Fix fastapi version compat

TTS_TYPE = "EDGE_TTS"需要的依赖

.gitignore

@@ -153,3 +153,4 @@ media
 flagged
 request_llms/ChatGLM-6b-onnx-u8s8
 .pre-commit-config.yaml
+themes/common.js.min.*.js

README.md

@@ -1,7 +1,7 @@
-> [!IMPORTANT]  
-> 2024.1.18: 更新3.70版本，支持Mermaid绘图库（让大模型绘制脑图）  
-> 2024.1.17: 恭迎GLM4，全力支持Qwen、GLM、DeepseekCoder等国内中文大语言基座模型！  
-> 2024.1.17: 某些依赖包尚不兼容python 3.12，推荐python 3.11。  
+> [!IMPORTANT]
+> 2024.5.1: 加入Doc2x翻译PDF论文的功能，[查看详情](https://github.com/binary-husky/gpt_academic/wiki/Doc2x)  
+> 2024.4.30: 3.75版本引入Edge-TTS和SoVits语音克隆模块，[查看详情](https://www.bilibili.com/video/BV1Rp421S7tF/)  
+> 2024.3.11: 恭迎Claude3和Moonshot，全力支持Qwen、GLM、DeepseekCoder等中文大语言模型！  
 > 2024.1.17: 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>
@@ -87,6 +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">
@@ -253,8 +257,7 @@ P.S. 如果需要依赖Latex的插件功能，请见Wiki。另外，您也可以
 # Advanced Usage
 ### I：自定义新的便捷按钮（学术快捷键）
 
