preserve theme selection

- block fastapi openapi reference(swagger and redoc) routes

.gitignore

@@ -153,3 +153,6 @@ media
 flagged
 request_llms/ChatGLM-6b-onnx-u8s8
 .pre-commit-config.yaml
+test.html
+objdump*
+*.min.*.js

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

@@ -1,6 +1,7 @@
 > [!IMPORTANT]
-> 2024.3.11: 恭迎Claude3和Moonshot，全力支持Qwen、GLM、DeepseekCoder等中文大语言模型！  
+> 2024.6.1: 版本3.80加入插件二级菜单功能（详见wiki）  
-> 2024.1.18: 更新3.70版本，支持Mermaid绘图库（让大模型绘制脑图）  
+> 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)  
+> 2024.3.11: 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>
@@ -66,7 +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
@@ -86,6 +87,10 @@ Latex论文一键校对 | [插件] 仿Grammarly对Latex文章进行语法、拼
 <img src="https://user-images.githubusercontent.com/96192199/279702205-d81137c3-affd-4cd1-bb5e-b15610389762.gif" width="700" >
 </div>
 
+<div align="center">
+<img src="https://github.com/binary-husky/gpt_academic/assets/96192199/70ff1ec5-e589-4561-a29e-b831079b37fb.gif" width="700" >
+</div>
+
 
 - 所有按钮都通过读取functional.py动态生成，可随意加自定义功能，解放剪贴板
 <div align="center">

check_proxy.py

@@ -1,33 +1,44 @@
 
-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:
-        return result
+            print(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:
-        return result
+            print(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']
+    try:
-    except: return None
+        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):
     """
@@ -71,7 +82,7 @@ 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 print亮黄, print亮绿, print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，',
@@ -124,7 +135,7 @@ 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
+            from shared_utils.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')
             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）？')

config.py

@@ -33,26 +33,29 @@ 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-4o", "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-3-turbo",
+                    "gpt-4", "gpt-4-32k", "azure-gpt-4", "glm-4", "glm-4v", "glm-3-turbo",
                     "gemini-pro", "chatglm3"
                     ]
 # --- --- --- ---
 # 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",
+#   "yi-34b-chat-0205","yi-34b-chat-200k","yi-large","yi-medium","yi-spark","yi-large-turbo","yi-large-preview",
 # ]
 # --- --- --- ---
-# 此外，为了更灵活地接入one-api多模型管理界面，您还可以在接入one-api时，
+# 此外，您还可以在接入one-api/vllm/ollama时，
-# 使用"one-api-*"前缀直接使用非标准方式接入的模型，例如
+# 使用"one-api-*","vllm-*","ollama-*"前缀直接使用非标准方式接入的模型，例如
-# AVAIL_LLM_MODELS = ["one-api-claude-3-sonnet-20240229(max_token=100000)"]
+# AVAIL_LLM_MODELS = ["one-api-claude-3-sonnet-20240229(max_token=100000)", "ollama-phi3(max_token=4096)"]
 # --- --- --- ---
 
 
@@ -60,7 +63,7 @@ AVAIL_LLM_MODELS = ["gpt-4-1106-preview", "gpt-4-turbo-preview", "gpt-4-vision-p
 
 # 重新URL重新定向，实现更换API_URL的作用（高危设置! 常规情况下不要修改! 通过修改此设置，您将把您的API-KEY和对话隐私完全暴露给您设定的中间人！）
 # 格式: API_URL_REDIRECT = {"https://api.openai.com/v1/chat/completions": "在这里填写重定向的api.openai.com的URL"}
-# 举例: API_URL_REDIRECT = {"https://api.openai.com/v1/chat/completions": "https://reverse-proxy-url/v1/chat/completions"}
+# 举例: API_URL_REDIRECT = {"https://api.openai.com/v1/chat/completions": "https://reverse-proxy-url/v1/chat/completions", "http://localhost:11434/api/chat": "在这里填写您ollama的URL"}
 API_URL_REDIRECT = {}
 
 
@@ -103,6 +106,10 @@ 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 +135,7 @@ 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
@@ -195,6 +202,12 @@ ALIYUN_ACCESSKEY="" # （无需填写）
 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 = "EDGE_TTS" # EDGE_TTS / LOCAL_SOVITS_API / DISABLE
+GPT_SOVITS_URL = ""
+EDGE_TTS_VOICE = "zh-CN-XiaoxiaoNeural"
+
+
 # 接入讯飞星火大模型 https://console.xfyun.cn/services/iat
 XFYUN_APPID = "00000000"
 XFYUN_API_SECRET = "bbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbb"
@@ -218,11 +231,23 @@ 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 = ""
 
 
+# DOC2X的PDF解析服务，注册账号并获取API KEY: https://doc2x.noedgeai.com/login
+DOC2X_API_KEY = ""
+
+
 # 自定义API KEY格式
 CUSTOM_API_KEY_PATTERN = ""
 
@@ -244,6 +269,10 @@ 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
 
@@ -252,23 +281,23 @@ 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
-
-
 # 启用插件热加载
 PLUGIN_HOT_RELOAD = False
 
@@ -365,6 +394,9 @@ 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

@@ -15,32 +15,43 @@ def get_crazy_functions():
     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.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.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.Conversation_To_File import 载入对话历史存档
-    from crazy_functions.对话历史存档 import 载入对话历史存档
+    from crazy_functions.Conversation_To_File import 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 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.批量翻译PDF文档_多线程 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
 
     function_plugins = {
         "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": {
@@ -75,14 +86,21 @@ 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),
+            "Function": None,
-            "AdvancedArgs": True,
+            "Class": Mermaid_Gen
-            "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",
+        },
+        "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 +206,42 @@ 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",
@@ -284,8 +316,52 @@ 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),
         },
+        "Latex英文纠错+高亮修正位置 [需Latex]": {
+            "Group": "学术",
+            "Color": "stop",
+            "AsButton": False,
+            "AdvancedArgs": True,
+            "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]": {
+            "Group": "学术",
+            "Color": "stop",
+            "AsButton": False,
+            "AdvancedArgs": True,
+            "ArgsReminder": 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". ',
+            "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
+        },
+        "本地Latex论文精细翻译（上传Latex项目）[需Latex]": {
+            "Group": "学术",
+            "Color": "stop",
+            "AsButton": False,
+            "AdvancedArgs": True,
+            "ArgsReminder": 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". ',
+            "Info": "本地Latex论文精细翻译 | 输入参数是路径",
+            "Function": HotReload(Latex翻译中文并重新编译PDF),
+        },
+        "PDF翻译中文并重新编译PDF（上传PDF）[需Latex]": {
+            "Group": "学术",
+            "Color": "stop",
+            "AsButton": False,
+            "AdvancedArgs": True,
+            "ArgsReminder": 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". ',
+            "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),   # 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
+        }
     }
 
+
     # -=--=- 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
@@ -305,36 +381,36 @@ def get_crazy_functions():
         print(trimmed_format_exc())
         print("Load function plugin failed")
 
-    try:
+    # try:
-        from crazy_functions.联网的ChatGPT import 连接网络回答问题
+    #     from crazy_functions.联网的ChatGPT import 连接网络回答问题
 
-        function_plugins.update(
+    #     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）": {
+    #             "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",
+    #                 "Group": "对话",
-                    "Color": "stop",
+    #                 "Color": "stop",
-                    "AsButton": False,  # 加入下拉菜单中
+    #                 "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",
+    #                 # "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),
+    #                 "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
+    #     from crazy_functions.联网的ChatGPT_bing版 import 连接bing搜索回答问题
 
-        function_plugins.update(
+    #     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）": {
+    #             "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",
+    #                 "Group": "对话",
-                    "Color": "stop",
+    #                 "Color": "stop",
-                    "AsButton": False,  # 加入下拉菜单中
+    #                 "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",
+    #                 "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),
+    #                 "Function": HotReload(连接bing搜索回答问题),
-                }
+    #             }
-            }
+    #         }
-        )
+    #     )
-    except:
+    # except:
-        print(trimmed_format_exc())
+    #     print(trimmed_format_exc())
-        print("Load function plugin failed")
+    #     print("Load function plugin failed")
 
     try:
         from crazy_functions.解析项目源代码 import 解析任意code项目
@@ -363,7 +439,7 @@ def get_crazy_functions():
                 "询问多个GPT模型（手动指定询问哪些模型）": {
                     "Group": "对话",
                     "Color": "stop",
-                    "AsButton": False,
+                    "AsButton": True,
                     "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),
@@ -458,7 +534,7 @@ def get_crazy_functions():
         print("Load function plugin failed")
 
     try:
-        from crazy_functions.批量Markdown翻译 import Markdown翻译指定语言
+        from crazy_functions.Markdown_Translate import Markdown翻译指定语言
 
         function_plugins.update(
             {
@@ -531,59 +607,6 @@ def get_crazy_functions():
         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",
-                    "AsButton": False,
-                    "AdvancedArgs": True,
-                    "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]": {
-                    "Group": "学术",
-                    "Color": "stop",
-                    "AsButton": False,
-                    "AdvancedArgs": True,
-                    "ArgsReminder": 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". ',
-                    "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),
-                },
-                "本地Latex论文精细翻译（上传Latex项目）[需Latex]": {
-                    "Group": "学术",
-                    "Color": "stop",
-                    "AsButton": False,
-                    "AdvancedArgs": True,
-                    "ArgsReminder": 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". ',
-                    "Info": "本地Latex论文精细翻译 | 输入参数是路径",
-                    "Function": HotReload(Latex翻译中文并重新编译PDF),
-                },
-                "PDF翻译中文并重新编译PDF（上传PDF）[需Latex]": {
-                    "Group": "学术",
-                    "Color": "stop",
-                    "AsButton": False,
-                    "AdvancedArgs": True,
-                    "ArgsReminder": 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". ',
-                    "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)
-                }
-            }
-        )
-    except:
-        print(trimmed_format_exc())
-        print("Load function plugin failed")
 
     try:
         from toolbox import get_conf

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
+        from textwrap import dedent
-        f.write(f'<!DOCTYPE html><head><meta charset="utf-8"><title>对话历史</title><style>{advanced_css}</style></head>')
+        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):
+            question, answer = contents[0], contents[1]
-                try:    # 这个bug没找到触发条件，暂时先这样顶一下
+            if question is None: question = ""
-                    if type(content) != str: content = str(content)
+            try: question = str(question)
-                except:
+            except: question = ""
-                    continue
+            if answer is None: answer = ""
-                f.write(content)
+            try: answer = str(answer)
-                if j == 0:
+            except: answer = ""
-                    f.write('<hr style="border-top: dotted 3px #ccc;">')
+            CHAT_PREVIEW_BUF += qa_from.format(QUESTION=question, ANSWER=answer)
-            f.write('<hr color="red"> \n\n')
+
-        f.write('<hr color="blue"> \n\n raw chat context:\n')
+        HISTORY_PREVIEW_BUF = ""
-        f.write('<code>')
         for h in history:
-            f.write("\n>>>" + h)
+            HISTORY_PREVIEW_BUF += history_from.format(ENTRY=h)
-        f.write('</code>')
+        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>
+    from bs4 import BeautifulSoup
-    pattern = re.compile(r'<head>.*?</head>', flags=re.DOTALL)
+    soup = BeautifulSoup(file_content, 'lxml')
-    file_content = re.sub(pattern, '', file_content)
+    # 提取QaBox信息
-    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))
     chatbot.clear()
-    for i, h in enumerate(html):
+    qa_box_list = []
-        i_say, gpt_say = h.split('<hr style="border-top: dotted 3px #ccc;">')
+    qa_boxes = soup.find_all("div", class_="QaBox")
-        chatbot.append([i_say, gpt_say])
+    for box in qa_boxes:
-    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。"])
+        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",
+    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。"))
-        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。"))
     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()
@@ -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/Internet_GPT.py

@@ -0,0 +1,142 @@
+from toolbox import CatchException, update_ui, get_conf
+from .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
+import urllib.request
+import random
+from functools import lru_cache
+from check_proxy import check_proxy
+
+@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 is None:
+        engines = 'bing'
+
+    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):
+
+    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)
+    urls = searxng_request(txt, proxies, categories, searxng_url, engines=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
+    chatbot.append([f"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 > -------------
+    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
+

crazy_functions/Internet_GPT_Wrap.py

@@ -0,0 +1,44 @@
+
+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", 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=["bing", "google", "duckduckgo"], default_value="bing", description="无", 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

@@ -4,7 +4,7 @@ from functools import partial
 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 =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-
@@ -107,6 +107,10 @@ def arxiv_download(chatbot, history, txt, allow_cache=True):
         except ValueError:
             return False
 
+    if txt.startswith('https://arxiv.org/pdf/'):
+        arxiv_id = txt.split('/')[-1]   # 2402.14207v2.pdf
+        txt = arxiv_id.split('v')[0]  # 2402.14207
+
     if ('.' in txt) and ('/' not in txt) and is_float(txt):  # is arxiv ID
         txt = 'https://arxiv.org/abs/' + txt.strip()
     if ('.' in txt) and ('/' not in txt) and is_float(txt[:10]):  # is arxiv ID
@@ -121,6 +125,7 @@ def arxiv_download(chatbot, history, txt, allow_cache=True):
     time.sleep(1)  # 刷新界面
 
     url_ = txt  # https://arxiv.org/abs/1707.06690
+
     if not txt.startswith('https://arxiv.org/abs/'):
         msg = f"解析arxiv网址失败, 期望格式例如: https://arxiv.org/abs/1707.06690。实际得到格式: {url_}。"
         yield from update_ui_lastest_msg(msg, chatbot=chatbot, history=history)  # 刷新界面
@@ -153,65 +158,72 @@ 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):
-    # Mathpix API credentials
+    if plugin_kwargs["method"] == "MATHPIX":
-    app_id, app_key = get_conf('MATHPIX_APPID', 'MATHPIX_APPKEY')
+        # Mathpix API credentials
-    headers = {"app_id": app_id, "app_key": app_key}
+        app_id, app_key = get_conf('MATHPIX_APPID', 'MATHPIX_APPKEY')
+        headers = {"app_id": app_id, "app_key": app_key}
 
-    # Step 1: Send PDF file for processing
+        # Step 1: Send PDF file for processing
-    options = {
+        options = {
-        "conversion_formats": {"tex.zip": True},
+            "conversion_formats": {"tex.zip": True},
-        "math_inline_delimiters": ["$", "$"],
+            "math_inline_delimiters": ["$", "$"],
-        "rm_spaces": True
+            "rm_spaces": True
-    }
+        }
 
-    response = requests.post(url="https://api.mathpix.com/v3/pdf",
+        response = requests.post(url="https://api.mathpix.com/v3/pdf",
-                             headers=headers,
+                                headers=headers,
-                             data={"options_json": json.dumps(options)},
+                                data={"options_json": json.dumps(options)},
-                             files={"file": open(pdf_file_path, "rb")})
+                                files={"file": open(pdf_file_path, "rb")})
 
-    if response.ok:
+        if response.ok:
-        pdf_id = response.json()["pdf_id"]
+            pdf_id = response.json()["pdf_id"]
-        print(f"PDF processing initiated. PDF ID: {pdf_id}")
+            print(f"PDF processing initiated. PDF ID: {pdf_id}")
 
-        # Step 2: Check processing status
+            # Step 2: Check processing status
-        while True:
+            while True:
-            conversion_response = requests.get(f"https://api.mathpix.com/v3/pdf/{pdf_id}", headers=headers)
+                conversion_response = requests.get(f"https://api.mathpix.com/v3/pdf/{pdf_id}", headers=headers)
-            conversion_data = conversion_response.json()
+                conversion_data = conversion_response.json()
 
-            if conversion_data["status"] == "completed":
+                if conversion_data["status"] == "completed":
-                print("PDF processing completed.")
+                    print("PDF processing completed.")
-                break
+                    break
-            elif conversion_data["status"] == "error":
+                elif conversion_data["status"] == "error":
-                print("Error occurred during processing.")
+                    print("Error occurred during processing.")
-            else:
+                else:
-                print(f"Processing status: {conversion_data['status']}")
+                    print(f"Processing status: {conversion_data['status']}")
-                time.sleep(5)  # wait for a few seconds before checking again
+                    time.sleep(5)  # wait for a few seconds before checking again
 
-        # Step 3: Save results to local files
+            # Step 3: Save results to local files
-        output_dir = os.path.join(os.path.dirname(pdf_file_path), 'mathpix_output')
+            output_dir = os.path.join(os.path.dirname(pdf_file_path), 'mathpix_output')
-        if not os.path.exists(output_dir):
+            if not os.path.exists(output_dir):
-            os.makedirs(output_dir)
+                os.makedirs(output_dir)
 
-        url = f"https://api.mathpix.com/v3/pdf/{pdf_id}.tex"
+            url = f"https://api.mathpix.com/v3/pdf/{pdf_id}.tex"
-        response = requests.get(url, headers=headers)
+            response = requests.get(url, headers=headers)
-        file_name_wo_dot = '_'.join(os.path.basename(pdf_file_path).split('.')[:-1])
+            file_name_wo_dot = '_'.join(os.path.basename(pdf_file_path).split('.')[:-1])
-        output_name = f"{file_name_wo_dot}.tex.zip"
+            output_name = f"{file_name_wo_dot}.tex.zip"
-        output_path = os.path.join(output_dir, output_name)
+            output_path = os.path.join(output_dir, output_name)
-        with open(output_path, "wb") as output_file:
+            with open(output_path, "wb") as output_file:
-            output_file.write(response.content)
+                output_file.write(response.content)
-        print(f"tex.zip file saved at: {output_path}")
+            print(f"tex.zip file saved at: {output_path}")
 
-        import zipfile
+            import zipfile
-        unzip_dir = os.path.join(output_dir, file_name_wo_dot)
+            unzip_dir = os.path.join(output_dir, file_name_wo_dot)
-        with zipfile.ZipFile(output_path, 'r') as zip_ref:
+            with zipfile.ZipFile(output_path, 'r') as zip_ref:
-            zip_ref.extractall(unzip_dir)
+                zip_ref.extractall(unzip_dir)
 
+            return unzip_dir
+
+        else:
+            print(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
 
-    else:
+
-        print(f"Error sending PDF for processing. Status code: {response.status_code}")
-        return None
 
 
 # =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-= 插件主程序1 =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
@@ -221,7 +233,7 @@ 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 ------------->
@@ -259,6 +271,8 @@ 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 ------------->
@@ -282,7 +296,7 @@ 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)
@@ -298,7 +312,7 @@ 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 ------------->
@@ -353,6 +367,8 @@ 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 ------------->
@@ -392,7 +408,7 @@ 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 ------------->
@@ -432,107 +448,101 @@ 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
-    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
 
