs to register Class",
+    "请选择": "Please select",
+    "旧插件的高级参数区确认按钮": "Confirm button in the advanced parameter area of the old plugin",
+    "多数情况": "In most cases",
+    "ollama 对齐支持 -=-=-=-=-=-=-": "ollama alignment support -=-=-=-=-=-=-",
+    "用该压缩包+Conversation_To_File进行反馈": "Use this compressed package + Conversation_To_File for feedback",
+    "名称": "Name",
+    "错误处理部分": "Error handling section",
+    "False为使用": "False for use",
+    "详细方法见第4节": "See Section 4 for detailed methods",
+    "在应用元组裁剪后": "After applying tuple clipping",
+    "深度求索": "Deep Search",
+    "绘制脑图的Demo": "Demo for Drawing Mind Maps",
+    "需要在表格前加上一个emoji": "Need to add an emoji in front of the table",
+    "批量Markdown翻译": "Batch Markdown Translation",
+    "将语言模型的生成文本朗读出来": "Read aloud the generated text of the language model",
+    "Function旧接口仅会在“VoidTerminal”中起作用": "The old interface of Function only works in 'VoidTerminal'",
+    "请配置 DOC2X_API_KEY": "Please configure DOC2X_API_KEY",
+    "如果同时询问“多个”大语言模型": "If inquiring about 'multiple' large language models at the same time",
+    "3.7 用于MC校正的宽松选择": "3.7 Loose selection for MC correction",
+    "咬的也不是人": "Not biting humans either",
+    "定义 后端state": "Define backend state",
+    "这个隐藏textbox负责装入当前弹出插件的属性": "This hidden textbox is responsible for loading the properties of the current pop-up plugin",
+    "会执行在不同的线程中": "Will be executed in different threads",
+    "定义cookies的一个孪生的前端存储区": "Define a twin front-end storage area for cookies",
+    "模型选择": "Model selection",
+    "应用于信号、标准化和等离子体共轭模式的最终切割": "Final cutting applied to signal, normalization, and plasma conjugate modes",
+    "确认参数并执行": "Confirm parameters and execute",
+    "请先上传文件": "Please upload the file first",
+    "以便公式渲染": "For formula rendering",
+    "加载PDF文件": "Load PDF file",
+    "LoadChatHistoryArchive | 输入参数为路径": "Load Chat History Archive | Input parameter is the path",
+    "日期选择": "Date selection",
+    "除 $ {B}^{ + } \\rightarrow  J/\\psi {K}^{ + } $ 否决": "Veto except for $ {B}^{ + } \\rightarrow  J/\\psi {K}^{ + } $",
+    "使用 0.2 的截断值会获得类似的效率": "Using a truncation value of 0.2 will achieve similar efficiency",
+    "请输入": "Please enter",
+    "当注册Class后": "After registering the Class",
+    "Markdown中使用不标准的表格": "Using non-standard tables in Markdown",
+    "采用非常宽松的截断值": "Using very loose truncation values",
+    "为了更灵活地接入vllm多模型管理界面": "To more flexibly access the vllm multi-model management interface",
+    "读取解析": "Read and parse",
+    "允许缓存": "Allow caching",
+    "Run2 中对 Kaon 鉴别的要求被收紧为 $ \\operatorname{ProbNNk}\\left": "The requirement for Kaon discrimination in Run2 has been tightened to $ \\operatorname{ProbNNk}\\left",
+    "当前使用人数太多": "Current user count is too high",
+    "提取historyBox信息": "Extract historyBox information",
+    "📚Arxiv论文精细翻译": "Fine translation of 📚Arxiv papers",
+    "检索中": "Searching",
+    "受到限制": "Restricted",
+    "3. 历史输入包含图像": "3. Historical input contains images",
+    "待通过互联网检索的问题": "Questions to be retrieved via the internet",
+    "使用 findall 方法查找所有匹配的 Base64 字符串": "Use findall method to find all matching Base64 strings",
+    "建立文件树": "Build file tree",
+    "经过clip": "Through clip",
+    "增强": "Enhance",
+    "对话存档": "Conversation archive",
+    "网页": "Webpage",
+    "怎么下载相关论文": "How to download related papers",
+    "当前对话是关于 Nginx 的介绍和使用等": "The current conversation is about the introduction and use of Nginx, etc.",
+    "从而提高学术论文检索的精度": "To improve the accuracy of academic paper retrieval",
+    "使用自然语言实现您的想法": "Implement your ideas using natural language",
+    "这样可以保证后续问答能读取到有效的历史记录": "This ensures that subsequent questions and answers can read valid historical records",
+    "生成对比html": "Generate comparison html",
+    "Doc2x API 页数受限": "Doc2x API page count limited",
+    "inputs 本次请求": "Inputs for this request",
+    "有其原问题": "Has its original question",
+    "在线搜索失败": "Online search failed",
+    "选择搜索引擎": "Choose a search engine",
+    "同步已知模型的其他信息": "Synchronize other information of known models",
+    "在线搜索服务": "Online search service",
+    "常规对话": "Regular conversation",
+    "使用正则表达式匹配模式": "Use regular expressions to match patterns",
+    "从而提高网页检索的精度": "To improve the accuracy of webpage retrieval",
+    "GPT-Academic输出文档": "GPT-Academic output document",
+    "/* 小按钮 */": "/* Small button */",
+    "历史记录": "History record",
+    "上传一系列python源文件": "Upload a series of python source files",
+    "仅DALLE3生效": "Only DALLE3 takes effect",
+    "判断给定的单个字符是否是全角字符": "Determine if the given single character is a full-width character",
+    "依次放入每组第一": "Put each group's first one by one",
+    "这部分代码会逐渐移动到common.js中": "This part of the code will gradually move to common.js",
+    "列出机器学习的三种应用": "List three applications of machine learning",
+    "更新主输入区的参数": "Update the parameters of the main input area",
+    "从以上搜索结果中抽取与问题": "Extract from the above search results related to the question",
+    "* 如果解码失败": "* If decoding fails",
+    "如果是已知模型": "If it is a known model",
+    "一": "One",
+    "模型切换时的回调": "Callback when switching models",
+    "加入历史": "Add to history",
+    "压缩结果": "Compress the result",
+    "使用 DALLE2/DALLE3 生成图片 | 输入参数字符串": "Use DALLE2/DALLE3 to generate images | Input parameter string",
+    "搜索分类": "Search category",
+    "获得空的回复": "Get an empty reply",
+    "多模态模型": "Multimodal model",
+    "移除注释": "Remove comments",
+    "对话背景": "Conversation background",
+    "获取需要执行的插件名称": "Get the name of the plugin to be executed",
+    "是否启动语音输入功能": "Whether to enable voice input function",
+    "更新高级参数输入区的参数": "Update the parameters of the advanced parameter input area",
+    "启用多模态能力": "Enable multimodal capabilities",
+    "请根据以上搜索结果回答问题": "Please answer the question based on the above search results",
+    "生成的问题要求指向对象清晰明确": "The generated question requires clear and specific references to the object",
+    "Arxiv论文翻译": "Translation of Arxiv paper",
+    "找不到该模型": "Model not found",
+    "提取匹配的数字部分并转换为整数": "Extract matching numeric parts and convert to integers",
+    "尝试进行搜索优化": "Try to optimize the search",
+    "重新梳理输入参数": "Reorganize input parameters",
+    "存储翻译好的arxiv论文的路径": "Path to store translated arxiv papers",
+    "尽量使用英文": "Use English as much as possible",
+    "插件二级菜单的实现": "Implementation of plugin submenus",
+    "* 增强优化": "Enhanced optimization",
+    "但属于其他用户": "But belongs to another user",
+    "不得有多余字符": "No extra characters allowed",
+    "怎么解决": "How to solve",
+    "根据综合回答问题": "Answer questions comprehensively",
+    "降低温度再试一次": "Lower the temperature and try again",
+    "作为一个网页搜索助手": "As a web search assistant",
+    "支持将文件直接粘贴到输入区": "Support pasting files directly into the input area",
+    "打开新对话": "Open a new conversation",
+    "但位置非法": "But the position is illegal",
+    "会自动读取输入框内容": "Will automatically read the input box content",
+    "移除模块的文档字符串": "Remove the module's docstrings",
+    "from crazy_functions.联网的ChatGPT_bing版 import 连接bing搜索回答问题": "from crazy_functions.online.ChatGPT_bing import connect_bing_search_to_answer_questions",
+    "关闭": "Close",
+    "学术论文": "Academic paper",
+    "多模态能力": "Multimodal capabilities",
+    "无渲染": "No rendering",
+    "弃用功能": "Deprecated feature",
+    "输入Searxng的地址": "Enter the address of Searxng",
+    "风格": "Style",
+    "介绍下第2点": "Introduce the second point",
+    "你的任务是结合历史记录": "Your task is to combine historical records",
+    "前端": "Frontend",
+    "采取措施丢弃一部分文本": "Take measures to discard some text",
+    "2. 输入包含图像": "2. Input contains images",
+    "输入问题": "Input question",
+    "可能原因": "Possible reasons",
+    "2. Java 是一种面向对象的编程语言": "Java is an object-oriented programming language",
+    "不支持的检索类型": "Unsupported retrieval type",
+    "第四步": "Step four",
+    "2. 机器学习在自然语言处理中的应用": "Applications of machine learning in natural language processing",
+    "浮动菜单定义": "Definition of floating menu",
+    "鿿": "Undefined",
+    "history 历史上下文": "History context",
+    "1. Java 是一种编译型语言": "Java is a compiled language",
+    "请根据给定的若干条搜索结果回答问题": "Answer the question based on the given search results",
+    "当输入文本 + 历史文本超出最大限制时": "When the input text + historical text exceeds the maximum limit",
+    "限DALLE3": "Limited to DALLE3",
+    "原问题": "Original question",
+    "日志文件": "Log file",
+    "输入图片描述": "Input image description",
+    "示例使用": "Example usage",
+    "后续参数": "Subsequent parameters",
+    "请用一句话对下面的程序文件做一个整体概述": "Please give a brief overview of the program file below in one sentence",
+    "当前对话是关于深度学习的介绍和应用等": "The current conversation is about the introduction and applications of deep learning",
+    "点击这里输入「关键词」搜索插件": "Click here to enter 'keywords' search plugin",
+    "按用户划分": "Divided by user",
+    "将结果写回源文件": "Write the results back to the source file",
+    "使用前切换到GPT系列模型": "Switch to GPT series model before using",
+    "正在读取下一段代码片段": "Reading the next code snippet",
+    "第二个搜索结果": "Second search result",
+    "作为一个学术论文搜索助手": "As an academic paper search assistant",
+    "搜索": "Search",
+    "无法从searxng获取信息！请尝试更换搜索引擎": "Unable to retrieve information from searxng! Please try changing the search engine",
+    "* 清洗搜索结果": "Cleaning search results",
+    "或者压缩包": "Or compressed file",
+    "模型": "Model",
+    "切换布局": "Switch layout",
+    "生成当前浏览器窗口的uuid": "Generate the uuid of the current browser window",
+    "左上角工具栏定义": "Definition of the top-left toolbar",
+    "from crazy_functions.联网的ChatGPT import ConnectToNetworkToAnswerQuestions": "from crazy_functions.ConnectToNetworkToAnswerQuestions import ChatGPT",
+    "对最相关的三个搜索结果进行总结": "Summarize the top three most relevant search results",
+    "刷新失效": "Refresh invalid",
+    "将处理后的 AST 转换回源代码": "Convert the processed AST back to source code",
+    "/* 插件下拉菜单 */": "/* Plugin dropdown menu */",
+    "移除类的文档字符串": "Remove the documentation strings of a class",
+    "请尽量不要修改": "Please try not to modify",
+    "并更换新的 API 秘钥": "And replace with a new API key",
+    "输入文件的路径": "Input file path",
+    "发现异常嵌套公式": "Identify nested formula exceptions",
+    "修复不标准的dollar公式符号的问题": "Fix the issue of non-standard dollar formula symbols",
+    "Searxng互联网检索服务": "Searxng Internet search service",
+    "联网检索中": "In network retrieval",
+    "并与“原问题语言相同”": "And in the same language as the original question",
+    "存在": "Exists",
+    "列出Java的三种特点": "List three characteristics of Java",
+    "3. Java 是一种跨平台的编程语言": "3. Java is a cross-platform programming language",
+    "所有源文件均已处理完毕": "All source files have been processed",
+    "限DALLE2": "Limited to DALLE2",
+    "紫东太初大模型 https": "Zidong Taichu Large Model https",
+    "🎨图片生成": "🎨 Image generation",
+    "1. 模型本身是多模态模型": "1. The model itself is multimodal",
+    "相关的信息": "Related information",
+    "* 或者使用搜索优化器": "* Or use a search optimizer",
+    "搜索查询": "Search query",
+    "当前对话是关于 Nginx 的介绍和在Ubuntu上的使用等": "The current conversation is about the introduction of Nginx and its use on Ubuntu, etc.",
+    "必须以json形式给出": "Must be provided in JSON format",
+    "开启": "Turn on",
+    "1. 机器学习在图像识别中的应用": "1. The application of machine learning in image recognition",
+    "处理代码片段": "Processing code snippet",
+    "则尝试获取其信息": "Then try to get its information",
+    "已完成的文件": "Completed file",
+    "注意这可能会消耗较多token": "Note that this may consume more tokens",
+    "多模型对话": "Multi-model conversation",
+    "现在有历史记录": "Now there is a history record",
+    "你知道 Python 么": "Do you know Python?",
+    "Base64编码": "Base64 encoding",
+    "Gradio的inbrowser触发不太稳定": "Gradio's in-browser trigger is not very stable",
+    "CJK标点符号": "CJK punctuation marks",
+    "请联系 Doc2x 方面": "Please contact Doc2x for details",
+    "耗尽generator避免报错": "Exhaust the generator to avoid errors",
+    "📚本地Latex论文精细翻译": "📚 Local Latex paper finely translated",
+    "* 尝试解码优化后的搜索结果": "* Try to decode the optimized search results",
+    "为这些代码添加docstring | 输入参数为路径": "Add docstring for these codes | Input parameter is path",
+    "读取插件参数": "Read plugin parameters",
+    "如果剩余的行数非常少": "If the remaining lines are very few",
+    "输出格式为JSON": "Output format is JSON",
+    "提取QaBox信息": "Extract QaBox information",
+    "不使用多模态能力": "Not using multimodal capabilities",
+    "解析源代码为 AST": "Parse source code into AST",
+    "使用前请切换模型到GPT系列": "Switch the model to GPT series before using",
+    "中文字符": "Chinese characters",
+    "用户的上传目录": "User's upload directory",
+    "请将文件上传后再执行该任务": "Please upload the file before executing this task",
+    "移除函数的文档字符串": "Remove the function's docstring",
+    "新版-更流畅": "New version - smoother",
+    "检索词": "Search term",
+    "获取插件参数": "Get plugin parameters",
+    "获取插件执行函数": "Get plugin execution function",
+    "为“原问题”生成个不同版本的“检索词”": "Generate different versions of 'search terms' for the 'original question'",
+    "并清洗重复的搜索结果": "Clean and remove duplicate search results",
+    "直接返回原始问题": "Directly return the original question",
+    "从不同角度": "From different perspectives",
+    "展示已经完成的部分": "Display completed parts",
+    "搜索优化": "Search optimization",
+    "解决缩进问题": "Resolve indentation issues",
+    "直接给出最多{num}个检索词": "Directly provide up to {num} search terms",
+    "对话数据": "Conversation data",
+    "定义一个正则表达式来匹配 Base64 字符串": "Define a regular expression to match Base64 strings",
+    "转化为kwargs字典": "Convert to kwargs dictionary",
+    "原始数据": "Original data",
+    "当以下条件满足时": "When the following conditions are met",
+    "主题修改": "Topic modification",
+    "Searxng服务地址": "Searxng service address",
+    "3. 机器学习在推荐系统中的应用": "3. Application of machine learning in recommendation systems",
+    "全角符号": "Full-width symbols",
+    "发送到大模型进行分析": "Send for analysis to a large model",
+    "一个常用的测试目录": "A commonly used test directory",
+    "在线搜索失败！": "Online search failed!",
+    "搜索语言": "Search language",
+    "万事俱备": "All is ready",
+    "指定了后续参数的名称": "Specified the names of subsequent parameters",
+    "是否使用搜索增强": "Whether to use search enhancement",
+    "你知道 GAN 么": "Do you know about GAN?",
+    "├── 互联网检索": "├── Internet retrieval",
+    "公式之中出现了异常": "An anomaly occurred in the formula",
+    "当前对话是关于深度学习的介绍和在图像识别中的应用等": "The current conversation is about the introduction of deep learning and its applications in image recognition, etc.",
+    "返回反转后的 Base64 字符串列表": "Return a list of Base64 strings reversed",
+    "一鼓作气处理掉": "Deal with it in one go",
+    "剩余源文件数量": "Remaining source file count",
+    "查互联网后回答": "Answer after checking the internet",
+    "需要生成图像的文本描述": "Text description for generating images",
+    "* 如果再次失败": "If failed again",
+    "质量": "Quality",
+    "请配置 TAICHU_API_KEY": "Please configure TAICHU_API_KEY",
+    "most_recent_uploaded 是一个放置最新上传图像的路径": "most_recent_uploaded is a path to place the latest uploaded images",
+    "真正的参数": "Actual parameters",
+    "生成带注释文件": "Generate files with annotations",
+    "源自": "From",
+    "怎么下载": "How to download",
+    "请稍后": "Please wait",
+    "会尝试结合历史记录进行搜索优化": "Will try to optimize the search by combining historical records",
+    "max_token_limit 最大token限制": "max_token_limit maximum token limit"
 }