-任意文本编辑器打开`core_functional.py`，添加如下条目，然后重启程序。（如果按钮已存在，那么可以直接修改（前缀、后缀都已支持热修改），无需重启程序即可生效。）
-例如
+现在已可以通过UI中的`界面外观`菜单中的`自定义菜单`添加新的便捷按钮。如果需要在代码中定义，请使用任意文本编辑器打开`core_functional.py`，添加如下条目即可：
 
 ```python
 "超级英译中": {

check_proxy.py

@@ -47,7 +47,7 @@ def backup_and_download(current_version, remote_version):
     shutil.copytree('./', backup_dir, ignore=lambda x, y: ['history'])
     proxies = get_conf('proxies')
     try:    r = requests.get('https://github.com/binary-husky/chatgpt_academic/archive/refs/heads/master.zip', proxies=proxies, stream=True)
-    except: r = requests.get('https://public.gpt-academic.top/publish/master.zip', proxies=proxies, stream=True)
+    except: r = requests.get('https://public.agent-matrix.com/publish/master.zip', proxies=proxies, stream=True)
     zip_file_path = backup_dir+'/master.zip'
     with open(zip_file_path, 'wb+') as f:
         f.write(r.content)
@@ -81,7 +81,7 @@ def patch_and_restart(path):
     dir_util.copy_tree(path_new_version, './')
     print亮绿('代码已经更新，即将更新pip包依赖……')
     for i in reversed(range(5)): time.sleep(1); print(i)
-    try: 
+    try:
         import subprocess
         subprocess.check_call([sys.executable, '-m', 'pip', 'install', '-r', 'requirements.txt'])
     except:
@@ -113,7 +113,7 @@ def auto_update(raise_error=False):
         import json
         proxies = get_conf('proxies')
         try:    response = requests.get("https://raw.githubusercontent.com/binary-husky/chatgpt_academic/master/version", proxies=proxies, timeout=5)
-        except: response = requests.get("https://public.gpt-academic.top/publish/version", proxies=proxies, timeout=5)
+        except: response = requests.get("https://public.agent-matrix.com/publish/version", proxies=proxies, timeout=5)
         remote_json_data = json.loads(response.text)
         remote_version = remote_json_data['version']
         if remote_json_data["show_feature"]:
@@ -159,7 +159,7 @@ def warm_up_modules():
         enc.encode("模块预热", disallowed_special=())
         enc = model_info["gpt-4"]['tokenizer']
         enc.encode("模块预热", disallowed_special=())
-        
+
 def warm_up_vectordb():
     print('正在执行一些模块的预热 ...')
     from toolbox import ProxyNetworkActivate
@@ -167,7 +167,7 @@ def warm_up_vectordb():
         import nltk
         with ProxyNetworkActivate("Warmup_Modules"): nltk.download("punkt")
 
-        
+
 if __name__ == '__main__':
     import os
     os.environ['no_proxy'] = '*'  # 避免代理网络产生意外污染

colorful.py

@@ -3,7 +3,7 @@ from sys import stdout
 
 if platform.system()=="Linux":
     pass
-else: 
+else:
     from colorama import init
     init()
 

config.py

@@ -2,8 +2,8 @@
     以下所有配置也都支持利用环境变量覆写，环境变量配置格式见docker-compose.yml。
     读取优先级：环境变量 > config_private.py > config.py
     --- --- --- --- --- --- --- --- --- --- --- --- --- --- --- --- --- --- --- --- ---
-    All the following configurations also support using environment variables to override, 
-    and the environment variable configuration format can be seen in docker-compose.yml. 
+    All the following configurations also support using environment variables to override,
+    and the environment variable configuration format can be seen in docker-compose.yml.
     Configuration reading priority: environment variable > config_private.py > config.py
 """
 
@@ -30,11 +30,37 @@ if USE_PROXY:
 else:
     proxies = None
 
-# ------------------------------------ 以下配置可以优化体验, 但大部分场合下并不需要修改 ------------------------------------
+# [step 3]>> 模型选择是 (注意: LLM_MODEL是默认选中的模型, 它*必须*被包含在AVAIL_LLM_MODELS列表中 )
+LLM_MODEL = "gpt-3.5-turbo-16k" # 可选 ↓↓↓
+AVAIL_LLM_MODELS = ["gpt-4-1106-preview", "gpt-4-turbo-preview", "gpt-4-vision-preview", "gpt-4-turbo", "gpt-4-turbo-2024-04-09",
+                    "gpt-3.5-turbo-1106", "gpt-3.5-turbo-16k", "gpt-3.5-turbo", "azure-gpt-3.5",
+                    "gpt-4", "gpt-4-32k", "azure-gpt-4", "glm-4", "glm-4v", "glm-3-turbo",
+                    "gemini-pro", "chatglm3"
+                    ]
+# --- --- --- ---
+# P.S. 其他可用的模型还包括
+# AVAIL_LLM_MODELS = [
+#   "qianfan", "deepseekcoder",
+#   "spark", "sparkv2", "sparkv3", "sparkv3.5",
+#   "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"
+#   "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"
+# ]
+# --- --- --- ---
+# 此外，您还可以在接入one-api/vllm/ollama时，
+# 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)", "ollama-phi3(max_token=4096)"]
+# --- --- --- ---
+
+
+# --------------- 以下配置可以优化体验 ---------------
 
 # 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"}
+# 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", "http://localhost:11434/api/chat": "在这里填写您ollama的URL"}
 API_URL_REDIRECT = {}
 
 
@@ -66,7 +92,7 @@ LAYOUT = "LEFT-RIGHT"   # "LEFT-RIGHT"（左右布局） # "TOP-DOWN"（上下
 
 
 # 暗色模式 / 亮色模式
-DARK_MODE = True        
+DARK_MODE = True
 
 
 # 发送请求到OpenAI后，等待多久判定为超时
@@ -85,20 +111,6 @@ MAX_RETRY = 2
 DEFAULT_FN_GROUPS = ['对话', '编程', '学术', '智能体']
 
 
-# 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-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", "api2d-gpt-4",
-                    "gemini-pro", "chatglm3", "claude-2", "zhipuai"]
-# P.S. 其他可用的模型还包括 [
-# "moss", "qwen-turbo", "qwen-plus", "qwen-max"
-# "zhipuai", "qianfan", "deepseekcoder", "llama2", "qwen-local", "gpt-3.5-turbo-0613", 
-# "gpt-3.5-turbo-16k-0613",  "gpt-3.5-random", "api2d-gpt-3.5-turbo", 'api2d-gpt-3.5-turbo-16k',
-# "spark", "sparkv2", "sparkv3", "chatglm_onnx", "claude-1-100k", "claude-2", "internlm", "jittorllms_pangualpha", "jittorllms_llama"
-# ]
-
-
 # 定义界面上“询问多个GPT模型”插件应该使用哪些模型，请从AVAIL_LLM_MODELS中选择，并在不同模型之间用`&`间隔，例如"gpt-3.5-turbo&chatglm3&azure-gpt-4"
 MULTI_QUERY_LLM_MODELS = "gpt-3.5-turbo&chatglm3"
 
@@ -127,6 +139,7 @@ CHATGLM_PTUNING_CHECKPOINT = "" # 例如"/home/hmp/ChatGLM2-6B/ptuning/output/6b
 LOCAL_MODEL_DEVICE = "cpu" # 可选 "cuda"
 LOCAL_MODEL_QUANT = "FP16" # 默认 "FP16" "INT4" 启用量化INT4版本 "INT8" 启用量化INT8版本
 
+
 # 设置gradio的并行线程数（不需要修改）
 CONCURRENT_COUNT = 100
 
@@ -144,7 +157,8 @@ ADD_WAIFU = False
 AUTHENTICATION = []
 
 
-# 如果需要在二级路径下运行（常规情况下，不要修改!!）（需要配合修改main.py才能生效!）
+# 如果需要在二级路径下运行（常规情况下，不要修改!!）
+# （举例 CUSTOM_PATH = "/gpt_academic"，可以让软件运行在 http://ip:port/gpt_academic/ 下。）
 CUSTOM_PATH = "/"
 
 
@@ -158,7 +172,7 @@ API_ORG = ""
 
 
 # 如果需要使用Slack Claude，使用教程详情见 request_llms/README.md
-SLACK_CLAUDE_BOT_ID = ''   
+SLACK_CLAUDE_BOT_ID = ''
 SLACK_CLAUDE_USER_TOKEN = ''
 
 
@@ -172,14 +186,8 @@ AZURE_ENGINE = "填入你亲手写的部署名"            # 读 docs\use_azure.
 AZURE_CFG_ARRAY = {}
 
 
-# 使用Newbing (不推荐使用，未来将删除)
-NEWBING_STYLE = "creative"  # ["creative", "balanced", "precise"]
-NEWBING_COOKIES = """
-put your new bing cookies here
-"""
-
-
-# 阿里云实时语音识别 配置难度较高 仅建议高手用户使用 参考 https://github.com/binary-husky/gpt_academic/blob/master/docs/use_audio.md
+# 阿里云实时语音识别 配置难度较高
+# 参考 https://github.com/binary-husky/gpt_academic/blob/master/docs/use_audio.md
 ENABLE_AUDIO = False
 ALIYUN_TOKEN=""     # 例如 f37f30e0f9934c34a992f6f64f7eba4f
 ALIYUN_APPKEY=""    # 例如 RoPlZrM88DnAFkZK
@@ -187,6 +195,12 @@ 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 = "DISABLE" # LOCAL / 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"
@@ -195,19 +209,30 @@ XFYUN_API_KEY = "aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa"
 
 # 接入智谱大模型
 ZHIPUAI_API_KEY = ""
-ZHIPUAI_MODEL = "glm-4" # 可选 "glm-3-turbo" "glm-4"
-
-
-# # 火山引擎YUNQUE大模型
-# YUNQUE_SECRET_KEY = ""
-# YUNQUE_ACCESS_KEY = ""
-# YUNQUE_MODEL = ""
+ZHIPUAI_MODEL = "" # 此选项已废弃，不再需要填写
 
 
 # Claude API KEY
 ANTHROPIC_API_KEY = ""
 
 
+# 月之暗面 API KEY
+MOONSHOT_API_KEY = ""
+
+
+# 零一万物(Yi Model) API KEY
+YIMODEL_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 = ""
 
@@ -224,8 +249,8 @@ HUGGINGFACE_ACCESS_TOKEN = "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"
 # 获取方法：复制以下空间https://huggingface.co/spaces/qingxu98/grobid，设为public，然后GROBID_URL = "https://(你的hf用户名如qingxu98)-(你的填写的空间名如grobid).hf.space"
 GROBID_URLS = [
     "https://qingxu98-grobid.hf.space","https://qingxu98-grobid2.hf.space","https://qingxu98-grobid3.hf.space",
-    "https://qingxu98-grobid4.hf.space","https://qingxu98-grobid5.hf.space", "https://qingxu98-grobid6.hf.space", 
-    "https://qingxu98-grobid7.hf.space", "https://qingxu98-grobid8.hf.space", 
+    "https://qingxu98-grobid4.hf.space","https://qingxu98-grobid5.hf.space", "https://qingxu98-grobid6.hf.space",
+    "https://qingxu98-grobid7.hf.space", "https://qingxu98-grobid8.hf.space",
 ]
 
 
@@ -246,7 +271,7 @@ 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
-WHEN_TO_USE_PROXY = ["Download_LLM", "Download_Gradio_Theme", "Connect_Grobid", 
+WHEN_TO_USE_PROXY = ["Download_LLM", "Download_Gradio_Theme", "Connect_Grobid",
                      "Warmup_Modules", "Nougat_Download", "AutoGen"]
 
 
@@ -261,7 +286,11 @@ PLUGIN_HOT_RELOAD = False
 # 自定义按钮的最大数量限制
 NUM_CUSTOM_BASIC_BTN = 4
 
+
+
 """
+--------------- 配置关联关系说明 ---------------
+
 在线大模型配置关联关系示意图
 │
 ├── "gpt-3.5-turbo" 等openai模型
@@ -285,7 +314,7 @@ NUM_CUSTOM_BASIC_BTN = 4
 │   ├── XFYUN_API_SECRET
 │   └── XFYUN_API_KEY
 │
-├── "claude-1-100k" 等claude模型
+├── "claude-3-opus-20240229" 等claude模型
 │   └── ANTHROPIC_API_KEY
 │
 ├── "stack-claude"
@@ -297,9 +326,11 @@ NUM_CUSTOM_BASIC_BTN = 4
 │   ├── BAIDU_CLOUD_API_KEY
 │   └── BAIDU_CLOUD_SECRET_KEY
 │
-├── "zhipuai" 智谱AI大模型chatglm_turbo
-│   ├── ZHIPUAI_API_KEY
-│   └── ZHIPUAI_MODEL
+├── "glm-4", "glm-3-turbo", "zhipuai" 智谱AI大模型
+│   └── ZHIPUAI_API_KEY
+│
+├── "yi-34b-chat-0205", "yi-34b-chat-200k" 等零一万物(Yi Model)大模型
+│   └── YIMODEL_API_KEY
 │
 ├── "qwen-turbo" 等通义千问大模型
 │   └──  DASHSCOPE_API_KEY
@@ -307,11 +338,12 @@ NUM_CUSTOM_BASIC_BTN = 4
 ├── "Gemini"
 │   └──  GEMINI_API_KEY
 │
-└── "newbing" Newbing接口不再稳定，不推荐使用
-    ├── NEWBING_STYLE
-    └── NEWBING_COOKIES
+└── "one-api-...(max_token=...)" 用一种更方便的方式接入one-api多模型管理界面
+    ├── AVAIL_LLM_MODELS
+    ├── API_KEY
+    └── API_URL_REDIRECT
+
 
-    
 本地大模型示意图
 │
 ├── "chatglm3"
@@ -351,6 +383,9 @@ NUM_CUSTOM_BASIC_BTN = 4
 │   └── ALIYUN_SECRET
 │
 └── PDF文档精准解析
-    └── GROBID_URLS
+    ├── GROBID_URLS
+    ├── MATHPIX_APPID
+    └── MATHPIX_APPKEY
+
 
 """

core_functional.py

@@ -34,16 +34,16 @@ def get_core_functions():
             # [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,
         },
-        
-        
+
+
         "总结绘制脑图": {
             # 前缀，会被加在你的输入之前。例如，用来描述你的要求，例如翻译、解释代码、润色等等
-            "Prefix":   r"",
+            "Prefix":   '''"""\n\n''',
             # 后缀，会被加在你的输入之后。例如，配合前缀可以把你的输入内容用引号圈起来
             "Suffix":
                 # dedent() 函数用于去除多行字符串的缩进
-                dedent("\n"+r'''
-                    ==============================
+                dedent("\n\n"+r'''
+                    """
 
                     使用mermaid flowchart对以上文本进行总结，概括上述段落的内容以及内在逻辑关系，例如：
 
@@ -57,15 +57,15 @@ def get_core_functions():
                         C --> |"箭头名2"| F["节点名6"]
                     ```
 
-                    警告：
+                    注意：
                     （1）使用中文
                     （2）节点名字使用引号包裹，如["Laptop"]
                     （3）`|` 和 `"`之间不要存在空格
                     （4）根据情况选择flowchart LR（从左到右）或者flowchart TD（从上到下）
                 '''),
         },
-        
-        
+
+
         "查找语法错误": {
             "Prefix":   r"Help me ensure that the grammar and the spelling is correct. "
                         r"Do not try to polish the text, if no mistake is found, tell me that this paragraph is good. "
@@ -85,14 +85,14 @@ def get_core_functions():
             "Suffix":   r"",
             "PreProcess": clear_line_break,    # 预处理：清除换行符
         },
-        
-        
+
+
         "中译英": {
             "Prefix":   r"Please translate following sentence to English:" + "\n\n",
             "Suffix":   r"",
         },
-        
-        
+
+
         "学术英中互译": {
             "Prefix":   build_gpt_academic_masked_string_langbased(
                             text_show_chinese=
@@ -112,29 +112,29 @@ def get_core_functions():
                         ) + "\n\n",
             "Suffix":   r"",
         },
-        
-        
+
+
         "英译中": {
             "Prefix":   r"翻译成地道的中文：" + "\n\n",
             "Suffix":   r"",
             "Visible":  False,
         },
-        
-        
+
+
         "找图片": {
             "Prefix":   r"我需要你找一张网络图片。使用Unsplash API(https://source.unsplash.com/960x640/?<英语关键词>)获取图片URL，"
                         r"然后请使用Markdown格式封装，并且不要有反斜线，不要用代码块。现在，请按以下描述给我发送图片：" + "\n\n",
             "Suffix":   r"",
             "Visible":  False,
         },
-        
-        
+
+
         "解释代码": {
             "Prefix":   r"请解释以下代码：" + "\n```\n",
             "Suffix":   "\n```\n",
         },
-        
-        
+
+
         "参考文献转Bib": {
             "Prefix":   r"Here are some bibliography items, please transform them into bibtex style."
                         r"Note that, reference styles maybe more than one kind, you should transform each item correctly."

crazy_functional.py

@@ -27,7 +27,7 @@ def get_crazy_functions():
     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.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批量翻译 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
@@ -70,11 +70,11 @@ def get_crazy_functions():
             "Info": "清除所有缓存文件，谨慎操作 | 不需要输入参数",
             "Function": HotReload(清除缓存),
         },
-        "生成多种Mermaid图表(从当前对话或文件(.pdf/.md)中生产图表）": {
+        "生成多种Mermaid图表(从当前对话或路径(.pdf/.md/.docx)中生产图表）": {
             "Group": "对话",
             "Color": "stop",
             "AsButton": False,
-            "Info" : "基于当前对话或PDF生成多种Mermaid图表,图表类型由模型判断",
+            "Info" : "基于当前对话或文件生成多种Mermaid图表,图表类型由模型判断",
             "Function": HotReload(生成多种Mermaid图表),
             "AdvancedArgs": True,
             "ArgsReminder": "请输入图类型对应的数字,不输入则为模型自行判断:1-流程图,2-序列图,3-类图,4-饼图,5-甘特图,6-状态图,7-实体关系图,8-象限提示图,9-思维导图",
@@ -532,8 +532,9 @@ def get_crazy_functions():
         print("Load function plugin failed")
 
     try:
-        from crazy_functions.Latex输出PDF结果 import Latex英文纠错加PDF对比
-        from crazy_functions.Latex输出PDF结果 import Latex翻译中文并重新编译PDF
+        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(
             {
@@ -550,9 +551,9 @@ def get_crazy_functions():
                     "Color": "stop",
                     "AsButton": False,
                     "AdvancedArgs": True,
-                    "ArgsReminder": "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。 "
-                    + "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: "
-                    + 'If the term "agent" is used in this section, it should be translated to "智能体". ',
+                    "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),
                 },
@@ -561,11 +562,22 @@ def get_crazy_functions():
                     "Color": "stop",
                     "AsButton": False,
                     "AdvancedArgs": True,
-                    "ArgsReminder": "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。 "
-                    + "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: "
-                    + 'If the term "agent" is used in this section, it should be translated to "智能体". ',
+                    "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)
                 }
             }
         )

crazy_functions/CodeInterpreter.py

@@ -1,232 +0,0 @@
-from collections.abc import Callable, Iterable, Mapping
-from typing import Any
-from toolbox import CatchException, update_ui, gen_time_str, trimmed_format_exc
-from toolbox import promote_file_to_downloadzone, get_log_folder
-from .crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
-from .crazy_utils import input_clipping, try_install_deps
-from multiprocessing import Process, Pipe
-import os
-import time
-
-templete = """
-```python
-import ...  # Put dependencies here, e.g. import numpy as np
-
-class TerminalFunction(object): # Do not change the name of the class, The name of the class must be `TerminalFunction`
-
-    def run(self, path):    # The name of the function must be `run`, it takes only a positional argument.
-        # rewrite the function you have just written here 
-        ...
-        return generated_file_path
-```
-"""
-
-def inspect_dependency(chatbot, history):
-    yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
-    return True
-
-def get_code_block(reply):
-    import re
-    pattern = r"```([\s\S]*?)```" # regex pattern to match code blocks
-    matches = re.findall(pattern, reply) # find all code blocks in text
-    if len(matches) == 1: 
-        return matches[0].strip('python') #  code block
-    for match in matches:
-        if 'class TerminalFunction' in match:
-            return match.strip('python') #  code block
-    raise RuntimeError("GPT is not generating proper code.")
-
-def gpt_interact_multi_step(txt, file_type, llm_kwargs, chatbot, history):
-    # 输入
-    prompt_compose = [
-        f'Your job:\n'
-        f'1. write a single Python function, which takes a path of a `{file_type}` file as the only argument and returns a `string` containing the result of analysis or the path of generated files. \n',
-        f"2. You should write this function to perform following task: " + txt + "\n",
-        f"3. Wrap the output python function with markdown codeblock."
-    ]
-    i_say = "".join(prompt_compose)
-    demo = []
-
-    # 第一步
-    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=demo, 
-        sys_prompt= r"You are a programmer."
-    )
-    history.extend([i_say, gpt_say])
-    yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 界面更新
-
-    # 第二步
-    prompt_compose = [
-        "If previous stage is successful, rewrite the function you have just written to satisfy following templete: \n",
-        templete
-    ]
-    i_say = "".join(prompt_compose); inputs_show_user = "If previous stage is successful, rewrite the function you have just written to satisfy executable templete. "
-    gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
-        inputs=i_say, inputs_show_user=inputs_show_user, 
-        llm_kwargs=llm_kwargs, chatbot=chatbot, history=history, 
-        sys_prompt= r"You are a programmer."
-    )
-    code_to_return = gpt_say
-    history.extend([i_say, gpt_say])
-    yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 界面更新
-    
-    # # 第三步
-    # i_say = "Please list to packages to install to run the code above. Then show me how to use `try_install_deps` function to install them."
-    # i_say += 'For instance. `try_install_deps(["opencv-python", "scipy", "numpy"])`'
-    # installation_advance = yield from request_gpt_model_in_new_thread_with_ui_alive(
-    #     inputs=i_say, inputs_show_user=inputs_show_user, 
-    #     llm_kwargs=llm_kwargs, chatbot=chatbot, history=history, 
-    #     sys_prompt= r"You are a programmer."
-    # )
-    # # # 第三步  
-    # i_say = "Show me how to use `pip` to install packages to run the code above. "
-    # i_say += 'For instance. `pip install -r opencv-python scipy numpy`'
-    # installation_advance = 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= r"You are a programmer."
-    # )
-    installation_advance = ""
-    
-    return code_to_return, installation_advance, txt, file_type, llm_kwargs, chatbot, history
-
-def make_module(code):
-    module_file = 'gpt_fn_' + gen_time_str().replace('-','_')
-    with open(f'{get_log_folder()}/{module_file}.py', 'w', encoding='utf8') as f:
-        f.write(code)
-
-    def get_class_name(class_string):
-        import re
-        # Use regex to extract the class name
-        class_name = re.search(r'class (\w+)\(', class_string).group(1)
-        return class_name
-
-    class_name = get_class_name(code)
-    return f"{get_log_folder().replace('/', '.')}.{module_file}->{class_name}"
-
-def init_module_instance(module):
-    import importlib
-    module_, class_ = module.split('->')
-    init_f = getattr(importlib.import_module(module_), class_)
-    return init_f()
-
-def for_immediate_show_off_when_possible(file_type, fp, chatbot):
-    if file_type in ['png', 'jpg']:
-        image_path = os.path.abspath(fp)
-        chatbot.append(['这是一张图片, 展示如下:',  
-            f'本地文件地址: <br/>`{image_path}`<br/>'+
-            f'本地文件预览: <br/><div align="center"><img src="file={image_path}"></div>'
-        ])
-    return chatbot
-
-def subprocess_worker(instance, file_path, return_dict):
-    return_dict['result'] = instance.run(file_path)
-
-def have_any_recent_upload_files(chatbot):
-    _5min = 5 * 60
-    if not chatbot: return False    # chatbot is None
-    most_recent_uploaded = chatbot._cookies.get("most_recent_uploaded", None)
-    if not most_recent_uploaded: return False   # most_recent_uploaded is None
-    if time.time() - most_recent_uploaded["time"] < _5min: return True # most_recent_uploaded is new
-    else: return False  # most_recent_uploaded is too old
-
-def get_recent_file_prompt_support(chatbot):
-    most_recent_uploaded = chatbot._cookies.get("most_recent_uploaded", None)
-    path = most_recent_uploaded['path']
-    return path
-
-@CatchException
-def 虚空终端CodeInterpreter(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
-    """
-    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
-    plugin_kwargs   插件模型的参数，暂时没有用武之地
-    chatbot         聊天显示框的句柄，用于显示给用户
-    history         聊天历史，前情提要
-    system_prompt   给gpt的静默提醒
-    user_request    当前用户的请求信息（IP地址等）
-    """
-    raise NotImplementedError
-
-    # 清空历史，以免输入溢出
-    history = []; clear_file_downloadzone(chatbot)
-
-    # 基本信息：功能、贡献者
-    chatbot.append([
-        "函数插件功能？",
-        "CodeInterpreter开源版, 此插件处于开发阶段, 建议暂时不要使用, 插件初始化中 ..."
-    ])
-    yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
-
-    if have_any_recent_upload_files(chatbot):
-        file_path = get_recent_file_prompt_support(chatbot)
-    else:
-        chatbot.append(["文件检索", "没有发现任何近期上传的文件。"])
-        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
-
-    # 读取文件
-    if ("recently_uploaded_files" in plugin_kwargs) and (plugin_kwargs["recently_uploaded_files"] == ""): plugin_kwargs.pop("recently_uploaded_files")
-    recently_uploaded_files = plugin_kwargs.get("recently_uploaded_files", None)
-    file_path = recently_uploaded_files[-1]
-    file_type = file_path.split('.')[-1]
-
-    # 粗心检查
-    if is_the_upload_folder(txt):
-        chatbot.append([
-            "...",
-            f"请在输入框内填写需求，然后再次点击该插件（文件路径 {file_path} 已经被记忆）"
-        ])
-        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
-        return
-    
-    # 开始干正事
-    for j in range(5):  # 最多重试5次
-        try:
-            code, installation_advance, txt, file_type, llm_kwargs, chatbot, history = \
-                yield from gpt_interact_multi_step(txt, file_type, llm_kwargs, chatbot, history)
-            code = get_code_block(code)
-            res = make_module(code)
-            instance = init_module_instance(res)
-            break
-        except Exception as e:
-            chatbot.append([f"第{j}次代码生成尝试，失败了", f"错误追踪\n```\n{trimmed_format_exc()}\n```\n"])
-            yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
-
-    # 代码生成结束, 开始执行
-    try:
-        import multiprocessing
-        manager = multiprocessing.Manager()
-        return_dict = manager.dict()
-
-        p = multiprocessing.Process(target=subprocess_worker, args=(instance, file_path, return_dict))
-        # only has 10 seconds to run
-        p.start(); p.join(timeout=10)
-        if p.is_alive(): p.terminate(); p.join()
-        p.close()
-        res = return_dict['result']
-        # res = instance.run(file_path)
-    except Exception as e:
-        chatbot.append(["执行失败了", f"错误追踪\n```\n{trimmed_format_exc()}\n```\n"])
-        # chatbot.append(["如果是缺乏依赖，请参考以下建议", installation_advance])
-        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
-        return
-
-    # 顺利完成，收尾
-    res = str(res)
-    if os.path.exists(res):
-        chatbot.append(["执行成功了，结果是一个有效文件", "结果：" + res])
-        new_file_path = promote_file_to_downloadzone(res, chatbot=chatbot)
-        chatbot = for_immediate_show_off_when_possible(file_type, new_file_path, chatbot)
-        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 界面更新
-    else:
-        chatbot.append(["执行成功了，结果是一个字符串", "结果：" + res])
-        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 界面更新   
-
-"""
-测试：
-    裁剪图像，保留下半部分
-    交换图像的蓝色通道和红色通道
-    将图像转为灰度图像
-    将csv文件转excel表格
-"""

crazy_functions/Latex全文润色.py

@@ -46,7 +46,7 @@ class PaperFileGroup():
                 manifest.append(path + '.polish.tex')
                 f.write(res)
         return manifest
-    
+
     def zip_result(self):
         import os, time
         folder = os.path.dirname(self.file_paths[0])
@@ -59,7 +59,7 @@ def 多文件润色(file_manifest, project_folder, llm_kwargs, plugin_kwargs, ch
     from .crazy_utils import request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency
 
 
-    #  <-------- 读取Latex文件，删除其中的所有注释 ----------> 
+    #  <-------- 读取Latex文件，删除其中的所有注释 ---------->
     pfg = PaperFileGroup()
 
     for index, fp in enumerate(file_manifest):
@@ -73,31 +73,31 @@ def 多文件润色(file_manifest, project_folder, llm_kwargs, plugin_kwargs, ch
             pfg.file_paths.append(fp)
             pfg.file_contents.append(clean_tex_content)
 
-    #  <-------- 拆分过长的latex文件 ----------> 
+    #  <-------- 拆分过长的latex文件 ---------->
     pfg.run_file_split(max_token_limit=1024)
     n_split = len(pfg.sp_file_contents)
 
 
-    #  <-------- 多线程润色开始 ----------> 
+    #  <-------- 多线程润色开始 ---------->
     if language == 'en':
         if mode == 'polish':
-            inputs_array = ["Below is a section from an academic paper, polish this section to meet the academic standard, " + 
-                            "improve the grammar, clarity and overall readability, do not modify any latex command such as \section, \cite and equations:" + 
+            inputs_array = [r"Below is a section from an academic paper, polish this section to meet the academic standard, " +
+                            r"improve the grammar, clarity and overall readability, do not modify any latex command such as \section, \cite and equations:" +
                             f"\n\n{frag}" for frag in pfg.sp_file_contents]
         else:
-            inputs_array = [r"Below is a section from an academic paper, proofread this section." + 
-                            r"Do not modify any latex command such as \section, \cite, \begin, \item and equations. " + 
-                            r"Answer me only with the revised text:" + 
+            inputs_array = [r"Below is a section from an academic paper, proofread this section." +
+                            r"Do not modify any latex command such as \section, \cite, \begin, \item and equations. " +
+                            r"Answer me only with the revised text:" +
                         f"\n\n{frag}" for frag in pfg.sp_file_contents]
         inputs_show_user_array = [f"Polish {f}" for f in pfg.sp_file_tag]
         sys_prompt_array = ["You are a professional academic paper writer." for _ in range(n_split)]
     elif language == 'zh':
         if mode == 'polish':
-            inputs_array = [f"以下是一篇学术论文中的一段内容，请将此部分润色以满足学术标准，提高语法、清晰度和整体可读性，不要修改任何LaTeX命令，例如\section，\cite和方程式：" + 
+            inputs_array = [r"以下是一篇学术论文中的一段内容，请将此部分润色以满足学术标准，提高语法、清晰度和整体可读性，不要修改任何LaTeX命令，例如\section，\cite和方程式：" +
                             f"\n\n{frag}" for frag in pfg.sp_file_contents]
         else:
-            inputs_array = [f"以下是一篇学术论文中的一段内容，请对这部分内容进行语法矫正。不要修改任何LaTeX命令，例如\section，\cite和方程式：" + 
-                            f"\n\n{frag}" for frag in pfg.sp_file_contents] 
+            inputs_array = [r"以下是一篇学术论文中的一段内容，请对这部分内容进行语法矫正。不要修改任何LaTeX命令，例如\section，\cite和方程式：" +
+                            f"\n\n{frag}" for frag in pfg.sp_file_contents]
         inputs_show_user_array = [f"润色 {f}" for f in pfg.sp_file_tag]
         sys_prompt_array=["你是一位专业的中文学术论文作家。" for _ in range(n_split)]
 
@@ -113,7 +113,7 @@ def 多文件润色(file_manifest, project_folder, llm_kwargs, plugin_kwargs, ch
         scroller_max_len = 80
     )
 
-    #  <-------- 文本碎片重组为完整的tex文件，整理结果为压缩包 ----------> 
+    #  <-------- 文本碎片重组为完整的tex文件，整理结果为压缩包 ---------->
     try:
         pfg.sp_file_result = []
         for i_say, gpt_say in zip(gpt_response_collection[0::2], gpt_response_collection[1::2]):
@@ -124,7 +124,7 @@ def 多文件润色(file_manifest, project_folder, llm_kwargs, plugin_kwargs, ch
     except:
         print(trimmed_format_exc())
 
-    #  <-------- 整理结果，退出 ----------> 
+    #  <-------- 整理结果，退出 ---------->
     create_report_file_name = time.strftime("%Y-%m-%d-%H-%M-%S", time.localtime()) + f"-chatgpt.polish.md"
     res = write_history_to_file(gpt_response_collection, file_basename=create_report_file_name)
     promote_file_to_downloadzone(res, chatbot=chatbot)

crazy_functions/Latex全文翻译.py

@@ -39,7 +39,7 @@ def 多文件翻译(file_manifest, project_folder, llm_kwargs, plugin_kwargs, ch
     import time, os, re
     from .crazy_utils import request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency
 
-    #  <-------- 读取Latex文件，删除其中的所有注释 ----------> 
+    #  <-------- 读取Latex文件，删除其中的所有注释 ---------->
     pfg = PaperFileGroup()
 
     for index, fp in enumerate(file_manifest):
@@ -53,11 +53,11 @@ def 多文件翻译(file_manifest, project_folder, llm_kwargs, plugin_kwargs, ch
             pfg.file_paths.append(fp)
             pfg.file_contents.append(clean_tex_content)
 
-    #  <-------- 拆分过长的latex文件 ----------> 
+    #  <-------- 拆分过长的latex文件 ---------->
     pfg.run_file_split(max_token_limit=1024)
     n_split = len(pfg.sp_file_contents)
 
-    #  <-------- 抽取摘要 ----------> 
+    #  <-------- 抽取摘要 ---------->
     # if language == 'en':
     #     abs_extract_inputs = f"Please write an abstract for this paper"
 
@@ -70,14 +70,14 @@ def 多文件翻译(file_manifest, project_folder, llm_kwargs, plugin_kwargs, ch
     #     sys_prompt="Your job is to collect information from materials。",
     # )
 
-    #  <-------- 多线程润色开始 ----------> 
+    #  <-------- 多线程润色开始 ---------->
     if language == 'en->zh':
-        inputs_array = ["Below is a section from an English academic paper, translate it into Chinese, do not modify any latex command such as \section, \cite and equations:" + 
+        inputs_array = ["Below is a section from an English academic paper, translate it into Chinese, do not modify any latex command such as \section, \cite and equations:" +
                         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)]
     elif language == 'zh->en':
-        inputs_array = [f"Below is a section from a Chinese academic paper, translate it into English, do not modify any latex command such as \section, \cite and equations:" + 
+        inputs_array = [f"Below is a section from a Chinese academic paper, translate it into English, do not modify any latex command such as \section, \cite and equations:" +
                         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)]
@@ -93,7 +93,7 @@ def 多文件翻译(file_manifest, project_folder, llm_kwargs, plugin_kwargs, ch
         scroller_max_len = 80
     )
 
-    #  <-------- 整理结果，退出 ----------> 
+    #  <-------- 整理结果，退出 ---------->
     create_report_file_name = time.strftime("%Y-%m-%d-%H-%M-%S", time.localtime()) + f"-chatgpt.polish.md"
     res = write_history_to_file(gpt_response_collection, create_report_file_name)
     promote_file_to_downloadzone(res, chatbot=chatbot)

crazy_functions/Latex输出PDF.py

@@ -0,0 +1,543 @@
+from toolbox import update_ui, trimmed_format_exc, get_conf, get_log_folder, promote_file_to_downloadzone, check_repeat_upload, map_file_to_sha256
+from toolbox import CatchException, report_exception, update_ui_lastest_msg, zip_result, gen_time_str
+from functools import partial
+import glob, os, requests, time, json, tarfile
+
+pj = os.path.join
+ARXIV_CACHE_DIR = os.path.expanduser(f"~/arxiv_cache/")
+
+
+# =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=- 工具函数 =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-
+# 专业词汇声明  = 'If the term "agent" is used in this section, it should be translated to "智能体". '
+def switch_prompt(pfg, mode, more_requirement):
+    """
+    Generate prompts and system prompts based on the mode for proofreading or translating.
+    Args:
+    - pfg: Proofreader or Translator instance.
+    - mode: A string specifying the mode, either 'proofread' or 'translate_zh'.
+
+    Returns:
+    - inputs_array: A list of strings containing prompts for users to respond to.
+    - sys_prompt_array: A list of strings containing prompts for system prompts.
+    """
+    n_split = len(pfg.sp_file_contents)
+    if mode == 'proofread_en':
+        inputs_array = [r"Below is a section from an academic paper, proofread this section." +
+                        r"Do not modify any latex command such as \section, \cite, \begin, \item and equations. " + more_requirement +
+                        r"Answer me only with the revised text:" +
+                        f"\n\n{frag}" for frag in pfg.sp_file_contents]
+        sys_prompt_array = ["You are a professional academic paper writer." for _ in range(n_split)]
+    elif mode == 'translate_zh':
+        inputs_array = [
+            r"Below is a section from an English academic paper, translate it into Chinese. " + more_requirement +
+            r"Do not modify any latex command such as \section, \cite, \begin, \item and equations. " +
+            r"Answer me only with the translated text:" +
+            f"\n\n{frag}" for frag in pfg.sp_file_contents]
+        sys_prompt_array = ["You are a professional translator." for _ in range(n_split)]
+    else:
+        assert False, "未知指令"
+    return inputs_array, sys_prompt_array
+
+
+def desend_to_extracted_folder_if_exist(project_folder):
+    """
+    Descend into the extracted folder if it exists, otherwise return the original folder.
+
+    Args:
+    - project_folder: A string specifying the folder path.
+
+    Returns:
+    - A string specifying the path to the extracted folder, or the original folder if there is no extracted folder.
+    """
+    maybe_dir = [f for f in glob.glob(f'{project_folder}/*') if os.path.isdir(f)]
+    if len(maybe_dir) == 0: return project_folder
+    if maybe_dir[0].endswith('.extract'): return maybe_dir[0]
+    return project_folder
+
+
+def move_project(project_folder, arxiv_id=None):
+    """
+    Create a new work folder and copy the project folder to it.
+
+    Args:
+    - project_folder: A string specifying the folder path of the project.
+
+    Returns:
+    - A string specifying the path to the new work folder.
+    """
+    import shutil, time
+    time.sleep(2)  # avoid time string conflict
+    if arxiv_id is not None:
+        new_workfolder = pj(ARXIV_CACHE_DIR, arxiv_id, 'workfolder')
+    else:
+        new_workfolder = f'{get_log_folder()}/{gen_time_str()}'
+    try:
+        shutil.rmtree(new_workfolder)
+    except:
+        pass
+
+    # align subfolder if there is a folder wrapper
+    items = glob.glob(pj(project_folder, '*'))
+    items = [item for item in items if os.path.basename(item) != '__MACOSX']
+    if len(glob.glob(pj(project_folder, '*.tex'))) == 0 and len(items) == 1:
+        if os.path.isdir(items[0]): project_folder = items[0]
+
+    shutil.copytree(src=project_folder, dst=new_workfolder)
+    return new_workfolder
+
+
+def arxiv_download(chatbot, history, txt, allow_cache=True):
+    def check_cached_translation_pdf(arxiv_id):
+        translation_dir = pj(ARXIV_CACHE_DIR, arxiv_id, 'translation')
+        if not os.path.exists(translation_dir):
+            os.makedirs(translation_dir)
+        target_file = pj(translation_dir, 'translate_zh.pdf')
+        if os.path.exists(target_file):
+            promote_file_to_downloadzone(target_file, rename_file=None, chatbot=chatbot)
+            target_file_compare = pj(translation_dir, 'comparison.pdf')
+            if os.path.exists(target_file_compare):
+                promote_file_to_downloadzone(target_file_compare, rename_file=None, chatbot=chatbot)
+            return target_file
+        return False
+
+    def is_float(s):
+        try:
+            float(s)
+            return 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
+        txt = 'https://arxiv.org/abs/' + txt[:10]
+
+    if not txt.startswith('https://arxiv.org'):
+        return txt, None    # 是本地文件，跳过下载
+
+    # <-------------- inspect format ------------->
+    chatbot.append([f"检测到arxiv文档连接", '尝试下载 ...'])
+    yield from update_ui(chatbot=chatbot, history=history)
+    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
+        return msg, None
+    # <-------------- set format ------------->
+    arxiv_id = url_.split('/abs/')[-1]
+    if 'v' in arxiv_id: arxiv_id = arxiv_id[:10]
+    cached_translation_pdf = check_cached_translation_pdf(arxiv_id)
+    if cached_translation_pdf and allow_cache: return cached_translation_pdf, arxiv_id
+
+    url_tar = url_.replace('/abs/', '/e-print/')
+    translation_dir = pj(ARXIV_CACHE_DIR, arxiv_id, 'e-print')
+    extract_dst = pj(ARXIV_CACHE_DIR, arxiv_id, 'extract')
+    os.makedirs(translation_dir, exist_ok=True)
+
+    # <-------------- download arxiv source file ------------->
+    dst = pj(translation_dir, arxiv_id + '.tar')
+    if os.path.exists(dst):
+        yield from update_ui_lastest_msg("调用缓存", chatbot=chatbot, history=history)  # 刷新界面
+    else:
+        yield from update_ui_lastest_msg("开始下载", chatbot=chatbot, history=history)  # 刷新界面
+        proxies = get_conf('proxies')
+        r = requests.get(url_tar, proxies=proxies)
+        with open(dst, 'wb+') as f:
+            f.write(r.content)
+    # <-------------- extract file ------------->
+    yield from update_ui_lastest_msg("下载完成", chatbot=chatbot, history=history)  # 刷新界面
+    from toolbox import extract_archive
+    extract_archive(file_path=dst, dest_dir=extract_dst)
+    return extract_dst, arxiv_id
+
+
+def pdf2tex_project(pdf_file_path):
+    # Mathpix API credentials
+    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
+    options = {
+        "conversion_formats": {"tex.zip": True},
+        "math_inline_delimiters": ["$", "$"],
+        "rm_spaces": True
+    }
+
+    response = requests.post(url="https://api.mathpix.com/v3/pdf",
+                             headers=headers,
+                             data={"options_json": json.dumps(options)},
+                             files={"file": open(pdf_file_path, "rb")})
+
+    if response.ok:
+        pdf_id = response.json()["pdf_id"]
+        print(f"PDF processing initiated. PDF ID: {pdf_id}")
+
+        # Step 2: Check processing status
+        while True:
+            conversion_response = requests.get(f"https://api.mathpix.com/v3/pdf/{pdf_id}", headers=headers)
+            conversion_data = conversion_response.json()
+
+            if conversion_data["status"] == "completed":
+                print("PDF processing completed.")
+                break
+            elif conversion_data["status"] == "error":
+                print("Error occurred during processing.")
+            else:
+                print(f"Processing status: {conversion_data['status']}")
+                time.sleep(5)  # wait for a few seconds before checking again
+
+        # Step 3: Save results to local files
+        output_dir = os.path.join(os.path.dirname(pdf_file_path), 'mathpix_output')
+        if not os.path.exists(output_dir):
+            os.makedirs(output_dir)
+
+        url = f"https://api.mathpix.com/v3/pdf/{pdf_id}.tex"
+        response = requests.get(url, headers=headers)
+        file_name_wo_dot = '_'.join(os.path.basename(pdf_file_path).split('.')[:-1])
+        output_name = f"{file_name_wo_dot}.tex.zip"
+        output_path = os.path.join(output_dir, output_name)
+        with open(output_path, "wb") as output_file:
+            output_file.write(response.content)
+        print(f"tex.zip file saved at: {output_path}")
+
+        import zipfile
+        unzip_dir = os.path.join(output_dir, file_name_wo_dot)
+        with zipfile.ZipFile(output_path, 'r') as zip_ref:
+            zip_ref.extractall(unzip_dir)
+
+        return unzip_dir
+
+    else:
+        print(f"Error sending PDF for processing. Status code: {response.status_code}")
+        return None
+
+
+# =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-= 插件主程序1 =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
+
+
+@CatchException
+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。"])
+    yield from update_ui(chatbot=chatbot, history=history)  # 刷新界面
+
+    # <-------------- more requirements ------------->
+    if ("advanced_arg" in plugin_kwargs) and (plugin_kwargs["advanced_arg"] == ""): plugin_kwargs.pop("advanced_arg")
+    more_req = plugin_kwargs.get("advanced_arg", "")
+    _switch_prompt_ = partial(switch_prompt, more_requirement=more_req)
+
+    # <-------------- check deps ------------->
+    try:
+        import glob, os, time, subprocess
+        subprocess.Popen(['pdflatex', '-version'])
+        from .latex_fns.latex_actions import Latex精细分解与转化, 编译Latex
+    except Exception as e:
+        chatbot.append([f"解析项目: {txt}",
+                        f"尝试执行Latex指令失败。Latex没有安装, 或者不在环境变量PATH中。安装方法https://tug.org/texlive/。报错信息\n\n```\n\n{trimmed_format_exc()}\n\n```\n\n"])
+        yield from update_ui(chatbot=chatbot, history=history)  # 刷新界面
+        return
+
+    # <-------------- clear history and read input ------------->
+    history = []
+    if os.path.exists(txt):
+        project_folder = txt
+    else:
+        if txt == "": txt = '空空如也的输入栏'
+        report_exception(chatbot, history, a=f"解析项目: {txt}", b=f"找不到本地项目或无权访问: {txt}")
+        yield from update_ui(chatbot=chatbot, history=history)  # 刷新界面
+        return
+    file_manifest = [f for f in glob.glob(f'{project_folder}/**/*.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 ------------->
+    project_folder = move_project(project_folder, arxiv_id=None)
+
+    # <-------------- if merge_translate_zh is already generated, skip gpt req ------------->
+    if not os.path.exists(project_folder + '/merge_proofread_en.tex'):
+        yield from Latex精细分解与转化(file_manifest, project_folder, llm_kwargs, plugin_kwargs,
+                                       chatbot, history, system_prompt, mode='proofread_en',
+                                       switch_prompt=_switch_prompt_)
+
+    # <-------------- compile PDF ------------->
+    success = yield from 编译Latex(chatbot, history, main_file_original='merge',
+                                   main_file_modified='merge_proofread_en',
+                                   work_folder_original=project_folder, work_folder_modified=project_folder,
+                                   work_folder=project_folder)
+
+    # <-------------- zip PDF ------------->
+    zip_res = zip_result(project_folder)
+    if success:
+        chatbot.append((f"成功啦", '请查收结果（压缩包）...'))
+        yield from update_ui(chatbot=chatbot, history=history);
+        time.sleep(1)  # 刷新界面
+        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 ...'))
+        yield from update_ui(chatbot=chatbot, history=history);
+        time.sleep(1)  # 刷新界面
+        promote_file_to_downloadzone(file=zip_res, chatbot=chatbot)
+
+    # <-------------- we are done ------------->
+    return success
+
+
+# =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-= 插件主程序2 =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
+
+@CatchException
+def Latex翻译中文并重新编译PDF(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。"])
+    yield from update_ui(chatbot=chatbot, history=history)  # 刷新界面
+
+    # <-------------- more requirements ------------->
+    if ("advanced_arg" in plugin_kwargs) and (plugin_kwargs["advanced_arg"] == ""): plugin_kwargs.pop("advanced_arg")
+    more_req = plugin_kwargs.get("advanced_arg", "")
+    no_cache = more_req.startswith("--no-cache")
+    if no_cache: more_req.lstrip("--no-cache")
+    allow_cache = not no_cache
+    _switch_prompt_ = partial(switch_prompt, more_requirement=more_req)
+
+    # <-------------- check deps ------------->
+    try:
+        import glob, os, time, subprocess
+        subprocess.Popen(['pdflatex', '-version'])
+        from .latex_fns.latex_actions import Latex精细分解与转化, 编译Latex
+    except Exception as e:
+        chatbot.append([f"解析项目: {txt}",
+                        f"尝试执行Latex指令失败。Latex没有安装, 或者不在环境变量PATH中。安装方法https://tug.org/texlive/。报错信息\n\n```\n\n{trimmed_format_exc()}\n\n```\n\n"])
+        yield from update_ui(chatbot=chatbot, history=history)  # 刷新界面
+        return
+
+    # <-------------- clear history and read input ------------->
+    history = []
+    try:
+        txt, arxiv_id = yield from arxiv_download(chatbot, history, txt, allow_cache)
+    except tarfile.ReadError as e:
+        yield from update_ui_lastest_msg(
+            "无法自动下载该论文的Latex源码，请前往arxiv打开此论文下载页面，点other Formats，然后download source手动下载latex源码包。接下来调用本地Latex翻译插件即可。",
+            chatbot=chatbot, history=history)
+        return
+
+    if txt.endswith('.pdf'):
+        report_exception(chatbot, history, a=f"解析项目: {txt}", b=f"发现已经存在翻译好的PDF文档")
+        yield from update_ui(chatbot=chatbot, history=history)  # 刷新界面
+        return
+
+    if os.path.exists(txt):
+        project_folder = txt
+    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法处理: {txt}")
+        yield from update_ui(chatbot=chatbot, history=history)  # 刷新界面
+        return
+
+    file_manifest = [f for f in glob.glob(f'{project_folder}/**/*.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 ------------->
+    project_folder = move_project(project_folder, arxiv_id)
+
+    # <-------------- if merge_translate_zh is already generated, skip gpt req ------------->
+    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,
+                                       chatbot, history, system_prompt, mode='translate_zh',
+                                       switch_prompt=_switch_prompt_)
+
+    # <-------------- compile PDF ------------->
+    success = yield from 编译Latex(chatbot, history, main_file_original='merge',
+                                   main_file_modified='merge_translate_zh', mode='translate_zh',
+                                   work_folder_original=project_folder, work_folder_modified=project_folder,
+                                   work_folder=project_folder)
+
+    # <-------------- zip PDF ------------->
+    zip_res = zip_result(project_folder)
+    if success:
+        chatbot.append((f"成功啦", '请查收结果（压缩包）...'))
+        yield from update_ui(chatbot=chatbot, history=history);
+        time.sleep(1)  # 刷新界面
+        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, 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);
+        time.sleep(1)  # 刷新界面
+        promote_file_to_downloadzone(file=zip_res, chatbot=chatbot)
+
+    # <-------------- we are done ------------->
+    return success
+
+
+#  =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=- 插件主程序3  =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
+
+@CatchException
+def PDF翻译中文并重新编译PDF(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
+    # <-------------- 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。"])
+    yield from update_ui(chatbot=chatbot, history=history)  # 刷新界面
+
+    # <-------------- more requirements ------------->
+    if ("advanced_arg" in plugin_kwargs) and (plugin_kwargs["advanced_arg"] == ""): plugin_kwargs.pop("advanced_arg")
+    more_req = plugin_kwargs.get("advanced_arg", "")
+    no_cache = more_req.startswith("--no-cache")
+    if no_cache: more_req.lstrip("--no-cache")
+    allow_cache = not no_cache
+    _switch_prompt_ = partial(switch_prompt, more_requirement=more_req)
+
+    # <-------------- check deps ------------->
+    try:
+        import glob, os, time, subprocess
+        subprocess.Popen(['pdflatex', '-version'])
+        from .latex_fns.latex_actions import Latex精细分解与转化, 编译Latex
+    except Exception as e:
+        chatbot.append([f"解析项目: {txt}",
+                        f"尝试执行Latex指令失败。Latex没有安装, 或者不在环境变量PATH中。安装方法https://tug.org/texlive/。报错信息\n\n```\n\n{trimmed_format_exc()}\n\n```\n\n"])
+        yield from update_ui(chatbot=chatbot, history=history)  # 刷新界面
+        return
+
+    # <-------------- clear history and read input ------------->
+    if os.path.exists(txt):
+        project_folder = txt
+    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法处理: {txt}")
+        yield from update_ui(chatbot=chatbot, history=history)  # 刷新界面
+        return
+
+    file_manifest = [f for f in glob.glob(f'{project_folder}/**/*.pdf', 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.pdf文件: {txt}")
+        yield from update_ui(chatbot=chatbot, history=history)  # 刷新界面
+        return
+    if len(file_manifest) != 1:
+        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])
+
+    # <-------------- check repeated pdf ------------->
+    chatbot.append([f"检查PDF是否被重复上传", "正在检查..."])
+    yield from update_ui(chatbot=chatbot, history=history)
+    repeat, project_folder = check_repeat_upload(file_manifest[0], hash_tag)
+
+    except_flag = False
+
+    if repeat:
+        yield from update_ui_lastest_msg(f"发现重复上传，请查收结果（压缩包）...", chatbot=chatbot, history=history)
+
+        try:
+            trans_html_file = [f for f in glob.glob(f'{project_folder}/**/*.trans.html', recursive=True)][0]
+            promote_file_to_downloadzone(trans_html_file, rename_file=None, chatbot=chatbot)
+
+            translate_pdf = [f for f in glob.glob(f'{project_folder}/**/merge_translate_zh.pdf', recursive=True)][0]
+            promote_file_to_downloadzone(translate_pdf, rename_file=None, chatbot=chatbot)
+
+            comparison_pdf = [f for f in glob.glob(f'{project_folder}/**/comparison.pdf', recursive=True)][0]
+            promote_file_to_downloadzone(comparison_pdf, rename_file=None, chatbot=chatbot)
+
+            zip_res = zip_result(project_folder)
+            promote_file_to_downloadzone(file=zip_res, chatbot=chatbot)
+
+            return True
+
+        except:
+            report_exception(chatbot, history, a=f"解析项目: {txt}", b=f"发现重复上传，但是无法找到相关文件")
+            yield from update_ui(chatbot=chatbot, history=history)
+
+            chatbot.append([f"没有相关文件", '尝试重新翻译PDF...'])
+            yield from update_ui(chatbot=chatbot, history=history)
+
+            except_flag = True
+
+
+    elif not repeat or except_flag:
+        yield from update_ui_lastest_msg(f"未发现重复上传", chatbot=chatbot, history=history)
+
+        # <-------------- 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 ------------->
+        project_folder = desend_to_extracted_folder_if_exist(project_folder)
+
+        # <-------------- move latex project away from temp folder ------------->
+        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 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,
+                                        chatbot, history, system_prompt, mode='translate_zh',
+                                        switch_prompt=_switch_prompt_)
+
+        # <-------------- 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)
+        success = yield from 编译Latex(chatbot, history, main_file_original='merge',
+                                    main_file_modified='merge_translate_zh', mode='translate_zh',
+                                    work_folder_original=project_folder, work_folder_modified=project_folder,
+                                    work_folder=project_folder)
+
+        # <-------------- zip PDF ------------->
+        zip_res = zip_result(project_folder)
+        if success:
+            chatbot.append((f"成功啦", '请查收结果（压缩包）...'))
+            yield from update_ui(chatbot=chatbot, history=history);
+            time.sleep(1)  # 刷新界面
+            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, 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);
+            time.sleep(1)  # 刷新界面
+            promote_file_to_downloadzone(file=zip_res, chatbot=chatbot)
+
+        # <-------------- we are done ------------->
+        return success

crazy_functions/Latex输出PDF结果.py

@@ -1,313 +0,0 @@
-from toolbox import update_ui, trimmed_format_exc, get_conf, get_log_folder, promote_file_to_downloadzone
-from toolbox import CatchException, report_exception, update_ui_lastest_msg, zip_result, gen_time_str
-from functools import partial
-import glob, os, requests, time, tarfile
-pj = os.path.join
-ARXIV_CACHE_DIR = os.path.expanduser(f"~/arxiv_cache/")
-
-# =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=- 工具函数 =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-
-# 专业词汇声明  = 'If the term "agent" is used in this section, it should be translated to "智能体". '
-def switch_prompt(pfg, mode, more_requirement):
-    """
-    Generate prompts and system prompts based on the mode for proofreading or translating.
-    Args:
-    - pfg: Proofreader or Translator instance.
-    - mode: A string specifying the mode, either 'proofread' or 'translate_zh'.
-
-    Returns:
-    - inputs_array: A list of strings containing prompts for users to respond to.
-    - sys_prompt_array: A list of strings containing prompts for system prompts.
-    """
-    n_split = len(pfg.sp_file_contents)
-    if mode == 'proofread_en':
-        inputs_array = [r"Below is a section from an academic paper, proofread this section." + 
-                        r"Do not modify any latex command such as \section, \cite, \begin, \item and equations. " + more_requirement +
-                        r"Answer me only with the revised text:" + 
-                        f"\n\n{frag}" for frag in pfg.sp_file_contents]
-        sys_prompt_array = ["You are a professional academic paper writer." for _ in range(n_split)]
-    elif mode == 'translate_zh':
-        inputs_array = [r"Below is a section from an English academic paper, translate it into Chinese. " + more_requirement + 
-                        r"Do not modify any latex command such as \section, \cite, \begin, \item and equations. " + 
-                        r"Answer me only with the translated text:" + 
-                        f"\n\n{frag}" for frag in pfg.sp_file_contents]
-        sys_prompt_array = ["You are a professional translator." for _ in range(n_split)]
-    else:
-        assert False, "未知指令"
-    return inputs_array, sys_prompt_array
-
-def desend_to_extracted_folder_if_exist(project_folder):
-    """ 
-    Descend into the extracted folder if it exists, otherwise return the original folder.
-
-    Args:
-    - project_folder: A string specifying the folder path.
-
-    Returns:
-    - A string specifying the path to the extracted folder, or the original folder if there is no extracted folder.
-    """
-    maybe_dir = [f for f in glob.glob(f'{project_folder}/*') if os.path.isdir(f)]
-    if len(maybe_dir) == 0: return project_folder
-    if maybe_dir[0].endswith('.extract'): return maybe_dir[0]
-    return project_folder
-
-def move_project(project_folder, arxiv_id=None):
-    """ 
-    Create a new work folder and copy the project folder to it.
-
-    Args:
-    - project_folder: A string specifying the folder path of the project.
-
-    Returns:
-    - A string specifying the path to the new work folder.
-    """
-    import shutil, time
-    time.sleep(2)   # avoid time string conflict
-    if arxiv_id is not None:
-        new_workfolder = pj(ARXIV_CACHE_DIR, arxiv_id, 'workfolder')
-    else:
-        new_workfolder = f'{get_log_folder()}/{gen_time_str()}'
-    try:
-        shutil.rmtree(new_workfolder)
-    except:
-        pass
-
-    # align subfolder if there is a folder wrapper
-    items = glob.glob(pj(project_folder,'*'))
-    items = [item for item in items if os.path.basename(item)!='__MACOSX']
-    if len(glob.glob(pj(project_folder,'*.tex'))) == 0 and len(items) == 1:
-        if os.path.isdir(items[0]): project_folder = items[0]
-
-    shutil.copytree(src=project_folder, dst=new_workfolder)
-    return new_workfolder
-
-def arxiv_download(chatbot, history, txt, allow_cache=True):
-    def check_cached_translation_pdf(arxiv_id):
-        translation_dir = pj(ARXIV_CACHE_DIR, arxiv_id, 'translation')
-        if not os.path.exists(translation_dir):
-            os.makedirs(translation_dir)
-        target_file = pj(translation_dir, 'translate_zh.pdf')
-        if os.path.exists(target_file):
-            promote_file_to_downloadzone(target_file, rename_file=None, chatbot=chatbot)
-            target_file_compare = pj(translation_dir, 'comparison.pdf')
-            if os.path.exists(target_file_compare):
-                promote_file_to_downloadzone(target_file_compare, rename_file=None, chatbot=chatbot)
-            return target_file
-        return False
-    def is_float(s):
-        try:
-            float(s)
-            return True
-        except ValueError:
-            return False
-    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
-        txt = 'https://arxiv.org/abs/' + txt[:10]
-    if not txt.startswith('https://arxiv.org'): 
-        return txt, None    # 是本地文件，跳过下载
-    
-    # <-------------- inspect format ------------->
-    chatbot.append([f"检测到arxiv文档连接", '尝试下载 ...']) 
-    yield from update_ui(chatbot=chatbot, history=history)
-    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
-        return msg, None
-    # <-------------- set format ------------->
-    arxiv_id = url_.split('/abs/')[-1]
-    if 'v' in arxiv_id: arxiv_id = arxiv_id[:10]
-    cached_translation_pdf = check_cached_translation_pdf(arxiv_id)
-    if cached_translation_pdf and allow_cache: return cached_translation_pdf, arxiv_id
-
-    url_tar = url_.replace('/abs/', '/e-print/')
-    translation_dir = pj(ARXIV_CACHE_DIR, arxiv_id, 'e-print')
-    extract_dst = pj(ARXIV_CACHE_DIR, arxiv_id, 'extract')
-    os.makedirs(translation_dir, exist_ok=True)
-    
-    # <-------------- download arxiv source file ------------->
-    dst = pj(translation_dir, arxiv_id+'.tar')
-    if os.path.exists(dst):
-        yield from update_ui_lastest_msg("调用缓存", chatbot=chatbot, history=history)  # 刷新界面
-    else:
-        yield from update_ui_lastest_msg("开始下载", chatbot=chatbot, history=history)  # 刷新界面
-        proxies = get_conf('proxies')
-        r = requests.get(url_tar, proxies=proxies)
-        with open(dst, 'wb+') as f:
-            f.write(r.content)
-    # <-------------- extract file ------------->
-    yield from update_ui_lastest_msg("下载完成", chatbot=chatbot, history=history)  # 刷新界面
-    from toolbox import extract_archive
-    extract_archive(file_path=dst, dest_dir=extract_dst)
-    return extract_dst, arxiv_id
-# =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-= 插件主程序1 =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=    
-
-
-@CatchException
-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。"])
-    yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
-    
-    # <-------------- more requirements ------------->
-    if ("advanced_arg" in plugin_kwargs) and (plugin_kwargs["advanced_arg"] == ""): plugin_kwargs.pop("advanced_arg")
-    more_req = plugin_kwargs.get("advanced_arg", "")
-    _switch_prompt_ = partial(switch_prompt, more_requirement=more_req)
-
-    # <-------------- check deps ------------->
-    try:
-        import glob, os, time, subprocess
-        subprocess.Popen(['pdflatex', '-version'])
-        from .latex_fns.latex_actions import Latex精细分解与转化, 编译Latex
-    except Exception as e:
-        chatbot.append([ f"解析项目: {txt}",
-            f"尝试执行Latex指令失败。Latex没有安装, 或者不在环境变量PATH中。安装方法https://tug.org/texlive/。报错信息\n\n```\n\n{trimmed_format_exc()}\n\n```\n\n"])
-        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
-        return
-    
-
-    # <-------------- clear history and read input ------------->
-    history = []
-    if os.path.exists(txt):
-        project_folder = txt
-    else:
-        if txt == "": txt = '空空如也的输入栏'
-        report_exception(chatbot, history, a = f"解析项目: {txt}", b = f"找不到本地项目或无权访问: {txt}")
-        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
-        return
-    file_manifest = [f for f in glob.glob(f'{project_folder}/**/*.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 ------------->
-    project_folder = move_project(project_folder, arxiv_id=None)
-
-
-    # <-------------- if merge_translate_zh is already generated, skip gpt req ------------->
-    if not os.path.exists(project_folder + '/merge_proofread_en.tex'):
-        yield from Latex精细分解与转化(file_manifest, project_folder, llm_kwargs, plugin_kwargs, 
-                                chatbot, history, system_prompt, mode='proofread_en', switch_prompt=_switch_prompt_)
-
-
-    # <-------------- compile PDF ------------->
-    success = yield from 编译Latex(chatbot, history, main_file_original='merge', main_file_modified='merge_proofread_en', 
-                             work_folder_original=project_folder, work_folder_modified=project_folder, work_folder=project_folder)
-    
-
-    # <-------------- zip PDF ------------->
-    zip_res = zip_result(project_folder)
-    if success:
-        chatbot.append((f"成功啦", '请查收结果（压缩包）...'))
-        yield from update_ui(chatbot=chatbot, history=history); time.sleep(1) # 刷新界面
-        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 ...'))
-        yield from update_ui(chatbot=chatbot, history=history); time.sleep(1) # 刷新界面
-        promote_file_to_downloadzone(file=zip_res, chatbot=chatbot)
-
-    # <-------------- we are done ------------->
-    return success
-
-# =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-= 插件主程序2 =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=    
-
-@CatchException
-def Latex翻译中文并重新编译PDF(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。"])
-    yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
-
-    # <-------------- more requirements ------------->
-    if ("advanced_arg" in plugin_kwargs) and (plugin_kwargs["advanced_arg"] == ""): plugin_kwargs.pop("advanced_arg")
-    more_req = plugin_kwargs.get("advanced_arg", "")
-    no_cache = more_req.startswith("--no-cache")
-    if no_cache: more_req.lstrip("--no-cache")
-    allow_cache = not no_cache
-    _switch_prompt_ = partial(switch_prompt, more_requirement=more_req)
-
-    # <-------------- check deps ------------->
-    try:
-        import glob, os, time, subprocess
-        subprocess.Popen(['pdflatex', '-version'])
-        from .latex_fns.latex_actions import Latex精细分解与转化, 编译Latex
-    except Exception as e:
-        chatbot.append([ f"解析项目: {txt}",
-            f"尝试执行Latex指令失败。Latex没有安装, 或者不在环境变量PATH中。安装方法https://tug.org/texlive/。报错信息\n\n```\n\n{trimmed_format_exc()}\n\n```\n\n"])
-        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
-        return
-    
-
-    # <-------------- clear history and read input ------------->
-    history = []
-    try:
-        txt, arxiv_id = yield from arxiv_download(chatbot, history, txt, allow_cache)