-    hash_tag = map_file_to_sha256(file_manifest[0])
+    if plugin_kwargs.get("method", "") == 'MATHPIX':
-
+        app_id, app_key = get_conf('MATHPIX_APPID', 'MATHPIX_APPKEY')
-    # <-------------- check repeated pdf ------------->
+        if len(app_id) == 0 or len(app_key) == 0:
-    chatbot.append([f"检查PDF是否被重复上传", "正在检查..."])
+            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)
+            yield from update_ui(chatbot=chatbot, history=history)  # 刷新界面
-    repeat, project_folder = check_repeat_upload(file_manifest[0], hash_tag)
+            return
-
+    if plugin_kwargs.get("method", "") == 'DOC2X':
-    except_flag = False
+        app_id, app_key = "", ""
-
+        DOC2X_API_KEY = get_conf('DOC2X_API_KEY')
-    if repeat:
+        if len(DOC2X_API_KEY) == 0:
-        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)
+            report_exception(chatbot, history, a="缺失 DOC2X_API_KEY。", b=f"请配置 DOC2X_API_KEY")
-
-        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, 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)
-
-        # <-------------- 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])
-        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)
-            return False
-
-        # <-------------- translate latex file into Chinese ------------->
-        yield from update_ui_lastest_msg("正在tex项目将翻译为中文...", chatbot=chatbot, history=history)
-        file_manifest = [f for f in glob.glob(f'{project_folder}/**/*.tex', 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.tex文件: {txt}")
             yield from update_ui(chatbot=chatbot, history=history)  # 刷新界面
             return
 
-        # <-------------- if is a zip/tar file ------------->
+    hash_tag = map_file_to_sha256(file_manifest[0])
-        project_folder = desend_to_extracted_folder_if_exist(project_folder)
 
-        # <-------------- move latex project away from temp folder ------------->
+    # # <-------------- check repeated pdf ------------->
-        project_folder = move_project(project_folder)
+    # 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)
 
-        # <-------------- set a hash tag for repeat-checking ------------->
+    # if repeat:
-        with open(pj(project_folder, hash_tag + '.tag'), 'w') as f:
+    #     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)
-            f.write(hash_tag)
+    #     try:
-            f.close()
+    #         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], 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)
+        return False
+
+    # <-------------- translate latex file into Chinese ------------->
+    yield from update_ui_lastest_msg("正在tex项目将翻译为中文...", chatbot=chatbot, history=history)
+    file_manifest = [f for f in glob.glob(f'{project_folder}/**/*.tex', 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.tex文件: {txt}")
+        yield from update_ui(chatbot=chatbot, history=history)  # 刷新界面
+        return
+
+    # <-------------- if is a zip/tar file ------------->
+    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 ------------->
+    with open(pj(project_folder, hash_tag + '.tag'), 'w') as f:
+        f.write(hash_tag)
+        f.close()
 
 
-        # <-------------- if merge_translate_zh is already generated, skip gpt req ------------->
+    # <-------------- if merge_translate_zh is already generated, skip gpt req ------------->
-        if not os.path.exists(project_folder + '/merge_translate_zh.tex'):
+    if not os.path.exists(project_folder + '/merge_translate_zh.tex'):
-            yield from Latex精细分解与转化(file_manifest, project_folder, llm_kwargs, plugin_kwargs,
+        yield from Latex精细分解与转化(file_manifest, project_folder, llm_kwargs, plugin_kwargs,
-                                        chatbot, history, system_prompt, mode='translate_zh',
+                                    chatbot, history, system_prompt, mode='translate_zh',
-                                        switch_prompt=_switch_prompt_)
+                                    switch_prompt=_switch_prompt_)
 
-        # <-------------- compile PDF ------------->
+    # <-------------- compile PDF ------------->
-        yield from update_ui_lastest_msg("正在将翻译好的项目tex项目编译为PDF...", chatbot=chatbot, history=history)
+    yield from update_ui_lastest_msg("正在将翻译好的项目tex项目编译为PDF...", chatbot=chatbot, history=history)
-        success = yield from 编译Latex(chatbot, history, main_file_original='merge',
+    success = yield from 编译Latex(chatbot, history, main_file_original='merge',
-                                    main_file_modified='merge_translate_zh', mode='translate_zh',
+                                main_file_modified='merge_translate_zh', mode='translate_zh',
-                                    work_folder_original=project_folder, work_folder_modified=project_folder,
+                                work_folder_original=project_folder, work_folder_modified=project_folder,
-                                    work_folder=project_folder)
+                                work_folder=project_folder)
 
-        # <-------------- zip PDF ------------->
+    # <-------------- zip PDF ------------->
-        zip_res = zip_result(project_folder)
+    zip_res = zip_result(project_folder)
-        if success:
+    if success:
-            chatbot.append((f"成功啦", '请查收结果（压缩包）...'))
+        chatbot.append((f"成功啦", '请查收结果（压缩包）...'))
-            yield from update_ui(chatbot=chatbot, history=history);
+        yield from update_ui(chatbot=chatbot, history=history);
-            time.sleep(1)  # 刷新界面
+        time.sleep(1)  # 刷新界面
-            promote_file_to_downloadzone(file=zip_res, chatbot=chatbot)
+        promote_file_to_downloadzone(file=zip_res, chatbot=chatbot)
-        else:
+    else:
-            chatbot.append((f"失败了",
+        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, 您可以到Github Issue区, 用该压缩包进行反馈。如系统是Linux，请检查系统字体（见Github wiki） ...'))
+                        '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, 您可以到Github Issue区, 用该压缩包进行反馈。如系统是Linux，请检查系统字体（见Github wiki） ...'))
-            yield from update_ui(chatbot=chatbot, history=history);
+        yield from update_ui(chatbot=chatbot, history=history);
-            time.sleep(1)  # 刷新界面
+        time.sleep(1)  # 刷新界面
-            promote_file_to_downloadzone(file=zip_res, chatbot=chatbot)
+        promote_file_to_downloadzone(file=zip_res, chatbot=chatbot)
 
-        # <-------------- we are done ------------->
+    # <-------------- we are done ------------->
-        return success
+    return success

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/Markdown_Translate.py

@@ -1,5 +1,5 @@
-import glob, time, os, re, logging
+import glob, shutil, os, re, logging
-from toolbox import update_ui, trimmed_format_exc, gen_time_str, disable_auto_promotion
+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
 fast_debug = False
@@ -18,7 +18,7 @@ class PaperFileGroup():
         def get_token_num(txt): return len(enc.encode(txt, disallowed_special=()))
         self.get_token_num = get_token_num
 
-    def run_file_split(self, max_token_limit=1900):
+    def run_file_split(self, max_token_limit=2048):
         """
         将长文本分离开来
         """
@@ -64,25 +64,25 @@ def 多文件翻译(file_manifest, project_folder, llm_kwargs, plugin_kwargs, ch
             pfg.file_contents.append(file_content)
 
     #  <-------- 拆分过长的Markdown文件 ---------->
-    pfg.run_file_split(max_token_limit=1500)
+    pfg.run_file_split(max_token_limit=2048)
     n_split = len(pfg.sp_file_contents)
 
     #  <-------- 多线程翻译开始 ---------->
     if language == 'en->zh':
-        inputs_array = ["This is a Markdown file, translate it into Chinese, do not modify any existing Markdown commands:" +
+        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:" +
+        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, only answer me with translated results:" +
+        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,
@@ -99,7 +99,12 @@ def 多文件翻译(file_manifest, project_folder, llm_kwargs, plugin_kwargs, ch
         for i_say, gpt_say in zip(gpt_response_collection[0::2], gpt_response_collection[1::2]):
             pfg.sp_file_result.append(gpt_say)
         pfg.merge_result()
-        pfg.write_result(language)
+        output_file_arr = pfg.write_result(language)
+        for output_file in output_file_arr:
+            promote_file_to_downloadzone(output_file, chatbot=chatbot)
+            if 'markdown_expected_output_path' in plugin_kwargs:
+                expected_f_name = plugin_kwargs['markdown_expected_output_path']
+                shutil.copyfile(output_file, expected_f_name)
     except:
         logging.error(trimmed_format_exc())
 
@@ -159,7 +164,6 @@ def Markdown英译中(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_p
         "函数插件功能？",
         "对整个Markdown项目进行翻译。函数插件贡献者: Binary-Husky"])
     yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
-    disable_auto_promotion(chatbot)
 
     # 尝试导入依赖，如果缺少依赖，则给出安装建议
     try:
@@ -199,7 +203,6 @@ def Markdown中译英(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_p
         "函数插件功能？",
         "对整个Markdown项目进行翻译。函数插件贡献者: Binary-Husky"])
     yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
-    disable_auto_promotion(chatbot)
 
     # 尝试导入依赖，如果缺少依赖，则给出安装建议
     try:
@@ -232,7 +235,6 @@ def Markdown翻译指定语言(txt, llm_kwargs, plugin_kwargs, chatbot, history,
         "函数插件功能？",
         "对整个Markdown项目进行翻译。函数插件贡献者: Binary-Husky"])
     yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
-    disable_auto_promotion(chatbot)
 
     # 尝试导入依赖，如果缺少依赖，则给出安装建议
     try:

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/crazy_utils.py

@@ -1,9 +1,20 @@
 from toolbox import update_ui, get_conf, trimmed_format_exc, get_max_token, Singleton
+from shared_utils.char_visual_effect import scolling_visual_effect
 import threading
 import os
 import logging
 
 def input_clipping(inputs, history, max_token_limit):
+    """
+    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']
@@ -158,7 +169,7 @@ 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,
         ):
@@ -283,6 +294,8 @@ 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 +308,7 @@ 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:].\
+            print_something_really_funny = f"[ ...`{scolling_visual_effect(mutable[thread_index][0], scroller_max_len)}`... ]"
-                replace('\n', '').replace('`', '.').replace(' ', '.').replace('<br/>', '.....').replace('$', '.')+"`... ]"
             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 +361,7 @@ 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
@@ -568,7 +580,7 @@ class nougat_interface():
         from toolbox import ProxyNetworkActivate
         logging.info(f'正在执行命令 {command}')
         with ProxyNetworkActivate("Nougat_Download"):
-            process = subprocess.Popen(command, shell=True, cwd=cwd, env=os.environ)
+            process = subprocess.Popen(command, shell=False, cwd=cwd, env=os.environ)
         try:
             stdout, stderr = process.communicate(timeout=timeout)
         except subprocess.TimeoutExpired:
@@ -592,7 +604,8 @@ class nougat_interface():
 
         yield from update_ui_lastest_msg("正在解析论文, 请稍候。进度：正在加载NOUGAT... （提示：首次运行需要花费较长时间下载NOUGAT参数）",
                                          chatbot=chatbot, history=history, delay=0)
-        self.nougat_with_timeout(f'nougat --out "{os.path.abspath(dst)}" "{os.path.abspath(fp)}"', os.getcwd(), timeout=3600)
+        command = ['nougat', '--out', os.path.abspath(dst), os.path.abspath(fp)]
+        self.nougat_with_timeout(command, cwd=os.getcwd(), timeout=3600)
         res = glob.glob(os.path.join(dst,'*.mmd'))
         if len(res) == 0:
             self.threadLock.release()

crazy_functions/json_fns/pydantic_io.py

@@ -62,8 +62,8 @@ class GptJsonIO():
         if "type" in reduced_schema:
             del reduced_schema["type"]
         # Ensure json in context is well-formed with double quotes.
+        schema_str = json.dumps(reduced_schema)
         if self.example_instruction:
-            schema_str = json.dumps(reduced_schema)
             return PYDANTIC_FORMAT_INSTRUCTIONS.format(schema=schema_str)
         else:
             return PYDANTIC_FORMAT_INSTRUCTIONS_SIMPLE.format(schema=schema_str)

crazy_functions/latex_fns/latex_actions.py

@@ -1,10 +1,11 @@
 from toolbox import update_ui, update_ui_lastest_msg, get_log_folder
-from toolbox import get_conf, objdump, objload, promote_file_to_downloadzone
+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
 
 import os, shutil
 import re

crazy_functions/latex_fns/latex_pickle_io.py

@@ -0,0 +1,46 @@
+import pickle
+
+
+class SafeUnpickler(pickle.Unpickler):
+
+    def get_safe_classes(self):
+        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()
+        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}'")
+
+def objdump(obj, file="objdump.tmp"):
+
+    with open(file, "wb+") as f:
+        pickle.dump(obj, f)
+    return
+
+
+def objload(file="objdump.tmp"):
+    import os
+
+    if not os.path.exists(file):
+        return
+    with open(file, "rb") as f:
+        unpickler = SafeUnpickler(f)
+        return unpickler.load()

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

@@ -1,83 +1,15 @@
-from toolbox import CatchException, report_exception, get_log_folder, gen_time_str, check_packages
+from toolbox import get_log_folder
-from toolbox import update_ui, promote_file_to_downloadzone, update_ui_lastest_msg, disable_auto_promotion
+from toolbox import update_ui, promote_file_to_downloadzone
 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
-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
-from .crazy_utils import read_and_clean_pdf_text
+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 shared_utils.colorful import *
-from colorful import *
 import os
 
-
+def 解析PDF_简单拆解(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt):
-@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([
-        "函数插件功能？",
-        "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 = []
-
-    from .crazy_utils import get_files_from_everything
-    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
-    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)
-    else:
-        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)
-
-
-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
+    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
@@ -116,7 +48,8 @@ def 解析PDF(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot,
             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],
+                "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)

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/pdf_fns/report_template_v2.html

@@ -0,0 +1,73 @@
+<!DOCTYPE html>
+<html xmlns="http://www.w3.org/1999/xhtml">
+
+<head>
+    <meta http-equiv="Content-Type" content="text/html; charset=UTF-8" />
+    <title>GPT-Academic 翻译报告书</title>
+    <style>
+        .centered-a {
+            color: red;
+            text-align: center;
+            margin-bottom: 2%;
+            font-size: 1.5em;
+        }
+        .centered-b {
+            color: red;
+            text-align: center;
+            margin-top: 10%;
+            margin-bottom: 20%;
+            font-size: 1.5em;
+        }
+        .centered-c {
+            color: rgba(255, 0, 0, 0);
+            text-align: center;
+            margin-top: 2%;
+            margin-bottom: 20%;
+            font-size: 7em;
+        }
+    </style>
+<script>
+        // Configure MathJax settings
+        MathJax = {
+            tex: {
+                inlineMath: [
+                    ['$', '$'],
+                    ['\(', '\)']
+                ]
+            }
+        }
+        addEventListener('zero-md-rendered', () => {MathJax.typeset(); console.log('MathJax typeset!');})
+    </script>
+    <!-- Load MathJax library -->
+    <script src="https://cdn.jsdelivr.net/npm/mathjax@3/es5/tex-chtml.js"></script>
+    <script
+        type="module"
+        src="https://cdn.jsdelivr.net/gh/zerodevx/zero-md@2/dist/zero-md.min.js"
+    ></script>
+
+</head>
+
+<body>
+    <div class="test_temp1" style="width:10%; height: 500px; float:left;">
+
+    </div>
+    <div class="test_temp2" style="width:80%; height: 500px; float:left;">
+        <!-- Simply set the `src` attribute to your MD file and win -->
+        <div class="centered-a">
+            请按Ctrl+S保存此页面，否则该页面可能在几分钟后失效。
+        </div>
+        <zero-md src="translated_markdown.md" no-shadow>
+        </zero-md>
+        <div class="centered-b">
+            本报告由GPT-Academic开源项目生成，地址：https://github.com/binary-husky/gpt_academic。
+        </div>
+        <div class="centered-c">
+            本报告由GPT-Academic开源项目生成，地址：https://github.com/binary-husky/gpt_academic。
+        </div>
+    </div>
+    <div class="test_temp3" style="width:10%; height: 500px; float:left;">
+    </div>
+
+    </body>
+
+</html>

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/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/批量翻译PDF文档_NOUGAT.py

@@ -5,7 +5,7 @@ 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 .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

crazy_functions/生成多种Mermaid图表.py

@@ -1,8 +1,11 @@
 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.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
+# 以下是每类图表的PROMPT
 SELECT_PROMPT = """
 “{subject}”
 =============
@@ -17,22 +20,24 @@ SELECT_PROMPT = """
 8 象限提示图
 不需要解释原因，仅需要输出单个不带任何标点符号的数字。
 """
-#没有思维导图!!!测试发现模型始终会优先选择思维导图
+# 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
+# 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") --> L1("Python")
-    P(编程) --> L2(C)
+    P("编程") --> L2("C")
-    P(编程) --> L3(C++)
+    P("编程") --> L3("C++")
-    P(编程) --> L4(Javascipt)
+    P("编程") --> L4("Javascipt")
-    P(编程) --> L5(PHP)
+    P("编程") --> L5("PHP")
 ```
 """
-#序列图
+# 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
@@ -43,9 +48,10 @@ sequenceDiagram
     B->>A: 返回数据
 ```
 """
-#类图
+# 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
@@ -63,9 +69,10 @@ classDiagram
     Class08 <--> C2: Cool label
 ```
 """
-#饼图
+# 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
@@ -73,38 +80,41 @@ pie title Pets adopted by volunteers
     "兔子" : 15
 ```
 """
-#甘特图
+# 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
+    section "设计"
-    需求分析 :done, des1, 2024-01-06,2024-01-08
+    "需求分析" :done, des1, 2024-01-06,2024-01-08
-    原型设计 :active, des2, 2024-01-09, 3d
+    "原型设计" :active, des2, 2024-01-09, 3d
-    UI设计 : des3, after des2, 5d
+    "UI设计" : des3, after des2, 5d
-    section 开发
+    section "开发"
-    前端开发 :2024-01-20, 10d
+    "前端开发" :2024-01-20, 10d
-    后端开发 :2024-01-20, 10d
+    "后端开发" :2024-01-20, 10d
 ```
 """
-#状态图
+# 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 --> [*]
+    "Still" --> [*]
-    Still --> Moving
+    "Still" --> "Moving"
-    Moving --> Still
+    "Moving" --> "Still"
-    Moving --> Crash
+    "Moving" --> "Crash"
-    Crash --> [*]
+    "Crash" --> [*]
 ```
 """
-#实体关系图
+# 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
@@ -124,118 +134,173 @@ erDiagram
     }
 ```
 """
-#象限提示图
+# 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"] --> B("Programming")
-    A[Hard skill] --> C(Design)
+    A["Hard skill"] --> C("Design")
-    D[Soft skill] --> E(Coordination)
+    D["Soft skill"] --> E("Coordination")
-    D[Soft skill] --> F(Communication)
+    D["Soft skill"] --> F("Communication")
 ```
 """
-#思维导图
+# 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
+    ("Origins")
-      Long history
+      ("Long history")
       ::icon(fa fa-book)
-      Popularisation
+      ("Popularisation")
-        British popular psychology author Tony Buzan
+        ("British popular psychology author Tony Buzan")
-    Research
+        ::icon(fa fa-user)
-      On effectiveness<br/>and features
+    ("Research")
-      On Automatic creation
+      ("On effectiveness<br/>and features")
-        Uses
+      ::icon(fa fa-search)
-            Creative techniques
+      ("On Automatic creation")
-            Strategic planning
+      ::icon(fa fa-robot)
-            Argument mapping
+        ("Uses")
-    Tools
+            ("Creative techniques")
-      Pen and paper
+            ::icon(fa fa-lightbulb-o)
-      Mermaid
+            ("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):
+
+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
+    txt = (
-    from crazy_functions.pdf_fns.breakdown_txt import breakdown_text_to_satisfy_token_limit
+        str(history).encode("utf-8", "ignore").decode()
-    txt = breakdown_text_to_satisfy_token_limit(txt=txt, limit=TOKEN_LIMIT_PER_FRAGMENT, llm_model=llm_kwargs['llm_model'])
+    )  # 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')
+    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
+        gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
-                                                                           llm_kwargs, chatbot,
+            i_say,
-                                                                           history=["The main content of the previous section is?", last_iteration_result], # 迭代上一次的结果
+            i_say_show_user,  # i_say=真正给chatgpt的提问， i_say_show_user=给用户看的提问
-                                                                           sys_prompt="Extracts the main content from the text section where it is located for graphing purposes, answer me with Chinese."  # 提示
+            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 = str(plugin_kwargs)  # 将图表类型参数赋值为插件参数
-    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
-    results_txt = '\n'.join(results)    #合并摘要
+    if gpt_say not in [
-    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
+        "1",
-        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
+        "2",
-        chatbot.append([i_say_show_user, gpt_say]); yield from update_ui(chatbot=chatbot, history=[])    # 更新UI
+        "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=[],
+                llm_kwargs=llm_kwargs,
-                sys_prompt=""
+                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']:
+        if gpt_say not in ["1", "2", "3", "4", "5", "6", "7", "8", "9"]:
-            gpt_say = '1'
+            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
+        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=[],
+        llm_kwargs=llm_kwargs,
-        sys_prompt=""
+        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
+    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 +313,21 @@ 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。\
+            "函数插件功能？",
-        \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"])
+            "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。\
-    yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+        \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
+    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 +335,104 @@ 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(
-                a = f"解析项目: {txt}",
+                chatbot,
-                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。")
+                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。",
+            )
 
         elif excption == "pdf":
-            report_exception(chatbot, history,
+            report_exception(
-                a = f"解析项目: {txt}",
+                chatbot,
-                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```。")
+                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```。",
+            )
 
         elif excption == "word_pip":
-                report_exception(chatbot, history,
+            report_exception(
-                    a=f"解析项目: {txt}",
+                chatbot,
-                    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```。")
+                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```。",
+            )
 