docs/translate_japanese.json

@@ -36,15 +36,15 @@
     "总结word文档": "SummarizeWordDocument",
     "解析ipynb文件": "ParseIpynbFile",
     "解析JupyterNotebook": "ParseJupyterNotebook",
-    "对话历史存档": "ConversationHistoryArchive",
-    "载入对话历史存档": "LoadConversationHistoryArchive",
+    "Conversation_To_File": "ConversationHistoryArchive",
+    "载入Conversation_To_File": "LoadConversationHistoryArchive",
     "删除所有本地对话历史记录": "DeleteAllLocalChatHistory",
     "Markdown英译中": "MarkdownTranslateFromEngToChi",
-    "批量Markdown翻译": "BatchTranslateMarkdown",
+    "Markdown_Translate": "BatchTranslateMarkdown",
     "批量总结PDF文档": "BatchSummarizePDFDocuments",
     "批量总结PDF文档pdfminer": "BatchSummarizePDFDocumentsUsingPDFMiner",
     "批量翻译PDF文档": "BatchTranslatePDFDocuments",
-    "PDF批量翻译": "BatchTranslatePDFDocumentsUsingMultiThreading",
+    "PDF_Translate": "BatchTranslatePDFDocumentsUsingMultiThreading",
     "谷歌检索小助手": "GoogleSearchAssistant",
     "理解PDF文档内容标准文件输入": "StandardFileInputForUnderstandingPDFDocumentContent",
     "理解PDF文档内容": "UnderstandingPDFDocumentContent",
@@ -1492,7 +1492,7 @@
     "交互功能模板函数": "InteractiveFunctionTemplateFunction",
     "交互功能函数模板": "InteractiveFunctionFunctionTemplate",
     "Latex英文纠错加PDF对比": "LatexEnglishErrorCorrectionWithPDFComparison",
-    "Latex输出PDF": "LatexOutputPDFResult",
+    "Latex_Function": "LatexOutputPDFResult",
     "Latex翻译中文并重新编译PDF": "TranslateChineseAndRecompilePDF",
     "语音助手": "VoiceAssistant",
     "微调数据集生成": "FineTuneDatasetGeneration",

docs/translate_std.json

@@ -6,17 +6,14 @@
     "Latex英文纠错加PDF对比": "CorrectEnglishInLatexWithPDFComparison",
     "下载arxiv论文并翻译摘要": "DownloadArxivPaperAndTranslateAbstract",
     "Markdown翻译指定语言": "TranslateMarkdownToSpecifiedLanguage",
-    "PDF批量翻译": "BatchTranslatePDFDocuments_MultiThreaded",
     "下载arxiv论文翻译摘要": "DownloadArxivPaperTranslateAbstract",
     "解析一个Python项目": "ParsePythonProject",
     "解析一个Golang项目": "ParseGolangProject",
     "代码重写为全英文_多线程": "RewriteCodeToEnglish_MultiThreaded",
     "解析一个CSharp项目": "ParsingCSharpProject",
     "删除所有本地对话历史记录": "DeleteAllLocalConversationHistoryRecords",
-    "批量Markdown翻译": "BatchTranslateMarkdown",
     "连接bing搜索回答问题": "ConnectBingSearchAnswerQuestion",
     "Langchain知识库": "LangchainKnowledgeBase",
-    "Latex输出PDF": "OutputPDFFromLatex",
     "把字符太少的块清除为回车": "ClearBlocksWithTooFewCharactersToNewline",
     "Latex精细分解与转化": "DecomposeAndConvertLatex",
     "解析一个C项目的头文件": "ParseCProjectHeaderFiles",
@@ -46,7 +43,7 @@
     "高阶功能模板函数": "HighOrderFunctionTemplateFunctions",
     "高级功能函数模板": "AdvancedFunctionTemplate",
     "总结word文档": "SummarizingWordDocuments",
-    "载入对话历史存档": "LoadConversationHistoryArchive",
+    "载入Conversation_To_File": "LoadConversationHistoryArchive",
     "Latex中译英": "LatexChineseToEnglish",
     "Latex英译中": "LatexEnglishToChinese",
     "连接网络回答问题": "ConnectToNetworkToAnswerQuestions",
@@ -70,7 +67,6 @@
     "读文章写摘要": "ReadArticleWriteSummary",
     "生成函数注释": "GenerateFunctionComments",
     "解析项目本身": "ParseProjectItself",
-    "对话历史存档": "ConversationHistoryArchive",
     "专业词汇声明": "ProfessionalTerminologyDeclaration",
     "解析docx": "ParseDocx",
     "解析源代码新": "ParsingSourceCodeNew",
@@ -104,5 +100,13 @@
     "随机小游戏": "RandomMiniGame",
     "互动小游戏": "InteractiveMiniGame",
     "解析历史输入": "ParseHistoricalInput",
-    "高阶功能模板函数示意图": "HighOrderFunctionTemplateDiagram"
+    "高阶功能模板函数示意图": "HighOrderFunctionTemplateDiagram",
+    "载入对话历史存档": "LoadChatHistoryArchive",
+    "对话历史存档": "ChatHistoryArchive",
+    "解析PDF_DOC2X_转Latex": "ParsePDF_DOC2X_toLatex",
+    "解析PDF_基于DOC2X": "ParsePDF_basedDOC2X",
+    "解析PDF_简单拆解": "ParsePDF_simpleDecomposition",
+    "解析PDF_DOC2X_单文件": "ParsePDF_DOC2X_singleFile",
+    "注释Python项目": "CommentPythonProject",
+    "注释源代码": "CommentSourceCode"
 }

docs/translate_traditionalchinese.json

@@ -35,15 +35,15 @@
     "总结word文档": "SummarizeWordDocument",
     "解析ipynb文件": "ParseIpynbFile",
     "解析JupyterNotebook": "ParseJupyterNotebook",
-    "对话历史存档": "ConversationHistoryArchive",
-    "载入对话历史存档": "LoadConversationHistoryArchive",
+    "Conversation_To_File": "ConversationHistoryArchive",
+    "载入Conversation_To_File": "LoadConversationHistoryArchive",
     "删除所有本地对话历史记录": "DeleteAllLocalConversationHistoryRecords",
     "Markdown英译中": "MarkdownEnglishToChinese",
-    "批量Markdown翻译": "BatchMarkdownTranslation",
+    "Markdown_Translate": "BatchMarkdownTranslation",
     "批量总结PDF文档": "BatchSummarizePDFDocuments",
     "批量总结PDF文档pdfminer": "BatchSummarizePDFDocumentsPdfminer",
     "批量翻译PDF文档": "BatchTranslatePDFDocuments",
-    "PDF批量翻译": "BatchTranslatePdfDocumentsMultithreaded",
+    "PDF_Translate": "BatchTranslatePdfDocumentsMultithreaded",
     "谷歌检索小助手": "GoogleSearchAssistant",
     "理解PDF文档内容标准文件输入": "StandardFileInputForUnderstandingPdfDocumentContent",
     "理解PDF文档内容": "UnderstandingPdfDocumentContent",
@@ -1468,7 +1468,7 @@
     "交互功能模板函数": "InteractiveFunctionTemplateFunctions",
     "交互功能函数模板": "InteractiveFunctionFunctionTemplates",
     "Latex英文纠错加PDF对比": "LatexEnglishCorrectionWithPDFComparison",
-    "Latex输出PDF": "OutputPDFFromLatex",
+    "Latex_Function": "OutputPDFFromLatex",
     "Latex翻译中文并重新编译PDF": "TranslateLatexToChineseAndRecompilePDF",
     "语音助手": "VoiceAssistant",
     "微调数据集生成": "FineTuneDatasetGeneration",

main.py

@@ -13,24 +13,40 @@ help_menu_description = \
 </br></br>如何语音对话: 请阅读Wiki
 </br></br>如何临时更换API_KEY: 在输入区输入临时API_KEY后提交（网页刷新后失效）"""
 
+from loguru import logger
 def enable_log(PATH_LOGGING):
-    import logging
-    admin_log_path = os.path.join(PATH_LOGGING, "admin")
-    os.makedirs(admin_log_path, exist_ok=True)
-    log_dir = os.path.join(admin_log_path, "chat_secrets.log")
-    try:logging.basicConfig(filename=log_dir, level=logging.INFO, encoding="utf-8", format="%(asctime)s %(levelname)-8s %(message)s", datefmt="%Y-%m-%d %H:%M:%S")
-    except:logging.basicConfig(filename=log_dir, level=logging.INFO,  format="%(asctime)s %(levelname)-8s %(message)s", datefmt="%Y-%m-%d %H:%M:%S")
-    # Disable logging output from the 'httpx' logger
-    logging.getLogger("httpx").setLevel(logging.WARNING)
-    print(f"所有对话记录将自动保存在本地目录{log_dir}, 请注意自我隐私保护哦！")
+    from shared_utils.logging import setup_logging
+    setup_logging(PATH_LOGGING)
+
+def encode_plugin_info(k, plugin)->str:
+    import copy
+    from themes.theme import to_cookie_str
+    plugin_ = copy.copy(plugin)
+    plugin_.pop("Function", None)
+    plugin_.pop("Class", None)
+    plugin_.pop("Button", None)
+    plugin_["Info"] = plugin.get("Info", k)
+    if plugin.get("AdvancedArgs", False):
+        plugin_["Label"] = f"插件[{k}]的高级参数说明：" + plugin.get("ArgsReminder", f"没有提供高级参数功能说明")
+    else:
+        plugin_["Label"] = f"插件[{k}]不需要高级参数。"
+    return to_cookie_str(plugin_)
 
 def main():
     import gradio as gr
-    if gr.__version__ not in ['3.32.9']:
+    if gr.__version__ not in ['3.32.9', '3.32.10', '3.32.11']:
         raise ModuleNotFoundError("使用项目内置Gradio获取最优体验! 请运行 `pip install -r requirements.txt` 指令安装内置Gradio及其他依赖, 详情信息见requirements.txt.")
-    from request_llms.bridge_all import predict
+    
+    # 一些基础工具
     from toolbox import format_io, find_free_port, on_file_uploaded, on_report_generated, get_conf, ArgsGeneralWrapper, DummyWith
-    # 建议您复制一个config_private.py放自己的秘密, 如API和代理网址
+
+    # 对话、日志记录
+    enable_log(get_conf("PATH_LOGGING"))
+
+    # 对话句柄
+    from request_llms.bridge_all import predict
+
+    # 读取配置
     proxies, WEB_PORT, LLM_MODEL, CONCURRENT_COUNT, AUTHENTICATION = get_conf('proxies', 'WEB_PORT', 'LLM_MODEL', 'CONCURRENT_COUNT', 'AUTHENTICATION')
     CHATBOT_HEIGHT, LAYOUT, AVAIL_LLM_MODELS, AUTO_CLEAR_TXT = get_conf('CHATBOT_HEIGHT', 'LAYOUT', 'AVAIL_LLM_MODELS', 'AUTO_CLEAR_TXT')
     ENABLE_AUDIO, AUTO_CLEAR_TXT, PATH_LOGGING, AVAIL_THEMES, THEME, ADD_WAIFU = get_conf('ENABLE_AUDIO', 'AUTO_CLEAR_TXT', 'PATH_LOGGING', 'AVAIL_THEMES', 'THEME', 'ADD_WAIFU')
@@ -42,12 +58,10 @@ def main():
     PORT = find_free_port() if WEB_PORT <= 0 else WEB_PORT
     from check_proxy import get_current_version
     from themes.theme import adjust_theme, advanced_css, theme_declaration, js_code_clear, js_code_reset, js_code_show_or_hide, js_code_show_or_hide_group2
-    from themes.theme import js_code_for_css_changing, js_code_for_toggle_darkmode, js_code_for_persistent_cookie_init
+    from themes.theme import js_code_for_toggle_darkmode, js_code_for_persistent_cookie_init
     from themes.theme import load_dynamic_theme, to_cookie_str, from_cookie_str, assign_user_uuid
     title_html = f"<h1 align=\"center\">GPT 学术优化 {get_current_version()}</h1>{theme_declaration}"
 
-    # 对话、日志记录
-    enable_log(PATH_LOGGING)
 
     # 一些普通功能模块
     from core_functional import get_core_functions
@@ -70,6 +84,7 @@ def main():
     from check_proxy import check_proxy, auto_update, warm_up_modules
     proxy_info = check_proxy(proxies)
 
+    # 切换布局
     gr_L1 = lambda: gr.Row().style()
     gr_L2 = lambda scale, elem_id: gr.Column(scale=scale, elem_id=elem_id, min_width=400)
     if LAYOUT == "TOP-DOWN":
@@ -84,7 +99,7 @@ def main():
     with gr.Blocks(title="GPT 学术优化", theme=set_theme, analytics_enabled=False, css=advanced_css) as app_block:
         gr.HTML(title_html)
         secret_css = gr.Textbox(visible=False, elem_id="secret_css")
-
+        register_advanced_plugin_init_arr = ""
 
         cookies, web_cookie_cache = make_cookie_cache() # 定义 后端state（cookies）、前端（web_cookie_cache）两兄弟
         with gr_L1():
@@ -96,8 +111,18 @@ def main():
                 with gr.Accordion("输入区", open=True, elem_id="input-panel") as area_input_primary:
                     with gr.Row():
                         txt = gr.Textbox(show_label=False, placeholder="Input question here.", elem_id='user_input_main').style(container=False)
-                    with gr.Row():
-                        submitBtn = gr.Button("提交", elem_id="elem_submit", variant="primary")
+                    with gr.Row(elem_id="gpt-submit-row"):
+                        multiplex_submit_btn = gr.Button("提交", elem_id="elem_submit_visible", variant="primary")
+                        multiplex_sel = gr.Dropdown(
+                            choices=[
+                                "常规对话", 
+                                "多模型对话", 
+                                "智能召回 RAG",
+                                # "智能上下文", 
+                            ], value="常规对话",
+                            interactive=True, label='', show_label=False,
+                            elem_classes='normal_mut_select', elem_id="gpt-submit-dropdown").style(container=False)
+                        submit_btn = gr.Button("提交", elem_id="elem_submit", variant="primary", visible=False)
                     with gr.Row():
                         resetBtn = gr.Button("重置", elem_id="elem_reset", variant="secondary"); resetBtn.style(size="sm")
                         stopBtn = gr.Button("停止", elem_id="elem_stop", variant="secondary"); stopBtn.style(size="sm")
@@ -106,7 +131,7 @@ def main():
                         with gr.Row():
                             audio_mic = gr.Audio(source="microphone", type="numpy", elem_id="elem_audio", streaming=True, show_label=False).style(container=False)
                     with gr.Row():
-                        status = gr.Markdown(f"Tip: 按Enter提交, 按Shift+Enter换行。当前模型: {LLM_MODEL} \n {proxy_info}", elem_id="state-panel")
+                        status = gr.Markdown(f"Tip: 按Enter提交, 按Shift+Enter换行。支持将文件直接粘贴到输入区。", elem_id="state-panel")
 
                 with gr.Accordion("基础功能区", open=True, elem_id="basic-panel") as area_basic_fn:
                     with gr.Row():
@@ -122,18 +147,20 @@ def main():
                             predefined_btns.update({k: functional[k]["Button"]})
                 with gr.Accordion("函数插件区", open=True, elem_id="plugin-panel") as area_crazy_fn:
                     with gr.Row():
-                        gr.Markdown("插件可读取“输入区”文本/路径作为参数（上传文件自动修正路径）")
+                        gr.Markdown("<small>插件可读取“输入区”文本/路径作为参数（上传文件自动修正路径）</small>")
                     with gr.Row(elem_id="input-plugin-group"):
                         plugin_group_sel = gr.Dropdown(choices=all_plugin_groups, label='', show_label=False, value=DEFAULT_FN_GROUPS,
                                                       multiselect=True, interactive=True, elem_classes='normal_mut_select').style(container=False)
                     with gr.Row():
-                        for k, plugin in plugins.items():
+                        for index, (k, plugin) in enumerate(plugins.items()):
                             if not plugin.get("AsButton", True): continue
                             visible = True if match_group(plugin['Group'], DEFAULT_FN_GROUPS) else False
                             variant = plugins[k]["Color"] if "Color" in plugin else "secondary"
                             info = plugins[k].get("Info", k)
+                            btn_elem_id = f"plugin_btn_{index}"
                             plugin['Button'] = plugins[k]['Button'] = gr.Button(k, variant=variant,
-                                visible=visible, info_str=f'函数插件区: {info}').style(size="sm")
+                                visible=visible, info_str=f'函数插件区: {info}', elem_id=btn_elem_id).style(size="sm")
+                            plugin['ButtonElemId'] = btn_elem_id
                     with gr.Row():
                         with gr.Accordion("更多函数插件", open=True):
                             dropdown_fn_list = []
@@ -142,86 +169,30 @@ def main():
                                 if not plugin.get("AsButton", True): dropdown_fn_list.append(k)     # 排除已经是按钮的插件
                                 elif plugin.get('AdvancedArgs', False): dropdown_fn_list.append(k)  # 对于需要高级参数的插件，亦在下拉菜单中显示
                             with gr.Row():
-                                dropdown = gr.Dropdown(dropdown_fn_list, value=r"打开插件列表", label="", show_label=False).style(container=False)
+                                dropdown = gr.Dropdown(dropdown_fn_list, value=r"点击这里输入「关键词」搜索插件", label="", show_label=False).style(container=False)
                             with gr.Row():
-                                plugin_advanced_arg = gr.Textbox(show_label=True, label="高级参数输入区", visible=False,
+                                plugin_advanced_arg = gr.Textbox(show_label=True, label="高级参数输入区", visible=False, elem_id="advance_arg_input_legacy",
                                                                  placeholder="这里是特殊函数插件的高级参数输入区").style(container=False)
                             with gr.Row():
-                                switchy_bt = gr.Button(r"请先从插件列表中选择", variant="secondary").style(size="sm")
+                                switchy_bt = gr.Button(r"请先从插件列表中选择", variant="secondary", elem_id="elem_switchy_bt").style(size="sm")
                     with gr.Row():
                         with gr.Accordion("点击展开“文件下载区”。", open=False) as area_file_up:
                             file_upload = gr.Files(label="任何文件, 推荐上传压缩文件(zip, tar)", file_count="multiple", elem_id="elem_upload")
 