-    except tarfile.ReadError as e:
-        yield from update_ui_lastest_msg(
-            "无法自动下载该论文的Latex源码，请前往arxiv打开此论文下载页面，点other Formats，然后download source手动下载latex源码包。接下来调用本地Latex翻译插件即可。", 
-            chatbot=chatbot, history=history)
-        return
-
-    if txt.endswith('.pdf'):
-        report_exception(chatbot, history, a = f"解析项目: {txt}", b = f"发现已经存在翻译好的PDF文档")
-        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
-        return
-    
-
-    if os.path.exists(txt):
-        project_folder = txt
-    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法处理: {txt}")
-        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
-        return
-    
-    file_manifest = [f for f in glob.glob(f'{project_folder}/**/*.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 ------------->
-    project_folder = move_project(project_folder, arxiv_id)
-
-
-    # <-------------- if merge_translate_zh is already generated, skip gpt req ------------->
-    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, 
-                                chatbot, history, system_prompt, mode='translate_zh', switch_prompt=_switch_prompt_)
-
-
-    # <-------------- compile PDF ------------->
-    success = yield from 编译Latex(chatbot, history, main_file_original='merge', main_file_modified='merge_translate_zh', mode='translate_zh', 
-                             work_folder_original=project_folder, work_folder_modified=project_folder, work_folder=project_folder)
-
-    # <-------------- zip PDF ------------->
-    zip_res = zip_result(project_folder)
-    if success:
-        chatbot.append((f"成功啦", '请查收结果（压缩包）...'))
-        yield from update_ui(chatbot=chatbot, history=history); time.sleep(1) # 刷新界面
-        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, 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); time.sleep(1) # 刷新界面
-        promote_file_to_downloadzone(file=zip_res, chatbot=chatbot)
-
-
-    # <-------------- we are done ------------->
-    return success

crazy_functions/PDF批量翻译.py

@@ -1,9 +1,11 @@
 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
+from toolbox import write_history_to_file, promote_file_to_downloadzone, get_conf, extract_archive
+from toolbox import generate_file_link, zip_folder, trimmed_format_exc, trimmed_format_exc_markdown
 from .crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
 from .crazy_utils import request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency
 from .crazy_utils import read_and_clean_pdf_text
+from .crazy_utils import get_files_from_everything
 from .pdf_fns.parse_pdf import parse_pdf, get_avail_grobid_url, translate_pdf
 from colorful import *
 import os
@@ -14,9 +16,7 @@ def 批量翻译PDF文档(txt, llm_kwargs, plugin_kwargs, chatbot, history, syst
 
     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"])
+    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
@@ -32,7 +32,6 @@ def 批量翻译PDF文档(txt, llm_kwargs, plugin_kwargs, chatbot, history, syst
     # 清空历史，以免输入溢出
     history = []
 
-    from .crazy_utils import get_files_from_everything
     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:
@@ -46,13 +45,161 @@ def 批量翻译PDF文档(txt, llm_kwargs, plugin_kwargs, chatbot, history, syst
         return
 
     # 开始正式执行任务
+    DOC2X_API_KEY = get_conf("DOC2X_API_KEY")
+    # ------- 第一种方法，效果最好，但是需要DOC2X服务 -------
+    if len(DOC2X_API_KEY) != 0:
+        try:
+            yield from 解析PDF_DOC2X(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, DOC2X_API_KEY, user_request)
+            return
+        except:
+            chatbot.append([None, f"DOC2X服务不可用，现在将执行效果稍差的旧版代码。{trimmed_format_exc_markdown()}"])
+            yield from update_ui(chatbot=chatbot, history=history)
+
+    # ------- 第二种方法，效果次优 -------
     grobid_url = get_avail_grobid_url()
     if grobid_url is not None:
         yield from 解析PDF_基于GROBID(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, grobid_url)
-    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)
+        return
 
+    # ------- 第三种方法，早期代码，效果不理想 -------
+    yield from update_ui_lastest_msg("GROBID服务不可用，请检查config中的GROBID_URL。作为替代，现在将执行效果稍差的旧版代码。", chatbot, history, delay=3)
+    yield from 解析PDF(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt)
+    return
+
+
+
+def 解析PDF_DOC2X_单文件(fp, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, DOC2X_API_KEY, user_request):
+
+    def pdf2markdown(filepath):
+        import requests, json, os
+        markdown_dir = get_log_folder(plugin_name="pdf_ocr")
+        doc2x_api_key = DOC2X_API_KEY
+        if doc2x_api_key.startswith('sk-'):
+            url = "https://api.doc2x.noedgeai.com/api/v1/pdf"
+        else:
+            url = "https://api.doc2x.noedgeai.com/api/platform/pdf"
+
+        chatbot.append((None, "加载PDF文件，发送至DOC2X解析..."))
+        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+
+        res = requests.post(
+            url,
+            files={"file": open(filepath, "rb")},
+            data={"ocr": "1"},
+            headers={"Authorization": "Bearer " + doc2x_api_key}
+        )
+        res_json = []
+        if res.status_code == 200:
+            decoded = res.content.decode("utf-8")
+            for z_decoded in decoded.split('\n'):
+                if len(z_decoded) == 0: continue
+                assert z_decoded.startswith("data: ")
+                z_decoded = z_decoded[len("data: "):]
+                decoded_json = json.loads(z_decoded)
+                res_json.append(decoded_json)
+        else:
+            raise RuntimeError(format("[ERROR] status code: %d, body: %s" % (res.status_code, res.text)))
+        uuid = res_json[0]['uuid']
+        to = "md" # latex, md, docx
+        url = "https://api.doc2x.noedgeai.com/api/export"+"?request_id="+uuid+"&to="+to
+
+        chatbot.append((None, f"读取解析: {url} ..."))
+        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+
+        res = requests.get(url, headers={"Authorization": "Bearer " + doc2x_api_key})
+        md_zip_path = os.path.join(markdown_dir, gen_time_str() + '.zip')
+        if res.status_code == 200:
+            with open(md_zip_path, "wb") as f: f.write(res.content)
+        else:
+            raise RuntimeError(format("[ERROR] status code: %d, body: %s" % (res.status_code, res.text)))
+        promote_file_to_downloadzone(md_zip_path, chatbot=chatbot)
+        chatbot.append((None, f"完成解析 {md_zip_path} ..."))
+        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+        return md_zip_path
+
+    def deliver_to_markdown_plugin(md_zip_path, user_request):
+        from crazy_functions.批量Markdown翻译 import Markdown英译中
+        import shutil, re
+
+        time_tag = gen_time_str()
+        target_path_base = get_log_folder(chatbot.get_user())
+        file_origin_name = os.path.basename(md_zip_path)
+        this_file_path = os.path.join(target_path_base, file_origin_name)
+        os.makedirs(target_path_base, exist_ok=True)
+        shutil.copyfile(md_zip_path, this_file_path)
+        ex_folder = this_file_path + ".extract"
+        extract_archive(
+            file_path=this_file_path, dest_dir=ex_folder
+        )
+
+        # edit markdown files
+        success, file_manifest, project_folder = get_files_from_everything(ex_folder, type='.md')
+        for generated_fp in file_manifest:
+            # 修正一些公式问题
+            with open(generated_fp, 'r', encoding='utf8') as f:
+                content = f.read()
+            # 将公式中的\[ \]替换成$$
+            content = content.replace(r'\[', r'$$').replace(r'\]', r'$$')
+            # 将公式中的\( \)替换成$
+            content = content.replace(r'\(', r'$').replace(r'\)', r'$')
+            content = content.replace('```markdown', '\n').replace('```', '\n')
+            with open(generated_fp, 'w', encoding='utf8') as f:
+                f.write(content)
+            promote_file_to_downloadzone(generated_fp, chatbot=chatbot)
+            yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+
+            # 生成在线预览html
+            file_name = '在线预览翻译（原文）' + gen_time_str() + '.html'
+            preview_fp = os.path.join(ex_folder, file_name)
+            from shared_utils.advanced_markdown_format import markdown_convertion_for_file
+            with open(generated_fp, "r", encoding="utf-8") as f:
+                md = f.read()
+                # Markdown中使用不标准的表格，需要在表格前加上一个emoji，以便公式渲染
+                md = re.sub(r'^<table>', r'😃<table>', md, flags=re.MULTILINE)
+            html = markdown_convertion_for_file(md)
+            with open(preview_fp, "w", encoding="utf-8") as f: f.write(html)
+            chatbot.append([None, f"生成在线预览：{generate_file_link([preview_fp])}"])
+            promote_file_to_downloadzone(preview_fp, chatbot=chatbot)
+
+
+
+        chatbot.append((None, f"调用Markdown插件 {ex_folder} ..."))
+        plugin_kwargs['markdown_expected_output_dir'] = ex_folder
+
+        translated_f_name = 'translated_markdown.md'
+        generated_fp = plugin_kwargs['markdown_expected_output_path'] = os.path.join(ex_folder, translated_f_name)
+        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+        yield from Markdown英译中(ex_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request)
+        if os.path.exists(generated_fp):
+            # 修正一些公式问题
+            with open(generated_fp, 'r', encoding='utf8') as f: content = f.read()
+            content = content.replace('```markdown', '\n').replace('```', '\n')
+            # Markdown中使用不标准的表格，需要在表格前加上一个emoji，以便公式渲染
+            content = re.sub(r'^<table>', r'😃<table>', content, flags=re.MULTILINE)
+            with open(generated_fp, 'w', encoding='utf8') as f: f.write(content)
+            # 生成在线预览html
+            file_name = '在线预览翻译' + gen_time_str() + '.html'
+            preview_fp = os.path.join(ex_folder, file_name)
+            from shared_utils.advanced_markdown_format import markdown_convertion_for_file
+            with open(generated_fp, "r", encoding="utf-8") as f:
+                md = f.read()
+            html = markdown_convertion_for_file(md)
+            with open(preview_fp, "w", encoding="utf-8") as f: f.write(html)
+            promote_file_to_downloadzone(preview_fp, chatbot=chatbot)
+            # 生成包含图片的压缩包
+            dest_folder = get_log_folder(chatbot.get_user())
+            zip_name = '翻译后的带图文档.zip'
+            zip_folder(source_folder=ex_folder, dest_folder=dest_folder, zip_name=zip_name)
+            zip_fp = os.path.join(dest_folder, zip_name)
+            promote_file_to_downloadzone(zip_fp, chatbot=chatbot)
+            yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+    md_zip_path = yield from pdf2markdown(fp)
+    yield from deliver_to_markdown_plugin(md_zip_path, user_request)
+
+def 解析PDF_DOC2X(file_manifest, *args):
+    for index, fp in enumerate(file_manifest):
+        yield from 解析PDF_DOC2X_单文件(fp, *args)
+    return
 
 def 解析PDF_基于GROBID(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, grobid_url):
     import copy, json
@@ -68,7 +215,7 @@ def 解析PDF_基于GROBID(file_manifest, project_folder, llm_kwargs, plugin_kwa
         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)))
@@ -97,7 +244,7 @@ def 解析PDF(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot,
 
         # 为了更好的效果，我们剥离Introduction之后的部分（如果有）
         paper_meta = page_one_fragments[0].split('introduction')[0].split('Introduction')[0].split('INTRODUCTION')[0]
-        
+
         # 单线，获取文章meta信息
         paper_meta_info = yield from request_gpt_model_in_new_thread_with_ui_alive(
             inputs=f"以下是一篇学术论文的基础信息，请从中提取出“标题”、“收录会议或期刊”、“作者”、“摘要”、“编号”、“作者邮箱”这六个部分。请用markdown格式输出，最后用中文翻译摘要部分。请提取：{paper_meta}",
@@ -121,7 +268,7 @@ def 解析PDF(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot,
         )
         gpt_response_collection_md = copy.deepcopy(gpt_response_collection)
         # 整理报告的格式
-        for i,k in enumerate(gpt_response_collection_md): 
+        for i,k in enumerate(gpt_response_collection_md):
             if i%2==0:
                 gpt_response_collection_md[i] = f"\n\n---\n\n ## 原文[{i//2}/{len(gpt_response_collection_md)//2}]： \n\n {paper_fragments[i//2].replace('#', '')}  \n\n---\n\n ## 翻译[{i//2}/{len(gpt_response_collection_md)//2}]：\n "
             else:
@@ -139,18 +286,18 @@ def 解析PDF(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot,
 
         # write html
         try:
-            ch = construct_html() 
+            ch = construct_html()
             orig = ""
             trans = ""
             gpt_response_collection_html = copy.deepcopy(gpt_response_collection)
-            for i,k in enumerate(gpt_response_collection_html): 
+            for i,k in enumerate(gpt_response_collection_html):
                 if i%2==0:
                     gpt_response_collection_html[i] = paper_fragments[i//2].replace('#', '')
                 else:
                     gpt_response_collection_html[i] = gpt_response_collection_html[i]
             final = ["论文概况", paper_meta_info.replace('# ', '### '),  "二、论文翻译",  ""]
             final.extend(gpt_response_collection_html)
-            for i, k in enumerate(final): 
+            for i, k in enumerate(final):
                 if i%2==0:
                     orig = k
                 if i%2==1:

crazy_functions/agent_fns/pipe.py

@@ -72,7 +72,7 @@ class PluginMultiprocessManager:
         if file_type.lower() in ['png', 'jpg']:
             image_path = os.path.abspath(fp)
             self.chatbot.append([
-                '检测到新生图像:', 
+                '检测到新生图像:',
                 f'本地文件预览: <br/><div align="center"><img src="file={image_path}"></div>'
             ])
             yield from update_ui(chatbot=self.chatbot, history=self.history)
@@ -114,21 +114,21 @@ class PluginMultiprocessManager:
             self.cnt = 1
             self.parent_conn = self.launch_subprocess_with_pipe() # ⭐⭐⭐
         repeated, cmd_to_autogen = self.send_command(txt)
-        if txt == 'exit': 
+        if txt == 'exit':
             self.chatbot.append([f"结束", "结束信号已明确，终止AutoGen程序。"])
             yield from update_ui(chatbot=self.chatbot, history=self.history)
             self.terminate()
             return "terminate"
-        
+
         # patience = 10
-        
+
         while True:
             time.sleep(0.5)
             if not self.alive:
                 # the heartbeat watchdog might have it killed
                 self.terminate()
                 return "terminate"
-            if self.parent_conn.poll(): 
+            if self.parent_conn.poll():
                 self.feed_heartbeat_watchdog()
                 if "[GPT-Academic] 等待中" in self.chatbot[-1][-1]:
                     self.chatbot.pop(-1)  # remove the last line
@@ -152,8 +152,8 @@ class PluginMultiprocessManager:
                     yield from update_ui(chatbot=self.chatbot, history=self.history)
                 if msg.cmd == "interact":
                     yield from self.overwatch_workdir_file_change()
-                    self.chatbot.append([f"程序抵达用户反馈节点.", msg.content + 
-                                         "\n\n等待您的进一步指令." + 
+                    self.chatbot.append([f"程序抵达用户反馈节点.", msg.content +
+                                         "\n\n等待您的进一步指令." +
                                          "\n\n(1) 一般情况下您不需要说什么, 清空输入区, 然后直接点击“提交”以继续. " +
                                          "\n\n(2) 如果您需要补充些什么, 输入要反馈的内容, 直接点击“提交”以继续. " +
                                          "\n\n(3) 如果您想终止程序, 输入exit, 直接点击“提交”以终止AutoGen并解锁. "

crazy_functions/agent_fns/watchdog.py

@@ -8,7 +8,7 @@ class WatchDog():
         self.interval = interval
         self.msg = msg
         self.kill_dog = False
-    
+
     def watch(self):
         while True:
             if self.kill_dog: break

crazy_functions/chatglm微调工具.py

@@ -46,7 +46,7 @@ def 微调数据集生成(txt, llm_kwargs, plugin_kwargs, chatbot, history, syst
     chatbot.append(("这是什么功能？", "[Local Message] 微调数据集生成"))
     if ("advanced_arg" in plugin_kwargs) and (plugin_kwargs["advanced_arg"] == ""): plugin_kwargs.pop("advanced_arg")
     args = plugin_kwargs.get("advanced_arg", None)
-    if args is None: 
+    if args is None:
         chatbot.append(("没给定指令", "退出"))
         yield from update_ui(chatbot=chatbot, history=history); return
     else:
@@ -69,7 +69,7 @@ def 微调数据集生成(txt, llm_kwargs, plugin_kwargs, chatbot, history, syst
             sys_prompt_array=[arguments.system_prompt for _ in (batch)],
             max_workers=10  # OpenAI所允许的最大并行过载
         )
-    
+
         with open(txt+'.generated.json', 'a+', encoding='utf8') as f:
             for b, r in zip(batch, res[1::2]):
                 f.write(json.dumps({"content":b, "summary":r}, ensure_ascii=False)+'\n')
@@ -95,12 +95,12 @@ def 启动微调(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt
     chatbot.append(("这是什么功能？", "[Local Message] 微调数据集生成"))
     if ("advanced_arg" in plugin_kwargs) and (plugin_kwargs["advanced_arg"] == ""): plugin_kwargs.pop("advanced_arg")
     args = plugin_kwargs.get("advanced_arg", None)
-    if args is None: 
+    if args is None:
         chatbot.append(("没给定指令", "退出"))
         yield from update_ui(chatbot=chatbot, history=history); return
     else:
         arguments = string_to_options(arguments=args)
-      
+
 
 
     pre_seq_len = arguments.pre_seq_len             # 128

crazy_functions/crazy_utils.py

@@ -12,7 +12,7 @@ def input_clipping(inputs, history, max_token_limit):
     mode = 'input-and-history'
     # 当 输入部分的token占比 小于 全文的一半时，只裁剪历史
     input_token_num = get_token_num(inputs)
-    if input_token_num < max_token_limit//2: 
+    if input_token_num < max_token_limit//2:
         mode = 'only-history'
         max_token_limit = max_token_limit - input_token_num
 
@@ -21,7 +21,7 @@ def input_clipping(inputs, history, max_token_limit):
     n_token = get_token_num('\n'.join(everything))
     everything_token = [get_token_num(e) for e in everything]
     delta = max(everything_token) // 16 # 截断时的颗粒度
-        
+
     while n_token > max_token_limit:
         where = np.argmax(everything_token)
         encoded = enc.encode(everything[where], disallowed_special=())
@@ -38,9 +38,9 @@ def input_clipping(inputs, history, max_token_limit):
     return inputs, history
 
 def request_gpt_model_in_new_thread_with_ui_alive(
-        inputs, inputs_show_user, llm_kwargs, 
+        inputs, inputs_show_user, llm_kwargs,
         chatbot, history, sys_prompt, refresh_interval=0.2,
-        handle_token_exceed=True, 
+        handle_token_exceed=True,
         retry_times_at_unknown_error=2,
         ):
     """
@@ -77,7 +77,7 @@ def request_gpt_model_in_new_thread_with_ui_alive(
         exceeded_cnt = 0
         while True:
             # watchdog error
-            if len(mutable) >= 2 and (time.time()-mutable[1]) > watch_dog_patience: 
+            if len(mutable) >= 2 and (time.time()-mutable[1]) > watch_dog_patience:
                 raise RuntimeError("检测到程序终止。")
             try:
                 # 【第一种情况】：顺利完成
@@ -135,17 +135,29 @@ def request_gpt_model_in_new_thread_with_ui_alive(
     yield from update_ui(chatbot=chatbot, history=[]) # 如果最后成功了，则删除报错信息
     return final_result
 
-def can_multi_process(llm):
-    if llm.startswith('gpt-'): return True
-    if llm.startswith('api2d-'): return True
-    if llm.startswith('azure-'): return True
-    if llm.startswith('spark'): return True
-    if llm.startswith('zhipuai'): return True
-    return False
+def can_multi_process(llm) -> bool:
+    from request_llms.bridge_all import model_info
+
+    def default_condition(llm) -> bool:
+        # legacy condition
+        if llm.startswith('gpt-'): return True
+        if llm.startswith('api2d-'): return True
+        if llm.startswith('azure-'): return True
+        if llm.startswith('spark'): return True
+        if llm.startswith('zhipuai') or llm.startswith('glm-'): return True
+        return False
+
+    if llm in model_info:
+        if 'can_multi_thread' in model_info[llm]:
+            return model_info[llm]['can_multi_thread']
+        else:
+            return default_condition(llm)
+    else:
+        return default_condition(llm)
 
 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, 
+        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,
         handle_token_exceed=True, show_user_at_complete=False,
         retry_times_at_unknown_error=2,
@@ -189,7 +201,7 @@ def request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
     # 屏蔽掉 chatglm的多线程，可能会导致严重卡顿
     if not can_multi_process(llm_kwargs['llm_model']):
         max_workers = 1
-        
+
     executor = ThreadPoolExecutor(max_workers=max_workers)
     n_frag = len(inputs_array)
     # 用户反馈
@@ -214,7 +226,7 @@ def request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
             try:
                 # 【第一种情况】：顺利完成
                 gpt_say = predict_no_ui_long_connection(
-                    inputs=inputs, llm_kwargs=llm_kwargs, history=history, 
+                    inputs=inputs, llm_kwargs=llm_kwargs, history=history,
                     sys_prompt=sys_prompt, observe_window=mutable[index], console_slience=True
                 )
                 mutable[index][2] = "已成功"
@@ -246,7 +258,7 @@ def request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
                 print(tb_str)
                 gpt_say += f"[Local Message] 警告，线程{index}在执行过程中遭遇问题, Traceback：\n\n{tb_str}\n\n"
                 if len(mutable[index][0]) > 0: gpt_say += "此线程失败前收到的回答：\n\n" + mutable[index][0]
-                if retry_op > 0: 
+                if retry_op > 0:
                     retry_op -= 1
                     wait = random.randint(5, 20)
                     if ("Rate limit reached" in tb_str) or ("Too Many Requests" in tb_str):
@@ -287,8 +299,8 @@ def request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
                 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' 
-                            if not done else f'`{mutable[thread_index][2]}`\n\n' 
+        stat_str = ''.join([f'`{mutable[thread_index][2]}`: {obs}\n\n'
+                            if not done else f'`{mutable[thread_index][2]}`\n\n'
                             for thread_index, done, obs in zip(range(len(worker_done)), worker_done, observe_win)])
         # 在前端打印些好玩的东西
         chatbot[-1] = [chatbot[-1][0], f'多线程操作已经开始，完成情况: \n\n{stat_str}' + ''.join(['.']*(cnt % 10+1))]
@@ -302,7 +314,7 @@ def request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
     for inputs_show_user, f in zip(inputs_show_user_array, futures):
         gpt_res = f.result()
         gpt_response_collection.extend([inputs_show_user, gpt_res])
-    
+
     # 是否在结束时，在界面上显示结果
     if show_user_at_complete:
         for inputs_show_user, f in zip(inputs_show_user_array, futures):
@@ -352,7 +364,7 @@ def read_and_clean_pdf_text(fp):
             if wtf['size'] not in fsize_statiscs: fsize_statiscs[wtf['size']] = 0
             fsize_statiscs[wtf['size']] += len(wtf['text'])
         return max(fsize_statiscs, key=fsize_statiscs.get)
-        
+
     def ffsize_same(a,b):
         """
         提取字体大小是否近似相等
@@ -388,7 +400,7 @@ def read_and_clean_pdf_text(fp):
             if index == 0:
                 page_one_meta = [" ".join(["".join([wtf['text'] for wtf in l['spans']]) for l in t['lines']]).replace(
                     '- ', '') for t in text_areas['blocks'] if 'lines' in t]
-                
+
         ############################## <第 2 步，获取正文主字体> ##################################
         try:
             fsize_statiscs = {}
@@ -404,7 +416,7 @@ def read_and_clean_pdf_text(fp):
         mega_sec = []
         sec = []
         for index, line in enumerate(meta_line):
-            if index == 0: 
+            if index == 0:
                 sec.append(line[fc])
                 continue
             if REMOVE_FOOT_NOTE:
@@ -501,12 +513,12 @@ def get_files_from_everything(txt, type): # type='.md'
     """
     这个函数是用来获取指定目录下所有指定类型（如.md）的文件，并且对于网络上的文件，也可以获取它。
     下面是对每个参数和返回值的说明：
-    参数 
-    - txt: 路径或网址，表示要搜索的文件或者文件夹路径或网络上的文件。 
+    参数
+    - txt: 路径或网址，表示要搜索的文件或者文件夹路径或网络上的文件。
     - type: 字符串，表示要搜索的文件类型。默认是.md。
-    返回值 
-    - success: 布尔值，表示函数是否成功执行。 
-    - file_manifest: 文件路径列表，里面包含以指定类型为后缀名的所有文件的绝对路径。 
+    返回值
+    - success: 布尔值，表示函数是否成功执行。
+    - file_manifest: 文件路径列表，里面包含以指定类型为后缀名的所有文件的绝对路径。
     - project_folder: 字符串，表示文件所在的文件夹路径。如果是网络上的文件，就是临时文件夹的路径。
     该函数详细注释已添加，请确认是否满足您的需要。
     """
@@ -556,7 +568,7 @@ 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:
@@ -570,7 +582,7 @@ class nougat_interface():
     def NOUGAT_parse_pdf(self, fp, chatbot, history):
         from toolbox import update_ui_lastest_msg
 
-        yield from update_ui_lastest_msg("正在解析论文, 请稍候。进度：正在排队, 等待线程锁...", 
+        yield from update_ui_lastest_msg("正在解析论文, 请稍候。进度：正在排队, 等待线程锁...",
                                          chatbot=chatbot, history=history, delay=0)
         self.threadLock.acquire()
         import glob, threading, os
@@ -578,9 +590,10 @@ class nougat_interface():
         dst = os.path.join(get_log_folder(plugin_name='nougat'), gen_time_str())
         os.makedirs(dst)
 
-        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）", 
+        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/diagram_fns/file_tree.py

@@ -10,7 +10,7 @@ class FileNode:
         self.parenting_ship = []
         self.comment = ""
         self.comment_maxlen_show = 50
-        
+
     @staticmethod
     def add_linebreaks_at_spaces(string, interval=10):
         return '\n'.join(string[i:i+interval] for i in range(0, len(string), interval))

crazy_functions/game_fns/game_ascii_art.py

@@ -8,7 +8,7 @@ import random
 
 class MiniGame_ASCII_Art(GptAcademicGameBaseState):
     def step(self, prompt, chatbot, history):
-        if self.step_cnt == 0:  
+        if self.step_cnt == 0:
             chatbot.append(["我画你猜（动物）", "请稍等..."])
         else:
             if prompt.strip() == 'exit':

crazy_functions/game_fns/game_interactive_story.py

@@ -88,8 +88,8 @@ class MiniGame_ResumeStory(GptAcademicGameBaseState):
         self.story = []
         chatbot.append(["互动写故事", f"这次的故事开头是：{self.headstart}"])
         self.sys_prompt_ = '你是一个想象力丰富的杰出作家。正在与你的朋友互动，一起写故事，因此你每次写的故事段落应少于300字（结局除外）。'
-        
-        
+
+
     def generate_story_image(self, story_paragraph):
         try:
             from crazy_functions.图片生成 import gen_image
@@ -98,13 +98,13 @@ class MiniGame_ResumeStory(GptAcademicGameBaseState):
             return f'<br/><div align="center"><img src="file={image_path}"></div>'
         except:
             return ''
-        
+
     def step(self, prompt, chatbot, history):
-        
+
         """
         首先，处理游戏初始化等特殊情况
         """
-        if self.step_cnt == 0:  
+        if self.step_cnt == 0:
             self.begin_game_step_0(prompt, chatbot, history)
             self.lock_plugin(chatbot)
             self.cur_task = 'head_start'
@@ -132,7 +132,7 @@ class MiniGame_ResumeStory(GptAcademicGameBaseState):
             inputs_ = prompts_hs.format(headstart=self.headstart)
             history_ = []
             story_paragraph = yield from request_gpt_model_in_new_thread_with_ui_alive(
-                inputs_, '故事开头', self.llm_kwargs, 
+                inputs_, '故事开头', self.llm_kwargs,
                 chatbot, history_, self.sys_prompt_
             )
             self.story.append(story_paragraph)
@@ -147,7 +147,7 @@ class MiniGame_ResumeStory(GptAcademicGameBaseState):
             inputs_ = prompts_interact.format(previously_on_story=previously_on_story)
             history_ = []
             self.next_choices = yield from request_gpt_model_in_new_thread_with_ui_alive(
-                inputs_, '请在以下几种故事走向中，选择一种（当然，您也可以选择给出其他故事走向）：', self.llm_kwargs, 
+                inputs_, '请在以下几种故事走向中，选择一种（当然，您也可以选择给出其他故事走向）：', self.llm_kwargs,
                 chatbot,
                 history_,
                 self.sys_prompt_
@@ -166,7 +166,7 @@ class MiniGame_ResumeStory(GptAcademicGameBaseState):
             inputs_ = prompts_resume.format(previously_on_story=previously_on_story, choice=self.next_choices, user_choice=prompt)
             history_ = []
             story_paragraph = yield from request_gpt_model_in_new_thread_with_ui_alive(
-                inputs_, f'下一段故事（您的选择是：{prompt}）。', self.llm_kwargs, 
+                inputs_, f'下一段故事（您的选择是：{prompt}）。', self.llm_kwargs,
                 chatbot, history_, self.sys_prompt_
             )
             self.story.append(story_paragraph)
@@ -181,10 +181,10 @@ class MiniGame_ResumeStory(GptAcademicGameBaseState):
             inputs_ = prompts_interact.format(previously_on_story=previously_on_story)
             history_ = []
             self.next_choices = yield from request_gpt_model_in_new_thread_with_ui_alive(
-                inputs_, 
-                '请在以下几种故事走向中，选择一种。当然，您也可以给出您心中的其他故事走向。另外，如果您希望剧情立即收尾，请输入剧情走向，并以“剧情收尾”四个字提示程序。', self.llm_kwargs, 
-                chatbot, 
-                history_, 
+                inputs_,
+                '请在以下几种故事走向中，选择一种。当然，您也可以给出您心中的其他故事走向。另外，如果您希望剧情立即收尾，请输入剧情走向，并以“剧情收尾”四个字提示程序。', self.llm_kwargs,
+                chatbot,
+                history_,
                 self.sys_prompt_
             )
             self.cur_task = 'user_choice'
@@ -200,7 +200,7 @@ class MiniGame_ResumeStory(GptAcademicGameBaseState):
             inputs_ = prompts_terminate.format(previously_on_story=previously_on_story, user_choice=prompt)
             history_ = []
             story_paragraph = yield from request_gpt_model_in_new_thread_with_ui_alive(
-                inputs_, f'故事收尾（您的选择是：{prompt}）。', self.llm_kwargs, 
+                inputs_, f'故事收尾（您的选择是：{prompt}）。', self.llm_kwargs,
                 chatbot, history_, self.sys_prompt_
             )
             # # 配图

crazy_functions/game_fns/game_utils.py

@@ -5,7 +5,7 @@ def get_code_block(reply):
     import re
     pattern = r"```([\s\S]*?)```" # regex pattern to match code blocks
     matches = re.findall(pattern, reply) # find all code blocks in text
-    if len(matches) == 1: 
+    if len(matches) == 1:
         return "```" + matches[0] + "```" #  code block
     raise RuntimeError("GPT is not generating proper code.")
 
@@ -13,10 +13,10 @@ def is_same_thing(a, b, llm_kwargs):
     from pydantic import BaseModel, Field
     class IsSameThing(BaseModel):
         is_same_thing: bool = Field(description="determine whether two objects are same thing.", default=False)
-        
-    def run_gpt_fn(inputs, sys_prompt, history=[]): 
+
+    def run_gpt_fn(inputs, sys_prompt, history=[]):
         return predict_no_ui_long_connection(
-            inputs=inputs, llm_kwargs=llm_kwargs, 
+            inputs=inputs, llm_kwargs=llm_kwargs,
             history=history, sys_prompt=sys_prompt, observe_window=[]
         )
 
@@ -24,7 +24,7 @@ def is_same_thing(a, b, llm_kwargs):
     inputs_01 = "Identity whether the user input and the target is the same thing: \n target object: {a} \n user input object: {b} \n\n\n".format(a=a, b=b)
     inputs_01 += "\n\n\n Note that the user may describe the target object with a different language, e.g. cat and 猫 are the same thing."
     analyze_res_cot_01 = run_gpt_fn(inputs_01, "", [])
-    
+
     inputs_02 = inputs_01 + gpt_json_io.format_instructions
     analyze_res = run_gpt_fn(inputs_02, "", [inputs_01, analyze_res_cot_01])
 

crazy_functions/gen_fns/gen_fns_shared.py

@@ -41,11 +41,11 @@ def is_function_successfully_generated(fn_path, class_name, return_dict):
         # Now you can create an instance of the class
         instance = some_class()
         return_dict['success'] = True
-        return 
+        return
     except:
         return_dict['traceback'] = trimmed_format_exc()
         return
-    
+
 def subprocess_worker(code, file_path, return_dict):
     return_dict['result'] = None
     return_dict['success'] = False

crazy_functions/ipc_fns/mp.py

@@ -1,4 +1,4 @@
-import platform 
+import platform
 import pickle
 import multiprocessing
 

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)
@@ -89,7 +89,7 @@ class GptJsonIO():
                  error + "\n\n" + \
                 "Now, fix this json string. \n\n"
         return prompt
-    
+
     def generate_output_auto_repair(self, response, gpt_gen_fn):
         """
         response: string containing canidate json

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
@@ -90,16 +91,16 @@ class LatexPaperSplit():
             "版权归原文作者所有。翻译内容可靠性无保障，请仔细鉴别并以原文为准。" + \
             "项目Github地址 \\url{https://github.com/binary-husky/gpt_academic/}。"
         # 请您不要删除或修改这行警告，除非您是论文的原作者（如果您是论文原作者，欢迎加REAME中的QQ联系开发者）
-        self.msg_declare = "为了防止大语言模型的意外谬误产生扩散影响，禁止移除或修改此警告。}}\\\\" 
+        self.msg_declare = "为了防止大语言模型的意外谬误产生扩散影响，禁止移除或修改此警告。}}\\\\"
         self.title = "unknown"
         self.abstract = "unknown"
 
     def read_title_and_abstract(self, txt):
         try:
             title, abstract = find_title_and_abs(txt)
-            if title is not None: 
+            if title is not None:
                 self.title = title.replace('\n', ' ').replace('\\\\', ' ').replace('  ', '').replace('  ', '')
-            if abstract is not None: 
+            if abstract is not None:
                 self.abstract = abstract.replace('\n', ' ').replace('\\\\', ' ').replace('  ', '').replace('  ', '')
         except:
             pass
@@ -111,7 +112,7 @@ class LatexPaperSplit():
         result_string = ""
         node_cnt = 0
         line_cnt = 0
-        
+
         for node in self.nodes:
             if node.preserve:
                 line_cnt += node.string.count('\n')
@@ -144,7 +145,7 @@ class LatexPaperSplit():
         return result_string
 
 
-    def split(self, txt, project_folder, opts): 
+    def split(self, txt, project_folder, opts):
         """
         break down latex file to a linked list,
         each node use a preserve flag to indicate whether it should
@@ -155,7 +156,7 @@ class LatexPaperSplit():
         manager = multiprocessing.Manager()
         return_dict = manager.dict()
         p = multiprocessing.Process(
-            target=split_subprocess, 
+            target=split_subprocess,
             args=(txt, project_folder, return_dict, opts))
         p.start()
         p.join()
@@ -217,13 +218,13 @@ def Latex精细分解与转化(file_manifest, project_folder, llm_kwargs, plugin
     from ..crazy_utils import request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency
     from .latex_actions import LatexPaperFileGroup, LatexPaperSplit
 
-    #  <-------- 寻找主tex文件 ----------> 
+    #  <-------- 寻找主tex文件 ---------->
     maintex = find_main_tex_file(file_manifest, mode)
     chatbot.append((f"定位主Latex文件", f'[Local Message] 分析结果：该项目的Latex主文件是{maintex}, 如果分析错误, 请立即终止程序, 删除或修改歧义文件, 然后重试。主程序即将开始, 请稍候。'))
     yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
     time.sleep(3)
 
-    #  <-------- 读取Latex文件, 将多文件tex工程融合为一个巨型tex ----------> 
+    #  <-------- 读取Latex文件, 将多文件tex工程融合为一个巨型tex ---------->
     main_tex_basename = os.path.basename(maintex)
     assert main_tex_basename.endswith('.tex')
     main_tex_basename_bare = main_tex_basename[:-4]
@@ -240,13 +241,13 @@ def Latex精细分解与转化(file_manifest, project_folder, llm_kwargs, plugin
     with open(project_folder + '/merge.tex', 'w', encoding='utf-8', errors='replace') as f:
         f.write(merged_content)
 
-    #  <-------- 精细切分latex文件 ----------> 
+    #  <-------- 精细切分latex文件 ---------->
     chatbot.append((f"Latex文件融合完成", f'[Local Message] 正在精细切分latex文件，这需要一段时间计算，文档越长耗时越长，请耐心等待。'))
     yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
     lps = LatexPaperSplit()
     lps.read_title_and_abstract(merged_content)
     res = lps.split(merged_content, project_folder, opts) # 消耗时间的函数
-    #  <-------- 拆分过长的latex片段 ----------> 
+    #  <-------- 拆分过长的latex片段 ---------->
     pfg = LatexPaperFileGroup()
     for index, r in enumerate(res):
         pfg.file_paths.append('segment-' + str(index))
@@ -255,17 +256,17 @@ def Latex精细分解与转化(file_manifest, project_folder, llm_kwargs, plugin
     pfg.run_file_split(max_token_limit=1024)
     n_split = len(pfg.sp_file_contents)
 
-    #  <-------- 根据需要切换prompt ----------> 
+    #  <-------- 根据需要切换prompt ---------->
     inputs_array, sys_prompt_array = switch_prompt(pfg, mode)
     inputs_show_user_array = [f"{mode} {f}" for f in pfg.sp_file_tag]
 
     if os.path.exists(pj(project_folder,'temp.pkl')):
 
-        #  <-------- 【仅调试】如果存在调试缓存文件，则跳过GPT请求环节 ----------> 
+        #  <-------- 【仅调试】如果存在调试缓存文件，则跳过GPT请求环节 ---------->
         pfg = objload(file=pj(project_folder,'temp.pkl'))
 
     else:
-        #  <-------- gpt 多线程请求 ----------> 
+        #  <-------- gpt 多线程请求 ---------->
         history_array = [[""] for _ in range(n_split)]
         # LATEX_EXPERIMENTAL, = get_conf('LATEX_EXPERIMENTAL')
         # if LATEX_EXPERIMENTAL:
@@ -284,32 +285,32 @@ def Latex精细分解与转化(file_manifest, project_folder, llm_kwargs, plugin
             scroller_max_len = 40
         )
 
-        #  <-------- 文本碎片重组为完整的tex片段 ----------> 
+        #  <-------- 文本碎片重组为完整的tex片段 ---------->
         pfg.sp_file_result = []
         for i_say, gpt_say, orig_content in zip(gpt_response_collection[0::2], gpt_response_collection[1::2], pfg.sp_file_contents):
             pfg.sp_file_result.append(gpt_say)
         pfg.merge_result()
 
-        # <-------- 临时存储用于调试 ----------> 
+        # <-------- 临时存储用于调试 ---------->
         pfg.get_token_num = None
         objdump(pfg, file=pj(project_folder,'temp.pkl'))
 
     write_html(pfg.sp_file_contents, pfg.sp_file_result, chatbot=chatbot, project_folder=project_folder)
 
-    #  <-------- 写出文件 ----------> 
+    #  <-------- 写出文件 ---------->
     msg = f"当前大语言模型: {llm_kwargs['llm_model']}，当前语言模型温度设定: {llm_kwargs['temperature']}。"
     final_tex = lps.merge_result(pfg.file_result, mode, msg)
     objdump((lps, pfg.file_result, mode, msg), file=pj(project_folder,'merge_result.pkl'))
 
     with open(project_folder + f'/merge_{mode}.tex', 'w', encoding='utf-8', errors='replace') as f:
         if mode != 'translate_zh' or "binary" in final_tex: f.write(final_tex)
-        
 
-    #  <-------- 整理结果, 退出 ----------> 
+
+    #  <-------- 整理结果, 退出 ---------->
     chatbot.append((f"完成了吗？", 'GPT结果已输出, 即将编译PDF'))
     yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
 
-    #  <-------- 返回 ----------> 
+    #  <-------- 返回 ---------->
     return project_folder + f'/merge_{mode}.tex'
 
 
@@ -362,7 +363,7 @@ def 编译Latex(chatbot, history, main_file_original, main_file_modified, work_f
 
         yield from update_ui_lastest_msg(f'尝试第 {n_fix}/{max_try} 次编译, 编译转化后的PDF ...', chatbot, history)   # 刷新Gradio前端界面
         ok = compile_latex_with_timeout(f'pdflatex -interaction=batchmode -file-line-error {main_file_modified}.tex', work_folder_modified)
-        
+
         if ok and os.path.exists(pj(work_folder_modified, f'{main_file_modified}.pdf')):
             # 只有第二步成功，才能继续下面的步骤
             yield from update_ui_lastest_msg(f'尝试第 {n_fix}/{max_try} 次编译, 编译BibTex ...', chatbot, history)    # 刷新Gradio前端界面
@@ -393,9 +394,9 @@ def 编译Latex(chatbot, history, main_file_original, main_file_modified, work_f
         original_pdf_success = os.path.exists(pj(work_folder_original, f'{main_file_original}.pdf'))
         modified_pdf_success = os.path.exists(pj(work_folder_modified, f'{main_file_modified}.pdf'))
         diff_pdf_success     = os.path.exists(pj(work_folder, f'merge_diff.pdf'))
-        results_ += f"原始PDF编译是否成功: {original_pdf_success};" 
-        results_ += f"转化PDF编译是否成功: {modified_pdf_success};" 
-        results_ += f"对比PDF编译是否成功: {diff_pdf_success};" 
+        results_ += f"原始PDF编译是否成功: {original_pdf_success};"
+        results_ += f"转化PDF编译是否成功: {modified_pdf_success};"
+        results_ += f"对比PDF编译是否成功: {diff_pdf_success};"
         yield from update_ui_lastest_msg(f'第{n_fix}编译结束:<br/>{results_}...', chatbot, history) # 刷新Gradio前端界面
 
         if diff_pdf_success:
@@ -409,7 +410,7 @@ def 编译Latex(chatbot, history, main_file_original, main_file_modified, work_f
                 shutil.copyfile(result_pdf, pj(work_folder, '..', 'translation', 'translate_zh.pdf'))
             promote_file_to_downloadzone(result_pdf, rename_file=None, chatbot=chatbot)  # promote file to web UI
             # 将两个PDF拼接
-            if original_pdf_success: 
+            if original_pdf_success:
                 try:
                     from .latex_toolbox import merge_pdfs
                     concat_pdf = pj(work_folder_modified, f'comparison.pdf')
@@ -425,7 +426,7 @@ def 编译Latex(chatbot, history, main_file_original, main_file_modified, work_f
             if n_fix>=max_try: break
             n_fix += 1
             can_retry, main_file_modified, buggy_lines = remove_buggy_lines(
-                file_path=pj(work_folder_modified, f'{main_file_modified}.tex'), 
+                file_path=pj(work_folder_modified, f'{main_file_modified}.tex'),
                 log_path=pj(work_folder_modified, f'{main_file_modified}.log'),
                 tex_name=f'{main_file_modified}.tex',
                 tex_name_pure=f'{main_file_modified}',
@@ -445,14 +446,14 @@ def write_html(sp_file_contents, sp_file_result, chatbot, project_folder):
         import shutil
         from crazy_functions.pdf_fns.report_gen_html import construct_html
         from toolbox import gen_time_str
-        ch = construct_html() 
+        ch = construct_html()
         orig = ""
         trans = ""
         final = []
-        for c,r in zip(sp_file_contents, sp_file_result): 
+        for c,r in zip(sp_file_contents, sp_file_result):
             final.append(c)
             final.append(r)
-        for i, k in enumerate(final): 
+        for i, k in enumerate(final):
             if i%2==0:
                 orig = k
             if i%2==1:

crazy_functions/latex_fns/latex_pickle_io.py

@@ -0,0 +1,38 @@
+import pickle
+
+
+class SafeUnpickler(pickle.Unpickler):
+
+    def get_safe_classes(self):
+        from .latex_actions import LatexPaperFileGroup, LatexPaperSplit
+        # 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,
+        }
+        return safe_classes
+
+    def find_class(self, module, name):
+        # 只允许特定的类进行反序列化
+        self.safe_classes = self.get_safe_classes()
+        if f'{module}.{name}' in self.safe_classes:
+            return self.safe_classes[f'{module}.{name}']
+        # 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/live_audio/aliyunASR.py

@@ -85,8 +85,8 @@ def write_numpy_to_wave(filename, rate, data, add_header=False):
 
 def is_speaker_speaking(vad, data, sample_rate):
     # Function to detect if the speaker is speaking
-    # The WebRTC VAD only accepts 16-bit mono PCM audio, 
-    # sampled at 8000, 16000, 32000 or 48000 Hz. 
+    # The WebRTC VAD only accepts 16-bit mono PCM audio,
+    # sampled at 8000, 16000, 32000 or 48000 Hz.
     # A frame must be either 10, 20, or 30 ms in duration:
     frame_duration = 30
     n_bit_each = int(sample_rate * frame_duration / 1000)*2 # x2 because audio is 16 bit (2 bytes)
@@ -94,7 +94,7 @@ def is_speaker_speaking(vad, data, sample_rate):
     for t in range(len(data)):
         if t!=0 and t % n_bit_each == 0:
             res_list.append(vad.is_speech(data[t-n_bit_each:t], sample_rate))
-    
+
     info = ''.join(['^' if r else '.' for r in res_list])
     info = info[:10]
     if any(res_list):
@@ -186,10 +186,10 @@ class AliyunASR():
         keep_alive_last_send_time = time.time()
         while not self.stop:
             # time.sleep(self.capture_interval)
-            audio = rad.read(uuid.hex) 
+            audio = rad.read(uuid.hex)
             if audio is not None:
                 # convert to pcm file
-                temp_file = f'{temp_folder}/{uuid.hex}.pcm' # 
+                temp_file = f'{temp_folder}/{uuid.hex}.pcm' #
                 dsdata = change_sample_rate(audio, rad.rate, NEW_SAMPLERATE) # 48000 --> 16000
                 write_numpy_to_wave(temp_file, NEW_SAMPLERATE, dsdata)
                 # read pcm binary

crazy_functions/live_audio/audio_io.py

@@ -3,12 +3,12 @@ from scipy import interpolate
 
 def Singleton(cls):
     _instance = {}
- 
+
     def _singleton(*args, **kargs):
         if cls not in _instance:
             _instance[cls] = cls(*args, **kargs)
         return _instance[cls]
- 
+
     return _singleton
 
 
@@ -39,7 +39,7 @@ class RealtimeAudioDistribution():
         else:
             res = None
         return res
-    
+
 def change_sample_rate(audio, old_sr, new_sr):
     duration = audio.shape[0] / old_sr
 

crazy_functions/multi_stage/multi_stage_utils.py

@@ -40,7 +40,7 @@ class GptAcademicState():
 
 class GptAcademicGameBaseState():
     """
-    1. first init: __init__ -> 
+    1. first init: __init__ ->
     """
     def init_game(self, chatbot, lock_plugin):
         self.plugin_name = None
@@ -53,7 +53,7 @@ class GptAcademicGameBaseState():
             raise ValueError("callback_fn is None")
         chatbot._cookies['lock_plugin'] = self.callback_fn
         self.dump_state(chatbot)
-        
+
     def get_plugin_name(self):
         if self.plugin_name is None:
             raise ValueError("plugin_name is None")
@@ -71,7 +71,7 @@ class GptAcademicGameBaseState():
         state = chatbot._cookies.get(f'plugin_state/{plugin_name}', None)
         if state is not None:
             state = pickle.loads(state)
-        else: 
+        else:
             state = cls()
             state.init_game(chatbot, lock_plugin)
         state.plugin_name = plugin_name
@@ -79,7 +79,7 @@ class GptAcademicGameBaseState():
         state.chatbot = chatbot
         state.callback_fn = callback_fn
         return state
-    
+
     def continue_game(self, prompt, chatbot, history):
         # 游戏主体
         yield from self.step(prompt, chatbot, history)

crazy_functions/pdf_fns/breakdown_txt.py

@@ -35,7 +35,7 @@ def cut(limit, get_token_fn, txt_tocut, must_break_at_empty_line, break_anyway=F
     remain_txt_to_cut_storage = ""
     # 为了加速计算，我们采样一个特殊的手段。当 remain_txt_to_cut > `_max` 时， 我们把 _max 后的文字转存至 remain_txt_to_cut_storage
     remain_txt_to_cut, remain_txt_to_cut_storage = maintain_storage(remain_txt_to_cut, remain_txt_to_cut_storage)
-    
+
     while True:
         if get_token_fn(remain_txt_to_cut) <= limit:
             # 如果剩余文本的token数小于限制，那么就不用切了

crazy_functions/pdf_fns/parse_pdf.py

@@ -64,8 +64,8 @@ def produce_report_markdown(gpt_response_collection, meta, paper_meta_info, chat
             # 再做一个小修改：重新修改当前part的标题，默认用英文的
             cur_value += value
             translated_res_array.append(cur_value)
-    res_path = write_history_to_file(meta +  ["# Meta Translation" , paper_meta_info] + translated_res_array, 
-                                     file_basename = f"{gen_time_str()}-translated_only.md", 
+    res_path = write_history_to_file(meta +  ["# Meta Translation" , paper_meta_info] + translated_res_array,
+                                     file_basename = f"{gen_time_str()}-translated_only.md",
                                      file_fullname = None,
                                      auto_caption = False)
     promote_file_to_downloadzone(res_path, rename_file=os.path.basename(res_path)+'.md', chatbot=chatbot)
@@ -144,11 +144,11 @@ def translate_pdf(article_dict, llm_kwargs, chatbot, fp, generated_conclusion_fi
     produce_report_markdown(gpt_response_collection, meta, paper_meta_info, chatbot, fp, generated_conclusion_files)
 
     # -=-=-=-=-=-=-=-= 写出HTML文件 -=-=-=-=-=-=-=-=
-    ch = construct_html() 
+    ch = construct_html()
     orig = ""
     trans = ""
     gpt_response_collection_html = copy.deepcopy(gpt_response_collection)
-    for i,k in enumerate(gpt_response_collection_html): 
+    for i,k in enumerate(gpt_response_collection_html):
         if i%2==0:
             gpt_response_collection_html[i] = inputs_show_user_array[i//2]
         else:
@@ -159,7 +159,7 @@ def translate_pdf(article_dict, llm_kwargs, chatbot, fp, generated_conclusion_fi
 
     final = ["", "", "一、论文概况",  "", "Abstract", paper_meta_info,  "二、论文翻译",  ""]
     final.extend(gpt_response_collection_html)
-    for i, k in enumerate(final): 
+    for i, k in enumerate(final):
         if i%2==0:
             orig = k
         if i%2==1:

crazy_functions/pdf_fns/parse_word.py

@@ -0,0 +1,85 @@
+from crazy_functions.crazy_utils import read_and_clean_pdf_text, get_files_from_everything
+import os
+import re
+def extract_text_from_files(txt, chatbot, history):
+    """
+    查找pdf/md/word并获取文本内容并返回状态以及文本
+
+    输入参数 Args:
+        chatbot: chatbot inputs and outputs （用户界面对话窗口句柄，用于数据流可视化）
+        history (list): List of chat history （历史，对话历史列表）
+
+    输出 Returns:
+        文件是否存在(bool)
+        final_result(list):文本内容
+        page_one(list):第一页内容/摘要
+        file_manifest(list):文件路径
+        excption(string):需要用户手动处理的信息,如没出错则保持为空
+    """
+
+    final_result = []
+    page_one = []
+    file_manifest = []
+    excption = ""
+
+    if txt == "":
+        final_result.append(txt)
+        return False, final_result, page_one, file_manifest, excption   #如输入区内容不是文件则直接返回输入区内容
+
+    #查找输入区内容中的文件
+    file_pdf,pdf_manifest,folder_pdf = get_files_from_everything(txt, '.pdf')
+    file_md,md_manifest,folder_md = get_files_from_everything(txt, '.md')
+    file_word,word_manifest,folder_word = get_files_from_everything(txt, '.docx')
+    file_doc,doc_manifest,folder_doc = get_files_from_everything(txt, '.doc')
+
+    if file_doc:
+        excption = "word"
+        return False, final_result, page_one, file_manifest, excption
+
+    file_num = len(pdf_manifest) + len(md_manifest) + len(word_manifest)
+    if file_num == 0:
+        final_result.append(txt)
+        return False, final_result, page_one, file_manifest, excption   #如输入区内容不是文件则直接返回输入区内容
+
+    if file_pdf:
+        try:    # 尝试导入依赖，如果缺少依赖，则给出安装建议
+            import fitz
+        except:
+            excption = "pdf"
+            return False, final_result, page_one, file_manifest, excption
+        for index, fp in enumerate(pdf_manifest):
+            file_content, pdf_one = read_and_clean_pdf_text(fp) # （尝试）按照章节切割PDF
+            file_content = file_content.encode('utf-8', 'ignore').decode()   # avoid reading non-utf8 chars
+            pdf_one = str(pdf_one).encode('utf-8', 'ignore').decode()  # avoid reading non-utf8 chars
+            final_result.append(file_content)
+            page_one.append(pdf_one)
+            file_manifest.append(os.path.relpath(fp, folder_pdf))
+
+    if file_md:
+        for index, fp in enumerate(md_manifest):
+            with open(fp, 'r', encoding='utf-8', errors='replace') as f:
+                file_content = f.read()
+            file_content = file_content.encode('utf-8', 'ignore').decode()
+            headers = re.findall(r'^#\s(.*)$', file_content, re.MULTILINE)  #接下来提取md中的一级/二级标题作为摘要
+            if len(headers) > 0:
+                page_one.append("\n".join(headers)) #合并所有的标题,以换行符分割
+            else:
+                page_one.append("")
+            final_result.append(file_content)
+            file_manifest.append(os.path.relpath(fp, folder_md))
+
+    if file_word:
+        try:    # 尝试导入依赖，如果缺少依赖，则给出安装建议
+            from docx import Document
+        except:
+            excption = "word_pip"
+            return False, final_result, page_one, file_manifest, excption
+        for index, fp in enumerate(word_manifest):
+            doc = Document(fp)
+            file_content = '\n'.join([p.text for p in doc.paragraphs])
+            file_content = file_content.encode('utf-8', 'ignore').decode()
+            page_one.append(file_content[:200])
+            final_result.append(file_content)
+            file_manifest.append(os.path.relpath(fp, folder_word))
+
+    return True, final_result, page_one, file_manifest, excption

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/vector_fns/vector_database.py

@@ -28,7 +28,7 @@ EMBEDDING_DEVICE = "cpu"
 
 # 基于上下文的prompt模版，请务必保留"{question}"和"{context}"
 PROMPT_TEMPLATE = """已知信息：
-{context} 
+{context}
 
 根据上述已知信息，简洁和专业的来回答用户的问题。如果无法从中得到答案，请说 “根据已知信息无法回答该问题” 或 “没有提供足够的相关信息”，不允许在答案中添加编造成分，答案请使用中文。 问题是：{question}"""
 
@@ -58,7 +58,7 @@ OPEN_CROSS_DOMAIN = False
 def similarity_search_with_score_by_vector(
         self, embedding: List[float], k: int = 4
 ) -> List[Tuple[Document, float]]:
-    
+
     def seperate_list(ls: List[int]) -> List[List[int]]:
         lists = []
         ls1 = [ls[0]]
@@ -200,7 +200,7 @@ class LocalDocQA:
             return vs_path, loaded_files
         else:
             raise RuntimeError("文件加载失败，请检查文件格式是否正确")
-        
+
     def get_loaded_file(self, vs_path):
         ds = self.vector_store.docstore
         return set([ds._dict[k].metadata['source'].split(vs_path)[-1] for k in ds._dict])
@@ -290,10 +290,10 @@ class knowledge_archive_interface():
         self.threadLock.acquire()
         # import uuid
         self.current_id = id
-        self.qa_handle, self.kai_path = construct_vector_store(   
-            vs_id=self.current_id, 
+        self.qa_handle, self.kai_path = construct_vector_store(
+            vs_id=self.current_id,
             vs_path=vs_path,
-            files=file_manifest, 
+            files=file_manifest,
             sentence_size=100,
             history=[],
             one_conent="",
@@ -304,7 +304,7 @@ class knowledge_archive_interface():
 
     def get_current_archive_id(self):
         return self.current_id
-    
+
     def get_loaded_file(self, vs_path):
         return self.qa_handle.get_loaded_file(vs_path)
 
@@ -312,10 +312,10 @@ class knowledge_archive_interface():
         self.threadLock.acquire()
         if not self.current_id == id:
             self.current_id = id
-            self.qa_handle, self.kai_path = construct_vector_store(   
-                vs_id=self.current_id, 
+            self.qa_handle, self.kai_path = construct_vector_store(
+                vs_id=self.current_id,
                 vs_path=vs_path,
-                files=[], 
+                files=[],
                 sentence_size=100,
                 history=[],
                 one_conent="",
@@ -329,7 +329,7 @@ class knowledge_archive_interface():
             query = txt,
             vs_path = self.kai_path,
             score_threshold=VECTOR_SEARCH_SCORE_THRESHOLD,
-            vector_search_top_k=VECTOR_SEARCH_TOP_K, 
+            vector_search_top_k=VECTOR_SEARCH_TOP_K,
             chunk_conent=True,
             chunk_size=CHUNK_SIZE,
             text2vec = self.get_chinese_text2vec(),

crazy_functions/vt_fns/vt_call_plugin.py

@@ -35,9 +35,9 @@ def get_recent_file_prompt_support(chatbot):
     most_recent_uploaded = chatbot._cookies.get("most_recent_uploaded", None)
     path = most_recent_uploaded['path']
     prompt =   "\nAdditional Information:\n"
-    prompt =   "In case that this plugin requires a path or a file as argument," 
-    prompt += f"it is important for you to know that the user has recently uploaded a file, located at: `{path}`" 
-    prompt += f"Only use it when necessary, otherwise, you can ignore this file." 
+    prompt =   "In case that this plugin requires a path or a file as argument,"
+    prompt += f"it is important for you to know that the user has recently uploaded a file, located at: `{path}`"
+    prompt += f"Only use it when necessary, otherwise, you can ignore this file."
     return prompt
 
 def get_inputs_show_user(inputs, plugin_arr_enum_prompt):
@@ -82,7 +82,7 @@ def execute_plugin(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prom
         msg += "\n但您可以尝试再试一次\n"
         yield from update_ui_lastest_msg(lastmsg=msg, chatbot=chatbot, history=history, delay=2)
         return
-    
+
     # ⭐ ⭐ ⭐ 确认插件参数
     if not have_any_recent_upload_files(chatbot):
         appendix_info = ""
@@ -99,7 +99,7 @@ def execute_plugin(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prom
     inputs = f"A plugin named {plugin_sel.plugin_selection} is selected, " + \
              "you should extract plugin_arg from the user requirement, the user requirement is: \n\n" + \
              ">> " + (txt + appendix_info).rstrip('\n').replace('\n','\n>> ') + '\n\n' + \
-             gpt_json_io.format_instructions 
+             gpt_json_io.format_instructions
     run_gpt_fn = lambda inputs, sys_prompt: predict_no_ui_long_connection(
         inputs=inputs, llm_kwargs=llm_kwargs, history=[], sys_prompt=sys_prompt, observe_window=[])
     plugin_sel = gpt_json_io.generate_output_auto_repair(run_gpt_fn(inputs, ""), run_gpt_fn)

crazy_functions/vt_fns/vt_modify_config.py

@@ -10,7 +10,7 @@ def modify_configuration_hot(txt, llm_kwargs, plugin_kwargs, chatbot, history, s
     ALLOW_RESET_CONFIG = get_conf('ALLOW_RESET_CONFIG')
     if not ALLOW_RESET_CONFIG:
         yield from update_ui_lastest_msg(
-            lastmsg=f"当前配置不允许被修改！如需激活本功能，请在config.py中设置ALLOW_RESET_CONFIG=True后重启软件。", 
+            lastmsg=f"当前配置不允许被修改！如需激活本功能，请在config.py中设置ALLOW_RESET_CONFIG=True后重启软件。",
             chatbot=chatbot, history=history, delay=2
         )
         return
@@ -35,7 +35,7 @@ def modify_configuration_hot(txt, llm_kwargs, plugin_kwargs, chatbot, history, s
     inputs = "Analyze how to change configuration according to following user input, answer me with json: \n\n" + \
              ">> " + txt.rstrip('\n').replace('\n','\n>> ') + '\n\n' + \
              gpt_json_io.format_instructions
-    
+
     run_gpt_fn = lambda inputs, sys_prompt: predict_no_ui_long_connection(
         inputs=inputs, llm_kwargs=llm_kwargs, history=[], sys_prompt=sys_prompt, observe_window=[])
     user_intention = gpt_json_io.generate_output_auto_repair(run_gpt_fn(inputs, ""), run_gpt_fn)
@@ -45,11 +45,11 @@ def modify_configuration_hot(txt, llm_kwargs, plugin_kwargs, chatbot, history, s
     ok = (explicit_conf in txt)
     if ok:
         yield from update_ui_lastest_msg(
-            lastmsg=f"正在执行任务: {txt}\n\n新配置{explicit_conf}={user_intention.new_option_value}", 
+            lastmsg=f"正在执行任务: {txt}\n\n新配置{explicit_conf}={user_intention.new_option_value}",
             chatbot=chatbot, history=history, delay=1
         )
         yield from update_ui_lastest_msg(
-            lastmsg=f"正在执行任务: {txt}\n\n新配置{explicit_conf}={user_intention.new_option_value}\n\n正在修改配置中", 
+            lastmsg=f"正在执行任务: {txt}\n\n新配置{explicit_conf}={user_intention.new_option_value}\n\n正在修改配置中",
             chatbot=chatbot, history=history, delay=2
         )
 
@@ -69,7 +69,7 @@ def modify_configuration_reboot(txt, llm_kwargs, plugin_kwargs, chatbot, history
     ALLOW_RESET_CONFIG = get_conf('ALLOW_RESET_CONFIG')
     if not ALLOW_RESET_CONFIG:
         yield from update_ui_lastest_msg(
-            lastmsg=f"当前配置不允许被修改！如需激活本功能，请在config.py中设置ALLOW_RESET_CONFIG=True后重启软件。", 
+            lastmsg=f"当前配置不允许被修改！如需激活本功能，请在config.py中设置ALLOW_RESET_CONFIG=True后重启软件。",
             chatbot=chatbot, history=history, delay=2
         )
         return

crazy_functions/vt_fns/vt_state.py

@@ -6,7 +6,7 @@ class VoidTerminalState():
 
     def reset_state(self):
         self.has_provided_explaination = False
- 
+
     def lock_plugin(self, chatbot):
         chatbot._cookies['lock_plugin'] = 'crazy_functions.虚空终端->虚空终端'
         chatbot._cookies['plugin_state'] = pickle.dumps(self)

crazy_functions/下载arxiv论文翻译摘要.py

@@ -144,8 +144,8 @@ def 下载arxiv论文并翻译摘要(txt, llm_kwargs, plugin_kwargs, chatbot, hi
     try:
         import bs4
     except:
-        report_exception(chatbot, history, 
-            a = f"解析项目: {txt}", 
+        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 beautifulsoup4```。")
         yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
         return
@@ -157,12 +157,12 @@ def 下载arxiv论文并翻译摘要(txt, llm_kwargs, plugin_kwargs, chatbot, hi
     try:
         pdf_path, info = download_arxiv_(txt)
     except:
-        report_exception(chatbot, history, 
-            a = f"解析项目: {txt}", 
+        report_exception(chatbot, history,
+            a = f"解析项目: {txt}",
             b = f"下载pdf文件未成功")
         yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
         return
-    
+
     # 翻译摘要等
     i_say =            f"请你阅读以下学术论文相关的材料，提取摘要，翻译为中文。材料如下：{str(info)}"
     i_say_show_user =  f'请你阅读以下学术论文相关的材料，提取摘要，翻译为中文。论文：{pdf_path}'

crazy_functions/互动小游戏.py

@@ -12,9 +12,9 @@ def 随机小游戏(prompt, llm_kwargs, plugin_kwargs, chatbot, history, system_
     # 选择游戏
     cls = MiniGame_ResumeStory
     # 如果之前已经初始化了游戏实例，则继续该实例；否则重新初始化
-    state = cls.sync_state(chatbot, 
-                           llm_kwargs, 
-                           cls, 
+    state = cls.sync_state(chatbot,
+                           llm_kwargs,
+                           cls,
                            plugin_name='MiniGame_ResumeStory',
                            callback_fn='crazy_functions.互动小游戏->随机小游戏',
                            lock_plugin=True
@@ -30,9 +30,9 @@ def 随机小游戏1(prompt, llm_kwargs, plugin_kwargs, chatbot, history, system
     # 选择游戏
     cls = MiniGame_ASCII_Art
     # 如果之前已经初始化了游戏实例，则继续该实例；否则重新初始化
-    state = cls.sync_state(chatbot, 
-                           llm_kwargs, 
-                           cls, 
+    state = cls.sync_state(chatbot,
+                           llm_kwargs,
+                           cls,
                            plugin_name='MiniGame_ASCII_Art',
                            callback_fn='crazy_functions.互动小游戏->随机小游戏1',
                            lock_plugin=True

crazy_functions/交互功能函数模板.py

@@ -38,7 +38,7 @@ def 交互功能模板函数(txt, llm_kwargs, plugin_kwargs, chatbot, history, s
         inputs=inputs_show_user=f"Extract all image urls in this html page, pick the first 5 images and show them with markdown format: \n\n {page_return}"
         gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
             inputs=inputs, inputs_show_user=inputs_show_user,
-            llm_kwargs=llm_kwargs, chatbot=chatbot, history=[], 
+            llm_kwargs=llm_kwargs, chatbot=chatbot, history=[],
             sys_prompt="When you want to show an image, use markdown format. e.g. ![image_description](image_url). If there are no image url provided, answer 'no image url provided'"
         )
         chatbot[-1] = [chatbot[-1][0], gpt_say]

crazy_functions/函数动态生成.py

@@ -6,10 +6,10 @@
     - 将图像转为灰度图像
     - 将csv文件转excel表格
 
-Testing: 
-    - Crop the image, keeping the bottom half. 
-    - Swap the blue channel and red channel of the image. 
-    - Convert the image to grayscale. 
+Testing:
+    - Crop the image, keeping the bottom half.
+    - Swap the blue channel and red channel of the image.
+    - Convert the image to grayscale.
     - Convert the CSV file to an Excel spreadsheet.
 """
 
@@ -29,12 +29,12 @@ import multiprocessing
 
 templete = """
 ```python
-import ...  # Put dependencies here, e.g. import numpy as np. 
+import ...  # Put dependencies here, e.g. import numpy as np.
 