-        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+        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
+            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
+            i_say_show_user = f"首先你从历史记录中提取摘要。"
-            chatbot.append([i_say_show_user, gpt_say]); yield from update_ui(chatbot=chatbot, history=history)    # 更新UI
+            gpt_say = "[Local Message] 收到。"  # 用户提示
-            yield from 解析历史输入(history,llm_kwargs,file_manifest,chatbot,plugin_kwargs)
+            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
+            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
+                i_say_show_user = f"[{i+1}/{file_num}]处理文件{file_manifest[i]}"
-                chatbot.append([i_say_show_user, gpt_say]); yield from update_ui(chatbot=chatbot, history=history)    # 更新UI
+                gpt_say = "[Local Message] 收到。"  # 用户提示
-                history = []    #如输入区内容为文件则清空历史记录
+                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/解析项目源代码.py

@@ -1,6 +1,7 @@
 from toolbox import update_ui, promote_file_to_downloadzone, disable_auto_promotion
 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
@@ -128,6 +129,7 @@ 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 +148,7 @@ 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 +167,7 @@ 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 +188,7 @@ 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 +211,7 @@ 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 +234,7 @@ 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 +264,7 @@ 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 +286,7 @@ 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 +307,7 @@ 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 +330,7 @@ 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 +368,7 @@ 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/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\批量翻译PDF文档_多线程.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\批量翻译PDF文档_多线程.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“批量翻译PDF文档_多线程.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\批量翻译PDF文档_多线程.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 |
-| 批量翻译PDF文档_多线程.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_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",
+    "Conversation_To_File": "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": "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",
-    "批量翻译PDF文档_多线程": "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",
-    "批量翻译PDF文档_多线程": "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 +100,11 @@
     "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"
 }

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",
+    "Conversation_To_File": "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": "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",
-    "批量翻译PDF文档_多线程": "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",

docs/use_tts.md

@@ -0,0 +1,58 @@
+# 使用TTS文字转语音
+
+
+## 1. 使用EDGE-TTS（简单）
+
+将本项目配置项修改如下即可
+
+```
+TTS_TYPE = "EDGE_TTS"
+EDGE_TTS_VOICE = "zh-CN-XiaoxiaoNeural"
+```
+
+## 2. 使用SoVITS（需要有显卡）
+
+使用以下docker-compose.yml文件，先启动SoVITS服务API
+
+  1. 创建以下文件夹结构
+      ```shell
+      .
+      ├── docker-compose.yml
+      └── reference
+          ├── clone_target_txt.txt
+          └── clone_target_wave.mp3
+      ```
+  2. 其中`docker-compose.yml`为
+      ```yaml
+      version: '3.8'
+      services:
+        gpt-sovits:
+          image: fuqingxu/sovits_gptac_trim:latest
+          container_name: sovits_gptac_container
+          working_dir: /workspace/gpt_sovits_demo
+          environment:
+            - is_half=False
+            - is_share=False
+          volumes:
+            - ./reference:/reference
+          ports:
+            - "19880:9880"  # 19880 为 sovits api 的暴露端口，记住它
+          shm_size: 16G
+          deploy:
+            resources:
+              reservations:
+                devices:
+                - driver: nvidia
+                  count: "all"
+                  capabilities: [gpu]
+          command: bash -c "python3 api.py"
+      ```
+  3. 其中`clone_target_wave.mp3`为需要克隆的角色音频，`clone_target_txt.txt`为该音频对应的文字文本（ https://wiki.biligame.com/ys/%E8%A7%92%E8%89%B2%E8%AF%AD%E9%9F%B3 ）
+  4. 运行`docker-compose up`
+  5. 将本项目配置项修改如下即可
+      (19880 为 sovits api 的暴露端口，与docker-compose.yml中的端口对应)
+      ```
+      TTS_TYPE = "LOCAL_SOVITS_API"
+      GPT_SOVITS_URL = "http://127.0.0.1:19880"
+      ```
+  6. 启动本项目

docs/use_vllm.md

@@ -0,0 +1,46 @@
+# 使用VLLM
+
+
+## 1. 首先启动 VLLM，自行选择模型
+
+```
+python -m vllm.entrypoints.openai.api_server --model /home/hmp/llm/cache/Qwen1___5-32B-Chat --tensor-parallel-size 2 --dtype=half
+```
+
+这里使用了存储在 `/home/hmp/llm/cache/Qwen1___5-32B-Chat` 的本地模型，可以根据自己的需求更改。
+
+## 2. 测试 VLLM
+
+```
+curl http://localhost:8000/v1/chat/completions \
+-H "Content-Type: application/json" \
+-d '{
+  "model": "/home/hmp/llm/cache/Qwen1___5-32B-Chat",
+  "messages": [
+  {"role": "system", "content": "You are a helpful assistant."},
+  {"role": "user", "content": "怎么实现一个去中心化的控制器?"}
+  ]
+}'
+```
+
+## 3. 配置本项目
+
+```
+API_KEY = "sk-123456789xxxxxxxxxxxxxxxxxxxxxxxxxxxxxx123456789"
+LLM_MODEL = "vllm-/home/hmp/llm/cache/Qwen1___5-32B-Chat(max_token=4096)"
+API_URL_REDIRECT = {"https://api.openai.com/v1/chat/completions": "http://localhost:8000/v1/chat/completions"}
+```
+
+```
+"vllm-/home/hmp/llm/cache/Qwen1___5-32B-Chat(max_token=4096)"
+其中
+  "vllm-"                                     是前缀（必要）
+  "/home/hmp/llm/cache/Qwen1___5-32B-Chat"    是模型名（必要）
+  "(max_token=6666)"                          是配置（非必要）
+```
+
+## 4. 启动！
+
+```
+python main.py
+```

main.py

@@ -1,4 +1,4 @@
-import os; os.environ['no_proxy'] = '*' # 避免代理网络产生意外污染
+import os, json; os.environ['no_proxy'] = '*' # 避免代理网络产生意外污染
 
 help_menu_description = \
 """Github源代码开源和更新[地址🚀](https://github.com/binary-husky/gpt_academic),
@@ -14,7 +14,7 @@ help_menu_description = \
 </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）"""
 
 def enable_log(PATH_LOGGING):
-    import logging, uuid
+    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")
@@ -26,22 +26,24 @@ def enable_log(PATH_LOGGING):
 
 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
-    from toolbox import format_io, find_free_port, on_file_uploaded, on_report_generated, get_conf, ArgsGeneralWrapper, load_chat_cookies, DummyWith
+    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
+
+    # 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')
     NUM_CUSTOM_BASIC_BTN, SSL_KEYFILE, SSL_CERTFILE = get_conf('NUM_CUSTOM_BASIC_BTN', 'SSL_KEYFILE', 'SSL_CERTFILE')
-    DARK_MODE, INIT_SYS_PROMPT, ADD_WAIFU = get_conf('DARK_MODE', 'INIT_SYS_PROMPT', 'ADD_WAIFU')
+    DARK_MODE, INIT_SYS_PROMPT, ADD_WAIFU, TTS_TYPE = get_conf('DARK_MODE', 'INIT_SYS_PROMPT', 'ADD_WAIFU', 'TTS_TYPE')
+    if LLM_MODEL not in AVAIL_LLM_MODELS: AVAIL_LLM_MODELS += [LLM_MODEL]
 
     # 如果WEB_PORT是-1, 则随机选取WEB端口
     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}"
 
@@ -69,6 +71,7 @@ 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":
@@ -79,15 +82,18 @@ def main():
     cancel_handles = []
     customize_btns = {}
     predefined_btns = {}
+    from shared_utils.cookie_manager import make_cookie_cache, make_history_cache
     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, web_cookie_cache = gr.Textbox(visible=False), gr.Textbox(visible=False)
+        secret_css = gr.Textbox(visible=False, elem_id="secret_css")
-        cookies = gr.State(load_chat_cookies())
+        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():
             with gr_L2(scale=2, elem_id="gpt-chat"):
                 chatbot = gr.Chatbot(label=f"当前模型：{LLM_MODEL}", elem_id="gpt-chatbot")
                 if LAYOUT == "TOP-DOWN":  chatbot.style(height=CHATBOT_HEIGHT)
-                history = gr.State([])
+                history, history_cache, history_cache_update = make_history_cache() # 定义 后端state（history）、前端（history_cache）、后端setter（history_cache_update）三兄弟
             with gr_L2(scale=1, elem_id="gpt-panel"):
                 with gr.Accordion("输入区", open=True, elem_id="input-panel") as area_input_primary:
                     with gr.Row():
@@ -102,7 +108,7 @@ 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():
@@ -118,18 +124,20 @@ 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 = []
@@ -138,84 +146,30 @@ 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"点击这里搜索插件列表", 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"):
+        # 左上角工具栏定义
-            with gr.Row():
+        from themes.gui_toolbar import define_gui_toolbar
-                with gr.Tab("上传文件", elem_id="interact-panel"):
+        checkboxes, checkboxes_2, max_length_sl, theme_dropdown, system_prompt, file_upload_2, md_dropdown, top_p, temperature = \
-                    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。")
+            define_gui_toolbar(AVAIL_LLM_MODELS, LLM_MODEL, INIT_SYS_PROMPT, THEME, AVAIL_THEMES, ADD_WAIFU, help_menu_description, js_code_for_toggle_darkmode)
-                    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, 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)""")
-
-                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);}""")
 
+        # 浮动菜单定义
+        from themes.gui_floating_menu import define_gui_floating_menu
+        area_input_secondary, txt2, area_customize, submitBtn2, 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):
@@ -238,6 +192,7 @@ 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
@@ -247,8 +202,9 @@ def main():
         cancel_handles.append(submitBtn2.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
-        resetBtn.click(lambda: ([], [], "已重置"), None, [chatbot, history, status])    # 再在后端清除history
+        reset_server_side_args = (lambda history: ([], [], "已重置", json.dumps(history)), [history], [chatbot, history, status, history_cache])
-        resetBtn2.click(lambda: ([], [], "已重置"), None, [chatbot, history, status])   # 再在后端清除history
+        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:
@@ -268,27 +224,42 @@ def main():
         file_upload.upload(on_file_uploaded, [file_upload, chatbot, txt, txt2, checkboxes, cookies], [chatbot, txt, txt2, cookies]).then(None, None, None,   _js=r"()=>{toast_push('上传完毕 ...'); cancel_loading_status();}")
         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:
+        def encode_plugin_info(k, plugin)->str:
-            if not plugins[k].get("AsButton", True): continue
+            import copy
-            click_handle = plugins[k]["Button"].click(ArgsGeneralWrapper(plugins[k]["Function"]), [*input_combo], output_combo)
+            from themes.theme import to_cookie_str
-            click_handle.then(on_report_generated, [cookies, file_upload, chatbot], [cookies, file_upload, chatbot])
+            plugin_ = copy.copy(plugin)
-            cancel_handles.append(click_handle)
+            plugin_.pop("Function", None)
-        # 函数插件-下拉菜单与随变按钮的互动
+            plugin_.pop("Class", None)
-        def on_dropdown_changed(k):
+            plugin_.pop("Button", None)
-            variant = plugins[k]["Color"] if "Color" in plugins[k] else "secondary"
+            plugin_["Info"] = plugin.get("Info", k)
-            info = plugins[k].get("Info", k)
+            if plugin.get("AdvancedArgs", False):
-            ret = {switchy_bt: gr.update(value=k, variant=variant, info_str=f'函数插件区: {info}')}
+                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")
-            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"]))})
             else:
-                ret.update({plugin_advanced_arg: gr.update(visible=False, label=f"插件[{k}]不需要高级参数。")})
+                plugin_["Label"] = f"插件[{k}]不需要高级参数。"
-            return ret
+            return to_cookie_str(plugin_)
-        dropdown.select(on_dropdown_changed, [dropdown], [switchy_bt, plugin_advanced_arg] )
 
+        # 插件的注册（前端代码注册）
+        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
+            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:
+                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] )
+        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:
@@ -296,21 +267,29 @@ 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])
+        switchy_bt.click(None, [switchy_bt], None, _js="(switchy_bt)=>on_flex_button_click(switchy_bt)")
-        theme_handle.then(
-            None,
-            [secret_css],
-            None,
-            _js=js_code_for_css_changing
-        )
         # 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"]:
-            yield from ArgsGeneralWrapper(plugins[k]["Function"])(request, *args, **kwargs)
+                if plugins[k].get("Class", None) is None:
-        click_handle = switchy_bt.click(route,[switchy_bt, *input_combo], output_combo)
+                    assert plugins[k].get("Function", None) is not None
-        click_handle.then(on_report_generated, [cookies, file_upload, chatbot], [cookies, file_upload, chatbot])
+                    yield from ArgsGeneralWrapper(plugins[k]["Function"])(request, *args, **kwargs)
-        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)
@@ -327,6 +306,8 @@ 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()
@@ -334,17 +315,18 @@ 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))
 
-        app_block.load(None, inputs=[], outputs=None, _js=f"""()=>GptAcademicJavaScriptInit("{DARK_MODE}","{INIT_SYS_PROMPT}","{ADD_WAIFU}","{LAYOUT}")""")    # 配置暗色主题或亮色主题
+    # 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：")
@@ -356,8 +338,9 @@ def main():
         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

@@ -34,9 +34,14 @@ 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):
@@ -66,8 +71,10 @@ 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"
+cohere_endpoint = "https://api.cohere.ai/v1/chat"
+ollama_endpoint = "http://localhost:11434/api/chat"
 yimodel_endpoint = "https://api.lingyiwanwu.com/v1/chat/completions"
-cohere_endpoint = 'https://api.cohere.ai/v1/chat'
+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'
@@ -85,8 +92,10 @@ 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")
@@ -110,6 +119,15 @@ 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,
@@ -173,6 +191,26 @@ 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-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,
@@ -200,6 +238,27 @@ model_info = {
         "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,
+        "token_cnt": get_token_num_gpt4,
+    },
+
+    "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,
@@ -247,6 +306,46 @@ 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,
+        "endpoint": None,
+        "max_token": 1000,
+        "tokenizer": tokenizer_gpt35,
+        "token_cnt": get_token_num_gpt35,
+    },
     "glm-3-turbo": {
         "fn_with_ui": zhipu_ui,
         "fn_without_ui": zhipu_noui,
@@ -625,14 +724,22 @@ if "qwen-turbo" in AVAIL_LLM_MODELS or "qwen-plus" in AVAIL_LLM_MODELS or "qwen-
     except:
         print(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
+        yimodel_4k_noui, yimodel_4k_ui = get_predict_function(
-        from .bridge_yimodel import predict as yimodel_ui
+            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_with_ui": yimodel_4k_ui,
-                "fn_without_ui": yimodel_noui,
+                "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,
@@ -640,14 +747,59 @@ 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_with_ui": yimodel_200k_ui,
-                "fn_without_ui": yimodel_noui,
+                "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())
@@ -708,6 +860,15 @@ 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:
@@ -760,8 +921,34 @@ if "deepseekcoder" in AVAIL_LLM_MODELS:   # deepseekcoder
         })
     except:
         print(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:
+        print(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)"]
@@ -770,21 +957,80 @@ 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。")
         continue
+    this_model_info = {
+        "fn_with_ui": chatgpt_ui,
+        "fn_without_ui": chatgpt_noui,
+        "can_multi_thread": True,
+        "endpoint": openai_endpoint,
+        "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)"]
+    # 其中
+    #   "vllm-"             是前缀（必要）
+    #   "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)
+    except:
+        print(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: {
             "fn_with_ui": chatgpt_ui,
             "fn_without_ui": chatgpt_noui,
+            "can_multi_thread": True,
             "endpoint": openai_endpoint,
             "max_token": max_token_tmp,
             "tokenizer": tokenizer_gpt35,
             "token_cnt": get_token_num_gpt35,
         },
     })
-
+# -=-=-=-=-=-=- ollama 对齐支持 -=-=-=-=-=-=-
+for model in [m for m in AVAIL_LLM_MODELS if m.startswith("ollama-")]:
+    from .bridge_ollama import predict_no_ui_long_connection as ollama_noui
+    from .bridge_ollama import predict as ollama_ui
+    break
+for model in [m for m in AVAIL_LLM_MODELS if m.startswith("ollama-")]:
+    # 为了更灵活地接入ollama多模型管理界面，设计了此接口，例子：AVAIL_LLM_MODELS = ["ollama-phi3(max_token=6666)"]
+    # 其中
+    #   "ollama-"           是前缀（必要）
+    #   "phi3"            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)
+    except:
+        print(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: {
+            "fn_with_ui": ollama_ui,
+            "fn_without_ui": ollama_noui,
+            "endpoint": ollama_endpoint,
+            "max_token": max_token_tmp,
+            "tokenizer": tokenizer_gpt35,
+            "token_cnt": get_token_num_gpt35,
+        },
+    })
 