-        with gr.Floating(init_x="0%", init_y="0%", visible=True, width=None, drag="forbidden", elem_id="tooltip"):
-            with gr.Row():
-                with gr.Tab("上传文件", elem_id="interact-panel"):
-                    gr.Markdown("请上传本地文件/压缩包供“函数插件区”功能调用。请注意: 上传文件后会自动把输入区修改为相应路径。")
-                    file_upload_2 = gr.Files(label="任何文件, 推荐上传压缩文件(zip, tar)", file_count="multiple", elem_id="elem_upload_float")
-
-                with gr.Tab("更换模型", elem_id="interact-panel"):
-                    md_dropdown = gr.Dropdown(AVAIL_LLM_MODELS, value=LLM_MODEL, elem_id="elem_model_sel", label="更换LLM模型/请求源").style(container=False)
-                    top_p = gr.Slider(minimum=-0, maximum=1.0, value=1.0, step=0.01,interactive=True, label="Top-p (nucleus sampling)",)
-                    temperature = gr.Slider(minimum=-0, maximum=2.0, value=1.0, step=0.01, interactive=True, label="Temperature", elem_id="elem_temperature")
-                    max_length_sl = gr.Slider(minimum=256, maximum=1024*32, value=4096, step=128, interactive=True, label="Local LLM MaxLength",)
-                    system_prompt = gr.Textbox(show_label=True, lines=2, placeholder=f"System Prompt", label="System prompt", value=INIT_SYS_PROMPT, elem_id="elem_prompt")
-                    temperature.change(None, inputs=[temperature], outputs=None,
-                        _js="""(temperature)=>gpt_academic_gradio_saveload("save", "elem_prompt", "js_temperature_cookie", temperature)""")
-                    system_prompt.change(None, inputs=[system_prompt], outputs=None,
-                        _js="""(system_prompt)=>gpt_academic_gradio_saveload("save", "elem_prompt", "js_system_prompt_cookie", system_prompt)""")
-                    md_dropdown.change(None, inputs=[md_dropdown], outputs=None,
-                        _js="""(md_dropdown)=>gpt_academic_gradio_saveload("save", "elem_model_sel", "js_md_dropdown_cookie", md_dropdown)""")
-
-                with gr.Tab("界面外观", elem_id="interact-panel"):
-                    theme_dropdown = gr.Dropdown(AVAIL_THEMES, value=THEME, label="更换UI主题").style(container=False)
-                    checkboxes = gr.CheckboxGroup(["基础功能区", "函数插件区", "浮动输入区", "输入清除键", "插件参数区"], value=["基础功能区", "函数插件区"], label="显示/隐藏功能区", elem_id='cbs').style(container=False)
-                    opt = ["自定义菜单"]
-                    value=[]
-                    if ADD_WAIFU: opt += ["添加Live2D形象"]; value += ["添加Live2D形象"]
-                    checkboxes_2 = gr.CheckboxGroup(opt, value=value, label="显示/隐藏自定义菜单", elem_id='cbsc').style(container=False)
-                    dark_mode_btn = gr.Button("切换界面明暗 ☀", variant="secondary").style(size="sm")
-                    dark_mode_btn.click(None, None, None, _js=js_code_for_toggle_darkmode)
-                with gr.Tab("帮助", elem_id="interact-panel"):
-                    gr.Markdown(help_menu_description)
-
-        with gr.Floating(init_x="20%", init_y="50%", visible=False, width="40%", drag="top") as area_input_secondary:
-            with gr.Accordion("浮动输入区", open=True, elem_id="input-panel2"):
-                with gr.Row() as row:
-                    row.style(equal_height=True)
-                    with gr.Column(scale=10):
-                        txt2 = gr.Textbox(show_label=False, placeholder="Input question here.",
-                                          elem_id='user_input_float', lines=8, label="输入区2").style(container=False)
-                    with gr.Column(scale=1, min_width=40):
-                        submitBtn2 = gr.Button("提交", variant="primary"); submitBtn2.style(size="sm")
-                        resetBtn2 = gr.Button("重置", variant="secondary"); resetBtn2.style(size="sm")
-                        stopBtn2 = gr.Button("停止", variant="secondary"); stopBtn2.style(size="sm")
-                        clearBtn2 = gr.Button("清除", elem_id="elem_clear2", variant="secondary", visible=False); clearBtn2.style(size="sm")
-
-
-        with gr.Floating(init_x="20%", init_y="50%", visible=False, width="40%", drag="top") as area_customize:
-            with gr.Accordion("自定义菜单", open=True, elem_id="edit-panel"):
-                with gr.Row() as row:
-                    with gr.Column(scale=10):
-                        AVAIL_BTN = [btn for btn in customize_btns.keys()] + [k for k in functional]
-                        basic_btn_dropdown = gr.Dropdown(AVAIL_BTN, value="自定义按钮1", label="选择一个需要自定义基础功能区按钮").style(container=False)
-                        basic_fn_title = gr.Textbox(show_label=False, placeholder="输入新按钮名称", lines=1).style(container=False)
-                        basic_fn_prefix = gr.Textbox(show_label=False, placeholder="输入新提示前缀", lines=4).style(container=False)
-                        basic_fn_suffix = gr.Textbox(show_label=False, placeholder="输入新提示后缀", lines=4).style(container=False)
-                    with gr.Column(scale=1, min_width=70):
-                        basic_fn_confirm = gr.Button("确认并保存", variant="primary"); basic_fn_confirm.style(size="sm")
-                        basic_fn_clean   = gr.Button("恢复默认", variant="primary"); basic_fn_clean.style(size="sm")
-
-                        from shared_utils.cookie_manager import assign_btn__fn_builder
-                        assign_btn = assign_btn__fn_builder(customize_btns, predefined_btns, cookies, web_cookie_cache)
-                        # update btn
-                        h = basic_fn_confirm.click(assign_btn, [web_cookie_cache, cookies, basic_btn_dropdown, basic_fn_title, basic_fn_prefix, basic_fn_suffix],
-                                                   [web_cookie_cache, cookies, *customize_btns.values(), *predefined_btns.values()])
-                        h.then(None, [web_cookie_cache], None, _js="""(web_cookie_cache)=>{setCookie("web_cookie_cache", web_cookie_cache, 365);}""")
-                        # clean up btn
-                        h2 = basic_fn_clean.click(assign_btn, [web_cookie_cache, cookies, basic_btn_dropdown, basic_fn_title, basic_fn_prefix, basic_fn_suffix, gr.State(True)],
-                                                   [web_cookie_cache, cookies, *customize_btns.values(), *predefined_btns.values()])
-                        h2.then(None, [web_cookie_cache], None, _js="""(web_cookie_cache)=>{setCookie("web_cookie_cache", web_cookie_cache, 365);}""")
+        # 左上角工具栏定义
+        from themes.gui_toolbar import define_gui_toolbar
+        checkboxes, checkboxes_2, max_length_sl, theme_dropdown, system_prompt, file_upload_2, md_dropdown, top_p, temperature = \
+            define_gui_toolbar(AVAIL_LLM_MODELS, LLM_MODEL, INIT_SYS_PROMPT, THEME, AVAIL_THEMES, ADD_WAIFU, help_menu_description, js_code_for_toggle_darkmode)
 
+        # 浮动菜单定义
+        from themes.gui_floating_menu import define_gui_floating_menu
+        area_input_secondary, txt2, area_customize, _, resetBtn2, clearBtn2, stopBtn2 = \
+            define_gui_floating_menu(customize_btns, functional, predefined_btns, cookies, web_cookie_cache)
 
+        # 插件二级菜单的实现
+        from themes.gui_advanced_plugin_class import define_gui_advanced_plugin_class
+        new_plugin_callback, route_switchy_bt_with_arg, usr_confirmed_arg = \
+            define_gui_advanced_plugin_class(plugins)
 
         # 功能区显示开关与功能区的互动
         def fn_area_visibility(a):
@@ -244,26 +215,27 @@ def main():
 
         # 整理反复出现的控件句柄组合
         input_combo = [cookies, max_length_sl, md_dropdown, txt, txt2, top_p, temperature, chatbot, history, system_prompt, plugin_advanced_arg]
+        input_combo_order = ["cookies", "max_length_sl", "md_dropdown", "txt", "txt2", "top_p", "temperature", "chatbot", "history", "system_prompt", "plugin_advanced_arg"]
         output_combo = [cookies, chatbot, history, status]
         predict_args = dict(fn=ArgsGeneralWrapper(predict), inputs=[*input_combo, gr.State(True)], outputs=output_combo)
+        
         # 提交按钮、重置按钮
-        cancel_handles.append(txt.submit(**predict_args))
-        cancel_handles.append(txt2.submit(**predict_args))
-        cancel_handles.append(submitBtn.click(**predict_args))
-        cancel_handles.append(submitBtn2.click(**predict_args))
+        multiplex_submit_btn.click(
+            None, [multiplex_sel], None, _js="""(multiplex_sel)=>multiplex_function_begin(multiplex_sel)""")
+        txt.submit(
+            None, [multiplex_sel], None, _js="""(multiplex_sel)=>multiplex_function_begin(multiplex_sel)""")
+        multiplex_sel.select(
+            None, [multiplex_sel], None, _js=f"""(multiplex_sel)=>run_multiplex_shift(multiplex_sel)""")
+        cancel_handles.append(submit_btn.click(**predict_args))
         resetBtn.click(None, None, [chatbot, history, status], _js=js_code_reset)   # 先在前端快速清除chatbot&status
         resetBtn2.click(None, None, [chatbot, history, status], _js=js_code_reset)  # 先在前端快速清除chatbot&status
-        reset_server_side_args = (lambda history: ([], [], "已重置", json.dumps(history)),
-                                  [history], [chatbot, history, status, history_cache])
+        reset_server_side_args = (lambda history: ([], [], "已重置", json.dumps(history)), [history], [chatbot, history, status, history_cache])
         resetBtn.click(*reset_server_side_args)    # 再在后端清除history，把history转存history_cache备用
         resetBtn2.click(*reset_server_side_args)   # 再在后端清除history，把history转存history_cache备用
         clearBtn.click(None, None, [txt, txt2], _js=js_code_clear)
         clearBtn2.click(None, None, [txt, txt2], _js=js_code_clear)
         if AUTO_CLEAR_TXT:
-            submitBtn.click(None, None, [txt, txt2], _js=js_code_clear)
-            submitBtn2.click(None, None, [txt, txt2], _js=js_code_clear)
-            txt.submit(None, None, [txt, txt2], _js=js_code_clear)
-            txt2.submit(None, None, [txt, txt2], _js=js_code_clear)
+            submit_btn.click(None, None, [txt, txt2], _js=js_code_clear)
         # 基础功能区的回调函数注册
         for k in functional:
             if ("Visible" in functional[k]) and (not functional[k]["Visible"]): continue
@@ -277,26 +249,26 @@ def main():
         file_upload_2.upload(on_file_uploaded, [file_upload_2, chatbot, txt, txt2, checkboxes, cookies], [chatbot, txt, txt2, cookies]).then(None, None, None, _js=r"()=>{toast_push('上传完毕 ...'); cancel_loading_status();}")
         # 函数插件-固定按钮区
         for k in plugins:
+            register_advanced_plugin_init_arr += f"""register_plugin_init("{k}","{encode_plugin_info(k, plugins[k])}");"""
+            if plugins[k].get("Class", None):
+                plugins[k]["JsMenu"] = plugins[k]["Class"]().get_js_code_for_generating_menu(k)
+                register_advanced_plugin_init_arr += """register_advanced_plugin_init_code("{k}","{gui_js}");""".format(k=k, gui_js=plugins[k]["JsMenu"])
             if not plugins[k].get("AsButton", True): continue
-            click_handle = plugins[k]["Button"].click(ArgsGeneralWrapper(plugins[k]["Function"]), [*input_combo], output_combo)
-            click_handle.then(on_report_generated, [cookies, file_upload, chatbot], [cookies, file_upload, chatbot]).then(None, [plugins[k]["Button"]], None, _js=r"(fn)=>on_plugin_exe_complete(fn)")
-            cancel_handles.append(click_handle)
-        # 函数插件-下拉菜单与随变按钮的互动
-        def on_dropdown_changed(k):
-            variant = plugins[k]["Color"] if "Color" in plugins[k] else "secondary"
-            info = plugins[k].get("Info", k)
-            ret = {switchy_bt: gr.update(value=k, variant=variant, info_str=f'函数插件区: {info}')}
-            if plugins[k].get("AdvancedArgs", False): # 是否唤起高级插件参数区
-                ret.update({plugin_advanced_arg: gr.update(visible=True,  label=f"插件[{k}]的高级参数说明：" + plugins[k].get("ArgsReminder", [f"没有提供高级参数功能说明"]))})
+            if plugins[k].get("Class", None) is None:
+                assert plugins[k].get("Function", None) is not None
+                click_handle = plugins[k]["Button"].click(None, inputs=[], outputs=None, _js=f"""()=>run_classic_plugin_via_id("{plugins[k]["ButtonElemId"]}")""")
             else:
-                ret.update({plugin_advanced_arg: gr.update(visible=False, label=f"插件[{k}]不需要高级参数。")})
-            return ret
-        dropdown.select(on_dropdown_changed, [dropdown], [switchy_bt, plugin_advanced_arg] )
+                click_handle = plugins[k]["Button"].click(None, inputs=[], outputs=None, _js=f"""()=>run_advanced_plugin_launch_code("{k}")""")
 
+        # 函数插件-下拉菜单与随变按钮的互动（新版-更流畅）
+        dropdown.select(None, [dropdown], None, _js=f"""(dropdown)=>run_dropdown_shift(dropdown)""")
+
+        # 模型切换时的回调
         def on_md_dropdown_changed(k):
             return {chatbot: gr.update(label="当前模型："+k)}
         md_dropdown.select(on_md_dropdown_changed, [md_dropdown], [chatbot])
 
+        # 主题修改
         def on_theme_dropdown_changed(theme, secret_css):
             adjust_theme, css_part1, _, adjust_dynamic_theme = load_dynamic_theme(theme)
             if adjust_dynamic_theme:
@@ -304,21 +276,29 @@ def main():
             else:
                 css_part2 = adjust_theme()._get_theme_css()
             return css_part2 + css_part1
+        theme_handle = theme_dropdown.select(on_theme_dropdown_changed, [theme_dropdown, secret_css], [secret_css]) # , _js="""change_theme_prepare""")
+        theme_handle.then(None, [theme_dropdown, secret_css], None, _js="""change_theme""")
 