 class TerminalFunction(object): # Do not change the name of the class, The name of the class must be `TerminalFunction`
 
     def run(self, path):    # The name of the function must be `run`, it takes only a positional argument.
-        # rewrite the function you have just written here 
+        # rewrite the function you have just written here
         ...
         return generated_file_path
 ```
@@ -48,7 +48,7 @@ def get_code_block(reply):
     import re
     pattern = r"```([\s\S]*?)```" # regex pattern to match code blocks
     matches = re.findall(pattern, reply) # find all code blocks in text
-    if len(matches) == 1: 
+    if len(matches) == 1:
         return matches[0].strip('python') #  code block
     for match in matches:
         if 'class TerminalFunction' in match:
@@ -68,8 +68,8 @@ def gpt_interact_multi_step(txt, file_type, llm_kwargs, chatbot, history):
 
     # 第一步
     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=demo, 
+        inputs=i_say, inputs_show_user=i_say,
+        llm_kwargs=llm_kwargs, chatbot=chatbot, history=demo,
         sys_prompt= r"You are a world-class programmer."
     )
     history.extend([i_say, gpt_say])
@@ -82,33 +82,33 @@ def gpt_interact_multi_step(txt, file_type, llm_kwargs, chatbot, history):
     ]
     i_say = "".join(prompt_compose); inputs_show_user = "If previous stage is successful, rewrite the function you have just written to satisfy executable templete. "
     gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
-        inputs=i_say, inputs_show_user=inputs_show_user, 
-        llm_kwargs=llm_kwargs, chatbot=chatbot, history=history, 
+        inputs=i_say, inputs_show_user=inputs_show_user,
+        llm_kwargs=llm_kwargs, chatbot=chatbot, history=history,
         sys_prompt= r"You are a programmer. You need to replace `...` with valid packages, do not give `...` in your answer!"
     )
     code_to_return = gpt_say
     history.extend([i_say, gpt_say])
     yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 界面更新
-    
+
     # # 第三步
     # i_say = "Please list to packages to install to run the code above. Then show me how to use `try_install_deps` function to install them."
     # i_say += 'For instance. `try_install_deps(["opencv-python", "scipy", "numpy"])`'
     # installation_advance = yield from request_gpt_model_in_new_thread_with_ui_alive(
-    #     inputs=i_say, inputs_show_user=inputs_show_user, 
-    #     llm_kwargs=llm_kwargs, chatbot=chatbot, history=history, 
+    #     inputs=i_say, inputs_show_user=inputs_show_user,
+    #     llm_kwargs=llm_kwargs, chatbot=chatbot, history=history,
     #     sys_prompt= r"You are a programmer."
     # )
 
-    # # # 第三步  
+    # # # 第三步
     # i_say = "Show me how to use `pip` to install packages to run the code above. "
     # i_say += 'For instance. `pip install -r opencv-python scipy numpy`'
     # installation_advance = 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, 
+    #     inputs=i_say, inputs_show_user=i_say,
+    #     llm_kwargs=llm_kwargs, chatbot=chatbot, history=history,
     #     sys_prompt= r"You are a programmer."
     # )
     installation_advance = ""
-    
+
     return code_to_return, installation_advance, txt, file_type, llm_kwargs, chatbot, history
 
 
@@ -117,7 +117,7 @@ def gpt_interact_multi_step(txt, file_type, llm_kwargs, chatbot, history):
 def for_immediate_show_off_when_possible(file_type, fp, chatbot):
     if file_type in ['png', 'jpg']:
         image_path = os.path.abspath(fp)
-        chatbot.append(['这是一张图片, 展示如下:',  
+        chatbot.append(['这是一张图片, 展示如下:',
             f'本地文件地址: <br/>`{image_path}`<br/>'+
             f'本地文件预览: <br/><div align="center"><img src="file={image_path}"></div>'
         ])
@@ -177,7 +177,7 @@ def 函数动态生成(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_
         chatbot.append(["文件检索", "没有发现任何近期上传的文件。"])
         yield from update_ui_lastest_msg("没有发现任何近期上传的文件。", chatbot, history, 1)
         return  # 2. 如果没有文件
-    
+
     # 读取文件
     file_type = file_list[0].split('.')[-1]
 
@@ -185,7 +185,7 @@ def 函数动态生成(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_
     if is_the_upload_folder(txt):
         yield from update_ui_lastest_msg(f"请在输入框内填写需求, 然后再次点击该插件! 至于您的文件，不用担心, 文件路径 {txt} 已经被记忆. ", chatbot, history, 1)
         return
-    
+
     # 开始干正事
     MAX_TRY = 3
     for j in range(MAX_TRY):  # 最多重试5次
@@ -238,7 +238,7 @@ def 函数动态生成(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_
             # chatbot.append(["如果是缺乏依赖，请参考以下建议", installation_advance])
             yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
             return
-        
+
         # 顺利完成，收尾
         res = str(res)
         if os.path.exists(res):
@@ -248,5 +248,5 @@ def 函数动态生成(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_
             yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 界面更新
         else:
             chatbot.append(["执行成功了，结果是一个字符串", "结果：" + res])
-            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
 

crazy_functions/命令行助手.py

@@ -21,8 +21,8 @@ def 命令行助手(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_pro
     i_say = "请写bash命令实现以下功能：" + txt
     # 开始
     gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
-        inputs=i_say, inputs_show_user=txt, 
-        llm_kwargs=llm_kwargs, chatbot=chatbot, history=[], 
+        inputs=i_say, inputs_show_user=txt,
+        llm_kwargs=llm_kwargs, chatbot=chatbot, history=[],
         sys_prompt="你是一个Linux大师级用户。注意，当我要求你写bash命令时，尽可能地仅用一行命令解决我的要求。"
     )
     yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 界面更新

crazy_functions/图片生成.py

@@ -7,7 +7,7 @@ def gen_image(llm_kwargs, prompt, resolution="1024x1024", model="dall-e-2", qual
     from request_llms.bridge_all import model_info
 
     proxies = get_conf('proxies')
-    # Set up OpenAI API key and model 
+    # Set up OpenAI API key and model
     api_key = select_api_key(llm_kwargs['api_key'], llm_kwargs['llm_model'])
     chat_endpoint = model_info[llm_kwargs['llm_model']]['endpoint']
     # 'https://api.openai.com/v1/chat/completions'
@@ -113,7 +113,7 @@ def 图片生成_DALLE2(prompt, llm_kwargs, plugin_kwargs, chatbot, history, sys
     if ("advanced_arg" in plugin_kwargs) and (plugin_kwargs["advanced_arg"] == ""): plugin_kwargs.pop("advanced_arg")
     resolution = plugin_kwargs.get("advanced_arg", '1024x1024')
     image_url, image_path = gen_image(llm_kwargs, prompt, resolution)
-    chatbot.append([prompt,  
+    chatbot.append([prompt,
         f'图像中转网址: <br/>`{image_url}`<br/>'+
         f'中转网址预览: <br/><div align="center"><img src="{image_url}"></div>'
         f'本地文件地址: <br/>`{image_path}`<br/>'+
@@ -144,7 +144,7 @@ def 图片生成_DALLE3(prompt, llm_kwargs, plugin_kwargs, chatbot, history, sys
         elif part in ['vivid', 'natural']:
             style = part
     image_url, image_path = gen_image(llm_kwargs, prompt, resolution, model="dall-e-3", quality=quality, style=style)
-    chatbot.append([prompt,  
+    chatbot.append([prompt,
         f'图像中转网址: <br/>`{image_url}`<br/>'+
         f'中转网址预览: <br/><div align="center"><img src="{image_url}"></div>'
         f'本地文件地址: <br/>`{image_path}`<br/>'+
@@ -164,7 +164,7 @@ class ImageEditState(GptAcademicState):
         confirm = (len(file_manifest) >= 1 and file_manifest[0].endswith('.png') and os.path.exists(file_manifest[0]))
         file = None if not confirm else file_manifest[0]
         return confirm, file
-    
+
     def lock_plugin(self, chatbot):
         chatbot._cookies['lock_plugin'] = 'crazy_functions.图片生成->图片修改_DALLE2'
         self.dump_state(chatbot)

crazy_functions/多智能体.py

@@ -57,11 +57,11 @@ def 多智能体终端(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_
         if get_conf("AUTOGEN_USE_DOCKER"):
             import docker
     except:
-        chatbot.append([ f"处理任务: {txt}", 
+        chatbot.append([ f"处理任务: {txt}",
             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 pyautogen docker```。"])
         yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
         return
-    
+
     # 尝试导入依赖，如果缺少依赖，则给出安装建议
     try:
         import autogen
@@ -72,7 +72,7 @@ def 多智能体终端(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_
         chatbot.append([f"处理任务: {txt}", f"缺少docker运行环境！"])
         yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
         return
-    
+
     # 解锁插件
     chatbot.get_cookies()['lock_plugin'] = None
     persistent_class_multi_user_manager = GradioMultiuserManagerForPersistentClasses()

crazy_functions/对话历史存档.py

@@ -66,7 +66,7 @@ def read_file_to_chat(chatbot, history, file_name):
         i_say, gpt_say = h.split('<hr style="border-top: dotted 3px #ccc;">')
         chatbot.append([i_say, gpt_say])
     chatbot.append([f"存档文件详情？", f"[Local Message] 载入对话{len(html)}条，上下文{len(history)}条。"])
-    return chatbot, history    
+    return chatbot, history
 
 @CatchException
 def 对话历史存档(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
@@ -80,7 +80,7 @@ def 对话历史存档(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_
     user_request    当前用户的请求信息（IP地址等）
     """
 
-    chatbot.append(("保存当前对话", 
+    chatbot.append(("保存当前对话",
         f"[Local Message] {write_chat_to_file(chatbot, history)}，您可以调用下拉菜单中的“载入对话历史存档”还原当下的对话。"))
     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
 
@@ -108,9 +108,9 @@ def 载入对话历史存档(txt, llm_kwargs, plugin_kwargs, chatbot, history, s
         if txt == "": txt = '空空如也的输入栏'
         import glob
         local_history = "<br/>".join([
-            "`"+hide_cwd(f)+f" ({gen_file_preview(f)})"+"`" 
+            "`"+hide_cwd(f)+f" ({gen_file_preview(f)})"+"`"
             for f in glob.glob(
-                f'{get_log_folder(get_user(chatbot), plugin_name="chat_history")}/**/{f_prefix}*.html', 
+                f'{get_log_folder(get_user(chatbot), plugin_name="chat_history")}/**/{f_prefix}*.html',
                 recursive=True
             )])
         chatbot.append([f"正在查找对话历史文件（html格式）: {txt}", f"找不到任何html文件: {txt}。但本地存储了以下历史文件，您可以将任意一个文件路径粘贴到输入区，然后重试：<br/>{local_history}"])
@@ -139,7 +139,7 @@ def 删除所有本地对话历史记录(txt, llm_kwargs, plugin_kwargs, chatbot
 
     import glob, os
     local_history = "<br/>".join([
-        "`"+hide_cwd(f)+"`" 
+        "`"+hide_cwd(f)+"`"
         for f in glob.glob(
             f'{get_log_folder(get_user(chatbot), plugin_name="chat_history")}/**/{f_prefix}*.html', recursive=True
         )])

crazy_functions/总结word文档.py

@@ -40,10 +40,10 @@ def 解析docx(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot
             i_say = f'请对下面的文章片段用中文做概述，文件名是{os.path.relpath(fp, project_folder)}，文章内容是 ```{paper_frag}```'
             i_say_show_user = f'请对下面的文章片段做概述: {os.path.abspath(fp)}的第{i+1}/{len(paper_fragments)}个片段。'
             gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
-                inputs=i_say, 
-                inputs_show_user=i_say_show_user, 
+                inputs=i_say,
+                inputs_show_user=i_say_show_user,
                 llm_kwargs=llm_kwargs,
-                chatbot=chatbot, 
+                chatbot=chatbot,
                 history=[],
                 sys_prompt="总结文章。"
             )
@@ -56,10 +56,10 @@ def 解析docx(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot
         if len(paper_fragments) > 1:
             i_say = f"根据以上的对话，总结文章{os.path.abspath(fp)}的主要内容。"
             gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
-                inputs=i_say, 
-                inputs_show_user=i_say, 
+                inputs=i_say,
+                inputs_show_user=i_say,
                 llm_kwargs=llm_kwargs,
-                chatbot=chatbot, 
+                chatbot=chatbot,
                 history=this_paper_history,
                 sys_prompt="总结文章。"
             )

crazy_functions/批量Markdown翻译.py

@@ -1,5 +1,5 @@
-import glob, time, os, re, logging
-from toolbox import update_ui, trimmed_format_exc, gen_time_str, disable_auto_promotion
+import glob, shutil, os, re, logging
+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
         """
@@ -53,7 +53,7 @@ class PaperFileGroup():
 def 多文件翻译(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, language='en'):
     from .crazy_utils import request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency
 
-    #  <-------- 读取Markdown文件，删除其中的所有注释 ----------> 
+    #  <-------- 读取Markdown文件，删除其中的所有注释 ---------->
     pfg = PaperFileGroup()
 
     for index, fp in enumerate(file_manifest):
@@ -63,23 +63,23 @@ def 多文件翻译(file_manifest, project_folder, llm_kwargs, plugin_kwargs, ch
             pfg.file_paths.append(fp)
             pfg.file_contents.append(file_content)
 
-    #  <-------- 拆分过长的Markdown文件 ----------> 
-    pfg.run_file_split(max_token_limit=1500)
+    #  <-------- 拆分过长的Markdown文件 ---------->
+    pfg.run_file_split(max_token_limit=2048)
     n_split = len(pfg.sp_file_contents)
 
-    #  <-------- 多线程翻译开始 ----------> 
+    #  <-------- 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)]
     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)]
     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)]
@@ -99,11 +99,16 @@ 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())
 
-    #  <-------- 整理结果，退出 ----------> 
+    #  <-------- 整理结果，退出 ---------->
     create_report_file_name = gen_time_str() + f"-chatgpt.md"
     res = write_history_to_file(gpt_response_collection, file_basename=create_report_file_name)
     promote_file_to_downloadzone(res, chatbot=chatbot)
@@ -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:
@@ -255,7 +257,7 @@ def Markdown翻译指定语言(txt, llm_kwargs, plugin_kwargs, chatbot, history,
         report_exception(chatbot, history, a = f"解析项目: {txt}", b = f"找不到任何.md文件: {txt}")
         yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
         return
-    
+
     if ("advanced_arg" in plugin_kwargs) and (plugin_kwargs["advanced_arg"] == ""): plugin_kwargs.pop("advanced_arg")
     language = plugin_kwargs.get("advanced_arg", 'Chinese')
     yield from 多文件翻译(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, language=language)

crazy_functions/批量总结PDF文档.py

@@ -17,7 +17,7 @@ def 解析PDF(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot,
         file_content, page_one = read_and_clean_pdf_text(file_name) # （尝试）按照章节切割PDF
         file_content = file_content.encode('utf-8', 'ignore').decode()   # avoid reading non-utf8 chars
         page_one = str(page_one).encode('utf-8', 'ignore').decode()  # avoid reading non-utf8 chars
-        
+
         TOKEN_LIMIT_PER_FRAGMENT = 2500
 
         from crazy_functions.pdf_fns.breakdown_txt import breakdown_text_to_satisfy_token_limit
@@ -25,7 +25,7 @@ def 解析PDF(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot,
         page_one_fragments = breakdown_text_to_satisfy_token_limit(txt=str(page_one), limit=TOKEN_LIMIT_PER_FRAGMENT//4, llm_model=llm_kwargs['llm_model'])
         # 为了更好的效果，我们剥离Introduction之后的部分（如果有）
         paper_meta = page_one_fragments[0].split('introduction')[0].split('Introduction')[0].split('INTRODUCTION')[0]
-        
+
         ############################## <第 1 步，从摘要中提取高价值信息，放到history中> ##################################
         final_results = []
         final_results.append(paper_meta)
@@ -44,10 +44,10 @@ def 解析PDF(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot,
             i_say = f"Read this section, recapitulate the content of this section with less than {NUM_OF_WORD} Chinese characters: {paper_fragments[i]}"
             i_say_show_user = f"[{i+1}/{n_fragment}] Read this section, recapitulate the content of this section with less than {NUM_OF_WORD} Chinese characters: {paper_fragments[i][:200]}"
             gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(i_say, i_say_show_user,  # i_say=真正给chatgpt的提问， i_say_show_user=给用户看的提问
-                                                                                llm_kwargs, chatbot, 
+                                                                                llm_kwargs, chatbot,
                                                                                 history=["The main idea of the previous section is?", last_iteration_result], # 迭代上一次的结果
                                                                                 sys_prompt="Extract the main idea of this section with Chinese."  # 提示
-                                                                                ) 
+                                                                                )
             iteration_results.append(gpt_say)
             last_iteration_result = gpt_say
 
@@ -67,15 +67,15 @@ def 解析PDF(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot,
     - (2):What are the past methods? What are the problems with them? Is the approach well motivated?
     - (3):What is the research methodology proposed in this paper?
     - (4):On what task and what performance is achieved by the methods in this paper? Can the performance support their goals?
-Follow the format of the output that follows:                  
+Follow the format of the output that follows:
 1. Title: xxx\n\n
 2. Authors: xxx\n\n
 3. Affiliation: xxx\n\n
 4. Keywords: xxx\n\n
 5. Urls: xxx or xxx , xxx \n\n
 6. Summary: \n\n
-    - (1):xxx;\n 
-    - (2):xxx;\n 
+    - (1):xxx;\n
+    - (2):xxx;\n
     - (3):xxx;\n
     - (4):xxx.\n\n
 Be sure to use Chinese answers (proper nouns need to be marked in English), statements as concise and academic as possible,
@@ -85,8 +85,8 @@ do not have too much repetitive information, numerical values using the original
         file_write_buffer.extend(final_results)
         i_say, final_results = input_clipping(i_say, final_results, max_token_limit=2000)
         gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
-            inputs=i_say, inputs_show_user='开始最终总结', 
-            llm_kwargs=llm_kwargs, chatbot=chatbot, history=final_results, 
+            inputs=i_say, inputs_show_user='开始最终总结',
+            llm_kwargs=llm_kwargs, chatbot=chatbot, history=final_results,
             sys_prompt= f"Extract the main idea of this paper with less than {NUM_OF_WORD} Chinese characters"
         )
         final_results.append(gpt_say)
@@ -114,8 +114,8 @@ def 批量总结PDF文档(txt, llm_kwargs, plugin_kwargs, chatbot, history, syst
     try:
         import fitz
     except:
-        report_exception(chatbot, history, 
-            a = f"解析项目: {txt}", 
+        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```。")
         yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
         return
@@ -134,7 +134,7 @@ def 批量总结PDF文档(txt, llm_kwargs, plugin_kwargs, chatbot, history, syst
 
     # 搜索需要处理的文件清单
     file_manifest = [f for f in glob.glob(f'{project_folder}/**/*.pdf', recursive=True)]
-    
+
     # 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.tex或.pdf文件: {txt}")

crazy_functions/批量总结PDF文档pdfminer.py

@@ -85,10 +85,10 @@ def 解析Paper(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbo
             msg = '正常'
             # ** gpt request **
             gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
-                inputs=i_say, 
-                inputs_show_user=i_say_show_user, 
+                inputs=i_say,
+                inputs_show_user=i_say_show_user,
                 llm_kwargs=llm_kwargs,
-                chatbot=chatbot, 
+                chatbot=chatbot,
                 history=[],
                 sys_prompt="总结文章。"
             )  # 带超时倒计时
@@ -106,10 +106,10 @@ def 解析Paper(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbo
         msg = '正常'
         # ** gpt request **
         gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
-            inputs=i_say, 
-            inputs_show_user=i_say, 
+            inputs=i_say,
+            inputs_show_user=i_say,
             llm_kwargs=llm_kwargs,
-            chatbot=chatbot, 
+            chatbot=chatbot,
             history=history,
             sys_prompt="总结文章。"
         )  # 带超时倒计时
@@ -138,8 +138,8 @@ def 批量总结PDF文档pdfminer(txt, llm_kwargs, plugin_kwargs, chatbot, histo
     try:
         import pdfminer, bs4
     except:
-        report_exception(chatbot, history, 
-            a = f"解析项目: {txt}", 
+        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 pdfminer beautifulsoup4```。")
         yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
         return

crazy_functions/批量翻译PDF文档_NOUGAT.py

@@ -76,8 +76,8 @@ def 批量翻译PDF文档(txt, llm_kwargs, plugin_kwargs, chatbot, history, syst
     success_mmd, file_manifest_mmd, _ = get_files_from_everything(txt, type='.mmd')
     success = success or success_mmd
     file_manifest += file_manifest_mmd
-    chatbot.append(["文件列表：", ", ".join([e.split('/')[-1] for e in file_manifest])]); 
-    yield from update_ui(      chatbot=chatbot, history=history) 
+    chatbot.append(["文件列表：", ", ".join([e.split('/')[-1] for e in file_manifest])]);
+    yield from update_ui(      chatbot=chatbot, history=history)
     # 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'

crazy_functions/数学动画生成manim.py

@@ -27,7 +27,7 @@ def eval_manim(code):
 
     class_name = get_class_name(code)
 
-    try: 
+    try:
         time_str = gen_time_str()
         subprocess.check_output([sys.executable, '-c', f"from gpt_log.MyAnimation import {class_name}; {class_name}().render()"])
         shutil.move(f'media/videos/1080p60/{class_name}.mp4', f'gpt_log/{class_name}-{time_str}.mp4')
@@ -36,7 +36,7 @@ def eval_manim(code):
         output = e.output.decode()
         print(f"Command returned non-zero exit status {e.returncode}: {output}.")
         return f"Evaluating python script failed: {e.output}."
-    except: 
+    except:
         print('generating mp4 failed')
         return "Generating mp4 failed."
 
@@ -45,7 +45,7 @@ def get_code_block(reply):
     import re
     pattern = r"```([\s\S]*?)```" # regex pattern to match code blocks
     matches = re.findall(pattern, reply) # find all code blocks in text
-    if len(matches) != 1: 
+    if len(matches) != 1:
         raise RuntimeError("GPT is not generating proper code.")
     return matches[0].strip('python') #  code block
 
@@ -61,7 +61,7 @@ def 动画生成(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt
     user_request    当前用户的请求信息（IP地址等）
     """
     # 清空历史，以免输入溢出
-    history = []    
+    history = []
 
     # 基本信息：功能、贡献者
     chatbot.append([
@@ -73,24 +73,24 @@ def 动画生成(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt
     # 尝试导入依赖, 如果缺少依赖, 则给出安装建议
     dep_ok = yield from inspect_dependency(chatbot=chatbot, history=history) # 刷新界面
     if not dep_ok: return
-    
+
     # 输入
     i_say = f'Generate a animation to show: ' + txt
     demo = ["Here is some examples of manim", examples_of_manim()]
     _, demo = input_clipping(inputs="", history=demo, max_token_limit=2560)
     # 开始
     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=demo, 
+        inputs=i_say, inputs_show_user=i_say,
+        llm_kwargs=llm_kwargs, chatbot=chatbot, history=demo,
         sys_prompt=
         r"Write a animation script with 3blue1brown's manim. "+
-        r"Please begin with `from manim import *`. " + 
+        r"Please begin with `from manim import *`. " +
         r"Answer me with a code block wrapped by ```."
     )
     chatbot.append(["开始生成动画", "..."])
     history.extend([i_say, gpt_say])
     yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 界面更新
-    
+
     # 将代码转为动画
     code = get_code_block(gpt_say)
     res = eval_manim(code)

crazy_functions/理解PDF文档内容.py

@@ -15,7 +15,7 @@ def 解析PDF(file_name, llm_kwargs, plugin_kwargs, chatbot, history, system_pro
     file_content, page_one = read_and_clean_pdf_text(file_name) # （尝试）按照章节切割PDF
     file_content = file_content.encode('utf-8', 'ignore').decode()   # avoid reading non-utf8 chars
     page_one = str(page_one).encode('utf-8', 'ignore').decode()  # avoid reading non-utf8 chars
-    
+
     TOKEN_LIMIT_PER_FRAGMENT = 2500
 
     from crazy_functions.pdf_fns.breakdown_txt import breakdown_text_to_satisfy_token_limit
@@ -23,7 +23,7 @@ def 解析PDF(file_name, llm_kwargs, plugin_kwargs, chatbot, history, system_pro
     page_one_fragments = breakdown_text_to_satisfy_token_limit(txt=str(page_one), limit=TOKEN_LIMIT_PER_FRAGMENT//4, llm_model=llm_kwargs['llm_model'])
     # 为了更好的效果，我们剥离Introduction之后的部分（如果有）
     paper_meta = page_one_fragments[0].split('introduction')[0].split('Introduction')[0].split('INTRODUCTION')[0]
-    
+
     ############################## <第 1 步，从摘要中提取高价值信息，放到history中> ##################################
     final_results = []
     final_results.append(paper_meta)
@@ -42,10 +42,10 @@ def 解析PDF(file_name, llm_kwargs, plugin_kwargs, chatbot, history, system_pro
         i_say = f"Read this section, recapitulate the content of this section with less than {NUM_OF_WORD} words: {paper_fragments[i]}"
         i_say_show_user = f"[{i+1}/{n_fragment}] Read this section, recapitulate the content of this section with less than {NUM_OF_WORD} words: {paper_fragments[i][:200]} ...."
         gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(i_say, i_say_show_user,  # i_say=真正给chatgpt的提问， i_say_show_user=给用户看的提问
-                                                                           llm_kwargs, chatbot, 
+                                                                           llm_kwargs, chatbot,
                                                                            history=["The main idea of the previous section is?", last_iteration_result], # 迭代上一次的结果
                                                                            sys_prompt="Extract the main idea of this section, answer me with Chinese."  # 提示
-                                                                        ) 
+                                                                        )
         iteration_results.append(gpt_say)
         last_iteration_result = gpt_say
 
@@ -76,8 +76,8 @@ def 理解PDF文档内容标准文件输入(txt, llm_kwargs, plugin_kwargs, chat
     try:
         import fitz
     except:
-        report_exception(chatbot, history, 
-            a = f"解析项目: {txt}", 
+        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```。")
         yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
         return

crazy_functions/生成函数注释.py

@@ -16,7 +16,7 @@ def 生成函数注释(file_manifest, project_folder, llm_kwargs, plugin_kwargs,
         chatbot.append((i_say_show_user, "[Local Message] waiting gpt response."))
         yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
 
-        if not fast_debug: 
+        if not fast_debug:
             msg = '正常'
             # ** gpt request **
             gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
@@ -27,7 +27,7 @@ def 生成函数注释(file_manifest, project_folder, llm_kwargs, plugin_kwargs,
             yield from update_ui(chatbot=chatbot, history=history, msg=msg) # 刷新界面
             if not fast_debug: time.sleep(2)
 
-    if not fast_debug: 
+    if not fast_debug:
         res = write_history_to_file(history)
         promote_file_to_downloadzone(res, chatbot=chatbot)
         chatbot.append(("完成了吗？", res))

crazy_functions/生成多种Mermaid图表.py

@@ -1,6 +1,5 @@
 from toolbox import CatchException, update_ui, report_exception
 from .crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
-from .crazy_utils import read_and_clean_pdf_text
 import datetime
 
 #以下是每类图表的PROMPT
@@ -162,7 +161,7 @@ mindmap
 ```
 """
 