 # -=-=-=-=-=-=- azure模型对齐支持 -=-=-=-=-=-=-
 AZURE_CFG_ARRAY = get_conf("AZURE_CFG_ARRAY") # <-- 用于定义和切换多个azure模型 -->
@@ -810,6 +1056,13 @@ 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):
@@ -846,13 +1099,11 @@ 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“一个”大语言模型（多数情况）：
-        # 如果只询问1个大语言模型：
         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)
@@ -905,8 +1156,26 @@ 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。
@@ -925,6 +1194,11 @@ 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

@@ -6,7 +6,6 @@ from toolbox import get_conf, ProxyNetworkActivate
 from .local_llm_class import LocalLLMHandle, get_local_llm_predict_fns
 
 
-
 # ------------------------------------------------------------------------------------------------------------------------
 # 🔌💻 Local Model
 # ------------------------------------------------------------------------------------------------------------------------
@@ -23,20 +22,45 @@ class GetGLM3Handle(LocalLLMHandle):
         import os, glob
         import os
         import platform
-        LOCAL_MODEL_QUANT, device = get_conf('LOCAL_MODEL_QUANT', 'LOCAL_MODEL_DEVICE')
 
-        if LOCAL_MODEL_QUANT == "INT4":         # INT4
+        LOCAL_MODEL_QUANT, device = get_conf("LOCAL_MODEL_QUANT", "LOCAL_MODEL_DEVICE")
-            _model_name_ = "THUDM/chatglm3-6b-int4"
+        _model_name_ = "THUDM/chatglm3-6b"
-        elif LOCAL_MODEL_QUANT == "INT8":       # INT8
+        # if LOCAL_MODEL_QUANT == "INT4":  # INT4
-            _model_name_ = "THUDM/chatglm3-6b-int8"
+        #     _model_name_ = "THUDM/chatglm3-6b-int4"
-        else:
+        # elif LOCAL_MODEL_QUANT == "INT8":  # INT8
-            _model_name_ = "THUDM/chatglm3-6b"  # FP16
+        #     _model_name_ = "THUDM/chatglm3-6b-int8"
-        with ProxyNetworkActivate('Download_LLM'):
+        # else:
-            chatglm_tokenizer = AutoTokenizer.from_pretrained(_model_name_, trust_remote_code=True)
+        #     _model_name_ = "THUDM/chatglm3-6b"  # FP16
-            if device=='cpu':
+        with ProxyNetworkActivate("Download_LLM"):
-                chatglm_model = AutoModel.from_pretrained(_model_name_, trust_remote_code=True, device='cpu').float()
+            chatglm_tokenizer = AutoTokenizer.from_pretrained(
+                _model_name_, trust_remote_code=True
+            )
+            if device == "cpu":
+                chatglm_model = AutoModel.from_pretrained(
+                    _model_name_,
+                    trust_remote_code=True,
+                    device="cpu",
+                ).float()
+            elif LOCAL_MODEL_QUANT == "INT4":  # INT4
+                chatglm_model = AutoModel.from_pretrained(
+                    pretrained_model_name_or_path=_model_name_,
+                    trust_remote_code=True,
+                    device="cuda",
+                    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,
+                )
             else:
-                chatglm_model = AutoModel.from_pretrained(_model_name_, trust_remote_code=True, device='cuda')
+                chatglm_model = AutoModel.from_pretrained(
+                    pretrained_model_name_or_path=_model_name_,
+                    trust_remote_code=True,
+                    device="cuda",
+                )
             chatglm_model = chatglm_model.eval()
 
         self._model = chatglm_model
@@ -46,32 +70,36 @@ class GetGLM3Handle(LocalLLMHandle):
     def llm_stream_generator(self, **kwargs):
         # 🏃‍♂️🏃‍♂️🏃‍♂️ 子进程执行
         def adaptor(kwargs):
-            query = kwargs['query']
+            query = kwargs["query"]
-            max_length = kwargs['max_length']
+            max_length = kwargs["max_length"]
-            top_p = kwargs['top_p']
+            top_p = kwargs["top_p"]
-            temperature = kwargs['temperature']
+            temperature = kwargs["temperature"]
-            history = kwargs['history']
+            history = kwargs["history"]
             return query, max_length, top_p, temperature, history
 
         query, max_length, top_p, temperature, history = adaptor(kwargs)
 
-        for response, history in self._model.stream_chat(self._tokenizer,
+        for response, history in self._model.stream_chat(
-                                                         query,
+            self._tokenizer,
-                                                         history,
+            query,
-                                                         max_length=max_length,
+            history,
-                                                         top_p=top_p,
+            max_length=max_length,
-                                                         temperature=temperature,
+            top_p=top_p,
-                                                         ):
+            temperature=temperature,
+        ):
             yield response
 
     def try_to_import_special_deps(self, **kwargs):
         # import something that will raise error if the user does not install requirement_*.txt
         # 🏃‍♂️🏃‍♂️🏃‍♂️ 主进程执行
         import importlib
+
         # importlib.import_module('modelscope')
 
 
 # ------------------------------------------------------------------------------------------------------------------------
 # 🔌💻 GPT-Academic Interface
 # ------------------------------------------------------------------------------------------------------------------------
-predict_no_ui_long_connection, predict = get_local_llm_predict_fns(GetGLM3Handle, model_name, history_format='chatglm3')
+predict_no_ui_long_connection, predict = get_local_llm_predict_fns(
+    GetGLM3Handle, model_name, history_format="chatglm3"
+)

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 +9,19 @@
 """
 
 import json
+import os
+import re
 import time
-import gradio as gr
 import logging
 import traceback
 import requests
-import importlib
 import random
 
 # 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 +39,57 @@ 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()
@@ -159,6 +208,7 @@ 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 +224,17 @@ 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
+    # 多模态模型
-    # logging.info(f'[raw_input] {raw_input}')
+    has_multimodal_capacity = model_info[llm_kwargs['llm_model']].get('has_multimodal_capacity', False)
-    chatbot.append((inputs, ""))
+    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 +244,7 @@ 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 +252,6 @@ 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 +259,11 @@ 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:
@@ -316,14 +377,17 @@ 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
     """
     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。")
 
-    api_key = select_api_key(llm_kwargs['api_key'], llm_kwargs['llm_model'])
+    if llm_kwargs['llm_model'].startswith('vllm-'):
+        api_key = 'no-api-key'
+    else:
+        api_key = select_api_key(llm_kwargs['api_key'], llm_kwargs['llm_model'])
 
     headers = {
         "Content-Type": "application/json",
@@ -336,36 +400,83 @@ 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"] = remove_image_if_contain_base64(history[index])
+                what_gpt_answer = {}
+                what_gpt_answer["role"] = "assistant"
+                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
+                    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)
+    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)
 
-    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)
     model = llm_kwargs['llm_model']
     if llm_kwargs['llm_model'].startswith('api2d-'):
         model = llm_kwargs['llm_model'][len('api2d-'):]
     if llm_kwargs['llm_model'].startswith('one-api-'):
         model = llm_kwargs['llm_model'][len('one-api-'):]
         model, _ = read_one_api_model_name(model)
-
+    if llm_kwargs['llm_model'].startswith('vllm-'):
+        model = llm_kwargs['llm_model'][len('vllm-'):]
+        model, _ = read_one_api_model_name(model)
     if model == "gpt-3.5-random": # 随机选择, 绕过openai访问频率限制
         model = random.choice([
             "gpt-3.5-turbo",
@@ -384,8 +495,6 @@ 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]} ..........")

request_llms/bridge_chatgpt_vision.py

@@ -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"):
+    # 弃用功能
-        # 实验性功能，自动检测并屏蔽失效的KEY，请勿使用
+    return
-        from request_llms.key_manager import ApiKeyManager
-        api_key = ApiKeyManager().add_key_to_blacklist(key)
 
 def get_full_error(chunk, stream_response):
     """

request_llms/bridge_google_gemini.py

@@ -8,7 +8,7 @@ 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
+from toolbox import get_conf, update_ui, update_ui_lastest_msg, have_any_recent_upload_image_files, trimmed_format_exc, log_chat
 
 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.' + \
@@ -99,6 +99,7 @@ def predict(inputs:str, llm_kwargs:dict, plugin_kwargs:dict, chatbot:ChatBotWith
             gpt_replying_buffer += paraphrase['text']    # 使用 json 解析库进行处理
             chatbot[-1] = (inputs, gpt_replying_buffer)
             history[-1] = gpt_replying_buffer
+            log_chat(llm_model=llm_kwargs["llm_model"], input_str=inputs, output_str=gpt_replying_buffer)
             yield from update_ui(chatbot=chatbot, history=history)
         if error_match:
             history = history[-2]  # 错误的不纳入对话

request_llms/bridge_ollama.py

@@ -22,8 +22,9 @@ import random
 # 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, trimmed_format_exc, is_the_upload_folder, read_one_api_model_name
-proxies, TIMEOUT_SECONDS, MAX_RETRY, YIMODEL_API_KEY = \
+proxies, TIMEOUT_SECONDS, MAX_RETRY = get_conf(
-    get_conf('proxies', 'TIMEOUT_SECONDS', 'MAX_RETRY', 'YIMODEL_API_KEY')
+    "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。'
@@ -45,8 +46,8 @@ def decode_chunk(chunk):
     chunkjson = None
     is_last_chunk = False
     try:
-        chunkjson = json.loads(chunk_decoded[6:])
+        chunkjson = json.loads(chunk_decoded)
-        is_last_chunk = chunkjson.get("lastOne", False)
+        is_last_chunk = chunkjson.get("done", False)
     except:
         pass
     return chunk_decoded, chunkjson, is_last_chunk
@@ -84,7 +85,6 @@ def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="",
 
     stream_response = response.iter_lines()
     result = ''
-    is_head_of_the_stream = True
     while True:
         try: chunk = next(stream_response)
         except StopIteration:
@@ -92,21 +92,18 @@ def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="",
         except requests.exceptions.ConnectionError:
             chunk = next(stream_response) # 失败了，重试一次？再失败就没办法了。
         chunk_decoded, chunkjson, is_last_chunk = decode_chunk(chunk)
-        if is_head_of_the_stream and (r'"object":"error"' not in chunk_decoded) and (r'"role":"assistant"' in chunk_decoded):
-            # 数据流的第一帧不携带content
-            is_head_of_the_stream = False; continue
         if chunk:
             try:
                 if is_last_chunk:
                     # 判定为数据流的结束，gpt_replying_buffer也写完了
                     logging.info(f'[response] {result}')
                     break
-                result += chunkjson['choices'][0]["delta"]["content"]
+                result += chunkjson['message']["content"]
-                if not console_slience: print(chunkjson['choices'][0]["delta"]["content"], end='')
+                if not console_slience: print(chunkjson['message']["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] += chunkjson['choices'][0]["delta"]["content"]
+                        observe_window[0] += chunkjson['message']["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:
@@ -130,8 +127,6 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
     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 len(YIMODEL_API_KEY) == 0:
-        raise RuntimeError("没有设置YIMODEL_API_KEY选项")
     if inputs == "":     inputs = "空空如也的输入栏"
     user_input = inputs
     if additional_fn is not None:
@@ -171,7 +166,6 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
 
     gpt_replying_buffer = ""
 
-    is_head_of_the_stream = True
     if stream:
         stream_response =  response.iter_lines()
         while True:
@@ -185,10 +179,6 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
             # 提前读取一些信息 （用于判断异常）
             chunk_decoded, chunkjson, is_last_chunk = decode_chunk(chunk)
 
-            if is_head_of_the_stream and (r'"object":"error"' not in chunk_decoded) and (r'"role":"assistant"' in chunk_decoded):
-                # 数据流的第一帧不携带content
-                is_head_of_the_stream = False; continue
-
             if chunk:
                 try:
                     if is_last_chunk:
@@ -196,8 +186,11 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
                         logging.info(f'[response] {gpt_replying_buffer}')
                         break
                     # 处理数据流的主体
-                    status_text = f"finish_reason: {chunkjson['choices'][0].get('finish_reason', 'null')}"
+                    try:
-                    gpt_replying_buffer = gpt_replying_buffer + chunkjson['choices'][0]["delta"]["content"]
+                        status_text = f"finish_reason: {chunkjson['error'].get('message', 'null')}"
+                    except:
+                        status_text = "finish_reason: null"
+                    gpt_replying_buffer = gpt_replying_buffer + chunkjson['message']["content"]
                     # 如果这里抛出异常，一般是文本过长，详情见get_full_error的输出
                     history[-1] = gpt_replying_buffer
                     chatbot[-1] = (history[-2], history[-1])
@@ -234,11 +227,9 @@ 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
     """
-    api_key = f"Bearer {YIMODEL_API_KEY}"
 
     headers = {
         "Content-Type": "application/json",
-        "Authorization": api_key
     }
 
     conversation_cnt = len(history) // 2
@@ -265,16 +256,14 @@ def generate_payload(inputs, llm_kwargs, history, system_prompt, stream):
     what_i_ask_now["content"] = inputs
     messages.append(what_i_ask_now)
     model = llm_kwargs['llm_model']
-    if llm_kwargs['llm_model'].startswith('one-api-'):
+    if llm_kwargs['llm_model'].startswith('ollama-'):
-        model = llm_kwargs['llm_model'][len('one-api-'):]
+        model = llm_kwargs['llm_model'][len('ollama-'):]
         model, _ = read_one_api_model_name(model)
-    tokens = 600 if llm_kwargs['llm_model'] == 'yi-34b-chat-0205' else 4096    #yi-34b-chat-0205只有4k上下文...
+    options = {"temperature": llm_kwargs['temperature']}
     payload = {
         "model": model,
         "messages": messages,
-        "temperature": llm_kwargs['temperature'],  # 1.0,
+        "options": options,
-        "stream": stream,
-        "max_tokens": tokens
     }
     try:
         print(f" {llm_kwargs['llm_model']} : {conversation_cnt} : {inputs[:100]} ..........")

request_llms/bridge_qianfan.py

@@ -82,6 +82,9 @@ def generate_from_baidu_qianfan(inputs, llm_kwargs, history, system_prompt):
         "ERNIE-Bot":            "https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/completions",
         "ERNIE-Bot-turbo":      "https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/eb-instant",
         "BLOOMZ-7B":            "https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/bloomz_7b1",
+        "ERNIE-Speed-128K":     "https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/ernie-speed-128k",
+        "ERNIE-Speed-8K":       "https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/ernie_speed",
+        "ERNIE-Lite-8K":        "https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/ernie-lite-8k",
 
         "Llama-2-70B-Chat":     "https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/llama_2_70b",
         "Llama-2-13B-Chat":     "https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/llama_2_13b",

request_llms/bridge_qwen.py

@@ -1,7 +1,7 @@
 import time
 import os
 from toolbox import update_ui, get_conf, update_ui_lastest_msg
-from toolbox import check_packages, report_exception
+from toolbox import check_packages, report_exception, log_chat
 
 model_name = 'Qwen'
 
@@ -59,6 +59,7 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
         chatbot[-1] = (inputs, response)
         yield from update_ui(chatbot=chatbot, history=history)
 
+    log_chat(llm_model=llm_kwargs["llm_model"], input_str=inputs, output_str=response)
     # 总结输出
     if response == f"[Local Message] 等待{model_name}响应中 ...":
         response = f"[Local Message] {model_name}响应异常 ..."

request_llms/bridge_taichu.py

@@ -0,0 +1,72 @@
+import time
+import os
+from toolbox import update_ui, get_conf, update_ui_lastest_msg, log_chat
+from toolbox import check_packages, report_exception, have_any_recent_upload_image_files
+from toolbox import ChatBotWithCookies
+
+# model_name = 'Taichu-2.0'
+# taichu_default_model = 'taichu_llm'
+
+def validate_key():
+    TAICHU_API_KEY = get_conf("TAICHU_API_KEY")
+    if TAICHU_API_KEY == '': return False
+    return True
+
+def predict_no_ui_long_connection(inputs:str, llm_kwargs:dict, history:list=[], sys_prompt:str="",
+                                  observe_window:list=[], console_slience:bool=False):
+    """
+        ⭐多线程方法
+        函数的说明请见 request_llms/bridge_all.py
+    """
+    watch_dog_patience = 5
+    response = ""
+
+    # if llm_kwargs["llm_model"] == "taichu":
+    #     llm_kwargs["llm_model"] = "taichu"
+
+    if validate_key() is False:
+        raise RuntimeError('请配置 TAICHU_API_KEY')
+
+    # 开始接收回复
+    from .com_taichu import TaichuChatInit
+    zhipu_bro_init = TaichuChatInit()
+    for chunk, response in zhipu_bro_init.generate_chat(inputs, llm_kwargs, history, sys_prompt):
+        if len(observe_window) >= 1:
+            observe_window[0] = response
+        if len(observe_window) >= 2:
+            if (time.time() - observe_window[1]) > watch_dog_patience:
+                raise RuntimeError("程序终止。")
+    return response
+
+
+def predict(inputs:str, llm_kwargs:dict, plugin_kwargs:dict, chatbot:ChatBotWithCookies,
+            history:list=[], system_prompt:str='', stream:bool=True, additional_fn:str=None):
+    """
+        ⭐单线程方法
+        函数的说明请见 request_llms/bridge_all.py
+    """
+    chatbot.append([inputs, ""])
+    yield from update_ui(chatbot=chatbot, history=history)
+
+    if validate_key() is False:
+        yield from update_ui_lastest_msg(lastmsg="[Local Message] 请配置ZHIPUAI_API_KEY", chatbot=chatbot, history=history, delay=0)
+        return
+
+    if additional_fn is not None:
+        from core_functional import handle_core_functionality
+        inputs, history = handle_core_functionality(additional_fn, inputs, history, chatbot)
+        chatbot[-1] = [inputs, ""]
+        yield from update_ui(chatbot=chatbot, history=history)
+
+    # if llm_kwargs["llm_model"] == "taichu":
+    #     llm_kwargs["llm_model"] = taichu_default_model
+
+    # 开始接收回复
+    from .com_taichu import TaichuChatInit
+    zhipu_bro_init = TaichuChatInit()
+    for chunk, response in zhipu_bro_init.generate_chat(inputs, llm_kwargs, history, system_prompt):
+        chatbot[-1] = [inputs, response]
+        yield from update_ui(chatbot=chatbot, history=history)
+    history.extend([inputs, response])
+    log_chat(llm_model=llm_kwargs["llm_model"], input_str=inputs, output_str=response)
+    yield from update_ui(chatbot=chatbot, history=history)

request_llms/bridge_zhipu.py

@@ -75,6 +75,10 @@ def predict(inputs:str, llm_kwargs:dict, plugin_kwargs:dict, chatbot:ChatBotWith
         llm_kwargs["llm_model"] = zhipuai_default_model
 
     if llm_kwargs["llm_model"] in ["glm-4v"]:
+        if (len(inputs) + sum(len(temp) for temp in history) + 1047) > 2000:
+            chatbot.append((inputs, "上下文长度超过glm-4v上限2000tokens，注意图片大约占用1,047个tokens"))
+            yield from update_ui(chatbot=chatbot, history=history)
+            return
         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"))

request_llms/com_qwenapi.py

@@ -65,8 +65,12 @@ class QwenRequestInstance():
                 self.result_buf += f"[Local Message] 请求错误：状态码：{response.status_code}，错误码:{response.code}，消息：{response.message}"
                 yield self.result_buf
                 break
-        logging.info(f'[raw_input] {inputs}')
+
-        logging.info(f'[response] {self.result_buf}')
+        # 耗尽generator避免报错
+        while True:
+            try: next(responses)
+            except: break
+
         return self.result_buf
 