-        theme_handle = theme_dropdown.select(on_theme_dropdown_changed, [theme_dropdown, secret_css], [secret_css])
-        theme_handle.then(
-            None,
-            [secret_css],
-            None,
-            _js=js_code_for_css_changing
-        )
+        switchy_bt.click(None, [switchy_bt], None, _js="(switchy_bt)=>on_flex_button_click(switchy_bt)")
         # 随变按钮的回调函数注册
         def route(request: gr.Request, k, *args, **kwargs):
-            if k in [r"打开插件列表", r"请先从插件列表中选择"]: return
+            if k not in [r"点击这里搜索插件列表", r"请先从插件列表中选择"]:
+                if plugins[k].get("Class", None) is None:
+                    assert plugins[k].get("Function", None) is not None
                     yield from ArgsGeneralWrapper(plugins[k]["Function"])(request, *args, **kwargs)
-        click_handle = switchy_bt.click(route,[switchy_bt, *input_combo], output_combo)
-        click_handle.then(on_report_generated, [cookies, file_upload, chatbot], [cookies, file_upload, chatbot]).then(None, [switchy_bt], None, _js=r"(fn)=>on_plugin_exe_complete(fn)")
-        cancel_handles.append(click_handle)
+        # 旧插件的高级参数区确认按钮（隐藏）
+        old_plugin_callback = gr.Button(r"未选定任何插件", variant="secondary", visible=False, elem_id="old_callback_btn_for_plugin_exe")
+        click_handle_ng = old_plugin_callback.click(route, [switchy_bt, *input_combo], output_combo)
+        click_handle_ng.then(on_report_generated, [cookies, file_upload, chatbot], [cookies, file_upload, chatbot]).then(None, [switchy_bt], None, _js=r"(fn)=>on_plugin_exe_complete(fn)")
+        cancel_handles.append(click_handle_ng)
+        # 新一代插件的高级参数区确认按钮（隐藏）
+        click_handle_ng = new_plugin_callback.click(route_switchy_bt_with_arg,
+            [
+                gr.State(["new_plugin_callback", "usr_confirmed_arg"] + input_combo_order), # 第一个参数: 指定了后续参数的名称
+                new_plugin_callback, usr_confirmed_arg, *input_combo                        # 后续参数: 真正的参数
+            ], output_combo)
+        click_handle_ng.then(on_report_generated, [cookies, file_upload, chatbot], [cookies, file_upload, chatbot]).then(None, [switchy_bt], None, _js=r"(fn)=>on_plugin_exe_complete(fn)")
+        cancel_handles.append(click_handle_ng)
         # 终止按钮的回调函数注册
         stopBtn.click(fn=None, inputs=None, outputs=None, cancels=cancel_handles)
         stopBtn2.click(fn=None, inputs=None, outputs=None, cancels=cancel_handles)
@@ -335,6 +315,8 @@ def main():
                 elif match_group(plugin['Group'], group_list): fns_list.append(k) # 刷新下拉列表
             return [*btn_list, gr.Dropdown.update(choices=fns_list)]
         plugin_group_sel.select(fn=on_group_change, inputs=[plugin_group_sel], outputs=[*[plugin['Button'] for name, plugin in plugins_as_btn.items()], dropdown])
+
+        # 是否启动语音输入功能
         if ENABLE_AUDIO:
             from crazy_functions.live_audio.audio_io import RealtimeAudioDistribution
             rad = RealtimeAudioDistribution()
@@ -342,30 +324,32 @@ def main():
                 rad.feed(cookies['uuid'].hex, audio)
             audio_mic.stream(deal_audio, inputs=[audio_mic, cookies])
 
-
+        # 生成当前浏览器窗口的uuid（刷新失效）
         app_block.load(assign_user_uuid, inputs=[cookies], outputs=[cookies])
 
+        # 初始化（前端）
         from shared_utils.cookie_manager import load_web_cookie_cache__fn_builder
         load_web_cookie_cache = load_web_cookie_cache__fn_builder(customize_btns, cookies, predefined_btns)
         app_block.load(load_web_cookie_cache, inputs = [web_cookie_cache, cookies],
             outputs = [web_cookie_cache, cookies, *customize_btns.values(), *predefined_btns.values()], _js=js_code_for_persistent_cookie_init)
-
         app_block.load(None, inputs=[], outputs=None, _js=f"""()=>GptAcademicJavaScriptInit("{DARK_MODE}","{INIT_SYS_PROMPT}","{ADD_WAIFU}","{LAYOUT}","{TTS_TYPE}")""")    # 配置暗色主题或亮色主题
+        app_block.load(None, inputs=[], outputs=None, _js="""()=>{REP}""".replace("REP", register_advanced_plugin_init_arr))
 
-    # gradio的inbrowser触发不太稳定，回滚代码到原始的浏览器打开函数
+    # Gradio的inbrowser触发不太稳定，回滚代码到原始的浏览器打开函数
     def run_delayed_tasks():
         import threading, webbrowser, time
-        print(f"如果浏览器没有自动打开，请复制并转到以下URL：")
-        if DARK_MODE:   print(f"\t「暗色主题已启用（支持动态切换主题）」: http://localhost:{PORT}")
-        else:           print(f"\t「亮色主题已启用（支持动态切换主题）」: http://localhost:{PORT}")
+        logger.info(f"如果浏览器没有自动打开，请复制并转到以下URL：")
+        if DARK_MODE:   logger.info(f"\t「暗色主题已启用（支持动态切换主题）」: http://localhost:{PORT}")
+        else:           logger.info(f"\t「亮色主题已启用（支持动态切换主题）」: http://localhost:{PORT}")
 
         def auto_updates(): time.sleep(0); auto_update()
         def open_browser(): time.sleep(2); webbrowser.open_new_tab(f"http://localhost:{PORT}")
         def warm_up_mods(): time.sleep(6); warm_up_modules()
 
         threading.Thread(target=auto_updates, name="self-upgrade", daemon=True).start() # 查看自动更新
-        threading.Thread(target=open_browser, name="open-browser", daemon=True).start() # 打开浏览器页面
         threading.Thread(target=warm_up_mods, name="warm-up",      daemon=True).start() # 预热tiktoken模块
+        if get_conf('AUTO_OPEN_BROWSER'):
+            threading.Thread(target=open_browser, name="open-browser", daemon=True).start() # 打开浏览器页面
 
     # 运行一些异步任务：自动更新、打开浏览器页面、预热tiktoken模块
     run_delayed_tasks()

request_llms/bridge_all.py

@@ -9,6 +9,7 @@
     2. predict_no_ui_long_connection(...)
 """
 import tiktoken, copy, re
+from loguru import logger
 from functools import lru_cache
 from concurrent.futures import ThreadPoolExecutor
 from toolbox import get_conf, trimmed_format_exc, apply_gpt_academic_string_mask, read_one_api_model_name
@@ -34,9 +35,14 @@ from .bridge_google_gemini import predict_no_ui_long_connection  as genai_noui
 from .bridge_zhipu import predict_no_ui_long_connection as zhipu_noui
 from .bridge_zhipu import predict as zhipu_ui
 
+from .bridge_taichu import predict_no_ui_long_connection as taichu_noui
+from .bridge_taichu import predict as taichu_ui
+
 from .bridge_cohere import predict as cohere_ui
 from .bridge_cohere import predict_no_ui_long_connection as cohere_noui
 
+from .oai_std_model_template import get_predict_function
+
 colors = ['#FF00FF', '#00FFFF', '#FF0000', '#990099', '#009999', '#990044']
 
 class LazyloadTiktoken(object):
@@ -46,9 +52,9 @@ class LazyloadTiktoken(object):
     @staticmethod
     @lru_cache(maxsize=128)
     def get_encoder(model):
-        print('正在加载tokenizer，如果是第一次运行，可能需要一点时间下载参数')
+        logger.info('正在加载tokenizer，如果是第一次运行，可能需要一点时间下载参数')
         tmp = tiktoken.encoding_for_model(model)
-        print('加载tokenizer完毕')
+        logger.info('加载tokenizer完毕')
         return tmp
 
     def encode(self, *args, **kwargs):
@@ -66,9 +72,10 @@ api2d_endpoint = "https://openai.api2d.net/v1/chat/completions"
 newbing_endpoint = "wss://sydney.bing.com/sydney/ChatHub"
 gemini_endpoint = "https://generativelanguage.googleapis.com/v1beta/models"
 claude_endpoint = "https://api.anthropic.com/v1/messages"
-yimodel_endpoint = "https://api.lingyiwanwu.com/v1/chat/completions"
 cohere_endpoint = "https://api.cohere.ai/v1/chat"
 ollama_endpoint = "http://localhost:11434/api/chat"
+yimodel_endpoint = "https://api.lingyiwanwu.com/v1/chat/completions"
+deepseekapi_endpoint = "https://api.deepseek.com/v1/chat/completions"
 
 if not AZURE_ENDPOINT.endswith('/'): AZURE_ENDPOINT += '/'
 azure_endpoint = AZURE_ENDPOINT + f'openai/deployments/{AZURE_ENGINE}/chat/completions?api-version=2023-05-15'
@@ -77,7 +84,7 @@ try:
     API_URL = get_conf("API_URL")
     if API_URL != "https://api.openai.com/v1/chat/completions":
         openai_endpoint = API_URL
-        print("警告！API_URL配置选项将被弃用，请更换为API_URL_REDIRECT配置")
+        logger.warning("警告！API_URL配置选项将被弃用，请更换为API_URL_REDIRECT配置")
 except:
     pass
 # 新版配置
@@ -86,9 +93,10 @@ if api2d_endpoint in API_URL_REDIRECT: api2d_endpoint = API_URL_REDIRECT[api2d_e
 if newbing_endpoint in API_URL_REDIRECT: newbing_endpoint = API_URL_REDIRECT[newbing_endpoint]
 if gemini_endpoint in API_URL_REDIRECT: gemini_endpoint = API_URL_REDIRECT[gemini_endpoint]
 if claude_endpoint in API_URL_REDIRECT: claude_endpoint = API_URL_REDIRECT[claude_endpoint]
-if yimodel_endpoint in API_URL_REDIRECT: yimodel_endpoint = API_URL_REDIRECT[yimodel_endpoint]
 if cohere_endpoint in API_URL_REDIRECT: cohere_endpoint = API_URL_REDIRECT[cohere_endpoint]
 if ollama_endpoint in API_URL_REDIRECT: ollama_endpoint = API_URL_REDIRECT[ollama_endpoint]
+if yimodel_endpoint in API_URL_REDIRECT: yimodel_endpoint = API_URL_REDIRECT[yimodel_endpoint]
+if deepseekapi_endpoint in API_URL_REDIRECT: deepseekapi_endpoint = API_URL_REDIRECT[deepseekapi_endpoint]
 
 # 获取tokenizer
 tokenizer_gpt35 = LazyloadTiktoken("gpt-3.5-turbo")
@@ -112,6 +120,15 @@ model_info = {
         "token_cnt": get_token_num_gpt35,
     },
 
+    "taichu": {
+        "fn_with_ui": taichu_ui,
+        "fn_without_ui": taichu_noui,
+        "endpoint": openai_endpoint,
+        "max_token": 4096,
+        "tokenizer": tokenizer_gpt35,
+        "token_cnt": get_token_num_gpt35,
+    },
+
     "gpt-3.5-turbo-16k": {
         "fn_with_ui": chatgpt_ui,
         "fn_without_ui": chatgpt_noui,
@@ -175,6 +192,36 @@ model_info = {
         "token_cnt": get_token_num_gpt4,
     },
 
+    "gpt-4o": {
+        "fn_with_ui": chatgpt_ui,
+        "fn_without_ui": chatgpt_noui,
+        "endpoint": openai_endpoint,
+        "has_multimodal_capacity": True,
+        "max_token": 128000,
+        "tokenizer": tokenizer_gpt4,
+        "token_cnt": get_token_num_gpt4,
+    },
+
+    "gpt-4o-mini": {
+        "fn_with_ui": chatgpt_ui,
+        "fn_without_ui": chatgpt_noui,
+        "endpoint": openai_endpoint,
+        "has_multimodal_capacity": True,
+        "max_token": 128000,
+        "tokenizer": tokenizer_gpt4,
+        "token_cnt": get_token_num_gpt4,
+    },
+
+    "gpt-4o-2024-05-13": {
+        "fn_with_ui": chatgpt_ui,
+        "fn_without_ui": chatgpt_noui,
+        "has_multimodal_capacity": True,
+        "endpoint": openai_endpoint,
+        "max_token": 128000,
+        "tokenizer": tokenizer_gpt4,
+        "token_cnt": get_token_num_gpt4,
+    },
+
     "gpt-4-turbo-preview": {
         "fn_with_ui": chatgpt_ui,
         "fn_without_ui": chatgpt_noui,
@@ -202,9 +249,27 @@ model_info = {
         "token_cnt": get_token_num_gpt4,
     },
 
+    "o1-preview": {
+        "fn_with_ui": chatgpt_ui,
+        "fn_without_ui": chatgpt_noui,
+        "endpoint": openai_endpoint,
+        "max_token": 128000,
+        "tokenizer": tokenizer_gpt4,
+        "token_cnt": get_token_num_gpt4,
+    },
+    "o1-mini": {
+        "fn_with_ui": chatgpt_ui,
+        "fn_without_ui": chatgpt_noui,
+        "endpoint": openai_endpoint,
+        "max_token": 128000,
+        "tokenizer": tokenizer_gpt4,
+        "token_cnt": get_token_num_gpt4,
+    },
+
     "gpt-4-turbo": {
         "fn_with_ui": chatgpt_ui,
         "fn_without_ui": chatgpt_noui,
+        "has_multimodal_capacity": True,
         "endpoint": openai_endpoint,
         "max_token": 128000,
         "tokenizer": tokenizer_gpt4,
@@ -214,13 +279,13 @@ model_info = {
     "gpt-4-turbo-2024-04-09": {
         "fn_with_ui": chatgpt_ui,
         "fn_without_ui": chatgpt_noui,
+        "has_multimodal_capacity": True,
         "endpoint": openai_endpoint,
         "max_token": 128000,
         "tokenizer": tokenizer_gpt4,
         "token_cnt": get_token_num_gpt4,
     },
 
-
     "gpt-3.5-random": {
         "fn_with_ui": chatgpt_ui,
         "fn_without_ui": chatgpt_noui,
@@ -268,6 +333,38 @@ model_info = {
         "tokenizer": tokenizer_gpt35,
         "token_cnt": get_token_num_gpt35,
     },
+    "glm-4-0520": {
+        "fn_with_ui": zhipu_ui,
+        "fn_without_ui": zhipu_noui,
+        "endpoint": None,
+        "max_token": 10124 * 8,
+        "tokenizer": tokenizer_gpt35,
+        "token_cnt": get_token_num_gpt35,
+    },
+    "glm-4-air": {
+        "fn_with_ui": zhipu_ui,
+        "fn_without_ui": zhipu_noui,
+        "endpoint": None,
+        "max_token": 10124 * 8,
+        "tokenizer": tokenizer_gpt35,
+        "token_cnt": get_token_num_gpt35,
+    },
+    "glm-4-airx": {
+        "fn_with_ui": zhipu_ui,
+        "fn_without_ui": zhipu_noui,
+        "endpoint": None,
+        "max_token": 10124 * 8,
+        "tokenizer": tokenizer_gpt35,
+        "token_cnt": get_token_num_gpt35,
+    },
+    "glm-4-flash": {
+         "fn_with_ui": zhipu_ui,
+        "fn_without_ui": zhipu_noui,
+        "endpoint": None,
+        "max_token": 10124 * 8,
+        "tokenizer": tokenizer_gpt35,
+        "token_cnt": get_token_num_gpt35,       
+    },
     "glm-4v": {
         "fn_with_ui": zhipu_ui,
         "fn_without_ui": zhipu_noui,
@@ -328,22 +425,46 @@ model_info = {
         "tokenizer": tokenizer_gpt35,
         "token_cnt": get_token_num_gpt35,
     },
+    # Gemini
+    # Note: now gemini-pro is an alias of gemini-1.0-pro.
+    # Warning: gemini-pro-vision has been deprecated.
+    # Support for gemini-pro-vision has been removed.
     "gemini-pro": {
         "fn_with_ui": genai_ui,
         "fn_without_ui": genai_noui,
         "endpoint": gemini_endpoint,
+        "has_multimodal_capacity": False,
         "max_token": 1024 * 32,
         "tokenizer": tokenizer_gpt35,
         "token_cnt": get_token_num_gpt35,
     },
-    "gemini-pro-vision": {
+    "gemini-1.0-pro": {
         "fn_with_ui": genai_ui,
         "fn_without_ui": genai_noui,
         "endpoint": gemini_endpoint,
+        "has_multimodal_capacity": False,
         "max_token": 1024 * 32,
         "tokenizer": tokenizer_gpt35,
         "token_cnt": get_token_num_gpt35,
     },
+    "gemini-1.5-pro": {
+        "fn_with_ui": genai_ui,
+        "fn_without_ui": genai_noui,
+        "endpoint": gemini_endpoint,
+        "has_multimodal_capacity": True,
+        "max_token": 1024 * 204800,
+        "tokenizer": tokenizer_gpt35,
+        "token_cnt": get_token_num_gpt35,
+    },
+    "gemini-1.5-flash": {
+        "fn_with_ui": genai_ui,
+        "fn_without_ui": genai_noui,
+        "endpoint": gemini_endpoint,
+        "has_multimodal_capacity": True,
+        "max_token": 1024 * 204800,
+        "tokenizer": tokenizer_gpt35,
+        "token_cnt": get_token_num_gpt35,
+    },
 