-def 解析历史输入(history,llm_kwargs,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
@@ -170,8 +169,6 @@ def 解析历史输入(history,llm_kwargs,chatbot,plugin_kwargs):
     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> ##################################
-    i_say_show_user = f'首先你从历史记录或文件中提取摘要。'; gpt_say = "[Local Message] 收到。"   # 用户提示
-    chatbot.append([i_say_show_user, gpt_say]); yield from update_ui(chatbot=chatbot, history=history)    # 更新UI
     results = []
     MAX_WORD_TOTAL = 4096
     n_txt = len(txt)
@@ -179,18 +176,18 @@ def 解析历史输入(history,llm_kwargs,chatbot,plugin_kwargs):
     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: {txt[i]}"
+        i_say = f"Read this section, recapitulate the content of this section with less than {NUM_OF_WORD} words in Chinese: {txt[i]}"
         i_say_show_user = f"[{i+1}/{n_txt}] Read this section, recapitulate the content of this section with less than {NUM_OF_WORD} words: {txt[i][:200]} ...."
         gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(i_say, i_say_show_user,  # i_say=真正给chatgpt的提问， i_say_show_user=给用户看的提问
-                                                                           llm_kwargs, chatbot, 
+                                                                           llm_kwargs, chatbot,
                                                                            history=["The main content of the previous section is?", last_iteration_result], # 迭代上一次的结果
                                                                            sys_prompt="Extracts the main content from the text section where it is located for graphing purposes, answer me with Chinese."  # 提示
-                                                                        ) 
+                                                                        )
         results.append(gpt_say)
         last_iteration_result = gpt_say
     ############################## <第 2 步，根据整理的摘要选择图表类型> ##################################
     if ("advanced_arg" in plugin_kwargs) and (plugin_kwargs["advanced_arg"] == ""): plugin_kwargs.pop("advanced_arg")
-    gpt_say = plugin_kwargs.get("advanced_arg", "")     #将图表类型参数赋值为插件参数  
+    gpt_say = plugin_kwargs.get("advanced_arg", "")     #将图表类型参数赋值为插件参数
     results_txt = '\n'.join(results)    #合并摘要
     if gpt_say not in ['1','2','3','4','5','6','7','8','9']:    #如插件参数不正确则使用对话模型判断
         i_say_show_user = f'接下来将判断适合的图表类型,如连续3次判断失败将会使用流程图进行绘制'; gpt_say = "[Local Message] 收到。"   # 用户提示
@@ -201,7 +198,7 @@ def 解析历史输入(history,llm_kwargs,chatbot,plugin_kwargs):
             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, 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
@@ -231,36 +228,12 @@ def 解析历史输入(history,llm_kwargs,chatbot,plugin_kwargs):
     gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
         inputs=i_say,
         inputs_show_user=i_say_show_user,
-        llm_kwargs=llm_kwargs, chatbot=chatbot, history=[], 
-        sys_prompt="你精通使用mermaid语法来绘制图表,首先确保语法正确,其次避免在mermaid语法中使用不允许的字符,此外也应当分考虑图表的可读性。"
+        llm_kwargs=llm_kwargs, chatbot=chatbot, history=[],
+        sys_prompt=""
     )
     history.append(gpt_say)
     yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 界面更新
 