 

request_llms/com_sparkapi.py

@@ -67,6 +67,7 @@ class SparkRequestInstance():
         self.gpt_url_v3 = "ws://spark-api.xf-yun.com/v3.1/chat"
         self.gpt_url_v35 = "wss://spark-api.xf-yun.com/v3.5/chat"
         self.gpt_url_img = "wss://spark-api.cn-huabei-1.xf-yun.com/v2.1/image"
+        self.gpt_url_v4 = "wss://spark-api.xf-yun.com/v4.0/chat"
 
         self.time_to_yield_event = threading.Event()
         self.time_to_exit_event = threading.Event()
@@ -94,6 +95,8 @@ class SparkRequestInstance():
             gpt_url = self.gpt_url_v3
         elif llm_kwargs['llm_model'] == 'sparkv3.5':
             gpt_url = self.gpt_url_v35
+        elif llm_kwargs['llm_model'] == 'sparkv4':
+            gpt_url = self.gpt_url_v4
         else:
             gpt_url = self.gpt_url
         file_manifest = []
@@ -194,6 +197,7 @@ def gen_params(appid, inputs, llm_kwargs, history, system_prompt, file_manifest)
         "sparkv2": "generalv2",
         "sparkv3": "generalv3",
         "sparkv3.5": "generalv3.5",
+        "sparkv4": "4.0Ultra"
     }
     domains_select = domains[llm_kwargs['llm_model']]
     if file_manifest: domains_select = 'image'

request_llms/com_taichu.py

@@ -0,0 +1,55 @@
+# encoding: utf-8
+# @Time   : 2024/1/22
+# @Author : Kilig947 & binary husky
+# @Descr   : 兼容最新的智谱Ai
+from toolbox import get_conf
+from toolbox import get_conf, encode_image, get_pictures_list
+import logging, os, requests
+import json
+class TaichuChatInit:
+    def __init__(self): ...
+
+    def __conversation_user(self, user_input: str, llm_kwargs:dict):
+        return {"role": "user", "content": user_input}
+
+    def __conversation_history(self, history:list, llm_kwargs:dict):
+        messages = []
+        conversation_cnt = len(history) // 2
+        if conversation_cnt:
+            for index in range(0, 2 * conversation_cnt, 2):
+                what_i_have_asked = self.__conversation_user(history[index], llm_kwargs)
+                what_gpt_answer = {
+                    "role": "assistant",
+                    "content": history[index + 1]
+                }
+                messages.append(what_i_have_asked)
+                messages.append(what_gpt_answer)
+        return messages
+
+    def generate_chat(self, inputs:str, llm_kwargs:dict, history:list, system_prompt:str):
+        TAICHU_API_KEY = get_conf("TAICHU_API_KEY")
+        params = {
+            'api_key': TAICHU_API_KEY,
+            'model_code': 'taichu_llm',
+            'question': '\n\n'.join(history) + inputs,
+            'prefix': system_prompt,
+            'temperature': llm_kwargs.get('temperature', 0.95),
+            'stream_format': 'json'
+        }
+
+        api = 'https://ai-maas.wair.ac.cn/maas/v1/model_api/invoke'
+        response = requests.post(api, json=params, stream=True)
+        results = ""
+        if response.status_code == 200:
+            response.encoding = 'utf-8'
+            for line in response.iter_lines(decode_unicode=True):
+                delta = json.loads(line)['choices'][0]['text']
+                results += delta
+                yield delta, results
+        else:
+            raise ValueError
+
+
+if __name__ == '__main__':
+    zhipu = TaichuChatInit()
+    zhipu.generate_chat('你好', {'llm_model': 'glm-4'}, [], '你是WPSAi')

request_llms/com_zhipuglm.py

@@ -36,8 +36,14 @@ class ZhipuChatInit:
             what_i_have_asked = {"role": "user", "content": []}
             what_i_have_asked['content'].append({"type": 'text', "text": user_input})
             if encode_img:
+                if len(encode_img) > 1:
+                    logging.warning("glm-4v只支持一张图片,将只取第一张图片进行处理")
+                    print("glm-4v只支持一张图片,将只取第一张图片进行处理")
                 img_d = {"type": "image_url",
-                         "image_url": {'url': encode_img}}
+                            "image_url": {
+                                "url": encode_img[0]['data']
+                            }
+                        }
                 what_i_have_asked['content'].append(img_d)
             return what_i_have_asked
 

request_llms/oai_std_model_template.py

@@ -0,0 +1,402 @@
+import json
+import time
+import logging
+import traceback
+import requests
+
+# 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_the_upload_folder,
+)
+
+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 get_full_error(chunk, stream_response):
+    """
+    尝试获取完整的错误信息
+    """
+    while True:
+        try:
+            chunk += next(stream_response)
+        except:
+            break
+    return chunk
+
+
+def decode_chunk(chunk):
+    """
+    用于解读"content"和"finish_reason"的内容
+    """
+    chunk = chunk.decode()
+    respose = ""
+    finish_reason = "False"
+    try:
+        chunk = json.loads(chunk[6:])
+    except:
+        respose = "API_ERROR"
+        finish_reason = chunk
+    # 错误处理部分
+    if "error" in chunk:
+        respose = "API_ERROR"
+        try:
+            chunk = json.loads(chunk)
+            finish_reason = chunk["error"]["code"]
+        except:
+            finish_reason = "API_ERROR"
+        return respose, finish_reason
+
+    try:
+        respose = chunk["choices"][0]["delta"]["content"]
+    except:
+        pass
+    try:
+        finish_reason = chunk["choices"][0]["finish_reason"]
+    except:
+        pass
+    return respose, finish_reason
+
+
+def generate_message(input, model, key, history, max_output_token, system_prompt, temperature):
+    """
+    整合所有信息，选择LLM模型，生成http请求，为发送请求做准备
+    """
+    api_key = f"Bearer {key}"
+
+    headers = {"Content-Type": "application/json", "Authorization": api_key}
+
+    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"] = input
+    messages.append(what_i_ask_now)
+    playload = {
+        "model": model,
+        "messages": messages,
+        "temperature": temperature,
+        "stream": True,
+        "max_tokens": max_output_token,
+    }
+    try:
+        print(f" {model} : {conversation_cnt} : {input[:100]} ..........")
+    except:
+        print("输入中可能存在乱码。")
+    return headers, playload
+
+
+def get_predict_function(
+        api_key_conf_name,
+        max_output_token,
+        disable_proxy = False
+    ):
+    """
+    为openai格式的API生成响应函数，其中传入参数：
+    api_key_conf_name：
+        `config.py`中此模型的APIKEY的名字，例如"YIMODEL_API_KEY"
+    max_output_token：
+        每次请求的最大token数量，例如对于01万物的yi-34b-chat-200k，其最大请求数为4096
+        ⚠️请不要与模型的最大token数量相混淆。
+    disable_proxy：
+        是否使用代理，True为不使用，False为使用。
+    """
+
+    APIKEY = get_conf(api_key_conf_name)
+
+    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秒不准咬人(咬的也不是人
+        if len(APIKEY) == 0:
+            raise RuntimeError(f"APIKEY为空,请检查配置文件的{APIKEY}")
+        if inputs == "":
+            inputs = "你好👋"
+        headers, playload = generate_message(
+            input=inputs,
+            model=llm_kwargs["llm_model"],
+            key=APIKEY,
+            history=history,
+            max_output_token=max_output_token,
+            system_prompt=sys_prompt,
+            temperature=llm_kwargs["temperature"],
+        )
+        retry = 0
+        while True:
+            try:
+                from .bridge_all import model_info
+
+                endpoint = model_info[llm_kwargs["llm_model"]]["endpoint"]
+                if not disable_proxy:
+                    response = requests.post(
+                        endpoint,
+                        headers=headers,
+                        proxies=proxies,
+                        json=playload,
+                        stream=True,
+                        timeout=TIMEOUT_SECONDS,
+                    )
+                else:
+                    response = requests.post(
+                        endpoint,
+                        headers=headers,
+                        json=playload,
+                        stream=True,
+                        timeout=TIMEOUT_SECONDS,
+                    )
+                break
+            except:
+                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)
+            except StopIteration:
+                break
+            except requests.exceptions.ConnectionError:
+                chunk = next(stream_response)  # 失败了，重试一次？再失败就没办法了。
+            response_text, finish_reason = decode_chunk(chunk)
+            # 返回的数据流第一次为空，继续等待
+            if response_text == "" and finish_reason != "False":
+                continue
+            if response_text == "API_ERROR" and (
+                finish_reason != "False" or finish_reason != "stop"
+            ):
+                chunk = get_full_error(chunk, stream_response)
+                chunk_decoded = chunk.decode()
+                print(chunk_decoded)
+                raise RuntimeError(
+                    f"API异常,请检测终端输出。可能的原因是:{finish_reason}"
+                )
+            if chunk:
+                try:
+                    if finish_reason == "stop":
+                        logging.info(f"[response] {result}")
+                        break
+                    result += response_text
+                    if not console_slience:
+                        print(response_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:
+                            observe_window[0] += response_text
+                        # 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。")
+                except Exception as e:
+                    chunk = get_full_error(chunk, stream_response)
+                    chunk_decoded = chunk.decode()
+                    error_msg = chunk_decoded
+                    print(error_msg)
+                    raise RuntimeError("Json解析不合常规")
+        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 len(APIKEY) == 0:
+            raise RuntimeError(f"APIKEY为空,请检查配置文件的{APIKEY}")
+        if inputs == "":
+            inputs = "你好👋"
+        if additional_fn is not None:
+            from core_functional import handle_core_functionality
+
+            inputs, history = handle_core_functionality(
+                additional_fn, inputs, history, chatbot
+            )
+        logging.info(f"[raw_input] {inputs}")
+        chatbot.append((inputs, ""))
+        yield from update_ui(
+            chatbot=chatbot, history=history, msg="等待响应"
+        )  # 刷新界面
+
+        # check mis-behavior
+        if is_the_upload_folder(inputs):
+            chatbot[-1] = (
+                inputs,
+                f"[Local Message] 检测到操作错误！当您上传文档之后，需点击“**函数插件区**”按钮进行处理，请勿点击“提交”按钮或者“基础功能区”按钮。",
+            )
+            yield from update_ui(
+                chatbot=chatbot, history=history, msg="正常"
+            )  # 刷新界面
+            time.sleep(2)
+
+        headers, playload = generate_message(
+            input=inputs,
+            model=llm_kwargs["llm_model"],
+            key=APIKEY,
+            history=history,
+            max_output_token=max_output_token,
+            system_prompt=system_prompt,
+            temperature=llm_kwargs["temperature"],
+        )
+
+        history.append(inputs)
+        history.append("")
+        retry = 0
+        while True:
+            try:
+                from .bridge_all import model_info
+
+                endpoint = model_info[llm_kwargs["llm_model"]]["endpoint"]
+                if not disable_proxy:
+                    response = requests.post(
+                        endpoint,
+                        headers=headers,
+                        proxies=proxies,
+                        json=playload,
+                        stream=True,
+                        timeout=TIMEOUT_SECONDS,
+                    )
+                else:
+                    response = requests.post(
+                        endpoint,
+                        headers=headers,
+                        json=playload,
+                        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 = ""
+
+        stream_response = response.iter_lines()
+        while True:
+            try:
+                chunk = next(stream_response)
+            except StopIteration:
+                break
+            except requests.exceptions.ConnectionError:
+                chunk = next(stream_response)  # 失败了，重试一次？再失败就没办法了。
+            response_text, finish_reason = decode_chunk(chunk)
+            # 返回的数据流第一次为空，继续等待
+            if response_text == "" and finish_reason != "False":
+                continue
+            if chunk:
+                try:
+                    if response_text == "API_ERROR" and (
+                        finish_reason != "False" or finish_reason != "stop"
+                    ):
+                        chunk = get_full_error(chunk, stream_response)
+                        chunk_decoded = chunk.decode()
+                        chatbot[-1] = (
+                            chatbot[-1][0],
+                            "[Local Message] {finish_reason},获得以下报错信息：\n"
+                            + chunk_decoded,
+                        )
+                        yield from update_ui(
+                            chatbot=chatbot,
+                            history=history,
+                            msg="API异常:" + chunk_decoded,
+                        )  # 刷新界面
+                        print(chunk_decoded)
+                        return
+
+                    if finish_reason == "stop":
+                        logging.info(f"[response] {gpt_replying_buffer}")
+                        break
+                    status_text = f"finish_reason: {finish_reason}"
+                    gpt_replying_buffer += response_text
+                    # 如果这里抛出异常，一般是文本过长，详情见get_full_error的输出
+                    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()
+                    chatbot[-1] = (
+                        chatbot[-1][0],
+                        "[Local Message] 解析错误,获得以下报错信息：\n" + chunk_decoded,
+                    )
+                    yield from update_ui(
+                        chatbot=chatbot, history=history, msg="Json异常" + chunk_decoded
+                    )  # 刷新界面
+                    print(chunk_decoded)
+                    return
+
+    return predict_no_ui_long_connection, predict

requirements.txt

@@ -1,7 +1,8 @@
-https://public.agent-matrix.com/publish/gradio-3.32.9-py3-none-any.whl
+https://public.agent-matrix.com/publish/gradio-3.32.10-py3-none-any.whl
+fastapi==0.110
 gradio-client==0.8
 pypdf2==2.12.1
-zhipuai>=2
+zhipuai==2.0.1
 tiktoken>=0.3.3
 requests[socks]
 pydantic==2.5.2
@@ -22,8 +23,10 @@ pyautogen
 colorama
 Markdown
 pygments
+edge-tts
 pymupdf
 openai
+rjsmin
 arxiv
 numpy
 rich

shared_utils/advanced_markdown_format.py

@@ -46,6 +46,16 @@ code_highlight_configs_block_mermaid = {
     },
 }
 
+
+mathpatterns = {
+    r"(?<!\\|\$)(\$)([^\$]+)(\$)": {"allow_multi_lines": False},  #  $...$
+    r"(?<!\\)(\$\$)([^\$]+)(\$\$)": {"allow_multi_lines": True},  # $$...$$
+    r"(?<!\\)(\\\[)(.+?)(\\\])": {"allow_multi_lines": False},  # \[...\]
+    r'(?<!\\)(\\\()(.+?)(\\\))': {'allow_multi_lines': False},                       # \(...\)
+    # r'(?<!\\)(\\begin{([a-z]+?\*?)})(.+?)(\\end{\2})': {'allow_multi_lines': True},  # \begin...\end
+    # r'(?<!\\)(\$`)([^`]+)(`\$)': {'allow_multi_lines': False},                       # $`...`$
+}
+
 def tex2mathml_catch_exception(content, *args, **kwargs):
     try:
         content = tex2mathml(content, *args, **kwargs)
@@ -96,14 +106,7 @@ def is_equation(txt):
         return False
     if "$" not in txt and "\\[" not in txt:
         return False
-    mathpatterns = {
+
-        r"(?<!\\|\$)(\$)([^\$]+)(\$)": {"allow_multi_lines": False},  #  $...$
-        r"(?<!\\)(\$\$)([^\$]+)(\$\$)": {"allow_multi_lines": True},  # $$...$$
-        r"(?<!\\)(\\\[)(.+?)(\\\])": {"allow_multi_lines": False},  # \[...\]
-        # r'(?<!\\)(\\\()(.+?)(\\\))': {'allow_multi_lines': False},                       # \(...\)
-        # r'(?<!\\)(\\begin{([a-z]+?\*?)})(.+?)(\\end{\2})': {'allow_multi_lines': True},  # \begin...\end
-        # r'(?<!\\)(\$`)([^`]+)(`\$)': {'allow_multi_lines': False},                       # $`...`$
-    }
     matches = []
     for pattern, property in mathpatterns.items():
         flags = re.ASCII | re.DOTALL if property["allow_multi_lines"] else re.ASCII
@@ -207,6 +210,118 @@ def fix_code_segment_indent(txt):
         return txt
 