     # cohere
     "cohere-command-r-plus": {
@@ -405,7 +526,7 @@ for model in AVAIL_LLM_MODELS:
 
 # -=-=-=-=-=-=- 以下部分是新加入的模型，可能附带额外依赖 -=-=-=-=-=-=-
 # claude家族
-claude_models = ["claude-instant-1.2","claude-2.0","claude-2.1","claude-3-haiku-20240307","claude-3-sonnet-20240229","claude-3-opus-20240229"]
+claude_models = ["claude-instant-1.2","claude-2.0","claude-2.1","claude-3-haiku-20240307","claude-3-sonnet-20240229","claude-3-opus-20240229","claude-3-5-sonnet-20240620"]
 if any(item in claude_models for item in AVAIL_LLM_MODELS):
     from .bridge_claude import predict_no_ui_long_connection as claude_noui
     from .bridge_claude import predict as claude_ui
@@ -469,6 +590,16 @@ if any(item in claude_models for item in AVAIL_LLM_MODELS):
             "token_cnt": get_token_num_gpt35,
         },
     })
+    model_info.update({
+        "claude-3-5-sonnet-20240620": {
+            "fn_with_ui": claude_ui,
+            "fn_without_ui": claude_noui,
+            "endpoint": claude_endpoint,
+            "max_token": 200000,
+            "tokenizer": tokenizer_gpt35,
+            "token_cnt": get_token_num_gpt35,
+        },
+    })    
 if "jittorllms_rwkv" in AVAIL_LLM_MODELS:
     from .bridge_jittorllms_rwkv import predict_no_ui_long_connection as rwkv_noui
     from .bridge_jittorllms_rwkv import predict as rwkv_ui
@@ -549,7 +680,7 @@ if "newbing" in AVAIL_LLM_MODELS:   # same with newbing-free
             }
         })
     except:
-        print(trimmed_format_exc())
+        logger.error(trimmed_format_exc())
 if "chatglmft" in AVAIL_LLM_MODELS:   # same with newbing-free
     try:
         from .bridge_chatglmft import predict_no_ui_long_connection as chatglmft_noui
@@ -565,7 +696,7 @@ if "chatglmft" in AVAIL_LLM_MODELS:   # same with newbing-free
             }
         })
     except:
-        print(trimmed_format_exc())
+        logger.error(trimmed_format_exc())
 # -=-=-=-=-=-=- 上海AI-LAB书生大模型 -=-=-=-=-=-=-
 if "internlm" in AVAIL_LLM_MODELS:
     try:
@@ -582,7 +713,7 @@ if "internlm" in AVAIL_LLM_MODELS:
             }
         })
     except:
-        print(trimmed_format_exc())
+        logger.error(trimmed_format_exc())
 if "chatglm_onnx" in AVAIL_LLM_MODELS:
     try:
         from .bridge_chatglmonnx import predict_no_ui_long_connection as chatglm_onnx_noui
@@ -598,7 +729,7 @@ if "chatglm_onnx" in AVAIL_LLM_MODELS:
             }
         })
     except:
-        print(trimmed_format_exc())
+        logger.error(trimmed_format_exc())
 # -=-=-=-=-=-=- 通义-本地模型 -=-=-=-=-=-=-
 if "qwen-local" in AVAIL_LLM_MODELS:
     try:
@@ -616,7 +747,7 @@ if "qwen-local" in AVAIL_LLM_MODELS:
             }
         })
     except:
-        print(trimmed_format_exc())
+        logger.error(trimmed_format_exc())
 # -=-=-=-=-=-=- 通义-在线模型 -=-=-=-=-=-=-
 if "qwen-turbo" in AVAIL_LLM_MODELS or "qwen-plus" in AVAIL_LLM_MODELS or "qwen-max" in AVAIL_LLM_MODELS:   # zhipuai
     try:
@@ -652,16 +783,24 @@ if "qwen-turbo" in AVAIL_LLM_MODELS or "qwen-plus" in AVAIL_LLM_MODELS or "qwen-
             }
         })
     except:
-        print(trimmed_format_exc())
+        logger.error(trimmed_format_exc())
 # -=-=-=-=-=-=- 零一万物模型 -=-=-=-=-=-=-
-if "yi-34b-chat-0205" in AVAIL_LLM_MODELS or "yi-34b-chat-200k" in AVAIL_LLM_MODELS:   # zhipuai
+yi_models = ["yi-34b-chat-0205","yi-34b-chat-200k","yi-large","yi-medium","yi-spark","yi-large-turbo","yi-large-preview"]
+if any(item in yi_models for item in AVAIL_LLM_MODELS):
     try:
-        from .bridge_yimodel import predict_no_ui_long_connection as yimodel_noui
-        from .bridge_yimodel import predict as yimodel_ui
+        yimodel_4k_noui, yimodel_4k_ui = get_predict_function(
+            api_key_conf_name="YIMODEL_API_KEY", max_output_token=600, disable_proxy=False
+            )
+        yimodel_16k_noui, yimodel_16k_ui = get_predict_function(
+            api_key_conf_name="YIMODEL_API_KEY", max_output_token=4000, disable_proxy=False
+            )
+        yimodel_200k_noui, yimodel_200k_ui = get_predict_function(
+            api_key_conf_name="YIMODEL_API_KEY", max_output_token=4096, disable_proxy=False
+            )
         model_info.update({
             "yi-34b-chat-0205": {
-                "fn_with_ui": yimodel_ui,
-                "fn_without_ui": yimodel_noui,
+                "fn_with_ui": yimodel_4k_ui,
+                "fn_without_ui": yimodel_4k_noui,
                 "can_multi_thread": False,  # 目前来说，默认情况下并发量极低，因此禁用
                 "endpoint": yimodel_endpoint,
                 "max_token": 4000,
@@ -669,17 +808,62 @@ if "yi-34b-chat-0205" in AVAIL_LLM_MODELS or "yi-34b-chat-200k" in AVAIL_LLM_MOD
                 "token_cnt": get_token_num_gpt35,
             },
             "yi-34b-chat-200k": {
-                "fn_with_ui": yimodel_ui,
-                "fn_without_ui": yimodel_noui,
+                "fn_with_ui": yimodel_200k_ui,
+                "fn_without_ui": yimodel_200k_noui,
                 "can_multi_thread": False,  # 目前来说，默认情况下并发量极低，因此禁用
                 "endpoint": yimodel_endpoint,
                 "max_token": 200000,
                 "tokenizer": tokenizer_gpt35,
                 "token_cnt": get_token_num_gpt35,
             },
+            "yi-large": {
+                "fn_with_ui": yimodel_16k_ui,
+                "fn_without_ui": yimodel_16k_noui,
+                "can_multi_thread": False,  # 目前来说，默认情况下并发量极低，因此禁用
+                "endpoint": yimodel_endpoint,
+                "max_token": 16000,
+                "tokenizer": tokenizer_gpt35,
+                "token_cnt": get_token_num_gpt35,
+            },
+            "yi-medium": {
+                "fn_with_ui": yimodel_16k_ui,
+                "fn_without_ui": yimodel_16k_noui,
+                "can_multi_thread": True,  # 这个并发量稍微大一点
+                "endpoint": yimodel_endpoint,
+                "max_token": 16000,
+                "tokenizer": tokenizer_gpt35,
+                "token_cnt": get_token_num_gpt35,
+            },
+            "yi-spark": {
+                "fn_with_ui": yimodel_16k_ui,
+                "fn_without_ui": yimodel_16k_noui,
+                "can_multi_thread": True,  # 这个并发量稍微大一点
+                "endpoint": yimodel_endpoint,
+                "max_token": 16000,
+                "tokenizer": tokenizer_gpt35,
+                "token_cnt": get_token_num_gpt35,
+            },
+            "yi-large-turbo": {
+                "fn_with_ui": yimodel_16k_ui,
+                "fn_without_ui": yimodel_16k_noui,
+                "can_multi_thread": False,  # 目前来说，默认情况下并发量极低，因此禁用
+                "endpoint": yimodel_endpoint,
+                "max_token": 16000,
+                "tokenizer": tokenizer_gpt35,
+                "token_cnt": get_token_num_gpt35,
+            },
+            "yi-large-preview": {
+                "fn_with_ui": yimodel_16k_ui,
+                "fn_without_ui": yimodel_16k_noui,
+                "can_multi_thread": False,  # 目前来说，默认情况下并发量极低，因此禁用
+                "endpoint": yimodel_endpoint,
+                "max_token": 16000,
+                "tokenizer": tokenizer_gpt35,
+                "token_cnt": get_token_num_gpt35,
+            },
         })
     except:
-        print(trimmed_format_exc())
+        logger.error(trimmed_format_exc())
 # -=-=-=-=-=-=- 讯飞星火认知大模型 -=-=-=-=-=-=-
 if "spark" in AVAIL_LLM_MODELS:
     try:
@@ -697,7 +881,7 @@ if "spark" in AVAIL_LLM_MODELS:
             }
         })
     except:
-        print(trimmed_format_exc())
+        logger.error(trimmed_format_exc())
 if "sparkv2" in AVAIL_LLM_MODELS:   # 讯飞星火认知大模型
     try:
         from .bridge_spark import predict_no_ui_long_connection as spark_noui
@@ -714,8 +898,8 @@ if "sparkv2" in AVAIL_LLM_MODELS:   # 讯飞星火认知大模型
             }
         })
     except:
-        print(trimmed_format_exc())
-if "sparkv3" in AVAIL_LLM_MODELS or "sparkv3.5" in AVAIL_LLM_MODELS:   # 讯飞星火认知大模型
+        logger.error(trimmed_format_exc())
+if any(x in AVAIL_LLM_MODELS for x in ("sparkv3", "sparkv3.5", "sparkv4")):   # 讯飞星火认知大模型
     try:
         from .bridge_spark import predict_no_ui_long_connection as spark_noui
         from .bridge_spark import predict as spark_ui
@@ -737,10 +921,19 @@ if "sparkv3" in AVAIL_LLM_MODELS or "sparkv3.5" in AVAIL_LLM_MODELS:   # 讯飞
                 "max_token": 4096,
                 "tokenizer": tokenizer_gpt35,
                 "token_cnt": get_token_num_gpt35,
+            },
+            "sparkv4":{
+                "fn_with_ui": spark_ui,
+                "fn_without_ui": spark_noui,
+                "can_multi_thread": True,
+                "endpoint": None,
+                "max_token": 4096,
+                "tokenizer": tokenizer_gpt35,
+                "token_cnt": get_token_num_gpt35,
             }
         })
     except:
-        print(trimmed_format_exc())
+        logger.error(trimmed_format_exc())
 if "llama2" in AVAIL_LLM_MODELS:   # llama2
     try:
         from .bridge_llama2 import predict_no_ui_long_connection as llama2_noui
@@ -756,7 +949,7 @@ if "llama2" in AVAIL_LLM_MODELS:   # llama2
             }
         })
     except:
-        print(trimmed_format_exc())
+        logger.error(trimmed_format_exc())
 # -=-=-=-=-=-=- 智谱 -=-=-=-=-=-=-
 if "zhipuai" in AVAIL_LLM_MODELS:   # zhipuai 是glm-4的别名，向后兼容配置
     try:
@@ -771,7 +964,7 @@ if "zhipuai" in AVAIL_LLM_MODELS:   # zhipuai 是glm-4的别名，向后兼容
             },
         })
     except:
-        print(trimmed_format_exc())
+        logger.error(trimmed_format_exc())
 # -=-=-=-=-=-=- 幻方-深度求索大模型 -=-=-=-=-=-=-
 if "deepseekcoder" in AVAIL_LLM_MODELS:   # deepseekcoder
     try:
@@ -788,9 +981,35 @@ if "deepseekcoder" in AVAIL_LLM_MODELS:   # deepseekcoder
             }
         })
     except:
-        print(trimmed_format_exc())
-
-
+        logger.error(trimmed_format_exc())
+# -=-=-=-=-=-=- 幻方-深度求索大模型在线API -=-=-=-=-=-=-
+if "deepseek-chat" in AVAIL_LLM_MODELS or "deepseek-coder" in AVAIL_LLM_MODELS:
+    try:
+        deepseekapi_noui, deepseekapi_ui = get_predict_function(
+            api_key_conf_name="DEEPSEEK_API_KEY", max_output_token=4096, disable_proxy=False
+            )
+        model_info.update({
+            "deepseek-chat":{
+                "fn_with_ui": deepseekapi_ui,
+                "fn_without_ui": deepseekapi_noui,
+                "endpoint": deepseekapi_endpoint,
+                "can_multi_thread": True,
+                "max_token": 32000,
+                "tokenizer": tokenizer_gpt35,
+                "token_cnt": get_token_num_gpt35,
+            },
+            "deepseek-coder":{
+                "fn_with_ui": deepseekapi_ui,
+                "fn_without_ui": deepseekapi_noui,
+                "endpoint": deepseekapi_endpoint,
+                "can_multi_thread": True,
+                "max_token": 16000,
+                "tokenizer": tokenizer_gpt35,
+                "token_cnt": get_token_num_gpt35,
+            },
+        })
+    except:
+        logger.error(trimmed_format_exc())
 # -=-=-=-=-=-=- one-api 对齐支持 -=-=-=-=-=-=-
 for model in [m for m in AVAIL_LLM_MODELS if m.startswith("one-api-")]:
     # 为了更灵活地接入one-api多模型管理界面，设计了此接口，例子：AVAIL_LLM_MODELS = ["one-api-mixtral-8x7b(max_token=6666)"]
@@ -799,12 +1018,13 @@ for model in [m for m in AVAIL_LLM_MODELS if m.startswith("one-api-")]:
     #   "mixtral-8x7b"      是模型名（必要）
     #   "(max_token=6666)"  是配置（非必要）
     try:
-        _, max_token_tmp = read_one_api_model_name(model)
+        origin_model_name, max_token_tmp = read_one_api_model_name(model)
+        # 如果是已知模型，则尝试获取其信息
+        original_model_info = model_info.get(origin_model_name.replace("one-api-", "", 1), None)
     except:
-        print(f"one-api模型 {model} 的 max_token 配置不是整数，请检查配置文件。")
+        logger.error(f"one-api模型 {model} 的 max_token 配置不是整数，请检查配置文件。")
         continue
-    model_info.update({
-        model: {
+    this_model_info = {
         "fn_with_ui": chatgpt_ui,
         "fn_without_ui": chatgpt_noui,
         "can_multi_thread": True,
@@ -812,8 +1032,17 @@ for model in [m for m in AVAIL_LLM_MODELS if m.startswith("one-api-")]:
         "max_token": max_token_tmp,
         "tokenizer": tokenizer_gpt35,
         "token_cnt": get_token_num_gpt35,
-        },
-    })
+    }
+
+    # 同步已知模型的其他信息
+    attribute = "has_multimodal_capacity"
+    if original_model_info is not None and original_model_info.get(attribute, None) is not None: this_model_info.update({attribute: original_model_info.get(attribute, None)})
+    # attribute = "attribute2"
+    # if original_model_info is not None and original_model_info.get(attribute, None) is not None: this_model_info.update({attribute: original_model_info.get(attribute, None)})
+    # attribute = "attribute3"
+    # if original_model_info is not None and original_model_info.get(attribute, None) is not None: this_model_info.update({attribute: original_model_info.get(attribute, None)})
+    model_info.update({model: this_model_info})
+
 # -=-=-=-=-=-=- vllm 对齐支持 -=-=-=-=-=-=-
 for model in [m for m in AVAIL_LLM_MODELS if m.startswith("vllm-")]:
     # 为了更灵活地接入vllm多模型管理界面，设计了此接口，例子：AVAIL_LLM_MODELS = ["vllm-/home/hmp/llm/cache/Qwen1___5-32B-Chat(max_token=6666)"]
@@ -824,7 +1053,7 @@ for model in [m for m in AVAIL_LLM_MODELS if m.startswith("vllm-")]:
     try:
         _, max_token_tmp = read_one_api_model_name(model)
     except:
-        print(f"vllm模型 {model} 的 max_token 配置不是整数，请检查配置文件。")
+        logger.error(f"vllm模型 {model} 的 max_token 配置不是整数，请检查配置文件。")
         continue
     model_info.update({
         model: {
@@ -851,7 +1080,7 @@ for model in [m for m in AVAIL_LLM_MODELS if m.startswith("ollama-")]:
     try:
         _, max_token_tmp = read_one_api_model_name(model)
     except:
-        print(f"ollama模型 {model} 的 max_token 配置不是整数，请检查配置文件。")
+        logger.error(f"ollama模型 {model} 的 max_token 配置不是整数，请检查配置文件。")
         continue
     model_info.update({
         model: {
@@ -888,6 +1117,13 @@ if len(AZURE_CFG_ARRAY) > 0:
             AVAIL_LLM_MODELS += [azure_model_name]
 