-def 输入区文件处理(txt):
-    if txt == "": return False, txt
-    success = True
-    import glob
-    from .crazy_utils import get_files_from_everything
-    file_pdf,pdf_manifest,folder_pdf = get_files_from_everything(txt, '.pdf')
-    file_md,md_manifest,folder_md = get_files_from_everything(txt, '.md')
-    if len(pdf_manifest) == 0 and len(md_manifest) == 0:
-        return False, txt   #如输入区内容不是文件则直接返回输入区内容
-    
-    final_result = ""
-    if file_pdf:
-        for index, fp in enumerate(pdf_manifest):
-            file_content, page_one = read_and_clean_pdf_text(fp) # （尝试）按照章节切割PDF
-            file_content = file_content.encode('utf-8', 'ignore').decode()   # avoid reading non-utf8 chars
-            final_result += "\n" + file_content
-    if file_md:
-        for index, fp in enumerate(md_manifest):
-            with open(fp, 'r', encoding='utf-8', errors='replace') as f:
-                file_content = f.read()
-            file_content = file_content.encode('utf-8', 'ignore').decode()
-            final_result += "\n" + file_content
-    return True, final_result
-    
 @CatchException
 def 生成多种Mermaid图表(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
     """
@@ -276,27 +249,48 @@ def 生成多种Mermaid图表(txt, llm_kwargs, plugin_kwargs, chatbot, history,
 
     # 基本信息：功能、贡献者
     chatbot.append([
-        "函数插件功能？", 
-        "根据当前聊天历史或文件中(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？",
+        "根据当前聊天历史或指定的路径文件(文件内容优先)绘制多种mermaid图表，将会由对话模型首先判断适合的图表类型，随后绘制图表。\
         \n您也可以使用插件参数指定绘制的图表类型,函数插件贡献者: Menghuan1918"])
     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:
-        import fitz
-    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```。")
-        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
-        return
-    
     if os.path.exists(txt):     #如输入区无内容则直接解析历史记录
-        file_exist, txt = 输入区文件处理(txt)
+        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)
     else:
         file_exist = False
+        excption = ""
+        file_manifest = []
 
-    if file_exist : history = []    #如输入区内容为文件则清空历史记录
-    history.append(txt)     #将解析后的txt传递加入到历史中
-    
-    yield from 解析历史输入(history,llm_kwargs,chatbot,plugin_kwargs)  
+    if excption != "":
+        if excption == "word":
+            report_exception(chatbot, history,
+                a = f"解析项目: {txt}",
+                b = f"找到了.doc文件，但是该文件格式不被支持，请先转化为.docx格式。")
+
+        elif excption == "pdf":
+            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```。")
+
+        elif excption == "word_pip":
+                report_exception(chatbot, history,
+                    a=f"解析项目: {txt}",
+                    b=f"导入软件依赖失败。使用该模块需要额外依赖，安装方法```pip install --upgrade python-docx pywin32```。")
+
+        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+
+    else:
+        if not file_exist:
+            history.append(txt)     #如输入区不是文件则将输入区内容加入历史记录
+            i_say_show_user = f'首先你从历史记录中提取摘要。'; gpt_say = "[Local Message] 收到。"   # 用户提示
+            chatbot.append([i_say_show_user, gpt_say]); yield from update_ui(chatbot=chatbot, history=history)    # 更新UI
+            yield from 解析历史输入(history,llm_kwargs,file_manifest,chatbot,plugin_kwargs)
+        else:
+            file_num = len(file_manifest)
+            for i in range(file_num):     #依次处理文件
+                i_say_show_user = f"[{i+1}/{file_num}]处理文件{file_manifest[i]}"; gpt_say = "[Local Message] 收到。"   # 用户提示
+                chatbot.append([i_say_show_user, gpt_say]); yield from update_ui(chatbot=chatbot, history=history)    # 更新UI
+                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)

crazy_functions/知识库问答.py

@@ -9,7 +9,7 @@ install_msg ="""
 
 3. python -m pip install unstructured[all-docs] --upgrade
 
-4. python -c 'import nltk; nltk.download("punkt")' 
+4. python -c 'import nltk; nltk.download("punkt")'
 """
 
 @CatchException
@@ -56,7 +56,7 @@ def 知识库文件注入(txt, llm_kwargs, plugin_kwargs, chatbot, history, syst
         chatbot.append(["没有找到任何可读取文件", "当前支持的格式包括: txt, md, docx, pptx, pdf, json等"])
         yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
         return
-    
+
     # < -------------------预热文本向量化模组--------------- >
     chatbot.append(['<br/>'.join(file_manifest), "正在预热文本向量化模组, 如果是第一次运行, 将消耗较长时间下载中文向量化模型..."])
     yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
@@ -109,8 +109,8 @@ def 读取知识库作答(txt, llm_kwargs, plugin_kwargs, chatbot, history, syst
     chatbot.append((txt, f'[知识库 {kai_id}] ' + prompt))
     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
     gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
-        inputs=prompt, inputs_show_user=txt, 
-        llm_kwargs=llm_kwargs, chatbot=chatbot, history=[], 
+        inputs=prompt, inputs_show_user=txt,
+        llm_kwargs=llm_kwargs, chatbot=chatbot, history=[],
         sys_prompt=system_prompt
     )
     history.extend((prompt, gpt_say))

crazy_functions/联网的ChatGPT.py

@@ -40,10 +40,10 @@ def scrape_text(url, proxies) -> str:
         '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: 
+    try:
         response = requests.get(url, headers=headers, proxies=proxies, timeout=8)
         if response.encoding == "ISO-8859-1": response.encoding = response.apparent_encoding
-    except: 
+    except:
         return "无法连接到该网页"
     soup = BeautifulSoup(response.text, "html.parser")
     for script in soup(["script", "style"]):
@@ -66,7 +66,7 @@ def 连接网络回答问题(txt, llm_kwargs, plugin_kwargs, chatbot, history, s
     user_request    当前用户的请求信息（IP地址等）
     """
     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}", 
+    chatbot.append((f"请结合互联网信息回答以下问题：{txt}",
                     "[Local Message] 请注意，您正在调用一个[函数插件]的模板，该模板可以实现ChatGPT联网信息综合。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。您若希望分享新的功能模组，请不吝PR！"))
     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
 
@@ -91,13 +91,13 @@ def 连接网络回答问题(txt, llm_kwargs, plugin_kwargs, chatbot, history, s
     # ------------- < 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, 
+        inputs=i_say,
+        history=history,
         max_token_limit=model_info[llm_kwargs['llm_model']]['max_token']*3//4
     )
     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, 
+        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)

crazy_functions/虚空终端.py

@@ -33,7 +33,7 @@ explain_msg = """
     - 「请调用插件，解析python源代码项目，代码我刚刚打包拖到上传区了」
     - 「请问Transformer网络的结构是怎样的？」
 
-2. 您可以打开插件下拉菜单以了解本项目的各种能力。    
+2. 您可以打开插件下拉菜单以了解本项目的各种能力。
 
 3. 如果您使用「调用插件xxx」、「修改配置xxx」、「请问」等关键词，您的意图可以被识别的更准确。
 
@@ -67,7 +67,7 @@ class UserIntention(BaseModel):
 def chat(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_intention):
     gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
         inputs=txt, inputs_show_user=txt,
-        llm_kwargs=llm_kwargs, chatbot=chatbot, history=[], 
+        llm_kwargs=llm_kwargs, chatbot=chatbot, history=[],
         sys_prompt=system_prompt
     )
     chatbot[-1] = [txt, gpt_say]
@@ -115,7 +115,7 @@ def 虚空终端(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt
     if is_the_upload_folder(txt):
         state.set_state(chatbot=chatbot, key='has_provided_explaination', value=False)
         appendix_msg = "\n\n**很好，您已经上传了文件**，现在请您描述您的需求。"
-        
+
     if is_certain or (state.has_provided_explaination):
         # 如果意图明确，跳过提示环节
         state.set_state(chatbot=chatbot, key='has_provided_explaination', value=True)
@@ -152,7 +152,7 @@ def 虚空终端主路由(txt, llm_kwargs, plugin_kwargs, chatbot, history, syst
         analyze_res = run_gpt_fn(inputs, "")
         try:
             user_intention = gpt_json_io.generate_output_auto_repair(analyze_res, run_gpt_fn)
-            lastmsg=f"正在执行任务: {txt}\n\n用户意图理解: 意图={explain_intention_to_user[user_intention.intention_type]}", 
+            lastmsg=f"正在执行任务: {txt}\n\n用户意图理解: 意图={explain_intention_to_user[user_intention.intention_type]}",
         except JsonStringError as e:
             yield from update_ui_lastest_msg(
                 lastmsg=f"正在执行任务: {txt}\n\n用户意图理解: 失败 当前语言模型（{llm_kwargs['llm_model']}）不能理解您的意图", chatbot=chatbot, history=history, delay=0)
@@ -161,7 +161,7 @@ def 虚空终端主路由(txt, llm_kwargs, plugin_kwargs, chatbot, history, syst
         pass
 
     yield from update_ui_lastest_msg(
-        lastmsg=f"正在执行任务: {txt}\n\n用户意图理解: 意图={explain_intention_to_user[user_intention.intention_type]}", 
+        lastmsg=f"正在执行任务: {txt}\n\n用户意图理解: 意图={explain_intention_to_user[user_intention.intention_type]}",
         chatbot=chatbot, history=history, delay=0)
 
     # 用户意图: 修改本项目的配置

crazy_functions/解析JupyterNotebook.py

@@ -12,6 +12,12 @@ class PaperFileGroup():
         self.sp_file_index = []
         self.sp_file_tag = []
 
+        # count_token
+        from request_llms.bridge_all import model_info
+        enc = model_info["gpt-3.5-turbo"]['tokenizer']
+        def get_token_num(txt): return len(enc.encode(txt, disallowed_special=()))
+        self.get_token_num = get_token_num
+
     def run_file_split(self, max_token_limit=1900):
         """
         将长文本分离开来
@@ -54,7 +60,7 @@ def parseNotebook(filename, enable_markdown=1):
         Code += f"This is {idx+1}th code block: \n"
         Code += code+"\n"
 
-    return Code 
+    return Code
 
 
 def ipynb解释(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt):

crazy_functions/解析项目源代码.py

@@ -82,13 +82,13 @@ def 解析源代码新(file_manifest, project_folder, llm_kwargs, plugin_kwargs,
             inputs=inputs, inputs_show_user=inputs_show_user, llm_kwargs=llm_kwargs, chatbot=chatbot,
             history=this_iteration_history_feed,   # 迭代之前的分析
             sys_prompt="你是一个程序架构分析师，正在分析一个项目的源代码。" + sys_prompt_additional)
-        
+
         diagram_code = make_diagram(this_iteration_files, result, this_iteration_history_feed)
         summary = "请用一句话概括这些文件的整体功能。\n\n" + diagram_code
         summary_result = yield from request_gpt_model_in_new_thread_with_ui_alive(
-            inputs=summary, 
-            inputs_show_user=summary, 
-            llm_kwargs=llm_kwargs, 
+            inputs=summary,
+            inputs_show_user=summary,
+            llm_kwargs=llm_kwargs,
             chatbot=chatbot,
             history=[i_say, result],   # 迭代之前的分析
             sys_prompt="你是一个程序架构分析师，正在分析一个项目的源代码。" + sys_prompt_additional)
@@ -345,9 +345,12 @@ def 解析任意code项目(txt, llm_kwargs, plugin_kwargs, chatbot, history, sys
     pattern_except_suffix = [_.lstrip(" ^*.,").rstrip(" ,") for _ in txt_pattern.split(" ") if _ != "" and _.strip().startswith("^*.")]
     pattern_except_suffix += ['zip', 'rar', '7z', 'tar', 'gz'] # 避免解析压缩文件
     # 将要忽略匹配的文件名(例如: ^README.md)
-    pattern_except_name = [_.lstrip(" ^*,").rstrip(" ,").replace(".", "\.") for _ in txt_pattern.split(" ") if _ != "" and _.strip().startswith("^") and not _.strip().startswith("^*.")]
+    pattern_except_name = [_.lstrip(" ^*,").rstrip(" ,").replace(".", r"\.") # 移除左边通配符，移除右侧逗号，转义点号
+                           for _ in txt_pattern.split(" ") # 以空格分割
+                           if (_ != "" and _.strip().startswith("^") and not _.strip().startswith("^*."))   # ^开始，但不是^*.开始
+                           ]
     # 生成正则表达式
-    pattern_except = '/[^/]+\.(' + "|".join(pattern_except_suffix) + ')$'
+    pattern_except = r'/[^/]+\.(' + "|".join(pattern_except_suffix) + ')$'
     pattern_except += '|/(' + "|".join(pattern_except_name) + ')$' if pattern_except_name != [] else ''
 
     history.clear()

crazy_functions/询问多个大语言模型.py

@@ -20,8 +20,8 @@ def 同时问询(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt
     # llm_kwargs['llm_model'] = 'chatglm&gpt-3.5-turbo&api2d-gpt-3.5-turbo' # 支持任意数量的llm接口，用&符号分隔
     llm_kwargs['llm_model'] = MULTI_QUERY_LLM_MODELS # 支持任意数量的llm接口，用&符号分隔
     gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
-        inputs=txt, inputs_show_user=txt, 
-        llm_kwargs=llm_kwargs, chatbot=chatbot, history=history, 
+        inputs=txt, inputs_show_user=txt,
+        llm_kwargs=llm_kwargs, chatbot=chatbot, history=history,
         sys_prompt=system_prompt,
         retry_times_at_unknown_error=0
     )
@@ -52,8 +52,8 @@ def 同时问询_指定模型(txt, llm_kwargs, plugin_kwargs, chatbot, history,
     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
 
     gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
-        inputs=txt, inputs_show_user=txt, 
-        llm_kwargs=llm_kwargs, chatbot=chatbot, history=history, 
+        inputs=txt, inputs_show_user=txt,
+        llm_kwargs=llm_kwargs, chatbot=chatbot, history=history,
         sys_prompt=system_prompt,
         retry_times_at_unknown_error=0
     )

crazy_functions/语音助手.py

@@ -39,7 +39,7 @@ class AsyncGptTask():
         try:
             MAX_TOKEN_ALLO = 2560
             i_say, history = input_clipping(i_say, history, max_token_limit=MAX_TOKEN_ALLO)
-            gpt_say_partial = predict_no_ui_long_connection(inputs=i_say, llm_kwargs=llm_kwargs, history=history, sys_prompt=sys_prompt, 
+            gpt_say_partial = predict_no_ui_long_connection(inputs=i_say, llm_kwargs=llm_kwargs, history=history, sys_prompt=sys_prompt,
                                                             observe_window=observe_window[index], console_slience=True)
         except ConnectionAbortedError as token_exceed_err:
             print('至少一个线程任务Token溢出而失败', e)
@@ -120,7 +120,7 @@ class InterviewAssistant(AliyunASR):
             yield from update_ui(chatbot=chatbot, history=history)      # 刷新界面
             self.plugin_wd.feed()
 
-            if self.event_on_result_chg.is_set(): 
+            if self.event_on_result_chg.is_set():
                 # called when some words have finished
                 self.event_on_result_chg.clear()
                 chatbot[-1] = list(chatbot[-1])
@@ -151,7 +151,7 @@ class InterviewAssistant(AliyunASR):
                 # add gpt task 创建子线程请求gpt，避免线程阻塞
                 history = chatbot2history(chatbot)
                 self.agt.add_async_gpt_task(self.buffered_sentence, len(chatbot)-1, llm_kwargs, history, system_prompt)
-                
+
                 self.buffered_sentence = ""
                 chatbot.append(["[ 请讲话 ]", "[ 正在等您说完问题 ]"])
                 yield from update_ui(chatbot=chatbot, history=history) # 刷新界面

crazy_functions/谷歌检索小助手.py

@@ -20,10 +20,10 @@ def get_meta_information(url, chatbot, history):
     proxies = get_conf('proxies')
     headers = {
         'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/116.0.0.0 Safari/537.36',
-        'Accept-Encoding': 'gzip, deflate, br', 
+        'Accept-Encoding': 'gzip, deflate, br',
         'Accept-Language': 'en-US,en;q=0.9,zh-CN;q=0.8,zh;q=0.7',
         'Cache-Control':'max-age=0',
-        'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7', 
+        'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7',
         'Connection': 'keep-alive'
     }
     try:
@@ -95,7 +95,7 @@ def get_meta_information(url, chatbot, history):
         )
         try: paper = next(search.results())
         except: paper = None
-        
+
         is_match = paper is not None and string_similar(title, paper.title) > 0.90
 
         # 如果在Arxiv上匹配失败，检索文章的历史版本的题目
@@ -146,8 +146,8 @@ def 谷歌检索小助手(txt, llm_kwargs, plugin_kwargs, chatbot, history, syst
         import math
         from bs4 import BeautifulSoup
     except:
-        report_exception(chatbot, history, 
-            a = f"解析项目: {txt}", 
+        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 beautifulsoup4 arxiv```。")
         yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
         return
@@ -163,7 +163,7 @@ def 谷歌检索小助手(txt, llm_kwargs, plugin_kwargs, chatbot, history, syst
         if len(meta_paper_info_list[:batchsize]) > 0:
             i_say = "下面是一些学术文献的数据，提取出以下内容：" + \
             "1、英文题目；2、中文题目翻译；3、作者；4、arxiv公开（is_paper_in_arxiv）；4、引用数量（cite）；5、中文摘要翻译。" + \
-            f"以下是信息源：{str(meta_paper_info_list[:batchsize])}" 
+            f"以下是信息源：{str(meta_paper_info_list[:batchsize])}"
 
             inputs_show_user = f"请分析此页面中出现的所有文章：{txt}，这是第{batch+1}批"
             gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
@@ -175,11 +175,11 @@ def 谷歌检索小助手(txt, llm_kwargs, plugin_kwargs, chatbot, history, syst
             history.extend([ f"第{batch+1}批", gpt_say ])
             meta_paper_info_list = meta_paper_info_list[batchsize:]
 