 
+def fix_dollar_sticking_bug(txt):
+    """
+    修复不标准的dollar公式符号的问题
+    """
+    txt_result = ""
+    single_stack_height = 0
+    double_stack_height = 0
+    while True:
+        while True:
+            index = txt.find('$')
+
+            if index == -1:
+                txt_result += txt
+                return txt_result
+
+            if single_stack_height > 0:
+                if txt[:(index+1)].find('\n') > 0 or txt[:(index+1)].find('<td>') > 0 or txt[:(index+1)].find('</td>') > 0:
+                    print('公式之中出现了异常 (Unexpect element in equation)')
+                    single_stack_height = 0
+                    txt_result += ' $'
+                    continue
+
+            if double_stack_height > 0:
+                if txt[:(index+1)].find('\n\n') > 0:
+                    print('公式之中出现了异常 (Unexpect element in equation)')
+                    double_stack_height = 0
+                    txt_result += '$$'
+                    continue
+
+            is_double = (txt[index+1] == '$')
+            if is_double:
+                if single_stack_height != 0:
+                    # add a padding
+                    txt = txt[:(index+1)] + " " + txt[(index+1):]
+                    continue
+                if double_stack_height == 0:
+                    double_stack_height = 1
+                else:
+                    double_stack_height = 0
+                txt_result += txt[:(index+2)]
+                txt = txt[(index+2):]
+            else:
+                if double_stack_height != 0:
+                    # print(txt[:(index)])
+                    print('发现异常嵌套公式')
+                if single_stack_height == 0:
+                    single_stack_height = 1
+                else:
+                    single_stack_height = 0
+                    # print(txt[:(index)])
+                txt_result += txt[:(index+1)]
+                txt = txt[(index+1):]
+            break
+
+
+def markdown_convertion_for_file(txt):
+    """
+    将Markdown格式的文本转换为HTML格式。如果包含数学公式，则先将公式转换为HTML格式。
+    """
+    from themes.theme import advanced_css
+    pre = f"""
+    <!DOCTYPE html><head><meta charset="utf-8"><title>PDF文档翻译</title><style>{advanced_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="markdown-body">
+    """
+    suf = """
+        </div>
+    </div>
+    <div class="test_temp3" style="width:10%; height: 500px; float:left;"></div>
+    </body>
+    """
+
+    if txt.startswith(pre) and txt.endswith(suf):
+        # print('警告，输入了已经经过转化的字符串，二次转化可能出问题')
+        return txt  # 已经被转化过，不需要再次转化
+
+    find_equation_pattern = r'<script type="math/tex(?:.*?)>(.*?)</script>'
+    txt = fix_markdown_indent(txt)
+    convert_stage_1 = fix_dollar_sticking_bug(txt)
+    # convert everything to html format
+    convert_stage_2 = markdown.markdown(
+        text=convert_stage_1,
+        extensions=[
+            "sane_lists",
+            "tables",
+            "mdx_math",
+            "pymdownx.superfences",
+            "pymdownx.highlight",
+        ],
+        extension_configs={**markdown_extension_configs, **code_highlight_configs},
+    )
+
+
+    def repl_fn(match):
+        content = match.group(2)
+        return f'<script type="math/tex">{content}</script>'
+
+    pattern = "|".join([pattern for pattern, property in mathpatterns.items() if not property["allow_multi_lines"]])
+    pattern = re.compile(pattern, flags=re.ASCII)
+    convert_stage_3 = pattern.sub(repl_fn, convert_stage_2)
+
+    convert_stage_4 = markdown_bug_hunt(convert_stage_3)
+
+    # 2. convert to rendered equation
+    convert_stage_5, n = re.subn(
+        find_equation_pattern, replace_math_render, convert_stage_4, flags=re.DOTALL
+    )
+    # cat them together
+    return pre + convert_stage_5 + suf
+
 @lru_cache(maxsize=128)  # 使用 lru缓存 加快转换速度
 def markdown_convertion(txt):
     """

shared_utils/char_visual_effect.py

@@ -0,0 +1,25 @@
+def is_full_width_char(ch):
+    """判断给定的单个字符是否是全角字符"""
+    if '\u4e00' <= ch <= '\u9fff':
+        return True  # 中文字符
+    if '\uff01' <= ch <= '\uff5e':
+        return True  # 全角符号
+    if '\u3000' <= ch <= '\u303f':
+        return True  # CJK标点符号
+    return False
+
+def scolling_visual_effect(text, scroller_max_len):
+    text = text.\
+            replace('\n', '').replace('`', '.').replace(' ', '.').replace('<br/>', '.....').replace('$', '.')
+    place_take_cnt = 0
+    pointer = len(text) - 1
+
+    if len(text) < scroller_max_len:
+        return text
+
+    while place_take_cnt < scroller_max_len and pointer > 0:
+        if is_full_width_char(text[pointer]): place_take_cnt += 2
+        else: place_take_cnt += 1
+        pointer -= 1
+
+    return text[pointer:]

shared_utils/config_loader.py

@@ -2,7 +2,7 @@ import importlib
 import time
 import os
 from functools import lru_cache
-from colorful import print亮红, print亮绿, print亮蓝
+from shared_utils.colorful import print亮红, print亮绿, print亮蓝
 
 pj = os.path.join
 default_user_name = 'default_user'

shared_utils/connect_void_terminal.py

@@ -15,13 +15,13 @@ import os
 
 def get_plugin_handle(plugin_name):
     """
-    e.g. plugin_name = 'crazy_functions.批量Markdown翻译->Markdown翻译指定语言'
+    e.g. plugin_name = 'crazy_functions.Markdown_Translate->Markdown翻译指定语言'
     """
     import importlib
 
     assert (
         "->" in plugin_name
-    ), "Example of plugin_name: crazy_functions.批量Markdown翻译->Markdown翻译指定语言"
+    ), "Example of plugin_name: crazy_functions.Markdown_Translate->Markdown翻译指定语言"
     module, fn_name = plugin_name.split("->")
     f_hot_reload = getattr(importlib.import_module(module, fn_name), fn_name)
     return f_hot_reload

shared_utils/cookie_manager.py

@@ -1,4 +1,7 @@
+import json
+import base64
 from typing import Callable
+
 def load_web_cookie_cache__fn_builder(customize_btns, cookies, predefined_btns)->Callable:
     def load_web_cookie_cache(persistent_cookie_, cookies_):
         import gradio as gr
@@ -22,7 +25,6 @@ def load_web_cookie_cache__fn_builder(customize_btns, cookies, predefined_btns)-
         return ret
     return load_web_cookie_cache
 
-
 def assign_btn__fn_builder(customize_btns, predefined_btns, cookies, web_cookie_cache)->Callable:
     def assign_btn(persistent_cookie_, cookies_, basic_btn_dropdown_, basic_fn_title, basic_fn_prefix, basic_fn_suffix, clean_up=False):
         import gradio as gr
@@ -59,3 +61,84 @@ def assign_btn__fn_builder(customize_btns, predefined_btns, cookies, web_cookie_
         return ret
     return assign_btn
 
+# cookies, web_cookie_cache = make_cookie_cache()
+def make_cookie_cache():
+    # 定义 后端state（cookies）、前端（web_cookie_cache）两兄弟
+    import gradio as gr
+    from toolbox import load_chat_cookies
+    # 定义cookies的后端state
+    cookies = gr.State(load_chat_cookies())
+    # 定义cookies的一个孪生的前端存储区（隐藏）
+    web_cookie_cache = gr.Textbox(visible=False, elem_id="web_cookie_cache")
+    return cookies, web_cookie_cache
+
+# history, history_cache, history_cache_update = make_history_cache()
+def make_history_cache():
+    # 定义 后端state（history）、前端（history_cache）、后端setter（history_cache_update）三兄弟
+    import gradio as gr
+    # 定义history的后端state
+    history = gr.State([])
+    # 定义history的一个孪生的前端存储区（隐藏）
+    history_cache = gr.Textbox(visible=False, elem_id="history_cache")
+    # 定义history_cache->history的更新方法（隐藏）。在触发这个按钮时，会先执行js代码更新history_cache，然后再执行python代码更新history
+    def process_history_cache(history_cache):
+        return json.loads(history_cache)
+    # 另一种更简单的setter方法
+    history_cache_update = gr.Button("", elem_id="elem_update_history", visible=False).click(
+        process_history_cache, inputs=[history_cache], outputs=[history])
+    return history, history_cache, history_cache_update
+
+
+
+# """
+# with gr.Row():
+#     txt = gr.Textbox(show_label=False, placeholder="Input question here.", elem_id='user_input_main').style(container=False)
+#     txtx = gr.Textbox(show_label=False, placeholder="Input question here.", elem_id='user_input_main').style(container=False)
+# with gr.Row():
+#     btn_value = "Test"
+#     elem_id = "TestCase"
+#     variant = "primary"
+#     input_list = [txt, txtx]
+#     output_list = [txt, txtx]
+#     input_name_list = ["txt(input)", "txtx(input)"]
+#     output_name_list = ["txt", "txtx"]
+#     js_callback = """(txt, txtx)=>{console.log(txt); console.log(txtx);}"""
+#     def function(txt, txtx):
+#         return "booo", "goooo"
+#     create_button_with_javascript_callback(btn_value, elem_id, variant, js_callback, input_list, output_list, function, input_name_list, output_name_list)
+# """
+def create_button_with_javascript_callback(btn_value, elem_id, variant, js_callback, input_list, output_list, function, input_name_list, output_name_list):
+    import gradio as gr
+    middle_ware_component = gr.Textbox(visible=False, elem_id=elem_id+'_buffer')
+    def get_fn_wrap():
+        def fn_wrap(*args):
+            summary_dict = {}
+            for name, value in zip(input_name_list, args):
+                summary_dict.update({name: value})
+
+            res = function(*args)
+
+            for name, value in zip(output_name_list, res):
+                summary_dict.update({name: value})
+
+            summary = base64.b64encode(json.dumps(summary_dict).encode('utf8')).decode("utf-8")
+            return (*res, summary)
+        return fn_wrap
+
+    btn = gr.Button(btn_value, elem_id=elem_id, variant=variant)
+    call_args = ""
+    for name in output_name_list:
+        call_args += f"""Data["{name}"],"""
+    call_args = call_args.rstrip(",")
+    _js_callback = """
+        (base64MiddleString)=>{
+            console.log('hello')
+            const stringData = atob(base64MiddleString);
+            let Data = JSON.parse(stringData);
+            call = JS_CALLBACK_GEN;
+            call(CALL_ARGS);
+        }
+    """.replace("JS_CALLBACK_GEN", js_callback).replace("CALL_ARGS", call_args)
+
+    btn.click(get_fn_wrap(), input_list, output_list+[middle_ware_component]).then(None, [middle_ware_component], None, _js=_js_callback)
+    return btn

shared_utils/fastapi_server.py

@@ -47,6 +47,28 @@ queue cocurrent effectiveness
 import os, requests, threading, time
 import uvicorn
 
+def validate_path_safety(path_or_url, user):
+    from toolbox import get_conf, default_user_name
+    from toolbox import FriendlyException
+    PATH_PRIVATE_UPLOAD, PATH_LOGGING = get_conf('PATH_PRIVATE_UPLOAD', 'PATH_LOGGING')
+    sensitive_path = None
+    path_or_url = os.path.relpath(path_or_url)
+    if path_or_url.startswith(PATH_LOGGING):    # 日志文件（按用户划分）
+        sensitive_path = PATH_LOGGING
+    elif path_or_url.startswith(PATH_PRIVATE_UPLOAD):   # 用户的上传目录（按用户划分）
+        sensitive_path = PATH_PRIVATE_UPLOAD
+    elif path_or_url.startswith('tests'):   # 一个常用的测试目录
+        return True
+    else:
+        raise FriendlyException(f"输入文件的路径 ({path_or_url}) 存在，但位置非法。请将文件上传后再执行该任务。") # return False
+    if sensitive_path:
+        allowed_users = [user, 'autogen', 'arxiv_cache', default_user_name]  # three user path that can be accessed
+        for user_allowed in allowed_users:
+            if f"{os.sep}".join(path_or_url.split(os.sep)[:2]) == os.path.join(sensitive_path, user_allowed):
+                return True
+        raise FriendlyException(f"输入文件的路径 ({path_or_url}) 存在，但属于其他用户。请将文件上传后再执行该任务。") # return False
+    return True
+
 def _authorize_user(path_or_url, request, gradio_app):
     from toolbox import get_conf, default_user_name
     PATH_PRIVATE_UPLOAD, PATH_LOGGING = get_conf('PATH_PRIVATE_UPLOAD', 'PATH_LOGGING')
@@ -59,7 +81,7 @@ def _authorize_user(path_or_url, request, gradio_app):
     if sensitive_path:
         token = request.cookies.get("access-token") or request.cookies.get("access-token-unsecure")
         user = gradio_app.tokens.get(token)  # get user
-        allowed_users = [user, 'autogen', default_user_name]  # three user path that can be accessed
+        allowed_users = [user, 'autogen', 'arxiv_cache', default_user_name]  # three user path that can be accessed
         for user_allowed in allowed_users:
             # exact match
             if f"{os.sep}".join(path_or_url.split(os.sep)[:2]) == os.path.join(sensitive_path, user_allowed):
@@ -77,7 +99,7 @@ class Server(uvicorn.Server):
         self.thread = threading.Thread(target=self.run, daemon=True)
         self.thread.start()
         while not self.started:
-            time.sleep(1e-3)
+            time.sleep(5e-2)
 
     def close(self):
         self.should_exit = True
@@ -137,6 +159,60 @@ def start_app(app_block, CONCURRENT_COUNT, AUTHENTICATION, PORT, SSL_KEYFILE, SS
                     return "越权访问!"
             return await endpoint(path_or_url, request)
 
+        from fastapi import Request, status
+        from fastapi.responses import FileResponse, RedirectResponse
+        @gradio_app.get("/academic_logout")
+        async def logout():
+            response = RedirectResponse(url=CUSTOM_PATH, status_code=status.HTTP_302_FOUND)
+            response.delete_cookie('access-token')
+            response.delete_cookie('access-token-unsecure')
+            return response
+
+    # --- --- enable TTS (text-to-speech) functionality --- ---
+    TTS_TYPE = get_conf("TTS_TYPE")
+    if TTS_TYPE != "DISABLE":
+        # audio generation functionality
+        import httpx
+        from fastapi import FastAPI, Request, HTTPException
+        from starlette.responses import Response
+        async def forward_request(request: Request, method: str) -> Response:
+            async with httpx.AsyncClient() as client:
+                try:
+                    # Forward the request to the target service
+                    if TTS_TYPE == "EDGE_TTS":
+                        import tempfile
+                        import edge_tts
+                        import wave
+                        import uuid
+                        from pydub import AudioSegment
+                        json = await request.json()
+                        voice = get_conf("EDGE_TTS_VOICE")
+                        tts = edge_tts.Communicate(text=json['text'], voice=voice)
+                        temp_folder = tempfile.gettempdir()
+                        temp_file_name = str(uuid.uuid4().hex)
+                        temp_file = os.path.join(temp_folder, f'{temp_file_name}.mp3')
+                        await tts.save(temp_file)
+                        try:
+                            mp3_audio = AudioSegment.from_file(temp_file, format="mp3")
+                            mp3_audio.export(temp_file, format="wav")
+                            with open(temp_file, 'rb') as wav_file: t = wav_file.read()
+                            os.remove(temp_file)
+                            return Response(content=t)
+                        except:
+                            raise RuntimeError("ffmpeg未安装，无法处理EdgeTTS音频。安装方法见`https://github.com/jiaaro/pydub#getting-ffmpeg-set-up`")
+                    if TTS_TYPE == "LOCAL_SOVITS_API":
+                        # Forward the request to the target service
+                        TARGET_URL = get_conf("GPT_SOVITS_URL")
+                        body = await request.body()
+                        resp = await client.post(TARGET_URL, content=body, timeout=60)
+                        # Return the response from the target service
+                        return Response(content=resp.content, status_code=resp.status_code, headers=dict(resp.headers))
+                except httpx.RequestError as e:
+                    raise HTTPException(status_code=400, detail=f"Request to the target service failed: {str(e)}")
+        @gradio_app.post("/vits")
+        async def forward_post_request(request: Request):
+            return await forward_request(request, "POST")
+
     # --- --- app_lifespan --- ---
     from contextlib import asynccontextmanager
     @asynccontextmanager
@@ -154,13 +230,22 @@ def start_app(app_block, CONCURRENT_COUNT, AUTHENTICATION, PORT, SSL_KEYFILE, SS
     fastapi_app = FastAPI(lifespan=app_lifespan)
     fastapi_app.mount(CUSTOM_PATH, gradio_app)
 
-    # --- --- favicon --- ---
+    # --- --- favicon and block fastapi api reference routes --- ---
+    from starlette.responses import JSONResponse
     if CUSTOM_PATH != '/':
         from fastapi.responses import FileResponse
         @fastapi_app.get("/favicon.ico")
         async def favicon():
             return FileResponse(app_block.favicon_path)
 
+        @fastapi_app.middleware("http")
+        async def middleware(request: Request, call_next):
+            if request.scope['path'] in ["/docs", "/redoc", "/openapi.json"]:
+                return JSONResponse(status_code=404, content={"message": "Not Found"})
+            response = await call_next(request)
+            return response
+
+
     # --- --- uvicorn.Config --- ---
     ssl_keyfile = None if SSL_KEYFILE == "" else SSL_KEYFILE
     ssl_certfile = None if SSL_CERTFILE == "" else SSL_CERTFILE

shared_utils/handle_upload.py

@@ -104,6 +104,14 @@ def extract_archive(file_path, dest_dir):
 
     elif file_extension in [".tar", ".gz", ".bz2"]:
         with tarfile.open(file_path, "r:*") as tarobj:
+            # 清理提取路径，移除任何不安全的元素
+            for member in tarobj.getmembers():
+                member_path = os.path.normpath(member.name)
+                full_path = os.path.join(dest_dir, member_path)
+                full_path = os.path.abspath(full_path)
+                if not full_path.startswith(os.path.abspath(dest_dir) + os.sep):
+                    raise Exception(f"Attempted Path Traversal in {member.name}")
+
             tarobj.extractall(path=dest_dir)
             print("Successfully extracted tar archive to {}".format(dest_dir))
 

shared_utils/key_pattern_manager.py

@@ -14,7 +14,7 @@ def is_openai_api_key(key):
     if len(CUSTOM_API_KEY_PATTERN) != 0:
         API_MATCH_ORIGINAL = re.match(CUSTOM_API_KEY_PATTERN, key)
     else:
-        API_MATCH_ORIGINAL = re.match(r"sk-[a-zA-Z0-9]{48}$|sess-[a-zA-Z0-9]{40}$", key)
+        API_MATCH_ORIGINAL = re.match(r"sk-[a-zA-Z0-9]{48}$|sk-proj-[a-zA-Z0-9]{48}$|sess-[a-zA-Z0-9]{40}$", key)
     return bool(API_MATCH_ORIGINAL)
 