 
+# -=-=-=-=-=-=--=-=-=-=-=-=--=-=-=-=-=-=--=-=-=-=-=-=-=-=
+# -=-=-=-=-=-=-=-=-=- ☝️ 以上是模型路由 -=-=-=-=-=-=-=-=-=
+# -=-=-=-=-=-=--=-=-=-=-=-=--=-=-=-=-=-=--=-=-=-=-=-=-=-=
+
+# -=-=-=-=-=-=--=-=-=-=-=-=--=-=-=-=-=-=--=-=-=-=-=-=-=-=
+# -=-=-=-=-=-=-= 👇 以下是多模型路由切换函数 -=-=-=-=-=-=-=
+# -=-=-=-=-=-=--=-=-=-=-=-=--=-=-=-=-=-=--=-=-=-=-=-=-=-=
 
 
 def LLM_CATCH_EXCEPTION(f):
@@ -924,13 +1160,11 @@ def predict_no_ui_long_connection(inputs:str, llm_kwargs:dict, history:list, sys
     model = llm_kwargs['llm_model']
     n_model = 1
     if '&' not in model:
-
-        # 如果只询问1个大语言模型：
+        # 如果只询问“一个”大语言模型（多数情况）：
         method = model_info[model]["fn_without_ui"]
         return method(inputs, llm_kwargs, history, sys_prompt, observe_window, console_slience)
     else:
-
-        # 如果同时询问多个大语言模型，这个稍微啰嗦一点，但思路相同，您不必读这个else分支
+        # 如果同时询问“多个”大语言模型，这个稍微啰嗦一点，但思路相同，您不必读这个else分支
         executor = ThreadPoolExecutor(max_workers=4)
         models = model.split('&')
         n_model = len(models)
@@ -983,8 +1217,26 @@ def predict_no_ui_long_connection(inputs:str, llm_kwargs:dict, history:list, sys
         res = '<br/><br/>\n\n---\n\n'.join(return_string_collect)
         return res
 
+# 根据基础功能区 ModelOverride 参数调整模型类型，用于 `predict` 中
+import importlib
+import core_functional
+def execute_model_override(llm_kwargs, additional_fn, method):
+    functional = core_functional.get_core_functions()
+    if (additional_fn in functional) and 'ModelOverride' in functional[additional_fn]:
+        # 热更新Prompt & ModelOverride
+        importlib.reload(core_functional)
+        functional = core_functional.get_core_functions()
+        model_override = functional[additional_fn]['ModelOverride']
+        if model_override not in model_info:
+            raise ValueError(f"模型覆盖参数 '{model_override}' 指向一个暂不支持的模型，请检查配置文件。")
+        method = model_info[model_override]["fn_with_ui"]
+        llm_kwargs['llm_model'] = model_override
+        return llm_kwargs, additional_fn, method
+    # 默认返回原参数
+    return llm_kwargs, additional_fn, method
 
-def predict(inputs:str, llm_kwargs:dict, *args, **kwargs):
+def predict(inputs:str, llm_kwargs:dict, plugin_kwargs:dict, chatbot,
+            history:list=[], system_prompt:str='', stream:bool=True, additional_fn:str=None):
     """
     发送至LLM，流式获取输出。
     用于基础的对话功能。
@@ -1003,6 +1255,11 @@ def predict(inputs:str, llm_kwargs:dict, *args, **kwargs):
     """
 
     inputs = apply_gpt_academic_string_mask(inputs, mode="show_llm")
-    method = model_info[llm_kwargs['llm_model']]["fn_with_ui"]  # 如果这里报错，检查config中的AVAIL_LLM_MODELS选项
-    yield from method(inputs, llm_kwargs, *args, **kwargs)
+
+    method = model_info[llm_kwargs['llm_model']]["fn_with_ui"]  # 如果这里报错，检查config中的AVAIL_LLM_MODELS选项
+
+    if additional_fn: # 根据基础功能区 ModelOverride 参数调整模型类型
+        llm_kwargs, additional_fn, method = execute_model_override(llm_kwargs, additional_fn, method)
+
+    yield from method(inputs, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, stream, additional_fn)
 

request_llms/bridge_chatglm3.py

@@ -18,7 +18,7 @@ class GetGLM3Handle(LocalLLMHandle):
 
     def load_model_and_tokenizer(self):
         # 🏃‍♂️🏃‍♂️🏃‍♂️ 子进程执行
-        from transformers import AutoModel, AutoTokenizer
+        from transformers import AutoModel, AutoTokenizer, BitsAndBytesConfig
         import os, glob
         import os
         import platform
@@ -45,15 +45,13 @@ class GetGLM3Handle(LocalLLMHandle):
                 chatglm_model = AutoModel.from_pretrained(
                     pretrained_model_name_or_path=_model_name_,
                     trust_remote_code=True,
-                    device="cuda",
-                    load_in_4bit=True,
+                    quantization_config=BitsAndBytesConfig(load_in_4bit=True),
                 )
             elif LOCAL_MODEL_QUANT == "INT8":  # INT8
                 chatglm_model = AutoModel.from_pretrained(
                     pretrained_model_name_or_path=_model_name_,
                     trust_remote_code=True,
-                    device="cuda",
-                    load_in_8bit=True,
+                    quantization_config=BitsAndBytesConfig(load_in_8bit=True),
                 )
             else:
                 chatglm_model = AutoModel.from_pretrained(

request_llms/bridge_chatglmft.py

@@ -1,12 +1,13 @@
 
 from transformers import AutoModel, AutoTokenizer
+from loguru import logger
+from toolbox import update_ui, get_conf
+from multiprocessing import Process, Pipe
 import time
 import os
 import json
 import threading
 import importlib
-from toolbox import update_ui, get_conf
-from multiprocessing import Process, Pipe
 
 load_message = "ChatGLMFT尚未加载，加载需要一段时间。注意，取决于`config.py`的配置，ChatGLMFT消耗大量的内存（CPU）或显存（GPU），也许会导致低配计算机卡死 ……"
 
@@ -78,7 +79,7 @@ class GetGLMFTHandle(Process):
                     config.pre_seq_len = model_args['pre_seq_len']
                     config.prefix_projection = model_args['prefix_projection']
 
-                    print(f"Loading prefix_encoder weight from {CHATGLM_PTUNING_CHECKPOINT}")
+                    logger.info(f"Loading prefix_encoder weight from {CHATGLM_PTUNING_CHECKPOINT}")
                     model = AutoModel.from_pretrained(model_args['model_name_or_path'], config=config, trust_remote_code=True)
                     prefix_state_dict = torch.load(os.path.join(CHATGLM_PTUNING_CHECKPOINT, "pytorch_model.bin"))
                     new_prefix_state_dict = {}
@@ -88,7 +89,7 @@ class GetGLMFTHandle(Process):
                     model.transformer.prefix_encoder.load_state_dict(new_prefix_state_dict)
 
                     if model_args['quantization_bit'] is not None and model_args['quantization_bit'] != 0:
-                        print(f"Quantized to {model_args['quantization_bit']} bit")
+                        logger.info(f"Quantized to {model_args['quantization_bit']} bit")
                         model = model.quantize(model_args['quantization_bit'])
                     model = model.cuda()
                     if model_args['pre_seq_len'] is not None:

request_llms/bridge_chatgpt.py

@@ -1,5 +1,3 @@
-# 借鉴了 https://github.com/GaiZhenbiao/ChuanhuChatGPT 项目
-
 """
     该文件中主要包含三个函数
 
@@ -11,19 +9,20 @@
 """
 
 import json
+import os
+import re
 import time
-import gradio as gr
-import logging
 import traceback
 import requests
-import importlib
 import random
 
+from loguru import logger
+
 # config_private.py放自己的秘密如API和代理网址
 # 读取时首先看是否存在私密的config_private配置文件（不受git管控），如果有，则覆盖原config文件
 from toolbox import get_conf, update_ui, is_any_api_key, select_api_key, what_keys, clip_history
 from toolbox import trimmed_format_exc, is_the_upload_folder, read_one_api_model_name, log_chat
-from toolbox import ChatBotWithCookies
+from toolbox import ChatBotWithCookies, have_any_recent_upload_image_files, encode_image
 proxies, TIMEOUT_SECONDS, MAX_RETRY, API_ORG, AZURE_CFG_ARRAY = \
     get_conf('proxies', 'TIMEOUT_SECONDS', 'MAX_RETRY', 'API_ORG', 'AZURE_CFG_ARRAY')
 
@@ -41,6 +40,57 @@ def get_full_error(chunk, stream_response):
             break
     return chunk
 
+def make_multimodal_input(inputs, image_paths):
+    image_base64_array = []
+    for image_path in image_paths:
+        path = os.path.abspath(image_path)
+        base64 = encode_image(path)
+        inputs = inputs + f'<br/><br/><div align="center"><img src="file={path}" base64="{base64}"></div>'
+        image_base64_array.append(base64)
+    return inputs, image_base64_array
+
+def reverse_base64_from_input(inputs):
+    # 定义一个正则表达式来匹配 Base64 字符串（假设格式为 base64="<Base64编码>"）
+    # pattern = re.compile(r'base64="([^"]+)"></div>')
+    pattern = re.compile(r'<br/><br/><div align="center"><img[^<>]+base64="([^"]+)"></div>')
+    # 使用 findall 方法查找所有匹配的 Base64 字符串
+    base64_strings = pattern.findall(inputs)
+    # 返回反转后的 Base64 字符串列表
+    return base64_strings
+
+def contain_base64(inputs):
+    base64_strings = reverse_base64_from_input(inputs)
+    return len(base64_strings) > 0
+
+def append_image_if_contain_base64(inputs):
+    if not contain_base64(inputs):
+        return inputs
+    else:
+        image_base64_array = reverse_base64_from_input(inputs)
+        pattern = re.compile(r'<br/><br/><div align="center"><img[^><]+></div>')
+        inputs = re.sub(pattern, '', inputs)
+        res = []
+        res.append({
+            "type": "text",
+            "text": inputs
+        })
+        for image_base64 in image_base64_array:
+            res.append({
+                "type": "image_url",
+                "image_url": {
+                    "url": f"data:image/jpeg;base64,{image_base64}"
+                }
+            })
+        return res
+
+def remove_image_if_contain_base64(inputs):
+    if not contain_base64(inputs):
+        return inputs
+    else:
+        pattern = re.compile(r'<br/><br/><div align="center"><img[^><]+></div>')
+        inputs = re.sub(pattern, '', inputs)
+        return inputs
+
 def decode_chunk(chunk):
     # 提前读取一些信息 （用于判断异常）
     chunk_decoded = chunk.decode()
@@ -98,7 +148,7 @@ def predict_no_ui_long_connection(inputs:str, llm_kwargs:dict, history:list=[],
             retry += 1
             traceback.print_exc()
             if retry > MAX_RETRY: raise TimeoutError
-            if MAX_RETRY!=0: print(f'请求超时，正在重试 ({retry}/{MAX_RETRY}) ……')
+            if MAX_RETRY!=0: logger.error(f'请求超时，正在重试 ({retry}/{MAX_RETRY}) ……')
 
     stream_response = response.iter_lines()
     result = ''
@@ -131,7 +181,7 @@ def predict_no_ui_long_connection(inputs:str, llm_kwargs:dict, history:list=[],
         if (not has_content) and (not has_role): continue # raise RuntimeError("发现不标准的第三方接口："+delta)
         if has_content: # has_role = True/False
             result += delta["content"]
-            if not console_slience: print(delta["content"], end='')
+            if not console_slience: logger.info(delta["content"], end='')
             if observe_window is not None:
                 # 观测窗，把已经获取的数据显示出去
                 if len(observe_window) >= 1:
@@ -159,6 +209,7 @@ def predict(inputs:str, llm_kwargs:dict, plugin_kwargs:dict, chatbot:ChatBotWith
     chatbot 为WebUI中显示的对话列表，修改它，然后yeild出去，可以直接修改对话界面内容
     additional_fn代表点击的哪个按钮，按钮见functional.py
     """
+    from .bridge_all import model_info
     if is_any_api_key(inputs):
         chatbot._cookies['api_key'] = inputs
         chatbot.append(("输入已识别为openai的api_key", what_keys(inputs)))
@@ -174,9 +225,17 @@ def predict(inputs:str, llm_kwargs:dict, plugin_kwargs:dict, chatbot:ChatBotWith
         from core_functional import handle_core_functionality
         inputs, history = handle_core_functionality(additional_fn, inputs, history, chatbot)
 
-    raw_input = inputs
-    # logging.info(f'[raw_input] {raw_input}')
-    chatbot.append((inputs, ""))
+    # 多模态模型
+    has_multimodal_capacity = model_info[llm_kwargs['llm_model']].get('has_multimodal_capacity', False)
+    if has_multimodal_capacity:
+        has_recent_image_upload, image_paths = have_any_recent_upload_image_files(chatbot, pop=True)
+    else:
+        has_recent_image_upload, image_paths = False, []
+    if has_recent_image_upload:
+        _inputs, image_base64_array = make_multimodal_input(inputs, image_paths)
+    else:
+        _inputs, image_base64_array = inputs, []
+    chatbot.append((_inputs, ""))
     yield from update_ui(chatbot=chatbot, history=history, msg="等待响应") # 刷新界面
 
     # check mis-behavior
@@ -186,7 +245,7 @@ def predict(inputs:str, llm_kwargs:dict, plugin_kwargs:dict, chatbot:ChatBotWith
         time.sleep(2)
 
     try:
-        headers, payload = generate_payload(inputs, llm_kwargs, history, system_prompt, stream)
+        headers, payload = generate_payload(inputs, llm_kwargs, history, system_prompt, image_base64_array, has_multimodal_capacity, stream)
     except RuntimeError as e:
         chatbot[-1] = (inputs, f"您提供的api-key不满足要求，不包含任何可用于{llm_kwargs['llm_model']}的api-key。您可能选择了错误的模型或请求源。")
         yield from update_ui(chatbot=chatbot, history=history, msg="api-key不满足要求") # 刷新界面
@@ -194,7 +253,6 @@ def predict(inputs:str, llm_kwargs:dict, plugin_kwargs:dict, chatbot:ChatBotWith
 
     # 检查endpoint是否合法
     try:
-        from .bridge_all import model_info
         endpoint = verify_endpoint(model_info[llm_kwargs['llm_model']]['endpoint'])
     except:
         tb_str = '```\n' + trimmed_format_exc() + '```'
@@ -202,7 +260,11 @@ def predict(inputs:str, llm_kwargs:dict, plugin_kwargs:dict, chatbot:ChatBotWith
         yield from update_ui(chatbot=chatbot, history=history, msg="Endpoint不满足要求") # 刷新界面
         return
 
-    history.append(inputs); history.append("")
+    # 加入历史
+    if has_recent_image_upload:
+        history.extend([_inputs, ""])
+    else:
+        history.extend([inputs, ""])
 
     retry = 0
     while True:
@@ -256,7 +318,6 @@ def predict(inputs:str, llm_kwargs:dict, plugin_kwargs:dict, chatbot:ChatBotWith
                     # 前者是API2D的结束条件，后者是OPENAI的结束条件
                     if ('data: [DONE]' in chunk_decoded) or (len(chunkjson['choices'][0]["delta"]) == 0):
                         # 判定为数据流的结束，gpt_replying_buffer也写完了
-                        # logging.info(f'[response] {gpt_replying_buffer}')
                         log_chat(llm_model=llm_kwargs["llm_model"], input_str=inputs, output_str=gpt_replying_buffer)
                         break
                     # 处理数据流的主体
@@ -283,7 +344,7 @@ def predict(inputs:str, llm_kwargs:dict, plugin_kwargs:dict, chatbot:ChatBotWith
                     error_msg = chunk_decoded
                     chatbot, history = handle_error(inputs, llm_kwargs, chatbot, history, chunk_decoded, error_msg)
                     yield from update_ui(chatbot=chatbot, history=history, msg="Json异常" + error_msg) # 刷新界面
-                    print(error_msg)
+                    logger.error(error_msg)
                     return
 
 def handle_error(inputs, llm_kwargs, chatbot, history, chunk_decoded, error_msg):
@@ -316,7 +377,7 @@ def handle_error(inputs, llm_kwargs, chatbot, history, chunk_decoded, error_msg)
         chatbot[-1] = (chatbot[-1][0], f"[Local Message] 异常 \n\n{tb_str} \n\n{regular_txt_to_markdown(chunk_decoded)}")
     return chatbot, history
 
-def generate_payload(inputs, llm_kwargs, history, system_prompt, stream):
+def generate_payload(inputs:str, llm_kwargs:dict, history:list, system_prompt:str, image_base64_array:list=[], has_multimodal_capacity:bool=False, stream:bool=True):
     """
     整合所有信息，选择LLM模型，生成http请求，为发送请求做准备
     """
@@ -339,17 +400,27 @@ def generate_payload(inputs, llm_kwargs, history, system_prompt, stream):
             azure_api_key_unshared = AZURE_CFG_ARRAY[llm_kwargs['llm_model']]["AZURE_API_KEY"]
             headers.update({"api-key": azure_api_key_unshared})
 
-    conversation_cnt = len(history) // 2
+    if has_multimodal_capacity:
+        # 当以下条件满足时，启用多模态能力：
+        # 1. 模型本身是多模态模型（has_multimodal_capacity）
+        # 2. 输入包含图像（len(image_base64_array) > 0）
+        # 3. 历史输入包含图像（ any([contain_base64(h) for h in history]) ）
+        enable_multimodal_capacity = (len(image_base64_array) > 0) or any([contain_base64(h) for h in history])
+    else:
+        enable_multimodal_capacity = False
 