-    chatbot.append(["状态？", 
+    chatbot.append(["状态？",
         "已经全部完成，您可以试试让AI写一个Related Works，例如您可以继续输入Write a \"Related Works\" section about \"你搜索的研究领域\" for me."])
     msg = '正常'
     yield from update_ui(chatbot=chatbot, history=history, msg=msg) # 刷新界面
     path = write_history_to_file(history)
     promote_file_to_downloadzone(path, chatbot=chatbot)
-    chatbot.append(("完成了吗？", path)); 
+    chatbot.append(("完成了吗？", path));
     yield from update_ui(chatbot=chatbot, history=history, msg=msg) # 刷新界面

crazy_functions/高级功能函数模板.py

@@ -40,7 +40,7 @@ def 高阶功能模板函数(txt, llm_kwargs, plugin_kwargs, chatbot, history, s
     """
     history = []    # 清空历史，以免输入溢出
     chatbot.append((
-        "您正在调用插件：历史上的今天", 
+        "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):
@@ -48,8 +48,8 @@ def 高阶功能模板函数(txt, llm_kwargs, plugin_kwargs, chatbot, history, s
         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。'
         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=[], 
+            inputs=i_say, inputs_show_user=i_say,
+            llm_kwargs=llm_kwargs, chatbot=chatbot, history=[],
             sys_prompt="当你想发送一张照片时，请使用Markdown, 并且不要有反斜线, 不要用代码块。使用 Unsplash API (https://source.unsplash.com/1280x720/? < PUT_YOUR_QUERY_HERE >)。"
         )
         chatbot[-1] = (i_say, gpt_say)
@@ -84,15 +84,15 @@ def 测试图表渲染(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_
     history = []    # 清空历史，以免输入溢出
     chatbot.append(("这是什么功能？", "一个测试mermaid绘制图表的功能，您可以在输入框中输入一些关键词，然后使用mermaid+llm绘制图表。"))
     yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 由于请求gpt需要一段时间，我们先及时地做一次界面更新
-    
+
     if txt == "": txt = "空白的输入栏" # 调皮一下
-    
+
     i_say_show_user = f'请绘制有关“{txt}”的逻辑关系图。'
     i_say = PROMPT.format(subject=txt)
     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, chatbot=chatbot, history=[],
         sys_prompt=""
     )
     history.append(i_say); history.append(gpt_say)

docker-compose.yml

@@ -1,12 +1,12 @@
 ## ===================================================
-# docker-compose.yml
+#                docker-compose.yml
 ## ===================================================
 # 1. 请在以下方案中选择任意一种，然后删除其他的方案
 # 2. 修改你选择的方案中的environment环境变量，详情请见github wiki或者config.py
 # 3. 选择一种暴露服务端口的方法，并对相应的配置做出修改：
-    # 【方法1: 适用于Linux，很方便，可惜windows不支持】与宿主的网络融合为一体，这个是默认配置
+    # 「方法1: 适用于Linux，很方便，可惜windows不支持」与宿主的网络融合为一体，这个是默认配置
     # network_mode: "host"
-    # 【方法2: 适用于所有系统包括Windows和MacOS】端口映射，把容器的端口映射到宿主的端口（注意您需要先删除network_mode: "host"，再追加以下内容）
+    # 「方法2: 适用于所有系统包括Windows和MacOS」端口映射，把容器的端口映射到宿主的端口（注意您需要先删除network_mode: "host"，再追加以下内容）
     # ports:
     #   - "12345:12345"  # 注意！12345必须与WEB_PORT环境变量相互对应
 # 4. 最后`docker-compose up`运行
@@ -25,7 +25,7 @@
 ## ===================================================
 
 ## ===================================================
-## 【方案零】 部署项目的全部能力（这个是包含cuda和latex的大型镜像。如果您网速慢、硬盘小或没有显卡，则不推荐使用这个）
+## 「方案零」 部署项目的全部能力（这个是包含cuda和latex的大型镜像。如果您网速慢、硬盘小或没有显卡，则不推荐使用这个）
 ## ===================================================
 version: '3'
 services:
@@ -63,10 +63,10 @@ services:
     #             count: 1
     #             capabilities: [gpu]
 
-    # 【WEB_PORT暴露方法1: 适用于Linux】与宿主的网络融合
+    # 「WEB_PORT暴露方法1: 适用于Linux」与宿主的网络融合
     network_mode: "host"
 
-    # 【WEB_PORT暴露方法2: 适用于所有系统】端口映射
+    # 「WEB_PORT暴露方法2: 适用于所有系统」端口映射
     # ports:
     #   - "12345:12345"  # 12345必须与WEB_PORT相互对应
 
@@ -75,10 +75,8 @@ services:
       bash -c "python3 -u main.py"
 
 
-
-
 ## ===================================================
-## 【方案一】 如果不需要运行本地模型（仅 chatgpt, azure, 星火, 千帆, claude 等在线大模型服务）
+## 「方案一」 如果不需要运行本地模型（仅 chatgpt, azure, 星火, 千帆, claude 等在线大模型服务）
 ## ===================================================
 version: '3'
 services:
@@ -97,16 +95,16 @@ services:
       # DEFAULT_WORKER_NUM:       '    10                                                                                             '
       # AUTHENTICATION:           '    [("username", "passwd"), ("username2", "passwd2")]                                             '
 
-    # 与宿主的网络融合
+    # 「WEB_PORT暴露方法1: 适用于Linux」与宿主的网络融合
     network_mode: "host"
 
-    # 不使用代理网络拉取最新代码
+    # 启动命令
     command: >
       bash -c "python3 -u main.py"
 
 
 ### ===================================================
-### 【方案二】 如果需要运行ChatGLM + Qwen + MOSS等本地模型
+### 「方案二」 如果需要运行ChatGLM + Qwen + MOSS等本地模型
 ### ===================================================
 version: '3'
 services:
@@ -130,8 +128,10 @@ services:
     devices:
       - /dev/nvidia0:/dev/nvidia0
 
-    # 与宿主的网络融合
+    # 「WEB_PORT暴露方法1: 适用于Linux」与宿主的网络融合
     network_mode: "host"
+
+    # 启动命令
     command: >
       bash -c "python3 -u main.py"
 
@@ -139,8 +139,9 @@ services:
     # command: >
     #   bash -c "pip install -r request_llms/requirements_qwen.txt && python3 -u main.py"
 
+
 ### ===================================================
-### 【方案三】 如果需要运行ChatGPT + LLAMA + 盘古 + RWKV本地模型
+### 「方案三」 如果需要运行ChatGPT + LLAMA + 盘古 + RWKV本地模型
 ### ===================================================
 version: '3'
 services:
@@ -164,16 +165,16 @@ services:
     devices:
       - /dev/nvidia0:/dev/nvidia0
 
-    # 与宿主的网络融合
+    # 「WEB_PORT暴露方法1: 适用于Linux」与宿主的网络融合
     network_mode: "host"
 
-    # 不使用代理网络拉取最新代码
+    # 启动命令
     command: >
       python3 -u main.py
 
 
 ## ===================================================
-## 【方案四】 ChatGPT + Latex
+## 「方案四」 ChatGPT + Latex
 ## ===================================================
 version: '3'
 services:
@@ -190,16 +191,16 @@ services:
       DEFAULT_WORKER_NUM:       '    10                                                                               '
       WEB_PORT:                 '    12303                                                                            '
 
-    # 与宿主的网络融合
+    # 「WEB_PORT暴露方法1: 适用于Linux」与宿主的网络融合
     network_mode: "host"
 
-    # 不使用代理网络拉取最新代码
+    # 启动命令
     command: >
       bash -c "python3 -u main.py"
 
 
 ## ===================================================
-## 【方案五】 ChatGPT + 语音助手 （请先阅读 docs/use_audio.md）
+## 「方案五」 ChatGPT + 语音助手 （请先阅读 docs/use_audio.md）
 ## ===================================================
 version: '3'
 services:
@@ -223,9 +224,9 @@ services:
       # (无需填写) ALIYUN_ACCESSKEY:         '    LTAI5q6BrFUzoRXVGUWnekh1                                         '
       # (无需填写) ALIYUN_SECRET:            '    eHmI20AVWIaQZ0CiTD2bGQVsaP9i68                                   '
 
-    # 与宿主的网络融合
+    # 「WEB_PORT暴露方法1: 适用于Linux」与宿主的网络融合
     network_mode: "host"
 
-    # 不使用代理网络拉取最新代码
+    # 启动命令
     command: >
       bash -c "python3 -u main.py"

docs/self_analysis.md

@@ -28,7 +28,7 @@
 | 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\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批量翻译.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 |
@@ -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批量翻译.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批量翻译.py”。它主要使用了“toolbox”、“request_gpt_model_in_new_thread_with_ui_alive”、“request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency”、“colorful”等Python库和自定义的模块“crazy_utils”的一些函数。程序实现了一个批量翻译PDF文档的功能，可以自动解析PDF文件中的基础信息，递归地切割PDF文件，翻译和处理PDF论文中的所有内容，并生成相应的翻译结果文件（包括md文件和html文件）。功能比较复杂，其中需要调用多个函数和依赖库，涉及到多线程操作和UI更新。文件中有详细的注释和变量命名，代码比较清晰易读。
 
 ## [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
 
@@ -331,7 +331,7 @@ 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\对话历史存档.py, crazy_functions\总结word文档.py, crazy_functions\总结音视频.py, crazy_functions\批量Markdown翻译.py, crazy_functions\批量总结PDF文档.py, crazy_functions\批量总结PDF文档pdfminer.py, crazy_functions\PDF批量翻译.py, crazy_functions\理解PDF文档内容.py, crazy_functions\生成函数注释.py, crazy_functions\联网的ChatGPT.py, crazy_functions\解析JupyterNotebook.py, crazy_functions\解析项目源代码.py, crazy_functions\询问多个大语言模型.py, crazy_functions\读文章写摘要.py。根据以上分析，用一句话概括程序的整体功能。
 
 | 文件名 | 功能简述 |
 | --- | --- |
@@ -343,7 +343,7 @@ crazy_functions\代码重写为全英文_多线程.py, crazy_functions\图片生
 | 批量Markdown翻译.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批量翻译.py | 将指定目录下的PDF文件进行中英文翻译 |
 | 理解PDF文档内容.py | 对PDF文件进行摘要生成和问题解答 |
 | 生成函数注释.py | 自动生成Python函数的注释 |
 | 联网的ChatGPT.py | 使用网络爬虫和ChatGPT模型进行聊天回答 |