 

shared_utils/text_mask.py

@@ -26,6 +26,8 @@ def apply_gpt_academic_string_mask(string, mode="show_all"):
     当字符串中有掩码tag时（<gpt_academic_string_mask><show_...>），根据字符串要给谁看（大模型，还是web渲染），对字符串进行处理，返回处理后的字符串
     示意图：https://mermaid.live/edit#pako:eNqlkUtLw0AUhf9KuOta0iaTplkIPlpduFJwoZEwJGNbzItpita2O6tF8QGKogXFtwu7cSHiq3-mk_oznFR8IYLgrGbuOd9hDrcCpmcR0GDW9ubNPKaBMDauuwI_A9M6YN-3y0bODwxsYos4BdMoBrTg5gwHF-d0mBH6-vqFQe58ed5m9XPW2uteX3Tubrj0ljLYcwxxR3h1zB43WeMs3G19yEM9uapDMe_NG9i2dagKw1Fee4c1D9nGEbtc-5n6HbNtJ8IyHOs8tbs7V2HrlDX2w2Y7XD_5haHEtQiNsOwfMVa_7TzsvrWIuJGo02qTrdwLk9gukQylHv3Afv1ML270s-HZUndrmW1tdA-WfvbM_jMFYuAQ6uCCxVdciTJ1CPLEITpo_GphypeouzXuw6XAmyi7JmgBLZEYlHwLB2S4gHMUO-9DH7tTnvf1CVoFFkBLSOk4QmlRTqpIlaWUHINyNFXjaQWpCYRURUKiWovBYo8X4ymEJFlECQUpqaQkJmuvWygPpg
     """
+    if not string:
+        return string
     if "<gpt_academic_string_mask>" not in string: # No need to process
         return string
 

tests/test_latex_auto_correct.py

@@ -0,0 +1,22 @@
+"""
+对项目中的各个插件进行测试。运行方法：直接运行 python tests/test_plugins.py
+"""
+
+
+import os, sys, importlib
+
+
+def validate_path():
+    dir_name = os.path.dirname(__file__)
+    root_dir_assume = os.path.abspath(dir_name + "/..")
+    os.chdir(root_dir_assume)
+    sys.path.append(root_dir_assume)
+
+
+validate_path()  # 返回项目根路径
+
+if __name__ == "__main__":
+    plugin_test = importlib.import_module('test_utils').plugin_test
+
+
+    plugin_test(plugin='crazy_functions.Latex_Function->Latex翻译中文并重新编译PDF', main_input="2203.01927")

tests/test_llms.py

@@ -14,12 +14,13 @@ validate_path()  # validate path so you can run from base directory
 
 if "在线模型":
     if __name__ == "__main__":
-        from request_llms.bridge_cohere import predict_no_ui_long_connection
+        from request_llms.bridge_taichu import predict_no_ui_long_connection
+        # from request_llms.bridge_cohere import predict_no_ui_long_connection
         # from request_llms.bridge_spark import predict_no_ui_long_connection
         # from request_llms.bridge_zhipu import predict_no_ui_long_connection
         # from request_llms.bridge_chatglm3 import predict_no_ui_long_connection
         llm_kwargs = {
-            "llm_model": "command-r-plus",
+            "llm_model": "taichu",
             "max_length": 4096,
             "top_p": 1,
             "temperature": 1,

tests/test_markdown.py

@@ -43,8 +43,10 @@ def validate_path():
 
 validate_path()  # validate path so you can run from base directory
 from toolbox import markdown_convertion
-
+from shared_utils.advanced_markdown_format import markdown_convertion_for_file
-html = markdown_convertion(md)
+with open("gpt_log/default_user/shared/2024-04-22-01-27-43.zip.extract/translated_markdown.md", "r", encoding="utf-8") as f:
+    md = f.read()
+html = markdown_convertion_for_file(md)
 # print(html)
 with open("test.html", "w", encoding="utf-8") as f:
     f.write(html)

tests/test_plugins.py

@@ -18,14 +18,18 @@ validate_path()  # 返回项目根路径
 if __name__ == "__main__":
     from tests.test_utils import plugin_test
 
+    plugin_test(plugin='crazy_functions.Internet_GPT->连接网络回答问题', main_input="谁是应急食品？")
+
     # plugin_test(plugin='crazy_functions.函数动态生成->函数动态生成', main_input='交换图像的蓝色通道和红色通道', advanced_arg={"file_path_arg": "./build/ants.jpg"})
 
-    # plugin_test(plugin='crazy_functions.Latex输出PDF->Latex翻译中文并重新编译PDF', main_input="2307.07522")
+    # plugin_test(plugin='crazy_functions.Latex_Function->Latex翻译中文并重新编译PDF', main_input="2307.07522")
 
-    plugin_test(
+    # plugin_test(plugin='crazy_functions.PDF_Translate->批量翻译PDF文档', main_input='build/pdf/t1.pdf')
-        plugin="crazy_functions.Latex输出PDF->Latex翻译中文并重新编译PDF",
+
-        main_input="G:/SEAFILE_LOCAL/50503047/我的资料库/学位/paperlatex/aaai/Fu_8368_with_appendix",
+    # plugin_test(
-    )
+    #     plugin="crazy_functions.Latex_Function->Latex翻译中文并重新编译PDF",
+    #     main_input="G:/SEAFILE_LOCAL/50503047/我的资料库/学位/paperlatex/aaai/Fu_8368_with_appendix",
+    # )
 
     # plugin_test(plugin='crazy_functions.虚空终端->虚空终端', main_input='修改api-key为sk-jhoejriotherjep')
 
@@ -41,9 +45,9 @@ if __name__ == "__main__":
 
     # plugin_test(plugin='crazy_functions.Latex全文润色->Latex英文润色', main_input="crazy_functions/test_project/latex/attention")
 
-    # plugin_test(plugin='crazy_functions.批量Markdown翻译->Markdown中译英', main_input="README.md")
+    # plugin_test(plugin='crazy_functions.Markdown_Translate->Markdown中译英', main_input="README.md")
 
-    # plugin_test(plugin='crazy_functions.批量翻译PDF文档_多线程->批量翻译PDF文档', main_input='crazy_functions/test_project/pdf_and_word/aaai.pdf')
+    # plugin_test(plugin='crazy_functions.PDF_Translate->批量翻译PDF文档', main_input='crazy_functions/test_project/pdf_and_word/aaai.pdf')
 
     # plugin_test(plugin='crazy_functions.谷歌检索小助手->谷歌检索小助手', main_input="https://scholar.google.com/scholar?hl=en&as_sdt=0%2C5&q=auto+reinforcement+learning&btnG=")
 
@@ -58,7 +62,7 @@ if __name__ == "__main__":
     # plugin_test(plugin='crazy_functions.数学动画生成manim->动画生成', main_input="A ball split into 2, and then split into 4, and finally split into 8.")
 
     # for lang in ["English", "French", "Japanese", "Korean", "Russian", "Italian", "German", "Portuguese", "Arabic"]:
-    #     plugin_test(plugin='crazy_functions.批量Markdown翻译->Markdown翻译指定语言', main_input="README.md", advanced_arg={"advanced_arg": lang})
+    #     plugin_test(plugin='crazy_functions.Markdown_Translate->Markdown翻译指定语言', main_input="README.md", advanced_arg={"advanced_arg": lang})
 
     # plugin_test(plugin='crazy_functions.知识库文件注入->知识库文件注入', main_input="./")
 
@@ -66,7 +70,7 @@ if __name__ == "__main__":
 
     # plugin_test(plugin='crazy_functions.知识库文件注入->读取知识库作答', main_input="远程云服务器部署？")
 
-    # plugin_test(plugin='crazy_functions.Latex输出PDF->Latex翻译中文并重新编译PDF', main_input="2210.03629")
+    # plugin_test(plugin='crazy_functions.Latex_Function->Latex翻译中文并重新编译PDF', main_input="2210.03629")
 
     # advanced_arg = {"advanced_arg":"--llm_to_learn=gpt-3.5-turbo --prompt_prefix='根据下面的服装类型提示，想象一个穿着者，对这个人外貌、身处的环境、内心世界、人设进行描写。要求：100字以内，用第二人称。' --system_prompt=''" }
     # plugin_test(plugin='crazy_functions.chatglm微调工具->微调数据集生成', main_input='build/dev.json', advanced_arg=advanced_arg)

tests/test_safe_pickle.py

@@ -0,0 +1,17 @@
+def validate_path():
+    import os, sys
+    os.path.dirname(__file__)
+    root_dir_assume = os.path.abspath(os.path.dirname(__file__) + "/..")
+    os.chdir(root_dir_assume)
+    sys.path.append(root_dir_assume)
+validate_path()  # validate path so you can run from base directory
+
+from crazy_functions.latex_fns.latex_pickle_io import objdump, objload
+from crazy_functions.latex_fns.latex_actions import LatexPaperFileGroup, LatexPaperSplit
+pfg = LatexPaperFileGroup()
+pfg.get_token_num = None
+pfg.target = "target_elem"
+x = objdump(pfg)
+t = objload()
+
+print(t.target)

tests/test_save_chat_to_html.py

@@ -0,0 +1,102 @@
+def validate_path():
+    import os, sys
+    os.path.dirname(__file__)
+    root_dir_assume = os.path.abspath(os.path.dirname(__file__) + "/..")
+    os.chdir(root_dir_assume)
+    sys.path.append(root_dir_assume)
+validate_path()  # validate path so you can run from base directory
+
+def write_chat_to_file(chatbot, history=None, file_name=None):
+    """
+    将对话记录history以Markdown格式写入文件中。如果没有指定文件名，则使用当前时间生成文件名。
+    """
+    import os
+    import time
+    from themes.theme import advanced_css
+    # debug
+    import pickle
+    # def objdump(obj, file="objdump.tmp"):
+    #     with open(file, "wb+") as f:
+    #         pickle.dump(obj, f)
+    #     return
+
+    def objload(file="objdump.tmp"):
+        import os
+        if not os.path.exists(file):
+            return
+        with open(file, "rb") as f:
+            return pickle.load(f)
+    # objdump((chatbot, history))
+    chatbot, history = objload()
+
+    with open("test.html", 'w', encoding='utf8') as f:
+        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):
+            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:
+            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)
+
+
+    from bs4 import BeautifulSoup
+    soup = BeautifulSoup(html_content, 'lxml')
+
+    # 提取QaBox信息
+    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})
+
+    # 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)
+
+    print('')
+
+
+write_chat_to_file(None, None, None)

tests/test_searxng.py

@@ -0,0 +1,58 @@
+def validate_path():
+    import os, sys
+    os.path.dirname(__file__)
+    root_dir_assume = os.path.abspath(os.path.dirname(__file__) + "/..")
+    os.chdir(root_dir_assume)
+    sys.path.append(root_dir_assume)
+validate_path()  # validate path so you can run from base directory
+
+from toolbox import get_conf
+import requests
+
+def searxng_request(query, proxies, categories='general', searxng_url=None, engines=None):
+    url = 'http://localhost:50001/'
+
+    if engines is None:
+        engine = 'bing,'
+    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': engine,
+        }
+    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': '112.112.112.112',
+        'X-Real-IP': '112.112.112.112'
+    }
+    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", ""),
+                "content": result.get("content", ""),
+                "link": result["url"],
+            }
+            print(result['engines'])
+            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'))
+res = searxng_request("vr environment", None, categories='science', searxng_url=None, engines=None)
+print(res)

themes/common.css

@@ -1,3 +1,9 @@
+#plugin_arg_menu {
+    transform: translate(-50%, -50%);
+    border: dashed;
+}
+
+
 /* hide remove all button */
 .remove-all.svelte-aqlk7e.svelte-aqlk7e.svelte-aqlk7e {
     visibility: hidden;
@@ -38,6 +44,7 @@
     left: calc(100% + 3px);
     top: 0;
     display: flex;
+    flex-direction: column;
     justify-content: space-between;
 }
 /* .message-btn-row-leading, .message-btn-row-trailing {
@@ -108,6 +115,7 @@
     border-width: thin;
     user-select: none;
     padding-left: 2%;
+    text-align: center;
 }
 
 .floating-component #input-panel2 {
@@ -117,3 +125,20 @@
     border-width: thin;
     border-top-width: 0;
 }
+
+.floating-component #plugin_arg_panel {
+    border-top-left-radius: 0px;
+    border-top-right-radius: 0px;
+    border: solid;
+    border-width: thin;
+    border-top-width: 0;
+}
+
+.floating-component #edit-panel {
+    border-top-left-radius: 0px;
+    border-top-right-radius: 0px;
+    border: solid;
+    border-width: thin;
+    border-top-width: 0;
+}
+

themes/common.py

@@ -1,18 +1,53 @@
+from functools import cache
 from toolbox import get_conf
 CODE_HIGHLIGHT, ADD_WAIFU, LAYOUT = get_conf("CODE_HIGHLIGHT", "ADD_WAIFU", "LAYOUT")
 
+def minimize_js(common_js_path):
+    try:
+        import rjsmin, hashlib, glob, os
+        # clean up old minimized js files, matching `common_js_path + '.min.*'`
+        for old_min_js in glob.glob(common_js_path + '.min.*.js'):
+            os.remove(old_min_js)
+        # use rjsmin to minimize `common_js_path`
+        c_jsmin = rjsmin.jsmin
+        with open(common_js_path, "r") as f:
+            js_content = f.read()
+        minimized_js_content = c_jsmin(js_content)
+        # compute sha256 hash of minimized js content
+        sha_hash = hashlib.sha256(minimized_js_content.encode()).hexdigest()[:8]
+        minimized_js_path = common_js_path + '.min.' + sha_hash + '.js'
+        # save to minimized js file
+        with open(minimized_js_path, "w") as f:
+            f.write(minimized_js_content)
+        # return minimized js file path
+        return minimized_js_path
+    except:
+        return common_js_path
+
+@cache
 def get_common_html_javascript_code():
     js = "\n"
-    for jsf in [
+    common_js_path_list = [
-        "file=themes/common.js",
+        "themes/common.js",
-    ]:
+        "themes/theme.js",
-        js += f"""<script src="{jsf}"></script>\n"""
+        "themes/init.js",
+    ]
 
-    # 添加Live2D
+    if ADD_WAIFU: # 添加Live2D
-    if ADD_WAIFU:
+        common_js_path_list += [
+            "themes/waifu_plugin/jquery.min.js",
+            "themes/waifu_plugin/jquery-ui.min.js",
+        ]
+
+    for common_js_path in common_js_path_list:
+        if '.min.' not in common_js_path:
+            minimized_js_path = minimize_js(common_js_path)
         for jsf in [
-            "file=themes/waifu_plugin/jquery.min.js",
+            f"file={minimized_js_path}",
-            "file=themes/waifu_plugin/jquery-ui.min.js",
         ]:
             js += f"""<script src="{jsf}"></script>\n"""
+
+    if not ADD_WAIFU:
+        js += """<script>window.loadLive2D = function(){};</script>\n"""
+
     return js

themes/default.css

@@ -24,8 +24,8 @@
 /* 小按钮 */
 #basic-panel .sm {
     font-family: "Microsoft YaHei UI", "Helvetica", "Microsoft YaHei", "ui-sans-serif", "sans-serif", "system-ui";
-    --button-small-text-weight: 600;
+    --button-small-text-weight: 400;
-    --button-small-text-size:   16px;
+    --button-small-text-size:   14px;
     border-bottom-right-radius: 6px;
     border-bottom-left-radius:  6px;
     border-top-right-radius:    6px;

themes/gradios.py

@@ -1,4 +1,3 @@
-import logging
 import os
 import gradio as gr
 from toolbox import get_conf, ProxyNetworkActivate
@@ -10,12 +9,15 @@ theme_dir = os.path.dirname(__file__)
 def dynamic_set_theme(THEME):
     set_theme = gr.themes.ThemeClass()
     with ProxyNetworkActivate("Download_Gradio_Theme"):
-        logging.info("正在下载Gradio主题，请稍等。")
+        print("正在下载Gradio主题，请稍等。")
-        if THEME.startswith("Huggingface-"):
+        try:
-            THEME = THEME.lstrip("Huggingface-")
+            if THEME.startswith("Huggingface-"):
-        if THEME.startswith("huggingface-"):
+                THEME = THEME.lstrip("Huggingface-")
-            THEME = THEME.lstrip("huggingface-")
+            if THEME.startswith("huggingface-"):
-        set_theme = set_theme.from_hub(THEME.lower())
+                THEME = THEME.lstrip("huggingface-")
+            set_theme = set_theme.from_hub(THEME.lower())
+        except:
+            print("下载Gradio主题时出现异常。")
     return set_theme
 
 
@@ -23,13 +25,16 @@ def adjust_theme():
     try:
         set_theme = gr.themes.ThemeClass()
         with ProxyNetworkActivate("Download_Gradio_Theme"):
-            logging.info("正在下载Gradio主题，请稍等。")
+            print("正在下载Gradio主题，请稍等。")
-            THEME = get_conf("THEME")
+            try:
-            if THEME.startswith("Huggingface-"):
+                THEME = get_conf("THEME")
-                THEME = THEME.lstrip("Huggingface-")
+                if THEME.startswith("Huggingface-"):
-            if THEME.startswith("huggingface-"):
+                    THEME = THEME.lstrip("Huggingface-")
-                THEME = THEME.lstrip("huggingface-")
+                if THEME.startswith("huggingface-"):
-            set_theme = set_theme.from_hub(THEME.lower())
+                    THEME = THEME.lstrip("huggingface-")
+                set_theme = set_theme.from_hub(THEME.lower())
+            except:
+                print("下载Gradio主题时出现异常。")
 
         from themes.common import get_common_html_javascript_code
         js = get_common_html_javascript_code()
@@ -49,9 +54,7 @@ def adjust_theme():
         )
     except Exception:
         set_theme = None
-        from toolbox import trimmed_format_exc
+        print("gradio版本较旧, 不能自定义字体和颜色。")
-
-        logging.error("gradio版本较旧, 不能自定义字体和颜色:", trimmed_format_exc())
     return set_theme
 