+    if not enable_multimodal_capacity:
+        # 不使用多模态能力
+        conversation_cnt = len(history) // 2
         messages = [{"role": "system", "content": system_prompt}]
         if conversation_cnt:
             for index in range(0, 2*conversation_cnt, 2):
                 what_i_have_asked = {}
                 what_i_have_asked["role"] = "user"
-            what_i_have_asked["content"] = history[index]
+                what_i_have_asked["content"] = remove_image_if_contain_base64(history[index])
                 what_gpt_answer = {}
                 what_gpt_answer["role"] = "assistant"
-            what_gpt_answer["content"] = history[index+1]
+                what_gpt_answer["content"] = remove_image_if_contain_base64(history[index+1])
                 if what_i_have_asked["content"] != "":
                     if what_gpt_answer["content"] == "": continue
                     if what_gpt_answer["content"] == timeout_bot_msg: continue
@@ -357,11 +428,46 @@ def generate_payload(inputs, llm_kwargs, history, system_prompt, stream):
                     messages.append(what_gpt_answer)
                 else:
                     messages[-1]['content'] = what_gpt_answer['content']
-
         what_i_ask_now = {}
         what_i_ask_now["role"] = "user"
         what_i_ask_now["content"] = inputs
         messages.append(what_i_ask_now)
+    else:
+        # 多模态能力
+        conversation_cnt = len(history) // 2
+        messages = [{"role": "system", "content": system_prompt}]
+        if conversation_cnt:
+            for index in range(0, 2*conversation_cnt, 2):
+                what_i_have_asked = {}
+                what_i_have_asked["role"] = "user"
+                what_i_have_asked["content"] = append_image_if_contain_base64(history[index])
+                what_gpt_answer = {}
+                what_gpt_answer["role"] = "assistant"
+                what_gpt_answer["content"] = append_image_if_contain_base64(history[index+1])
+                if what_i_have_asked["content"] != "":
+                    if what_gpt_answer["content"] == "": continue
+                    if what_gpt_answer["content"] == timeout_bot_msg: continue
+                    messages.append(what_i_have_asked)
+                    messages.append(what_gpt_answer)
+                else:
+                    messages[-1]['content'] = what_gpt_answer['content']
+        what_i_ask_now = {}
+        what_i_ask_now["role"] = "user"
+        what_i_ask_now["content"] = []
+        what_i_ask_now["content"].append({
+            "type": "text",
+            "text": inputs
+        })
+        for image_base64 in image_base64_array:
+            what_i_ask_now["content"].append({
+                "type": "image_url",
+                "image_url": {
+                    "url": f"data:image/jpeg;base64,{image_base64}"
+                }
+            })
+        messages.append(what_i_ask_now)
+
+
     model = llm_kwargs['llm_model']
     if llm_kwargs['llm_model'].startswith('api2d-'):
         model = llm_kwargs['llm_model'][len('api2d-'):]
@@ -380,7 +486,6 @@ def generate_payload(inputs, llm_kwargs, history, system_prompt, stream):
             "gpt-3.5-turbo-16k-0613",
             "gpt-3.5-turbo-0301",
         ])
-        logging.info("Random select model:" + model)
 
     payload = {
         "model": model,
@@ -389,13 +494,8 @@ def generate_payload(inputs, llm_kwargs, history, system_prompt, stream):
         "top_p": llm_kwargs['top_p'],  # 1.0,
         "n": 1,
         "stream": stream,
-        "presence_penalty": 0,
-        "frequency_penalty": 0,
     }
-    try:
-        print(f" {llm_kwargs['llm_model']} : {conversation_cnt} : {inputs[:100]} ..........")
-    except:
-        print('输入中可能存在乱码。')
+
     return headers,payload
 
 

request_llms/bridge_chatgpt_vision.py

@@ -8,15 +8,15 @@
     2. predict_no_ui_long_connection：支持多线程
 """
 
+import os
 import json
 import time
-import logging
 import requests
 import base64
-import os
 import glob
+from loguru import logger
 from toolbox import get_conf, update_ui, is_any_api_key, select_api_key, what_keys, clip_history, trimmed_format_exc, is_the_upload_folder, \
-    update_ui_lastest_msg, get_max_token, encode_image, have_any_recent_upload_image_files
+    update_ui_lastest_msg, get_max_token, encode_image, have_any_recent_upload_image_files, log_chat
 
 
 proxies, TIMEOUT_SECONDS, MAX_RETRY, API_ORG, AZURE_CFG_ARRAY = \
@@ -27,10 +27,8 @@ timeout_bot_msg = '[Local Message] Request timeout. Network error. Please check
 
 
 def report_invalid_key(key):
-    if get_conf("BLOCK_INVALID_APIKEY"):
-        # 实验性功能，自动检测并屏蔽失效的KEY，请勿使用
-        from request_llms.key_manager import ApiKeyManager
-        api_key = ApiKeyManager().add_key_to_blacklist(key)
+    # 弃用功能
+    return
 
 def get_full_error(chunk, stream_response):
     """
@@ -102,7 +100,6 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
         inputs, history = handle_core_functionality(additional_fn, inputs, history, chatbot)
 
     raw_input = inputs
-    logging.info(f'[raw_input] {raw_input}')
     def make_media_input(inputs, image_paths):
         for image_path in image_paths:
             inputs = inputs + f'<br/><br/><div align="center"><img src="file={os.path.abspath(image_path)}"></div>'
@@ -187,7 +184,7 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
                         # 判定为数据流的结束，gpt_replying_buffer也写完了
                         lastmsg = chatbot[-1][-1] + f"\n\n\n\n「{llm_kwargs['llm_model']}调用结束，该模型不具备上下文对话能力，如需追问，请及时切换模型。」"
                         yield from update_ui_lastest_msg(lastmsg, chatbot, history, delay=1)
-                        logging.info(f'[response] {gpt_replying_buffer}')
+                        log_chat(llm_model=llm_kwargs["llm_model"], input_str=inputs, output_str=gpt_replying_buffer)
                         break
                     # 处理数据流的主体
                     status_text = f"finish_reason: {chunkjson['choices'][0].get('finish_reason', 'null')}"
@@ -212,7 +209,7 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
                     error_msg = chunk_decoded
                     chatbot, history = handle_error(inputs, llm_kwargs, chatbot, history, chunk_decoded, error_msg, api_key)
                     yield from update_ui(chatbot=chatbot, history=history, msg="Json异常" + error_msg) # 刷新界面
-                    print(error_msg)
+                    logger.error(error_msg)
                     return
 
 def handle_error(inputs, llm_kwargs, chatbot, history, chunk_decoded, error_msg, api_key=""):
@@ -303,10 +300,7 @@ def generate_payload(inputs, llm_kwargs, history, system_prompt, image_paths):
         "presence_penalty": 0,
         "frequency_penalty": 0,
     }
-    try:
-        print(f" {llm_kwargs['llm_model']} : {inputs[:100]} ..........")
-    except:
-        print('输入中可能存在乱码。')
+
     return headers, payload, api_key
 
 

request_llms/bridge_chatgpt_website.py

@@ -1,281 +0,0 @@
-# 借鉴了 https://github.com/GaiZhenbiao/ChuanhuChatGPT 项目
-
-"""
-    该文件中主要包含三个函数
-
-    不具备多线程能力的函数：
-    1. predict: 正常对话时使用，具备完备的交互功能，不可多线程
-
-    具备多线程调用能力的函数
-    2. predict_no_ui_long_connection：支持多线程
-"""
-
-import json
-import time
-import gradio as gr
-import logging
-import traceback
-import requests
-import importlib
-
-# config_private.py放自己的秘密如API和代理网址
-# 读取时首先看是否存在私密的config_private配置文件（不受git管控），如果有，则覆盖原config文件
-from toolbox import get_conf, update_ui, is_any_api_key, select_api_key, what_keys, clip_history, trimmed_format_exc
-proxies, TIMEOUT_SECONDS, MAX_RETRY, API_ORG = \
-    get_conf('proxies', 'TIMEOUT_SECONDS', 'MAX_RETRY', 'API_ORG')
-
-timeout_bot_msg = '[Local Message] Request timeout. Network error. Please check proxy settings in config.py.' + \
-                  '网络错误，检查代理服务器是否可用，以及代理设置的格式是否正确，格式须是[协议]://[地址]:[端口]，缺一不可。'
-
-def get_full_error(chunk, stream_response):
-    """
-        获取完整的从Openai返回的报错
-    """
-    while True:
-        try:
-            chunk += next(stream_response)
-        except:
-            break
-    return chunk
-
-
-def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="", observe_window=None, console_slience=False):
-    """
-    发送至chatGPT，等待回复，一次性完成，不显示中间过程。但内部用stream的方法避免中途网线被掐。
-    inputs：
-        是本次问询的输入
-    sys_prompt:
-        系统静默prompt
-    llm_kwargs：
-        chatGPT的内部调优参数
-    history：
-        是之前的对话列表
-    observe_window = None：
-        用于负责跨越线程传递已经输出的部分，大部分时候仅仅为了fancy的视觉效果，留空即可。observe_window[0]：观测窗。observe_window[1]：看门狗
-    """
-    watch_dog_patience = 5 # 看门狗的耐心, 设置5秒即可
-    headers, payload = generate_payload(inputs, llm_kwargs, history, system_prompt=sys_prompt, stream=True)
-    retry = 0
-    while True:
-        try:
-            # make a POST request to the API endpoint, stream=False
-            from .bridge_all import model_info
-            endpoint = model_info[llm_kwargs['llm_model']]['endpoint']
-            response = requests.post(endpoint, headers=headers, proxies=proxies,
-                                    json=payload, stream=True, timeout=TIMEOUT_SECONDS); break
-        except requests.exceptions.ReadTimeout as e:
-            retry += 1
-            traceback.print_exc()
-            if retry > MAX_RETRY: raise TimeoutError
-            if MAX_RETRY!=0: print(f'请求超时，正在重试 ({retry}/{MAX_RETRY}) ……')
-
-    stream_response =  response.iter_lines()
-    result = ''
-    while True:
-        try: chunk = next(stream_response).decode()
-        except StopIteration:
-            break
-        except requests.exceptions.ConnectionError:
-            chunk = next(stream_response).decode() # 失败了，重试一次？再失败就没办法了。
-        if len(chunk)==0: continue
-        if not chunk.startswith('data:'):
-            error_msg = get_full_error(chunk.encode('utf8'), stream_response).decode()
-            if "reduce the length" in error_msg:
-                raise ConnectionAbortedError("OpenAI拒绝了请求:" + error_msg)
-            else:
-                raise RuntimeError("OpenAI拒绝了请求：" + error_msg)
-        if ('data: [DONE]' in chunk): break # api2d 正常完成
-        json_data = json.loads(chunk.lstrip('data:'))['choices'][0]
-        delta = json_data["delta"]
-        if len(delta) == 0: break
-        if "role" in delta: continue
-        if "content" in delta:
-            result += delta["content"]
-            if not console_slience: print(delta["content"], end='')
-            if observe_window is not None:
-                # 观测窗，把已经获取的数据显示出去
-                if len(observe_window) >= 1: observe_window[0] += delta["content"]
-                # 看门狗，如果超过期限没有喂狗，则终止
-                if len(observe_window) >= 2:
-                    if (time.time()-observe_window[1]) > watch_dog_patience:
-                        raise RuntimeError("用户取消了程序。")
-        else: raise RuntimeError("意外Json结构："+delta)
-    if json_data['finish_reason'] == 'content_filter':
-        raise RuntimeError("由于提问含不合规内容被Azure过滤。")
-    if json_data['finish_reason'] == 'length':
-        raise ConnectionAbortedError("正常结束，但显示Token不足，导致输出不完整，请削减单次输入的文本量。")
-    return result
-
-
-def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_prompt='', stream = True, additional_fn=None):
-    """
-    发送至chatGPT，流式获取输出。
-    用于基础的对话功能。
-    inputs 是本次问询的输入
-    top_p, temperature是chatGPT的内部调优参数
-    history 是之前的对话列表（注意无论是inputs还是history，内容太长了都会触发token数量溢出的错误）
-    chatbot 为WebUI中显示的对话列表，修改它，然后yeild出去，可以直接修改对话界面内容
-    additional_fn代表点击的哪个按钮，按钮见functional.py
-    """
-    if additional_fn is not None:
-        from core_functional import handle_core_functionality
-        inputs, history = handle_core_functionality(additional_fn, inputs, history, chatbot)
-
-    raw_input = inputs
-    logging.info(f'[raw_input] {raw_input}')
-    chatbot.append((inputs, ""))
-    yield from update_ui(chatbot=chatbot, history=history, msg="等待响应") # 刷新界面
-
-    try:
-        headers, payload = generate_payload(inputs, llm_kwargs, history, system_prompt, stream)
-    except RuntimeError as e:
-        chatbot[-1] = (inputs, f"您提供的api-key不满足要求，不包含任何可用于{llm_kwargs['llm_model']}的api-key。您可能选择了错误的模型或请求源。")
-        yield from update_ui(chatbot=chatbot, history=history, msg="api-key不满足要求") # 刷新界面
-        return
-
-    history.append(inputs); history.append("")
-
-    retry = 0
-    while True:
-        try:
-            # make a POST request to the API endpoint, stream=True
-            from .bridge_all import model_info
-            endpoint = model_info[llm_kwargs['llm_model']]['endpoint']
-            response = requests.post(endpoint, headers=headers, proxies=proxies,
-                                    json=payload, stream=True, timeout=TIMEOUT_SECONDS);break
-        except:
-            retry += 1
-            chatbot[-1] = ((chatbot[-1][0], timeout_bot_msg))
-            retry_msg = f"，正在重试 ({retry}/{MAX_RETRY}) ……" if MAX_RETRY > 0 else ""
-            yield from update_ui(chatbot=chatbot, history=history, msg="请求超时"+retry_msg) # 刷新界面
-            if retry > MAX_RETRY: raise TimeoutError
-
-    gpt_replying_buffer = ""
-
-    is_head_of_the_stream = True
-    if stream:
-        stream_response =  response.iter_lines()
-        while True:
-            try:
-                chunk = next(stream_response)
-            except StopIteration:
-                # 非OpenAI官方接口的出现这样的报错，OpenAI和API2D不会走这里
-                chunk_decoded = chunk.decode()
-                error_msg = chunk_decoded
-                chatbot, history = handle_error(inputs, llm_kwargs, chatbot, history, chunk_decoded, error_msg)
-                yield from update_ui(chatbot=chatbot, history=history, msg="非Openai官方接口返回了错误:" + chunk.decode()) # 刷新界面
-                return
-
-            # print(chunk.decode()[6:])
-            if is_head_of_the_stream and (r'"object":"error"' not in chunk.decode()):
-                # 数据流的第一帧不携带content
-                is_head_of_the_stream = False; continue
-
-            if chunk:
-                try:
-                    chunk_decoded = chunk.decode()
-                    # 前者是API2D的结束条件，后者是OPENAI的结束条件
-                    if 'data: [DONE]' in chunk_decoded:
-                        # 判定为数据流的结束，gpt_replying_buffer也写完了
-                        logging.info(f'[response] {gpt_replying_buffer}')
-                        break
-                    # 处理数据流的主体
-                    chunkjson = json.loads(chunk_decoded[6:])
-                    status_text = f"finish_reason: {chunkjson['choices'][0]['finish_reason']}"
-                    delta = chunkjson['choices'][0]["delta"]
-                    if "content" in delta:
-                        gpt_replying_buffer = gpt_replying_buffer + delta["content"]
-                    history[-1] = gpt_replying_buffer
-                    chatbot[-1] = (history[-2], history[-1])
-                    yield from update_ui(chatbot=chatbot, history=history, msg=status_text) # 刷新界面
-                except Exception as e:
-                    yield from update_ui(chatbot=chatbot, history=history, msg="Json解析不合常规") # 刷新界面
-                    chunk = get_full_error(chunk, stream_response)
-                    chunk_decoded = chunk.decode()
-                    error_msg = chunk_decoded
-                    chatbot, history = handle_error(inputs, llm_kwargs, chatbot, history, chunk_decoded, error_msg)
-                    yield from update_ui(chatbot=chatbot, history=history, msg="Json异常" + error_msg) # 刷新界面
-                    print(error_msg)
-                    return
-
-def handle_error(inputs, llm_kwargs, chatbot, history, chunk_decoded, error_msg):
-    from .bridge_all import model_info
-    openai_website = ' 请登录OpenAI查看详情 https://platform.openai.com/signup'
-    if "reduce the length" in error_msg:
-        if len(history) >= 2: history[-1] = ""; history[-2] = "" # 清除当前溢出的输入：history[-2] 是本次输入, history[-1] 是本次输出
-        history = clip_history(inputs=inputs, history=history, tokenizer=model_info[llm_kwargs['llm_model']]['tokenizer'],
-                                               max_token_limit=(model_info[llm_kwargs['llm_model']]['max_token'])) # history至少释放二分之一
-        chatbot[-1] = (chatbot[-1][0], "[Local Message] Reduce the length. 本次输入过长, 或历史数据过长. 历史缓存数据已部分释放, 您可以请再次尝试. (若再次失败则更可能是因为输入过长.)")
-                        # history = []    # 清除历史
-    elif "does not exist" in error_msg:
-        chatbot[-1] = (chatbot[-1][0], f"[Local Message] Model {llm_kwargs['llm_model']} does not exist. 模型不存在, 或者您没有获得体验资格.")
-    elif "Incorrect API key" in error_msg:
-        chatbot[-1] = (chatbot[-1][0], "[Local Message] Incorrect API key. OpenAI以提供了不正确的API_KEY为由, 拒绝服务. " + openai_website)
-    elif "exceeded your current quota" in error_msg:
-        chatbot[-1] = (chatbot[-1][0], "[Local Message] You exceeded your current quota. OpenAI以账户额度不足为由, 拒绝服务." + openai_website)
-    elif "account is not active" in error_msg:
-        chatbot[-1] = (chatbot[-1][0], "[Local Message] Your account is not active. OpenAI以账户失效为由, 拒绝服务." + openai_website)
-    elif "associated with a deactivated account" in error_msg:
-        chatbot[-1] = (chatbot[-1][0], "[Local Message] You are associated with a deactivated account. OpenAI以账户失效为由, 拒绝服务." + openai_website)
-    elif "bad forward key" in error_msg:
-        chatbot[-1] = (chatbot[-1][0], "[Local Message] Bad forward key. API2D账户额度不足.")
-    elif "Not enough point" in error_msg:
-        chatbot[-1] = (chatbot[-1][0], "[Local Message] Not enough point. API2D账户点数不足.")
-    else:
-        from toolbox import regular_txt_to_markdown
-        tb_str = '```\n' + trimmed_format_exc() + '```'
-        chatbot[-1] = (chatbot[-1][0], f"[Local Message] 异常 \n\n{tb_str} \n\n{regular_txt_to_markdown(chunk_decoded)}")
-    return chatbot, history
-
-def generate_payload(inputs, llm_kwargs, history, system_prompt, stream):
-    """
-    整合所有信息，选择LLM模型，生成http请求，为发送请求做准备
-    """
-    if not is_any_api_key(llm_kwargs['api_key']):
-        raise AssertionError("你提供了错误的API_KEY。\n\n1. 临时解决方案：直接在输入区键入api_key，然后回车提交。\n\n2. 长效解决方案：在config.py中配置。")
-
-    headers = {
-        "Content-Type": "application/json",
-    }
-
-    conversation_cnt = len(history) // 2
-
-    messages = [{"role": "system", "content": system_prompt}]
-    if conversation_cnt:
-        for index in range(0, 2*conversation_cnt, 2):
-            what_i_have_asked = {}
-            what_i_have_asked["role"] = "user"
-            what_i_have_asked["content"] = history[index]
-            what_gpt_answer = {}
-            what_gpt_answer["role"] = "assistant"
-            what_gpt_answer["content"] = history[index+1]
-            if what_i_have_asked["content"] != "":
-                if what_gpt_answer["content"] == "": continue
-                if what_gpt_answer["content"] == timeout_bot_msg: continue
-                messages.append(what_i_have_asked)
-                messages.append(what_gpt_answer)
-            else:
-                messages[-1]['content'] = what_gpt_answer['content']
-
-    what_i_ask_now = {}
-    what_i_ask_now["role"] = "user"
-    what_i_ask_now["content"] = inputs
-    messages.append(what_i_ask_now)
-
-    payload = {
-        "model": llm_kwargs['llm_model'].strip('api2d-'),
-        "messages": messages,
-        "temperature": llm_kwargs['temperature'],  # 1.0,
-        "top_p": llm_kwargs['top_p'],  # 1.0,
-        "n": 1,
-        "stream": stream,
-        "presence_penalty": 0,
-        "frequency_penalty": 0,
-    }
-    try:
-        print(f" {llm_kwargs['llm_model']} : {conversation_cnt} : {inputs[:100]} ..........")
-    except:
-        print('输入中可能存在乱码。')
-    return headers,payload
-
-