 

themes/gui_advanced_plugin_class.py

@@ -0,0 +1,57 @@
+import gradio as gr
+import json
+from toolbox import format_io, find_free_port, on_file_uploaded, on_report_generated, get_conf, ArgsGeneralWrapper, DummyWith
+
+def define_gui_advanced_plugin_class(plugins):
+    # 定义新一代插件的高级参数区
+    with gr.Floating(init_x="50%", init_y="50%", visible=False, width="30%", drag="top", elem_id="plugin_arg_menu"):
+        with gr.Accordion("选择插件参数", open=True, elem_id="plugin_arg_panel"):
+            for u in range(8):
+                with gr.Row():
+                    gr.Textbox(show_label=True, label="T1", placeholder="请输入", lines=1, visible=False, elem_id=f"plugin_arg_txt_{u}").style(container=False)
+            for u in range(8):
+                with gr.Row(): # PLUGIN_ARG_MENU
+                    gr.Dropdown(label="T1", value="请选择", choices=[], visible=True, elem_id=f"plugin_arg_drop_{u}", interactive=True)
+
+            with gr.Row():
+                # 这个隐藏textbox负责装入当前弹出插件的属性
+                gr.Textbox(show_label=False, placeholder="请输入", lines=1, visible=False,
+                        elem_id=f"invisible_current_pop_up_plugin_arg").style(container=False)
+                usr_confirmed_arg = gr.Textbox(show_label=False, placeholder="请输入", lines=1, visible=False,
+                        elem_id=f"invisible_current_pop_up_plugin_arg_final").style(container=False)
+
+                arg_confirm_btn = gr.Button("确认参数并执行", variant="stop")
+                arg_confirm_btn.style(size="sm")
+
+                arg_cancel_btn = gr.Button("取消", variant="stop")
+                arg_cancel_btn.click(None, None, None, _js="""()=>close_current_pop_up_plugin()""")
+                arg_cancel_btn.style(size="sm")
+
+                arg_confirm_btn.click(None, None, None, _js="""()=>execute_current_pop_up_plugin()""")
+                invisible_callback_btn_for_plugin_exe = gr.Button(r"未选定任何插件", variant="secondary", visible=False, elem_id="invisible_callback_btn_for_plugin_exe").style(size="sm")
+                # 随变按钮的回调函数注册
+                def route_switchy_bt_with_arg(request: gr.Request, input_order, *arg):
+                    arguments = {k:v for k,v in zip(input_order, arg)}      # 重新梳理输入参数，转化为kwargs字典
+                    which_plugin = arguments.pop('new_plugin_callback')     # 获取需要执行的插件名称
+                    if which_plugin in [r"未选定任何插件"]: return
+                    usr_confirmed_arg = arguments.pop('usr_confirmed_arg')  # 获取插件参数
+                    arg_confirm: dict = {}
+                    usr_confirmed_arg_dict = json.loads(usr_confirmed_arg)  # 读取插件参数
+                    for arg_name in usr_confirmed_arg_dict:
+                        arg_confirm.update({arg_name: str(usr_confirmed_arg_dict[arg_name]['user_confirmed_value'])})
+
+                    if plugins[which_plugin].get("Class", None) is not None:  # 获取插件执行函数
+                        plugin_obj = plugins[which_plugin]["Class"]
+                        plugin_exe = plugin_obj.execute
+                    else:
+                        plugin_exe = plugins[which_plugin]["Function"]
+
+                    arguments['plugin_advanced_arg'] = arg_confirm          # 更新高级参数输入区的参数
+                    if arg_confirm.get('main_input', None) is not None:     # 更新主输入区的参数
+                        arguments['txt'] = arg_confirm['main_input']
+
+                    # 万事俱备，开始执行
+                    yield from ArgsGeneralWrapper(plugin_exe)(request, *arguments.values())
+
+    return invisible_callback_btn_for_plugin_exe, route_switchy_bt_with_arg, usr_confirmed_arg
+

themes/gui_floating_menu.py

@@ -0,0 +1,41 @@
+import gradio as gr
+
+def define_gui_floating_menu(customize_btns, functional, predefined_btns, cookies, web_cookie_cache):
+    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);}""")
+    return area_input_secondary, txt2, area_customize, submitBtn2, resetBtn2, clearBtn2, stopBtn2

themes/gui_toolbar.py

@@ -0,0 +1,34 @@
+import gradio as gr
+
+def define_gui_toolbar(AVAIL_LLM_MODELS, LLM_MODEL, INIT_SYS_PROMPT, THEME, AVAIL_THEMES, ADD_WAIFU, help_menu_description, js_code_for_toggle_darkmode):
+    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)
+    return checkboxes, checkboxes_2, max_length_sl, theme_dropdown, system_prompt, file_upload_2, md_dropdown, top_p, temperature

themes/init.js

@@ -0,0 +1,125 @@
+async function GptAcademicJavaScriptInit(dark, prompt, live2d, layout, tts) {
+    // 第一部分，布局初始化
+    audio_fn_init();
+    minor_ui_adjustment();
+    chatbotIndicator = gradioApp().querySelector('#gpt-chatbot > div.wrap');
+    var chatbotObserver = new MutationObserver(() => {
+        chatbotContentChanged(1);
+    });
+    chatbotObserver.observe(chatbotIndicator, { attributes: true, childList: true, subtree: true });
+    if (layout === "LEFT-RIGHT") { chatbotAutoHeight(); }
+    if (layout === "LEFT-RIGHT") { limit_scroll_position(); }
+
+    // 第二部分，读取Cookie，初始话界面
+    let searchString = "";
+    let bool_value = "";
+    //  darkmode 深色模式
+    if (getCookie("js_darkmode_cookie")) {
+        dark = getCookie("js_darkmode_cookie")
+    }
+    dark = dark == "True";
+    if (document.querySelectorAll('.dark').length) {
+        if (!dark) {
+            document.querySelectorAll('.dark').forEach(el => el.classList.remove('dark'));
+        }
+    } else {
+        if (dark) {
+            document.querySelector('body').classList.add('dark');
+        }
+    }
+
+    //  自动朗读
+    if (tts != "DISABLE"){
+        enable_tts = true;
+        if (getCookie("js_auto_read_cookie")) {
+            auto_read_tts = getCookie("js_auto_read_cookie")
+            auto_read_tts = auto_read_tts == "True";
+            if (auto_read_tts) {
+                allow_auto_read_tts_flag = true;
+            }
+        }
+    }
+
+    // SysPrompt 系统静默提示词
+    gpt_academic_gradio_saveload("load", "elem_prompt", "js_system_prompt_cookie", null, "str");
+    // Temperature 大模型温度参数
+    gpt_academic_gradio_saveload("load", "elem_temperature", "js_temperature_cookie", null, "float");
+    // md_dropdown 大模型类型选择
+    if (getCookie("js_md_dropdown_cookie")) {
+        const cached_model = getCookie("js_md_dropdown_cookie");
+        var model_sel = await get_gradio_component("elem_model_sel");
+        // determine whether the cached model is in the choices
+        if (model_sel.props.choices.includes(cached_model)){
+            // change dropdown
+            gpt_academic_gradio_saveload("load", "elem_model_sel", "js_md_dropdown_cookie", null, "str");
+            // 连锁修改chatbot的label
+            push_data_to_gradio_component({
+                label: '当前模型：' + getCookie("js_md_dropdown_cookie"),
+                __type__: 'update'
+            }, "gpt-chatbot", "obj")
+        }
+    }
+
+
+
+    // clearButton 自动清除按钮
+    if (getCookie("js_clearbtn_show_cookie")) {
+        // have cookie
+        bool_value = getCookie("js_clearbtn_show_cookie")
+        bool_value = bool_value == "True";
+        searchString = "输入清除键";
+
+        if (bool_value) {
+            // make btns appear
+            let clearButton = document.getElementById("elem_clear"); clearButton.style.display = "block";
+            let clearButton2 = document.getElementById("elem_clear2"); clearButton2.style.display = "block";
+            // deal with checkboxes
+            let arr_with_clear_btn = update_array(
+                await get_data_from_gradio_component('cbs'), "输入清除键", "add"
+            )
+            push_data_to_gradio_component(arr_with_clear_btn, "cbs", "no_conversion");
+        } else {
+            // make btns disappear
+            let clearButton = document.getElementById("elem_clear"); clearButton.style.display = "none";
+            let clearButton2 = document.getElementById("elem_clear2"); clearButton2.style.display = "none";
+            // deal with checkboxes
+            let arr_without_clear_btn = update_array(
+                await get_data_from_gradio_component('cbs'), "输入清除键", "remove"
+            )
+            push_data_to_gradio_component(arr_without_clear_btn, "cbs", "no_conversion");
+        }
+    }
+
+    // live2d 显示
+    if (getCookie("js_live2d_show_cookie")) {
+        // have cookie
+        searchString = "添加Live2D形象";
+        bool_value = getCookie("js_live2d_show_cookie");
+        bool_value = bool_value == "True";
+        if (bool_value) {
+            loadLive2D();
+            let arr_with_live2d = update_array(
+                await get_data_from_gradio_component('cbsc'), "添加Live2D形象", "add"
+            )
+            push_data_to_gradio_component(arr_with_live2d, "cbsc", "no_conversion");
+        } else {
+            try {
+                $('.waifu').hide();
+                let arr_without_live2d = update_array(
+                    await get_data_from_gradio_component('cbsc'), "添加Live2D形象", "remove"
+                )
+                push_data_to_gradio_component(arr_without_live2d, "cbsc", "no_conversion");
+            } catch (error) {
+            }
+        }
+    } else {
+        // do not have cookie
+        if (live2d) {
+            loadLive2D();
+        } else {
+        }
+    }
+
+    // 主题加载（恢复到上次）
+    change_theme("", "")
+}

themes/theme.js

@@ -0,0 +1,41 @@
+async function try_load_previous_theme(){
+    if (getCookie("js_theme_selection_cookie")) {
+        theme_selection = getCookie("js_theme_selection_cookie");
+        let css = localStorage.getItem('theme-' + theme_selection);
+        if (css) {
+            change_theme(theme_selection, css);
+        }
+    }
+}
+
+async function change_theme(theme_selection, css) {
+    if (theme_selection.length==0) {
+        try_load_previous_theme();
+        return;
+    }
+
+    var existingStyles = document.querySelectorAll("body > gradio-app > div > style")
+    for (var i = 0; i < existingStyles.length; i++) {
+        var style = existingStyles[i];
+        style.parentNode.removeChild(style);
+    }
+    var existingStyles = document.querySelectorAll("style[data-loaded-css]");
+    for (var i = 0; i < existingStyles.length; i++) {
+        var style = existingStyles[i];
+        style.parentNode.removeChild(style);
+    }
+
+    setCookie("js_theme_selection_cookie", theme_selection, 3);
+    localStorage.setItem('theme-' + theme_selection, css);
+
+    var styleElement = document.createElement('style');
+    styleElement.setAttribute('data-loaded-css', 'placeholder');
+    styleElement.innerHTML = css;
+    document.body.appendChild(styleElement);
+}
+
+
+// // 记录本次的主题切换
+// async function change_theme_prepare(theme_selection, secret_css) {
+//     setCookie("js_theme_selection_cookie", theme_selection, 3);
+// }

themes/theme.py

@@ -71,29 +71,10 @@ def from_cookie_str(c):
 """
 -=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-
 第 3 部分
-内嵌的javascript代码
+内嵌的javascript代码（这部分代码会逐渐移动到common.js中）
 -=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-
 """
 
-js_code_for_css_changing = """(css) => {
-    var existingStyles = document.querySelectorAll("body > gradio-app > div > style")
-    for (var i = 0; i < existingStyles.length; i++) {
-        var style = existingStyles[i];
-        style.parentNode.removeChild(style);
-    }
-    var existingStyles = document.querySelectorAll("style[data-loaded-css]");
-    for (var i = 0; i < existingStyles.length; i++) {
-        var style = existingStyles[i];
-        style.parentNode.removeChild(style);
-    }
-    var styleElement = document.createElement('style');
-    styleElement.setAttribute('data-loaded-css', 'placeholder');
-    styleElement.innerHTML = css;
-    document.body.appendChild(styleElement);
-}
-"""
-
-
 js_code_for_toggle_darkmode = """() => {
     if (document.querySelectorAll('.dark').length) {
         setCookie("js_darkmode_cookie", "False", 365);
@@ -111,10 +92,12 @@ js_code_for_persistent_cookie_init = """(web_cookie_cache, cookie) => {
 }
 """
 
-
+# 详见 themes/common.js
 js_code_reset = """
 (a,b,c)=>{
-    return [[], [], "已重置"];
+    let stopButton = document.getElementById("elem_stop");
+    stopButton.click();
+    return reset_conversation(a,b);
 }
 """
 

themes/waifu_plugin/waifu-tips.js

@@ -142,7 +142,13 @@ function initModel(waifuPath, type) {
     if (live2d_settings.waifuEdgeSide[0] == 'left') $(".waifu").css("left",live2d_settings.waifuEdgeSide[1]+'px');
     else if (live2d_settings.waifuEdgeSide[0] == 'right') $(".waifu").css("right",live2d_settings.waifuEdgeSide[1]+'px');
 
-    window.waifuResize = function() { $(window).width() <= Number(live2d_settings.waifuMinWidth.replace('px','')) ? $(".waifu").hide() : $(".waifu").show(); };
+    window.waifuResize = function() {
+        console.log('resize');
+        if ($('.waifu')[0].style.display === "none" ){
+        } else{
+            $(window).width() <= Number(live2d_settings.waifuMinWidth.replace('px','')) ? $(".waifu").hide() : $(".waifu").show();
+        }
+    };
     if (live2d_settings.waifuMinWidth != 'disable') { waifuResize(); $(window).resize(function() {waifuResize()}); }
 
     try {

toolbox.py

@@ -1,3 +1,4 @@
+
 import importlib
 import time
 import inspect
@@ -10,6 +11,7 @@ import glob
 import logging
 import uuid
 from functools import wraps
+from textwrap import dedent
 from shared_utils.config_loader import get_conf
 from shared_utils.config_loader import set_conf
 from shared_utils.config_loader import set_multi_conf
@@ -79,6 +81,8 @@ class ChatBotWithCookies(list):
     def get_cookies(self):
         return self._cookies
 
+    def get_user(self):
+        return self._cookies.get("user_name", default_user_name)
 
 def ArgsGeneralWrapper(f):
     """
@@ -88,7 +92,7 @@ def ArgsGeneralWrapper(f):
     """
     def decorated(request: gradio.Request, cookies:dict, max_length:int, llm_model:str,
                   txt:str, txt2:str, top_p:float, temperature:float, chatbot:list,
-                  history:list, system_prompt:str, plugin_advanced_arg:str, *args):
+                  history:list, system_prompt:str, plugin_advanced_arg:dict, *args):
         txt_passon = txt
         if txt == "" and txt2 != "": txt_passon = txt2
         # 引入一个有cookie的chatbot
@@ -112,9 +116,10 @@ def ArgsGeneralWrapper(f):
             'client_ip': request.client.host,
             'most_recent_uploaded': cookies.get('most_recent_uploaded')
         }
-        plugin_kwargs = {
+        if isinstance(plugin_advanced_arg, str):
-            "advanced_arg": plugin_advanced_arg,
+            plugin_kwargs = {"advanced_arg": plugin_advanced_arg}
-        }
+        else:
+            plugin_kwargs = plugin_advanced_arg
         chatbot_with_cookie = ChatBotWithCookies(cookies)
         chatbot_with_cookie.write_list(chatbot)
 
@@ -191,6 +196,19 @@ def trimmed_format_exc():
     return str.replace(current_path, replace_path)
 
 
+def trimmed_format_exc_markdown():
+    return '\n\n```\n' + trimmed_format_exc() + '```'
+
+
+class FriendlyException(Exception):
+    def generate_error_html(self):
+        return dedent(f"""
+            <div class="center-div" style="color: crimson;text-align: center;">
+                {"<br>".join(self.args)}
+            </div>
+        """)
+
+
 def CatchException(f):
     """
     装饰器函数，捕捉函数f中的异常并封装到一个生成器中返回，并显示到聊天当中。
@@ -201,13 +219,18 @@ def CatchException(f):
                   chatbot_with_cookie:ChatBotWithCookies, history:list, *args, **kwargs):
         try:
             yield from f(main_input, llm_kwargs, plugin_kwargs, chatbot_with_cookie, history, *args, **kwargs)
+        except FriendlyException as e:
+            if len(chatbot_with_cookie) == 0:
+                chatbot_with_cookie.clear()
+                chatbot_with_cookie.append(["插件调度异常", None])
+            chatbot_with_cookie[-1] = [chatbot_with_cookie[-1][0], e.generate_error_html()]
+            yield from update_ui(chatbot=chatbot_with_cookie, history=history, msg=f'异常')  # 刷新界面
         except Exception as e:
-            from toolbox import get_conf
             tb_str = '```\n' + trimmed_format_exc() + '```'
             if len(chatbot_with_cookie) == 0:
                 chatbot_with_cookie.clear()
                 chatbot_with_cookie.append(["插件调度异常", "异常原因"])
-            chatbot_with_cookie[-1] = (chatbot_with_cookie[-1][0], f"[Local Message] 插件调用出错: \n\n{tb_str} \n")
+            chatbot_with_cookie[-1] = [chatbot_with_cookie[-1][0], f"[Local Message] 插件调用出错: \n\n{tb_str} \n"]
             yield from update_ui(chatbot=chatbot_with_cookie, history=history, msg=f'异常 {e}')  # 刷新界面
 
     return decorated
@@ -534,6 +557,17 @@ def on_file_uploaded(
     return chatbot, txt, txt2, cookies
 
 
+def generate_file_link(report_files:List[str]):
+    file_links = ""
+    for f in report_files:
+        file_links += (
+            f'<br/><a href="file={os.path.abspath(f)}" target="_blank">{f}</a>'
+        )
+    return file_links
+
+
+
+
 def on_report_generated(cookies:dict, files:List[str], chatbot:ChatBotWithCookies):
     if "files_to_promote" in cookies:
         report_files = cookies["files_to_promote"]
@@ -547,7 +581,7 @@ def on_report_generated(cookies:dict, files:List[str], chatbot:ChatBotWithCookie
         file_links += (
             f'<br/><a href="file={os.path.abspath(f)}" target="_blank">{f}</a>'
         )
-    chatbot.append(["报告如何远程获取？", f"报告已经添加到右侧“文件上传区”（可能处于折叠状态），请查收。{file_links}"])
+    chatbot.append(["报告如何远程获取？", f"报告已经添加到右侧“文件下载区”（可能处于折叠状态），请查收。{file_links}"])
     return cookies, report_files, chatbot
 
 
@@ -866,23 +900,6 @@ class ProxyNetworkActivate:
         return
 
 
-def objdump(obj, file="objdump.tmp"):
-    import pickle
-
-    with open(file, "wb+") as f:
-        pickle.dump(obj, f)
-    return
-
-
-def objload(file="objdump.tmp"):
-    import pickle, os
-
-    if not os.path.exists(file):
-        return
-    with open(file, "rb") as f:
-        return pickle.load(f)
-
-
 def Singleton(cls):
     """
     一个单实例装饰器
@@ -904,15 +921,18 @@ def get_pictures_list(path):
     return file_manifest
 
 
-def have_any_recent_upload_image_files(chatbot:ChatBotWithCookies):
+def have_any_recent_upload_image_files(chatbot:ChatBotWithCookies, pop:bool=False):
     _5min = 5 * 60
     if chatbot is None:
         return False, None  # chatbot is None
-    most_recent_uploaded = chatbot._cookies.get("most_recent_uploaded", None)
+    if pop:
+        most_recent_uploaded = chatbot._cookies.pop("most_recent_uploaded", None)
+    else:
+        most_recent_uploaded = chatbot._cookies.get("most_recent_uploaded", None)
+    # most_recent_uploaded 是一个放置最新上传图像的路径
     if not most_recent_uploaded:
         return False, None  # most_recent_uploaded is None
     if time.time() - most_recent_uploaded["time"] < _5min:
-        most_recent_uploaded = chatbot._cookies.get("most_recent_uploaded", None)
         path = most_recent_uploaded["path"]
         file_manifest = get_pictures_list(path)
         if len(file_manifest) == 0:

version

@@ -1,5 +1,5 @@
 {
-  "version": 3.74,
+  "version": 3.81,
   "show_feature": true,
-  "new_feature": "增加多用户文件鉴权验证提高安全性 <-> 优化oneapi接入方法 <-> 接入Cohere和月之暗面模型 <-> 简化挂载二级目录的步骤 <-> 支持Mermaid绘图库（让大模型绘制脑图）"
+  "new_feature": "支持更复杂的插件框架 <-> 上传文件时显示进度条 <-> 添加TTS语音输出（EdgeTTS和SoVits语音克隆） <-> Doc2x PDF翻译 <-> 添加回溯对话按钮"
 }