request_llms/bridge_claude.py

@@ -9,15 +9,16 @@
     具备多线程调用能力的函数
     2. predict_no_ui_long_connection：支持多线程
 """
-import logging
 import os
 import time
 import traceback
 import json
 import requests
+from loguru import logger
 from toolbox import get_conf, update_ui, trimmed_format_exc, encode_image, every_image_file_in_path, log_chat
+
 picture_system_prompt = "\n当回复图像时,必须说明正在回复哪张图像。所有图像仅在最后一个问题中提供,即使它们在历史记录中被提及。请使用'这是第X张图像:'的格式来指明您正在描述的是哪张图像。"
-Claude_3_Models = ["claude-3-haiku-20240307", "claude-3-sonnet-20240229", "claude-3-opus-20240229"]
+Claude_3_Models = ["claude-3-haiku-20240307", "claude-3-sonnet-20240229", "claude-3-opus-20240229", "claude-3-5-sonnet-20240620"]
 
 # config_private.py放自己的秘密如API和代理网址
 # 读取时首先看是否存在私密的config_private配置文件（不受git管控），如果有，则覆盖原config文件
@@ -101,7 +102,7 @@ def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="",
             retry += 1
             traceback.print_exc()
             if retry > MAX_RETRY: raise TimeoutError
-            if MAX_RETRY!=0: print(f'请求超时，正在重试 ({retry}/{MAX_RETRY}) ……')
+            if MAX_RETRY!=0: logger.error(f'请求超时，正在重试 ({retry}/{MAX_RETRY}) ……')
     stream_response = response.iter_lines()
     result = ''
     while True:
@@ -116,12 +117,11 @@ def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="",
                 if need_to_pass:
                     pass
                 elif is_last_chunk:
-                    # logging.info(f'[response] {result}')
+                    # logger.info(f'[response] {result}')
                     break
                 else:
                     if chunkjson and chunkjson['type'] == 'content_block_delta':
                         result += chunkjson['delta']['text']
-                        print(chunkjson['delta']['text'], end='')
                         if observe_window is not None:
                             # 观测窗，把已经获取的数据显示出去
                             if len(observe_window) >= 1:
@@ -134,7 +134,7 @@ def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="",
                 chunk = get_full_error(chunk, stream_response)
                 chunk_decoded = chunk.decode()
                 error_msg = chunk_decoded
-                print(error_msg)
+                logger.error(error_msg)
                 raise RuntimeError("Json解析不合常规")
 
     return result
@@ -200,7 +200,7 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
             retry += 1
             traceback.print_exc()
             if retry > MAX_RETRY: raise TimeoutError
-            if MAX_RETRY!=0: print(f'请求超时，正在重试 ({retry}/{MAX_RETRY}) ……')
+            if MAX_RETRY!=0: logger.error(f'请求超时，正在重试 ({retry}/{MAX_RETRY}) ……')
     stream_response = response.iter_lines()
     gpt_replying_buffer = ""
 
@@ -217,7 +217,7 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
                     pass
                 elif is_last_chunk:
                     log_chat(llm_model=llm_kwargs["llm_model"], input_str=inputs, output_str=gpt_replying_buffer)
-                    # logging.info(f'[response] {gpt_replying_buffer}')
+                    # logger.info(f'[response] {gpt_replying_buffer}')
                     break
                 else:
                     if chunkjson and chunkjson['type'] == 'content_block_delta':
@@ -230,7 +230,7 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
                 chunk = get_full_error(chunk, stream_response)
                 chunk_decoded = chunk.decode()
                 error_msg = chunk_decoded
-                print(error_msg)
+                logger.error(error_msg)
                 raise RuntimeError("Json解析不合常规")
 
 def multiple_picture_types(image_paths):

request_llms/bridge_cohere.py

@@ -13,11 +13,9 @@
 import json
 import time
 import gradio as gr
-import logging
 import traceback
 import requests
-import importlib
-import random
+from loguru import logger
 
 # config_private.py放自己的秘密如API和代理网址
 # 读取时首先看是否存在私密的config_private配置文件（不受git管控），如果有，则覆盖原config文件
@@ -98,7 +96,7 @@ def predict_no_ui_long_connection(inputs:str, llm_kwargs:dict, history:list=[],
             retry += 1
             traceback.print_exc()
             if retry > MAX_RETRY: raise TimeoutError
-            if MAX_RETRY!=0: print(f'请求超时，正在重试 ({retry}/{MAX_RETRY}) ……')
+            if MAX_RETRY!=0: logger.error(f'请求超时，正在重试 ({retry}/{MAX_RETRY}) ……')
 
     stream_response = response.iter_lines()
     result = ''
@@ -113,7 +111,7 @@ def predict_no_ui_long_connection(inputs:str, llm_kwargs:dict, history:list=[],
         if chunkjson['event_type'] == 'stream-start': continue
         if chunkjson['event_type'] == 'text-generation':
             result += chunkjson["text"]
-            if not console_slience: print(chunkjson["text"], end='')
+            if not console_slience: logger.info(chunkjson["text"], end='')
             if observe_window is not None:
                 # 观测窗，把已经获取的数据显示出去
                 if len(observe_window) >= 1:
@@ -153,7 +151,7 @@ def predict(inputs:str, llm_kwargs:dict, plugin_kwargs:dict, chatbot:ChatBotWith
         inputs, history = handle_core_functionality(additional_fn, inputs, history, chatbot)
 
     raw_input = inputs
-    # logging.info(f'[raw_input] {raw_input}')
+    # logger.info(f'[raw_input] {raw_input}')
     chatbot.append((inputs, ""))
     yield from update_ui(chatbot=chatbot, history=history, msg="等待响应") # 刷新界面
 
@@ -237,7 +235,7 @@ def predict(inputs:str, llm_kwargs:dict, plugin_kwargs:dict, chatbot:ChatBotWith
                     error_msg = chunk_decoded
                     chatbot, history = handle_error(inputs, llm_kwargs, chatbot, history, chunk_decoded, error_msg)
                     yield from update_ui(chatbot=chatbot, history=history, msg="Json异常" + error_msg) # 刷新界面
-                    print(error_msg)
+                    logger.error(error_msg)
                     return
 
 def handle_error(inputs, llm_kwargs, chatbot, history, chunk_decoded, error_msg):

request_llms/bridge_deepseekcoder.py

@@ -1,12 +1,13 @@
 model_name = "deepseek-coder-6.7b-instruct"
 cmd_to_install = "未知" # "`pip install -r request_llms/requirements_qwen.txt`"
 
-import os
 from toolbox import ProxyNetworkActivate
 from toolbox import get_conf
-from .local_llm_class import LocalLLMHandle, get_local_llm_predict_fns
+from request_llms.local_llm_class import LocalLLMHandle, get_local_llm_predict_fns
 from threading import Thread
+from loguru import logger
 import torch
+import os
 
 def download_huggingface_model(model_name, max_retry, local_dir):
     from huggingface_hub import snapshot_download
@@ -15,7 +16,7 @@ def download_huggingface_model(model_name, max_retry, local_dir):
             snapshot_download(repo_id=model_name, local_dir=local_dir, resume_download=True)
             break
         except Exception as e:
-            print(f'\n\n下载失败，重试第{i}次中...\n\n')
+            logger.error(f'\n\n下载失败，重试第{i}次中...\n\n')
     return local_dir
 # ------------------------------------------------------------------------------------------------------------------------
 # 🔌💻 Local Model
@@ -112,7 +113,6 @@ class GetCoderLMHandle(LocalLLMHandle):
         generated_text = ""
         for new_text in self._streamer:
             generated_text += new_text
-            # print(generated_text)
             yield generated_text
 
 

request_llms/bridge_google_gemini.py

@@ -8,15 +8,15 @@ import os
 import time
 from request_llms.com_google import GoogleChatInit
 from toolbox import ChatBotWithCookies
-from toolbox import get_conf, update_ui, update_ui_lastest_msg, have_any_recent_upload_image_files, trimmed_format_exc, log_chat
+from toolbox import get_conf, update_ui, update_ui_lastest_msg, have_any_recent_upload_image_files, trimmed_format_exc, log_chat, encode_image
 
 proxies, TIMEOUT_SECONDS, MAX_RETRY = get_conf('proxies', 'TIMEOUT_SECONDS', 'MAX_RETRY')
 timeout_bot_msg = '[Local Message] Request timeout. Network error. Please check proxy settings in config.py.' + \
                   '网络错误，检查代理服务器是否可用，以及代理设置的格式是否正确，格式须是[协议]://[地址]:[端口]，缺一不可。'
 
 
-def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="", observe_window=None,
-                                  console_slience=False):
+def predict_no_ui_long_connection(inputs:str, llm_kwargs:dict, history:list=[], sys_prompt:str="", observe_window:list=[],
+                                  console_slience:bool=False):
     # 检查API_KEY
     if get_conf("GEMINI_API_KEY") == "":
         raise ValueError(f"请配置 GEMINI_API_KEY。")
@@ -44,9 +44,20 @@ def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="",
             raise RuntimeError(f'{gpt_replying_buffer} 对话错误')
     return gpt_replying_buffer
 
+def make_media_input(inputs, image_paths):
+    image_base64_array = []
+    for image_path in image_paths:
+        path = os.path.abspath(image_path)
+        inputs = inputs + f'<br/><br/><div align="center"><img src="file={path}"></div>'
+        base64 = encode_image(path)
+        image_base64_array.append(base64)
+    return inputs, image_base64_array
 
 def predict(inputs:str, llm_kwargs:dict, plugin_kwargs:dict, chatbot:ChatBotWithCookies,
             history:list=[], system_prompt:str='', stream:bool=True, additional_fn:str=None):
+    
+    from .bridge_all import model_info
+
     # 检查API_KEY
     if get_conf("GEMINI_API_KEY") == "":
         yield from update_ui_lastest_msg(f"请配置 GEMINI_API_KEY。", chatbot=chatbot, history=history, delay=0)
@@ -57,18 +68,17 @@ def predict(inputs:str, llm_kwargs:dict, plugin_kwargs:dict, chatbot:ChatBotWith
         from core_functional import handle_core_functionality
         inputs, history = handle_core_functionality(additional_fn, inputs, history, chatbot)
 
-    if "vision" in llm_kwargs["llm_model"]:
-        have_recent_file, image_paths = have_any_recent_upload_image_files(chatbot)
-        if not have_recent_file:
-            chatbot.append((inputs, "没有检测到任何近期上传的图像文件，请上传jpg格式的图片，此外，请注意拓展名需要小写"))
-            yield from update_ui(chatbot=chatbot, history=history, msg="等待图片") # 刷新界面
-            return
-        def make_media_input(inputs, image_paths):
-            for image_path in image_paths:
-                inputs = inputs + f'<br/><br/><div align="center"><img src="file={os.path.abspath(image_path)}"></div>'
-            return inputs
-        if have_recent_file:
-            inputs = make_media_input(inputs, image_paths)
+    # multimodal capacity
+    # inspired by codes in bridge_chatgpt
+    has_multimodal_capacity = model_info[llm_kwargs['llm_model']].get('has_multimodal_capacity', False)
+    if has_multimodal_capacity:
+        has_recent_image_upload, image_paths = have_any_recent_upload_image_files(chatbot, pop=True)
+    else:
+        has_recent_image_upload, image_paths = False, []
+    if has_recent_image_upload:
+        inputs, image_base64_array = make_media_input(inputs, image_paths)
+    else:
+        inputs, image_base64_array = inputs, []
 
     chatbot.append((inputs, ""))
     yield from update_ui(chatbot=chatbot, history=history)
@@ -76,7 +86,7 @@ def predict(inputs:str, llm_kwargs:dict, plugin_kwargs:dict, chatbot:ChatBotWith
     retry = 0
     while True:
         try:
-            stream_response = genai.generate_chat(inputs, llm_kwargs, history, system_prompt)
+            stream_response = genai.generate_chat(inputs, llm_kwargs, history, system_prompt, image_base64_array, has_multimodal_capacity)
             break
         except Exception as e:
             retry += 1
@@ -112,7 +122,6 @@ def predict(inputs:str, llm_kwargs:dict, plugin_kwargs:dict, chatbot:ChatBotWith
         yield from update_ui(chatbot=chatbot, history=history)
 
 
-
 if __name__ == '__main__':
     import sys
     llm_kwargs = {'llm_model': 'gemini-pro'}

request_llms/bridge_internlm.py

@@ -65,10 +65,10 @@ class GetInternlmHandle(LocalLLMHandle):
 
     def llm_stream_generator(self, **kwargs):
         import torch
-        import logging
         import copy
         import warnings
         import torch.nn as nn
+        from loguru import logger as logging 
         from transformers.generation.utils import LogitsProcessorList, StoppingCriteriaList, GenerationConfig
 
         # 🏃‍♂️🏃‍♂️🏃‍♂️ 子进程执行
@@ -119,7 +119,7 @@ class GetInternlmHandle(LocalLLMHandle):
         elif generation_config.max_new_tokens is not None:
             generation_config.max_length = generation_config.max_new_tokens + input_ids_seq_length
             if not has_default_max_length:
-                logging.warn(
+                logging.warning(
                     f"Both `max_new_tokens` (={generation_config.max_new_tokens}) and `max_length`(="
                     f"{generation_config.max_length}) seem to have been set. `max_new_tokens` will take precedence. "
                     "Please refer to the documentation for more information. "