docs/translate_english.json

@@ -44,7 +44,7 @@
     "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": "BatchTranslatePDFDocuments_MultiThreaded",
+    "PDF批量翻译": "BatchTranslatePDFDocuments_MultiThreaded",
     "谷歌检索小助手": "GoogleSearchAssistant",
     "理解PDF文档内容标准文件输入": "UnderstandPdfDocumentContentStandardFileInput",
     "理解PDF文档内容": "UnderstandPdfDocumentContent",
@@ -1392,7 +1392,7 @@
     "1. 临时解决方案": "1. Temporary Solution",
     "直接在输入区键入api_key": "Enter the api_key Directly in the Input Area",
     "然后回车提交": "Submit after pressing Enter",
-    "2. 长效解决方案": "Long-term solution",
+    "2. 长效解决方案": "2. Long-term solution",
     "在config.py中配置": "Configure in config.py",
     "等待响应": "Waiting for response",
     "api-key不满足要求": "API key does not meet requirements",
@@ -1668,7 +1668,7 @@
     "Markdown翻译指定语言": "TranslateMarkdownToSpecifiedLanguage",
     "Langchain知识库": "LangchainKnowledgeBase",
     "Latex英文纠错加PDF对比": "CorrectEnglishInLatexWithPDFComparison",
-    "Latex输出PDF结果": "OutputPDFFromLatex",
+    "Latex输出PDF": "OutputPDFFromLatex",
     "Latex翻译中文并重新编译PDF": "TranslateChineseToEnglishInLatexAndRecompilePDF",
     "sprint亮靛": "SprintIndigo",
     "寻找Latex主文件": "FindLatexMainFile",
@@ -2184,7 +2184,8 @@
     "接驳VoidTerminal": "Connect to VoidTerminal",
     "**很好": "**Very good",
     "对话|编程": "Conversation&ImageGenerating|Programming",
-    "对话|编程|学术": "Conversation&ImageGenerating|Programming|Academic",    "4. 建议使用 GPT3.5 或更强的模型": "4. It is recommended to use GPT3.5 or a stronger model",
+    "对话|编程|学术": "Conversation|Programming|Academic",
+    "4. 建议使用 GPT3.5 或更强的模型": "4. It is recommended to use GPT3.5 or a stronger model",
     "「请调用插件翻译PDF论文": "Please call the plugin to translate the PDF paper",
     "3. 如果您使用「调用插件xxx」、「修改配置xxx」、「请问」等关键词": "3. If you use keywords such as 'call plugin xxx', 'modify configuration xxx', 'please', etc.",
     "以下是一篇学术论文的基本信息": "The following is the basic information of an academic paper",
@@ -3004,5 +3005,748 @@
     "1. 上传图片": "TranslatedText",
     "保存状态": "TranslatedText",
     "GPT-Academic对话存档": "TranslatedText",
-    "Arxiv论文精细翻译": "TranslatedText"
-}
+    "Arxiv论文精细翻译": "TranslatedText",
+    "from crazy_functions.AdvancedFunctionTemplate import 测试图表渲染": "from crazy_functions.AdvancedFunctionTemplate import test_chart_rendering",
+    "测试图表渲染": "test_chart_rendering",
+    "请使用「LatexEnglishCorrection+高亮修正位置": "Please use 'LatexEnglishCorrection+highlight corrected positions",
+    "输出代码片段中！": "Output code snippet!",
+    "使用多种方式尝试切分文本": "Attempt to split the text in various ways",
+    "你是一个作家": "You are a writer",
+    "如果无法从中得到答案": "If unable to get an answer from it",
+    "无法读取以下数据": "Unable to read the following data",
+    "不允许直接报错": "Direct error reporting is not allowed",
+    "您也可以使用插件参数指定绘制的图表类型": "You can also specify the type of chart to be drawn using plugin parameters",
+    "不要包含太多情节": "Do not include too many plots",
+    "翻译为中文后重新编译为PDF": "Recompile into PDF after translating into Chinese",
+    "采样温度": "Sampling temperature",
+    "直接修改config.py": "Directly modify config.py",
+    "处理文件": "Handle file",
+    "判断返回是否正确": "Determine if the return is correct",
+    "gemini 不允许对话轮次为偶数": "Gemini does not allow the number of dialogue rounds to be even",
+    "8 象限提示图": "8-quadrant prompt diagram",
+    "基于上下文的prompt模版": "Context-based prompt template",
+    "^开始": "^Start",
+    "输出文本的最大tokens限制": "Maximum tokens limit for output text",
+    "在这个例子中": "In this example",
+    "以及处理PDF文件的示例代码": "And example code for handling PDF files",
+    "更新cookie": "Update cookie",
+    "获取公共缩进": "Get public indentation",
+    "请你给出围绕“{subject}”的序列图": "Please provide a sequence diagram around '{subject}'",
+    "请确保使用小写的模型名称": "Please ensure the use of lowercase model names",
+    "出现人物时": "When characters appear",
+    "azure模型对齐支持 -=-=-=-=-=-=-": "Azure model alignment support -=-=-=-=-=-=-",
+    "请一分钟后重试": "Please try again in one minute",
+    "解析GEMINI消息出错": "Error parsing GEMINI message",
+    "选择提示词": "Select prompt words",
+    "取值范围是": "The value range is",
+    "它会在": "It will be",
+    "加载文件": "Load file",
+    "是预定义按钮": "Is a predefined button",
+    "消息": "Message",
+    "默认搜索5条结果": "Default search for 5 results",
+    "第 2 部分": "Part 2",
+    "我们采样一个特殊的手段": "We sample a special method",
+    "后端开发": "Backend development",
+    "接下来提取md中的一级/二级标题作为摘要": "Next, extract the first/second-level headings in md as summaries",
+    "一个年轻人穿过天安门广场向纪念堂走去": "A young person walks through Tiananmen Square towards the Memorial Hall",
+    "将会使用这些摘要绘制图表": "Will use these summaries to draw charts",
+    "8-象限提示图": "8-quadrant prompt diagram",
+    "首先": "First",
+    "设计了此接口": "Designed this interface",
+    "本地模型": "Local model",
+    "所有图像仅在最后一个问题中提供": "All images are provided only in the last question",
+    "如连续3次判断失败将会使用流程图进行绘制": "If there are 3 consecutive failures, a flowchart will be used to draw",
+    "为了更灵活地接入one-api多模型管理界面": "To access the one-api multi-model management interface more flexibly",
+    "UI设计": "UI design",
+    "不允许在答案中添加编造成分": "Fabrication is not allowed in the answer",
+    "尽可能地": "As much as possible",
+    "先在前端快速清除chatbot&status": "First, quickly clear chatbot & status in the frontend",
+    "You exceeded your current quota. Cohere以账户额度不足为由": "You exceeded your current quota. Cohere due to insufficient account quota",
+    "合并所有的标题": "Merge all headings",
+    "跳过下载": "Skip download",
+    "中生产图表": "Production Chart",
+    "如输入区内容不是文件则直接返回输入区内容": "Return the content of the input area directly if it is not a file",
+    "用温度取样的另一种方法": "Another method of temperature sampling",
+    "不需要解释原因": "No need to explain the reason",
+    "一场延续了两万年的星际战争已接近尾声": "An interstellar war that has lasted for 20,000 years is drawing to a close",
+    "依次处理文件": "Process files in order",
+    "第一幕的字数少于300字": "The first act has fewer than 300 characters",
+    "已成功加载": "Successfully loaded",
+    "还是web渲染": "Web rendering",
+    "解析分辨率": "Resolution parsing",
+    "如果剩余文本的token数大于限制": "If the number of remaining text tokens exceeds the limit",
+    "你可以修改整个句子的顺序以确保翻译后的段落符合中文的语言习惯": "You can change the order of the whole sentence to ensure that the translated paragraph is in line with Chinese language habits",
+    "并同时充分考虑中文的语法、清晰、简洁和整体可读性": "And at the same time, fully consider Chinese grammar, clarity, conciseness, and overall readability",
+    "否则返回": "Otherwise return",
+    "一个特殊标记": "A special mark",
+    "4. 后续剧情发展4": "4. Plot development",
+    "恢复默认": "Restore default",
+    "转义点号": "Escape period",
+    "检查DASHSCOPE_API_KEY": "Check DASHSCOPE_API_KEY",
+    "阿里灵积云API_KEY": "Aliyun API_KEY",
+    "文件是否存在": "Check if the file exists",
+    "您的选择是": "Your choice is",
+    "处理用户对话": "Handle user dialogue",
+    "即": "That is",
+    "将会由对话模型首先判断适合的图表类型": "The dialogue model will first determine the appropriate chart type",
+    "以查看所有的配置信息": "To view all configuration information",
+    "用于初始化包的属性和导入模块": "For initializing package properties and importing modules",
+    "to_markdown_tabs 文件list 转换为 md tab": "to_markdown_tabs Convert file list to MD tab",
+    "更换模型": "Replace Model",
+    "从以下文本中提取摘要": "Extract Summary from the Following Text",
+    "表示捕获任意长度的文本": "Indicates Capturing Text of Arbitrary Length",
+    "可能是一个模块的初始化文件": "May Be an Initialization File for a Module",
+    "处理提问与输出": "Handle Questions and Outputs",
+    "需要的再做些简单调整即可": "Some Simple Adjustments Needed",
+    "所以这个没有用": "So This Is Not Useful",
+    "请配置 DASHSCOPE_API_KEY": "Please Configure DASHSCOPE_API_KEY",
+    "不是预定义按钮": "Not a Predefined Button",
+    "让读者能够感受到你的故事世界": "Let Readers Feel Your Story World",
+    "开始整理headers与message": "Start Organizing Headers and Messages",
+    "兼容最新的智谱Ai": "Compatible with the Latest ZhiPu AI",
+    "对于某些PDF会有第一个段落就以小写字母开头": "For Some PDFs, the First Paragraph May Start with a Lowercase Letter",
+    "问题是": "The Issue Is",
+    "也就是说它会匹配尽可能少的字符": "That Is, It Will Match the Least Amount of Characters Possible",
+    "未能成功加载": "Failed to Load Successfully",
+    "接入通义千问在线大模型 https": "Access TongYi QianWen Online Large Model HTTPS",
+    "用不太优雅的方式处理一个core_functional.py中出现的mermaid渲染特例": "Handle a Mermaid Rendering Special Case in core_functional.py in an Ugly Way",
+    "您也可以选择给出其他故事走向": "You Can Also Choose to Provide Alternative Storylines",
+    "改善非markdown输入的显示效果": "Improve Display Effects for Non-Markdown Input",
+    "在二十二世纪编年史中": "In the Chronicle of the 22nd Century",
+    "docs 为Document列表": "docs Are a List of Documents",
+    "互动写故事": "Interactive Story Writing",
+    "4 饼图": "Pie Chart",
+    "正在生成插图中": "Generating Illustration",
+    "路径不存在": "Path Does Not Exist",
+    "PDF翻译中文": "PDF Translation to Chinese",
+    "进行简短的环境描写": "Conduct a Brief Environmental Description",
+    "学术英中互译": "Academic English-Chinese Translation",
+    "且少于2个段落": "And less than 2 paragraphs",
+    "html_view_blank 超链接": "HTML View Blank Hyperlink",
+    "处理 history": "Handle History",
+    "非Cohere官方接口返回了错误": "Non-Cohere Official Interface Returned an Error",
+    "缺失 MATHPIX_APPID 和 MATHPIX_APPKEY": "Missing MATHPIX_APPID and MATHPIX_APPKEY",
+    "搜索知识库内容条数": "Search Knowledge Base Content Count",
+    "返回数据": "Return Data",
+    "没有相关文件": "No Relevant Files",
+    "知识库路径": "Knowledge Base Path",
+    "质量与风格默认值": "Quality and Style Defaults",
+    "包含了用于文本切分的函数": "Contains Functions for Text Segmentation",
+    "请你给出围绕“{subject}”的逻辑关系图": "Please Provide a Logic Diagram Surrounding '{subject}'",
+    "官方Pro服务器🧪": "Official Pro Server",
+    "不支持同时处理多个pdf文件": "Does Not Support Processing Multiple PDF Files Simultaneously",
+    "查询5天历史事件": "Query 5-Day Historical Events",
+    "你是经验丰富的翻译": "You Are an Experienced Translator",
+    "html输入": "HTML Input",
+    "输入文件不存在": "Input File Does Not Exist",
+    "很多人生来就会莫名其妙地迷上一样东西": "Many People Are Born with an Unexplained Attraction to Something",
+    "默认值为 0.7": "Default Value is 0.7",
+    "值越大": "The Larger the Value",
+    "以下文件未能成功加载": "The Following Files Failed to Load",
+    "在线模型": "Online Model",
+    "切割输入": "Cut Input",
+    "修改docker-compose.yml等价于修改容器内部的环境变量": "Modifying docker-compose.yml is Equivalent to Modifying the Internal Environment Variables of the Container",
+    "以换行符分割": "Split by Line Break",
+    "修复中文乱码的问题": "Fix Chinese Character Encoding Issues",
+    "zhipuai 是glm-4的别名": "zhipuai is an alias for glm-4",
+    "保证其在允许范围内": "Ensure it is within the permissible range",
+    "段尾如果有多余的\\n就去掉它": "Remove any extra \\n at the end of the paragraph",
+    "是否流式输出": "Whether to stream output",
+    "1-流程图": "1-Flowchart",
+    "学术语料润色": "Academic text polishing",
+    "已经超过了模型的最大上下文或是模型格式错误": "Has exceeded the model's maximum context or there is a model format error",
+    "英文省略号": "English ellipsis",
+    "登录成功": "Login successful",
+    "随便切一下吧": "Just cut it randomly",
+    "PDF转换为tex项目失败": "PDF conversion to TeX project failed",
+    "的 max_token 配置不是整数": "The max_token configuration is not an integer",
+    "根据当前聊天历史或指定的路径文件": "According to the current chat history or specified path file",
+    "你必须利用以下文档中包含的信息回答这个问题": "You must use the information contained in the following document to answer this question",
+    "对话、日志记录": "Dialogue, logging",
+    "内容至知识库": "Content to knowledge base",
+    "在银河系的中心": "At the center of the Milky Way",
+    "检查PDF是否被重复上传": "Check if the PDF has been uploaded multiple times",
+    "取最后 max_prompt_tokens 个 token 输入模型": "Take the last max_prompt_tokens tokens as input to the model",
+    "请输入图类型对应的数字": "Please enter the corresponding number for the graph type",
+    "插件主程序3  =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=": "Plugin main program 3 -=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=",
+    "正在tex项目将翻译为中文": "The TeX project is being translated into Chinese",
+    "适配润色区域": "Adapter polishing area",
+    "首先你从历史记录中提取摘要": "First, you extract an abstract from the history",
+    "讯飞星火认知大模型 -=-=-=-=-=-=-": "iFLYTEK Spark Cognitive Model -=-=-=-=-=-=-=-=-=-",
+    "包含了用于构建和管理向量数据库的函数和类包含了用于构建和管理向量数据库的函数和类包含了用于构建和管理向量数据库的函数和类": "Contains functions and classes for building and managing vector databases",
+    "另外": "Additionally",
+    "内部调优参数": "Internal tuning parameters",
+    "输出格式例如": "Example of Output Format",
+    "当回复图像时": "When Responding with an Image",
+    "越权访问!": "Unauthorized Access!",
+    "如果给出的 prompt 的 token 长度超过此限制": "If the Given Prompt's Token Length Exceeds This Limit",
+    "因此你每次写的故事段落应少于300字": "Therefore, Each Story Paragraph You Write Should Be Less Than 300 Words",
+    "尽量短": "As Concise as Possible",
+    "中文提示词就不显示了": "Chinese Keywords Will Not Be Displayed",
+    "请在前文的基础上": "Please Based on the Previous Text",
+    "20张": "20 Sheets",
+    "文件内容优先": "File Content Takes Priority",
+    "状态图": "State Diagram",
+    "开始查找合适切分点的偏移": "Start Looking for the Offset of an Appropriate Split Point",
+    "已知信息": "Known Information",
+    "文心一言大模型": "Wenxin Yanyan Large Model",
+    "传递进来一些奇怪的东西": "Passing in Some Weird Things",
+    "很多规则中会考虑分号": "Many Rules Consider the Semicolon",
+    "请配置YUNQUE_SECRET_KEY": "Please Configure YUNQUE_SECRET_KEY",
+    "6-状态图": "6-State Diagram",
+    "输出文本的最小tokens限制": "Minimum Tokens Limit for Output Text",
+    "服务节点": "Service Node",
+    "云雀大模型": "Lark Large Model",
+    "请配置 GEMINI_API_KEY": "Please Configure GEMINI_API_KEY",
+    "可以让软件运行在 http": "Can Run the Software Over HTTP",
+    "基于当前对话或文件GenerateMultipleMermaidCharts": "Generate Multiple Mermaid Charts Based on the Current Conversation or File",
+    "剧情收尾": "Plot Conclusion",
+    "请开始提问": "Please Begin Your Question",
+    "第一页内容/摘要": "First Page Content/Summary",
+    "无法判断则返回image/jpeg": "Return image/jpeg If Unable to Determine",
+    "仅需要输出单个不带任何标点符号的数字": "Single digit without any punctuation",
+    "以下是每类图表的PROMPT": "Here are the PROMPTS for each type of chart",
+    "状态码": "Status code",
+    "TopP值越大输出的tokens类型越丰富": "The larger the TopP value, the richer the types of output tokens",
+    "files_filter_handler 根据type过滤文件": "files_filter_handler filters files by type",
+    "比较每一页的内容是否相同": "Compare whether each page's content is the same",
+    "前往": "Go to",
+    "请输入剧情走向": "Please enter the plot direction",
+    "故事收尾": "Story ending",
+    "必须说明正在回复哪张图像": "Must specify which image is being replied to",
+    "历史文件继续上传": "Continue uploading historical files",
+    "因此禁用": "Therefore disabled",
+    "使用lru缓存": "Use LRU caching",
+    "该装饰器是大多数功能调用的入口": "This decorator is the entry point for most function calls",
+    "如果需要开启": "If needed to enable",
+    "使用 json 解析库进行处理": "Process using JSON parsing library",
+    "将PDF转换为Latex项目": "Convert PDF to LaTeX project",
+    "7-实体关系图": "7-Entity relationship diagram",
+    "根据用户的提示": "According to the user's prompt",
+    "当前用户的请求信息": "Current user's request information",
+    "配置关联关系说明": "Configuration relationship description",
+    "这段代码是使用Python编程语言中的re模块": "This code uses the re module in the Python programming language",
+    "link_mtime_to_md 文件增加本地时间参数": "link_mtime_to_md adds local time parameter to the file",
+    "从当前对话或路径": "From the current conversation or path",
+    "一起写故事": "Write a story together",
+    "前端开发": "Front-end development",
+    "开区间": "Open interval",
+    "如插件参数不正确则使用对话模型判断": "If the plugin parameters are incorrect, use the dialogue model for judgment",
+    "对字符串进行处理": "Process the string",
+    "简洁和专业的来回答用户的问题": "Answer user questions concisely and professionally",
+    "如输入区不是文件则将输入区内容加入历史记录": "If the input area is not a file, add the content of the input area to the history",
+    "编写一个小说的第一幕": "Write the first act of a novel",
+    "更具创造性；": "More creative;",
+    "用于解析和翻译PDF文件的功能和相关辅助函数用于解析和翻译PDF文件的功能和相关辅助函数用于解析和翻译PDF文件的功能和相关辅助函数": "Functions and related auxiliary functions for parsing and translating PDF files",
+    "月之暗面 -=-=-=-=-=-=-": "The Dark Side of the Moon -=-=-=-=-=-=-",
+    "2. 后续剧情发展2": "2. Subsequent plot development 2",
+    "请先提供文本的更正版本": "Please provide the corrected version of the text first",
+    "修改环境变量": "Modify environment variables",
+    "读取之前的自定义按钮": "Read previous custom buttons",
+    "如果为0": "If it is 0",
+    "函数用于去除多行字符串的缩进": "Function to remove indentation from multiline strings",
+    "请绘制有关“": "Please draw something about \"",
+    "给出4种不同的后续剧情发展方向": "Provide 4 different directions for subsequent plot development",
+    "新调优版本GPT-4🔥": "Newly tuned version GPT-4🔥",
+    "已弃用": "Deprecated",
+    "参考 https": "Refer to https",
+    "发现重复上传": "Duplicate upload detected",
+    "本项目的所有配置都集中在config.py中": "All configurations for this project are centralized in config.py",
+    "默认值为 0.95": "Default value is 0.95",
+    "请查阅": "Please refer to",
+    "此选项已废弃": "This option is deprecated",
+    "找到了.doc文件": ".doc file found",
+    "他们的目的地是南极": "Their destination is Antarctica",
+    "lang_reference这段文字是": "The lang_reference text is",
+    "正在尝试生成对比PDF": "Attempting to generate a comparative PDF",
+    "input_encode_handler 提取input中的文件": "input_encode_handler Extracts files from input",
+    "使用中文": "Use Chinese",
+    "一些垃圾第三方接口会出现这样的错误": "Some crappy third-party interfaces may produce such errors",
+    "例如将空格转换为&nbsp": "For example, converting spaces to &nbsp",
+    "请你给出围绕“{subject}”的类图": "Please provide a class diagram around '{subject}'",
+    "是插件的内部参数": "Is an internal parameter of the plugin",
+    "网络波动时可选其他": "Alternative options when network fluctuates",
+    "非Cohere官方接口的出现这样的报错": "Such errors occur in non-Cohere official interfaces",
+    "是前缀": "Is a prefix",
+    "默认 None": "Default None",
+    "如果几天后能顺利到达那里": "If we can smoothly arrive there in a few days",
+    "输出1": "Output 1",
+    "3-类图": "3-Class Diagram",
+    "如需绘制思维导图请使用参数调用": "Please use parameters to call if you need to draw a mind map",
+    "正在将PDF转换为tex项目": "Converting PDF to TeX project",
+    "列出10个经典名著": "List 10 classic masterpieces",
+    "? 在这里用作非贪婪匹配": "? Used here as a non-greedy match",
+    "左上角更换模型菜单中可切换openai": "Switch to OpenAI in the model change menu in the top left corner",
+    "原样返回": "Return as is",
+    "请配置 MATHPIX_APPID 和 MATHPIX_APPKEY": "Please configure MATHPIX_APPID and MATHPIX_APPKEY",
+    "概括上述段落的内容以及内在逻辑关系": "Summarize the content of the above paragraph and its inherent logical relationship",
+    "cookie相关工具函数": "Cookie-related utility functions",
+    "请你给出围绕“{subject}”的饼图": "Please provide a pie chart around '{subject}'",
+    "原型设计": "Prototype design",
+    "必须为正数": "Must be a positive number",
+    "又一阵剧痛从肝部袭来": "Another wave of severe pain strikes from the liver",
+    "智谱AI": "Zhipu AI",
+    "基础功能区按钮的附加功能": "Additional functions of the basic functional area buttons",
+    "one-api 对齐支持 -=-=-=-=-=-=-": "one-api alignment support -=-=-=-=-=-=-",
+    "5 甘特图": "5 Gantt chart",
+    "用于初始化包的属性和导入模块是一个包的初始化文件": "The file used for initializing package properties and importing modules is an initialization file for the package",
+    "创建并修改config_private.py": "Create and modify config_private.py",
+    "会使输出更随机": "Would make the output more random",
+    "已添加": "Added",
+    "估计一个切分点": "Estimate a split point",
+    "\\n\\n1. 临时解决方案": "\\n\\n1. Temporary solution",
+    "没有回答": "No answer",
+    "尝试重新翻译PDF": "Try to retranslate the PDF",
+    "被这个解码给耍了": "Fooled by this decoding",
+    "再在后端清除history": "Clear history on the backend again",
+    "根据情况选择flowchart LR": "Choose flowchart LR based on the situation",
+    "幻方-深度求索大模型 -=-=-=-=-=-=-": "Deep Seek Large Model -=-=-=-=-=-=-",
+    "即使它们在历史记录中被提及": "Even if they are mentioned in the history",
+    "此处需要进一步优化逻辑": "Further logic optimization is needed here",
+    "借鉴自同目录下的bridge_ChatGPT.py": "Derived from the bridge_ChatGPT.py in the same directory",
+    "正是这样": "That's exactly right",
+    "您也可以给出您心中的其他故事走向": "You can also provide other story directions in your mind",
+    "文本预处理": "Text preprocessing",
+    "请登录": "Please log in",
+    "请修改docker-compose": "Please modify docker-compose",
+    "运行一些异步任务": "Run some asynchronous tasks",
+    "5-甘特图": "5-Gantt chart",
+    "3 类图": "3-Class diagram",
+    "因为你接下来将会与用户互动续写下面的情节": "Because you will interact with the user to continue writing the plot below",
+    "避免把同一个文件添加多次": "Avoid adding the same file multiple times",
+    "可挑选精度": "Selectable precision",
+    "调皮一下": "Play a joke",
+    "并解析": "And parse",
+    "您可以在输入框中输入一些关键词": "You can enter some keywords in the input box",
+    "文件加载失败": "File loading failed",
+    "请你给出围绕“{subject}”的甘特图": "Please provide a Gantt chart around \"{subject}\"",
+    "上传PDF": "Upload PDF",
+    "请判断适合使用的流程图类型": "Please determine the suitable flowchart type",
+    "错误码": "Error code",
+    "非markdown输入": "Non-markdown input",
+    "所以只能通过提示词对第几张图片进行定位": "So can only locate the image by the prompt",
+    "避免下载到缓存文件": "Avoid downloading cached files",
+    "没有思维导图!!!测试发现模型始终会优先选择思维导图": "No mind map!!! Testing found that the model always prioritizes mind maps",
+    "请登录Cohere查看详情 https": "Please log in to Cohere for details https",
+    "检查历史上传的文件是否与新上传的文件相同": "Check if the previously uploaded file is the same as the newly uploaded file",
+    "加载主题相关的工具函数": "Load theme-related utility functions",
+    "图表类型由模型判断": "Chart type is determined by the model",
+    "⭐ 多线程方法": "Multi-threading method",
+    "获取 max_token 的值": "Get the value of max_token",
+    "空白的输入栏": "Blank input field",
+    "根据整理的摘要选择图表类型": "Select chart type based on the organized summary",
+    "返回 True": "Return True",
+    "这里为了区分中英文情景搞复杂了一点": "Here it's a bit complicated to distinguish between Chinese and English contexts",
+    "ZHIPUAI_MODEL 配置项选项已经弃用": "ZHIPUAI_MODEL configuration option is deprecated",
+    "但是这里我把它忽略不计": "But here I ignore it",
+    "非必要": "Not necessary",
+    "思维导图": "Mind map",
+    "插件」": "Plugin",
+    "重复文件路径": "Duplicate file path",
+    "之间不要存在空格": "No spaces between fields",
+    "破折号、英文双引号等同样忽略": "Ignore dashes, English quotes, etc.",
+    "填写 VOLC_ACCESSKEY": "Enter VOLC_ACCESSKEY",
+    "称为核取样": "Called nuclear sampling",
+    "Incorrect API key. 请确保API key有效": "Incorrect API key. Please ensure the API key is valid",
+    "如输入区内容为文件则清空历史记录": "If the input area content is a file, clear the history",
+    "并处理精度问题": "And handle precision issues",
+    "并给出修改的理由": "And provide reasons for the changes",
+    "至此已经超出了正常接口应该进入的范围": "This has exceeded the scope that a normal interface should enter",
+    "并已加载知识库": "And the knowledge base has been loaded",
+    "file_manifest_filter_html 根据type过滤文件": "file_manifest_filter_html filters files by type",
+    "participant B as 系统": "participant B as System",
+    "要留出足够的互动空间": "Leave enough interaction space",
+    "请你给出围绕“{subject}”的实体关系图": "Please provide an entity relationship diagram around '{subject}'",
+    "答案请使用中文": "Please answer in Chinese",
+    "输出会更加稳定或确定": "The output will be more stable or certain",
+    "是一个包的初始化文件": "Is an initialization file for a package",
+    "用于加载和分割文件中的文本的通用文件加载器用于加载和分割文件中的文本的通用文件加载器用于加载和分割文件中的文本的通用文件加载器": "A universal file loader for loading and splitting text in files",
+    "围绕我选定的剧情情节": "Around the plot I have chosen",
+    "Mathpix 拥有执行PDF的OCR功能": "Mathpix has OCR functionality for PDFs",
+    "是否允许暴力切分": "Whether to allow violent segmentation",
+    "清空 txt_tmp 对应的位置方便下次搜索": "Clear the location corresponding to txt_tmp for easier next search",
+    "编写小说的最后一幕": "Write the last scene of the novel",
+    "可能是一个模块的初始化文件根据位置和名称": "May be an initialization file for a module based on position and name",
+    "更新新的自定义按钮": "Update new custom button",
+    "把分句符\\n放到双引号后": "Put the sentence separator \\n after the double quotes",
+    "序列图": "Sequence diagram",
+    "兼容非markdown输入": "Compatible with non-markdown input",
+    "那么就切": "Then cut",
+    "4-饼图": "4-Pie chart",
+    "结束剧情": "End of the plot",
+    "字数要求": "Word count requirement",
+    "以下是对以上文本的总结": "Below is a summary of the above text",
+    "但不要同时调整两个参数": "But do not adjust two parameters at the same time",
+    "📌省略": "Omit",
+    "请查看message": "Please check the message",
+    "如果所有页的内容都相同": "If all pages have the same content",
+    "我将在这4个选择中": "I will choose from these 4 options",
+    "请设置为True": "Please set to True",
+    "当 remain_txt_to_cut": "When remain_txt_to_cut",
+    "后续输出被截断": "Subsequent output is truncated",
+    "检查API_KEY": "Check API_KEY",
+    "阿里云实时语音识别 配置难度较高": "Alibaba Cloud real-time speech recognition has a higher configuration difficulty",
+    "图像生成提示为空白": "Image generation prompt is blank",
+    "由于实体关系图用到了{}符号": "Because the entity relationship diagram uses the {} symbol",
+    "系统繁忙": "System busy",
+    "月之暗面 API KEY": "Dark side of the moon API KEY",
+    "编写小说的下一幕": "Write the next scene of the novel",
+    "选择一种": "Choose one",
+    "或者flowchart TD": "Or flowchart TD",
+    "请把以下学术文章段落翻译成中文": "Please translate the following academic article paragraph into Chinese",
+    "7 实体关系图": "7 Entity relationship diagram",
+    "处理游戏的主体逻辑": "Handle the main logic of the game",
+    "请以“{headstart}”为开头": "Please start with \"{headstart}\"",
+    "匹配后单段上下文长度": "Length of single segment context after matching",
+    "先行者知道": "The pioneer knows",
+    "以及处理PDF文件的示例代码包含了用于文本切分的函数": "Example code for processing PDF files includes functions for text segmentation",
+    "未发现重复上传": "No duplicate uploads found",
+    "那么就不用切了": "Then there's no need to split",
+    "目前来说": "Currently",
+    "请在LLM_MODEL中配置": "Please configure in LLM_MODEL",
+    "是否启用上下文关联": "Whether to enable context association",
+    "为了加速计算": "To speed up calculations",
+    "登录请求": "Login request",
+    "这里解释一下正则表达式中的几个特殊字符": "Explanation of some special characters in regular expressions",
+    "其中数字对应关系为": "The corresponding relationship of the numbers is",
+    "修改配置有三种方法": "There are three ways to modify the configuration",
+    "请前往arxiv打开此论文下载页面": "Please go to arXiv and open the paper download page",
+    "然后download source手动下载latex源码包": "Then manually download the LaTeX source package by downloading the source",
+    "功能单元": "Functional unit",
+    "你需要翻译的文本如下": "The text you need to translate is as follows",
+    "以便于后续快速的匹配和查找操作": "To facilitate rapid matching and search operations later",
+    "文本内容": "Text content",
+    "自动更新、打开浏览器页面、预热tiktoken模块": "Auto-update, open browser page, warm up tiktoken module",
+    "原样传递": "Pass through as is",
+    "但是该文件格式不被支持": "But the file format is not supported",
+    "他现在是全宇宙中唯一的一个人了": "He is now the only person in the entire universe",
+    "取值范围0~1": "Value range 0~1",
+    "搜索匹配score阈值": "Search match score threshold",
+    "当字符串中有掩码tag时": "When there is a mask tag in the string",
+    "错误的不纳入对话": "Errors are not included in the conversation",
+    "英语": "English",
+    "象限提示图": "Quadrant prompt diagram",
+    "由于不管提供文本是什么": "Because regardless of what the provided text is",
+    "确定后续剧情的发展": "Determine the development of the subsequent plot",
+    "处理空输入导致报错的问题 https": "Handle the error caused by empty input",
+    "第 3 部分": "Part 3",
+    "不能等于 0 或 1": "Cannot be equal to 0 or 1",
+    "同时过大的图表可能需要复制到在线编辑器中进行渲染": "Large charts may need to be copied to an online editor for rendering",
+    "装饰器函数ArgsGeneralWrapper": "Decorator function ArgsGeneralWrapper",
+    "写个函数移除所有的换行符": "Write a function to remove all line breaks",
+    "默认为False": "Default is False",
+    "实例化BaiduSpider": "Instantiate BaiduSpider",
+    "9-思维导图": "Mind Map 9",
+    "是否开启跨域": "Whether to enable cross-domain",
+    "随机InteractiveMiniGame": "Random InteractiveMiniGame",
+    "用于构建HTML报告的类和方法用于构建HTML报告的类和方法用于构建HTML报告的类和方法": "Classes and methods for building HTML reports",
+    "这里填一个提示词字符串就行了": "Just fill in a prompt string here",
+    "文本切分": "Text segmentation",
+    "用于在生成mermaid图表时隐藏代码块": "Used to hide code blocks when generating mermaid charts",
+    "如果剩余文本的token数小于限制": "If the number of tokens in the remaining text is less than the limit",
+    "未能在规定时间内完成任务": "Failed to complete the task within the specified time",
+    "API key has been deactivated. Cohere以账户失效为由": "API key has been deactivated. Cohere cited account expiration as the reason",
+    "正在使用讯飞图片理解API": "Using the Xunfei Image Understanding API",
+    "如果您使用docker-compose部署": "If you deploy using docker-compose",
+    "最大输入 token 数": "Maximum input token count",
+    "遇到了控制请求速率限制": "Encountered control request rate limit",
+    "数值范围约为0-1100": "The numerical range is approximately 0-1100",
+    "几乎使他晕厥过去": "Almost made him faint",
+    "识图模型GPT-4V": "Image recognition model GPT-4V",
+    "零一万物模型 -=-=-=-=-=-=-": "Zero-One Universe Model",
+    "所有对话记录将自动保存在本地目录": "All conversation records will be saved automatically in the local directory",
+    "饼图": "Pie Chart",
+    "添加Live2D": "Add Live2D",
+    "⭐ 单线程方法": "Single-threaded Method",
+    "配图": "Illustration",
+    "根据上述已知信息": "Based on the Above Known Information",
+    "1. 后续剧情发展1": "1. Subsequent Plot Development 1",
+    "2-序列图": "Sequence Diagram",
+    "流程图": "Flowchart",
+    "需求分析": "Requirement Analysis",
+    "我认为更合理的是": "I Think a More Reasonable Approach Is",
+    "claude家族": "Claude Family",
+    "”的逻辑关系图": "Logic Relationship Diagram",
+    "给出人物的名字": "Provide the Names of Characters",
+    "无法自动下载该论文的Latex源码": "Unable to Automatically Download the LaTeX Source Code of the Paper",
+    "需要用户手动处理的信息": "Information That Requires Manual Processing by Users",
+    "点击展开“文件下载区”": "Click to Expand 'File Download Area'",
+    "生成长度过长": "Excessive Length Generated",
+    "\\n\\n2. 长效解决方案": "2. Long-term Solution",
+    "=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-= 插件主程序2 =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=": "=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-= Plugin Main Program 2 =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=",
+    "title 项目开发流程": "Title Project Development Process",
+    "如果您希望剧情立即收尾": "If You Want the Plot to End Immediately",
+    "空格转换为&nbsp": "Space Converted to  ",
+    "图片数量超过api上限": "Number of Images Exceeds API Limit",
+    "他知道": "He Knows",
+    "在这里输入自定义参数「分辨率-质量": "Enter Custom Parameters Here 'Resolution-Quality",
+    "例如ChatGLM&gpt-3.5-turbo&gpt-4": "For example ChatGLM, gpt-3.5-turbo, and gpt-4",
+    "账户管理": "Account Management",
+    "正在将翻译好的项目tex项目编译为PDF": "Compiling the Translated Project .tex Project into PDF",
+    "我们把 _max 后的文字转存至 remain_txt_to_cut_storage": "We save the text after _max to the remain_txt_to_cut_storage",
+    "标签之前停止匹配": "Stop matching before the label",
+    "例子": "Example",
+    "遍历检查是否有额外参数": "Iterate to check for extra parameters",
+    "文本分句长度": "Length of text segmentation",
+    "请你给出围绕“{subject}”的状态图": "Please provide a state diagram surrounding \"{subject}\"",
+    "用stream的方法避免中途网线被掐": "Use the stream method to avoid the cable being disconnected midway",
+    "然后在markdown表格中列出修改的内容": "Then list the changes in a Markdown table",
+    "以上是从文章中提取的摘要": "The above is an abstract extracted from the article",
+    "但是无法找到相关文件": "But unable to find the relevant file",
+    "上海AI-LAB书生大模型 -=-=-=-=-=-=-": "Shanghai AI-LAB Shu Sheng Large Model -=-=-=-=-=-=-",
+    "遇到第一个": "Meet the first",
+    "存储在名为const_extract_exp的变量中": "Stored in a variable named const_extract_exp",
+    "括号在正则表达式中表示捕获组": "Parentheses represent capture groups in regular expressions",
+    "那里的太空中渐渐隐现出一个方形区域": "A square area gradually appears in the space there",
+    "智谱GLM4超级模型🔥": "Zhipu GLM4 Super Model🔥",
+    "故事开头": "Beginning of the story",
+    "请检查文件格式是否正确": "Please check if the file format is correct",
+    "这个模式被编译成一个正则表达式对象": "This pattern is compiled into a regular expression object",
+    "单字符断句符": "Single character sentence break",
+    "看后续支持吧": "Let's see the follow-up support",
+    "markdown输入": "Markdown input",
+    "系统": "System",
+    "80字以内": "Within 80 characters",
+    "一个测试mermaid绘制图表的功能": "A function to test the Mermaid chart drawing",
+    "输入部分": "Input section",
+    "移除右侧逗号": "Remove the comma on the right",
+    "因此思维导图仅能通过参数调用": "Therefore, the mind map can only be invoked through parameters",
+    "6 状态图": "State Diagram",
+    "类图": "Class Diagram",
+    "不要重复前文": "Do not repeat the previous text",
+    "但内部": "But internally",
+    "小说的下一幕字数少于300字": "The next scene of the novel has fewer than 300 words",
+    "每个发展方向都精明扼要地用一句话说明": "Each development direction is concisely described in one sentence",
+    "充分考虑其之间的逻辑": "Fully consider the logic between them",
+    "兼顾前端状态的功能": "Take into account the functionality of the frontend state",
+    "1 流程图": "Flowchart",
+    "用户QQ群925365219": "User QQ Group 925365219",
+    "通义-本地模型 -=-=-=-=-=-=-": "Tongyi - Local Model",
+    "取值范围0-1000": "Value range 0-1000",
+    "但不是^*.开始": "But not ^*. Start",
+    "他们将钻出地壳去看诗云": "They will emerge from the crust to see the poetry cloud",
+    "我们正在互相讨论": "We are discussing with each other",
+    "值越小": "The smaller the value",
+    "请在以下几种故事走向中": "Please choose from the following story directions",
+    "请先把模型切换至gpt-*": "Please switch the model to gpt-* first",
+    "不再需要填写": "No longer needs to be filled out",
+    "深夜": "Late at night",
+    "小说的前文回顾": "Review of the previous text of the novel",
+    "项目文件树": "Project file tree",
+    "如果双引号前有终止符": "If there is a terminator before the double quotes",
+    "participant A as 用户": "Participant A as User",
+    "处理游戏初始化等特殊情况": "Handle special cases like game initialization",
+    "然后使用mermaid+llm绘制图表": "Then use mermaid+llm to draw charts",
+    "0表示不生效": "0 means not effective",
+    "在以下的剧情发展中": "In the following plot development",
+    "模型考虑具有 top_p 概率质量 tokens 的结果": "Model considering results with top_p probability quality tokens",
+    "根据字符串要给谁看": "Depending on who is intended to view the string",
+    "没有设置YIMODEL_API_KEY选项": "YIMODEL_API_KEY option is not set",
+    "换行符转换为": "Convert line breaks to",
+    "-风格": "-style",
+    "默认情况下并发量极低": "Default to a very low level of concurrency",
+    "为字符串加上上面定义的前缀和后缀": "Add the defined prefix and suffix to the string",
+    "先切换模型到gpt-*": "Switch the model to gpt-* first",
+    "它确保我们匹配的任意文本是尽可能短的": "It ensures that any text we match is as short as possible",
+    "积极地运用环境描写、人物描写等手法": "Actively use techniques such as environmental and character descriptions",
+    "零一万物": "Zero One Universe",
+    "html_local_file 本地文件取相对路径": "html_local_file takes the relative path of the local file",
+    "伊依一行三人乘坐一艘游艇在南太平洋上做吟诗航行": "Yi Yi and three others set sail on a yacht to recite poetry in the South Pacific",
+    "移除左边通配符": "Remove left wildcard characters",
+    "随后绘制图表": "Draw a chart subsequently",
+    "输入2": "Input 2",
+    "所以用最没有意义的一个点代替": "Therefore, replace it with the most meaningless point",
+    "等": "etc.",
+    "是本地文件": "Is a local file",
+    "正在文本切分": "Text segmentation in progress",
+    "等价于修改容器内部的环境变量": "Equivalent to modifying the environment variables inside the container",
+    "cohere等请求源": "Cohere and other request sources",
+    "我们再把 remain_txt_to_cut_storage 中的部分文字取出": "Then we extract part of the text from remain_txt_to_cut_storage",
+    "生成带掩码tag的字符串": "Generate a string with masked tags",
+    "智谱 -=-=-=-=-=-=-": "ZhiPu -=-=-=-=-=-=-",
+    "前缀字符串": "Prefix string",
+    "Temperature值越大随机性越大": "The larger the Temperature value, the greater the randomness",
+    "借用PDF切割中的函数对文本进行切割": "Use functions from PDF cutting to segment the text",
+    "挑选一种剧情发展": "Choose a plot development",
+    "将换行符转换为": "Convert line breaks to",
+    "0.1 意味着模型解码器只考虑从前 10% 的概率的候选集中取 tokens": "0.1 means the model decoder only considers taking tokens from the top 10% probability candidates",
+    "确定故事的下一步": "Determine the next step of the story",
+    "个文件的显示": "Display of a file",
+    "用于控制输出tokens的多样性": "Used to control the diversity of output tokens",
+    "导入BaiduSpider": "Import BaiduSpider",
+    "不输入则为模型自行判断": "If not entered, the model will judge on its own",
+    "准备下一次迭代": "Prepare for the next iteration",
+    "包含一些用于文本处理和模型微调的函数和装饰器包含一些用于文本处理和模型微调的函数和装饰器包含一些用于文本处理和模型微调的函数和装饰器": "Contains functions and decorators for text processing and model fine-tuning",
+    "由于没有单独的参数保存包含图片的历史": "Since there is no separate parameter to save the history with images",
+    "section 开发": "section development",
+    "注意这里没有掩码tag": "Note that there is no mask tag here",
+    "section 设计": "section design",
+    "对话|编程|学术|智能体": "Dialogue | Programming | Academic | Intelligent Agent",
+    "您只需要选择其中一种即可": "You only need to choose one of them",
+    "添加Live2D形象": "Add Live2D image",
+    "请用以下命令安装": "Please install with the following command",
+    "触发了Google的安全访问策略": "Triggered Google's safe access policy",
+    "参数示例「1024x1024-hd-vivid」 || 分辨率支持 「1024x1024」": "Parameter example '1024x1024-hd-vivid' || Resolution support '1024x1024'",
+    "结局除外": "Excluding the ending",
+    "subgraph 函数调用": "subgraph function call",
+    "项目示意图": "Project diagram",
+    "实体关系图": "Entity relationship diagram",
+    "计算机把他的代号定为M102": "The computer named his code M102",
+    "首先尝试用双空行": "Try using double empty lines first",
+    "接下来将判断适合的图表类型": "Next, determine the appropriate chart type",
+    "注意前面的几句都小心保留了双引号": "Note that the previous sentences have carefully preserved double quotes",
+    "您正在调用插件": "You are calling a plugin",
+    "从上到下": "From top to bottom",
+    "请配置HUOSHAN_API_KEY": "Please configure HUOSHAN_API_KEY",
+    "知识检索内容相关度 Score": "Knowledge retrieval content relevance score",
+    "所以不会被处理": "So it will not be processed",
+    "设置10秒即可": "Set to 10 seconds",
+    "以空格分割": "Separated by space",
+    "根据位置和名称": "According to position and name",
+    "一些垃圾第三方接口出现这样的错误": "Some crappy third-party interfaces have this error",
+    "////////////////////// 输入清除键 ///////////////////////////": "////////////////////// Input Clear Key ///////////////////////////",
+    "并解析为html or md 文本": "And parse as HTML or MD text",
+    "匹配单段内容的连接上下文长度": "Matching single section content connection context length",
+    "控制输出的随机性": "Control the randomness of output",
+    "是模型名": "Is model name",
+    "请检查配置文件": "Please check the configuration file",
+    "如何使用one-api快速接入": "How to quickly access using one-api",
+    "请求失败": "Request failed",
+    "追加列表": "Append list",
+    "////////////////////// 函数插件区 ///////////////////////////": "////////////////////// Function Plugin Area ///////////////////////////",
+    "你是WPSAi": "You are WPSAi",
+    "第五部分 一些文件处理方法": "Part Five Some file processing methods",
+    "圆圆迷上了肥皂泡": "Yuan Yuan is fascinated by soap bubbles",
+    "可选参数": "Optional parameters",
+    "one-api模型": "one-api model",
+    "port/gpt_academic/ 下": "Under port/gpt_academic/",
+    "下一段故事": "Next part of the story",
+    "* 表示前一个字符可以出现0次或多次": "* means the previous character can appear 0 or more times",
+    "向后兼容配置": "Backward compatible configuration",
+    "输出部分": "Output section",
+    "稍后": "Later",
+    "比如比喻、拟人、排比、对偶、夸张等等": "For example, similes, personification, parallelism, antithesis, hyperbole, etc.",
+    "是自定义按钮": "Is a custom button",
+    "你需要根据用户给出的小说段落": "You need to based on the novel paragraph given by the user",
+    "以mermaid flowchart的形式展示": "Display in the form of a mermaid flowchart",
+    "最后一幕的字数少于1000字": "The last scene has fewer than 1000 words",
+    "如没出错则保持为空": "Keep it empty if there are no errors",
+    "建议您根据应用场景调整 top_p 或 temperature 参数": "It is recommended to adjust the top_p or temperature parameters according to the application scenario",
+    "仿佛他的出生就是要和这东西约会似的": "As if his birth was meant to date this thing",
+    "处理特殊的渲染问题": "Handle special rendering issues",
+    "我认为最合理的故事结局是": "I think the most reasonable ending for the story is",
+    "请给出上方内容的思维导图": "Please provide a mind map of the content above",
+    "点other Formats": "Click on other Formats",
+    "文件加载完毕": "File loaded",
+    "Your account is not active. Cohere以账户失效为由": "Your account is not active. Cohere cites the account's inactivation as the reason",
+    "找不到任何.pdf文件": "Cannot find any .pdf files",
+    "请根据判断结果绘制相应的图表": "Please draw the corresponding chart based on the judgment result",
+    "积极地运用修辞手法": "Actively use rhetorical devices",
+    "工具函数 =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-": "Utility function -=-=-=-=-=-=-=-=-=-=-=-=-=-=-=",
+    "=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-= 插件主程序1 =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=": "=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-= Plugin Main Program 1 =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=",
+    "在": "In",
+    "即正则表达式库": "That is, the regular expression library",
+    "////////////////////// 基础功能区 ///////////////////////////": "////////////////////// Basic Function Area ///////////////////////////",
+    "并重新编译PDF | 输入参数为路径": "And recompile PDF | Input parameter is the path",
+    "甘特图": "Gantt Chart",
+    "但是需要注册账号": "But registration is required",
+    "获取完整的从Cohere返回的报错": "Get the complete error message returned from Cohere",
+    "合并摘要": "Merge Summary",
+    "这最后一课要提前讲了": "The last lesson will be taught ahead of schedule",
+    "大模型": "Large Model",
+    "查找输入区内容中的文件": "Find files in the input area content",
+    "预处理参数": "Preprocessing Parameters",
+    "这段代码定义了一个名为ProxyNetworkActivate的空上下文管理器": "This code defines an empty context manager named ProxyNetworkActivate",
+    "对话错误": "Dialogue Error",
+    "确定故事的结局": "Determine the ending of the story",
+    "第 1 部分": "Part 1",
+    "直到遇到括号外部最近的限定符": "Until the nearest qualifier outside the parentheses is encountered",
+    "负责向用户前端展示对话": "Responsible for displaying dialogue to the user frontend",
+    "查询内容": "Query Content",
+    "匹配结果更精准": "More accurate matching results",
+    "根据选择的图表类型绘制图表": "Draw a chart based on the selected chart type",
+    "空格、换行、空字符串都会报错": "Spaces, line breaks, and empty strings will all result in errors",
+    "请尝试削减单次输入的文本量": "Please try to reduce the amount of text in a single input",
+    "上传到路径": "Upload to path",
+    "中": "In",
+    "后缀字符串": "Suffix string",
+    "您还可以在接入one-api时": "You can also when accessing one-api",
+    "请说 “根据已知信息无法回答该问题” 或 “没有提供足够的相关信息”": "Please say 'Cannot answer the question based on available information' or 'Not enough relevant information is provided'",
+    "Cohere和API2D不会走这里": "Cohere and API2D will not go here",
+    "节点名字使用引号包裹": "Node names should be enclosed in quotes",
+    "这次的故事开头是": "The beginning of this story is",
+    "你是一个想象力丰富的杰出作家": "You are a brilliant writer with a rich imagination",
+    "正在与你的朋友互动": "Interacting with your friends",
+    "/「-hd」 || 风格支持 「-vivid」": "/ '-hd' || Style supports '-vivid'",
+    "如输入区无内容则直接解析历史记录": "If the input area is empty, parse the history directly",
+    "根据以上的情节": "Based on the above plot",
+    "将图表类型参数赋值为插件参数": "Set the chart type parameter to the plugin parameter",
+    "根据图片类型返回image/jpeg": "Return image/jpeg based on image type",
+    "如果lang_reference是英文": "If lang_reference is English",
+    "示意图": "Schematic diagram",
+    "完整参数列表": "Complete parameter list",
+    "仿佛灿烂的群星的背景被剪出一个方口": "As if the brilliant background of stars has been cut out into a square",
+    "如果没有找到合适的切分点": "If no suitable splitting point is found",
+    "获取数据": "Get data",
+    "内嵌的javascript代码": "Embedded JavaScript code",
+    "绘制多种mermaid图表": "Draw various mermaid charts",
+    "无效": "Invalid",
+    "查找pdf/md/word并获取文本内容并返回状态以及文本": "Search for pdf/md/word, retrieve text content, and return status and text",
+    "总结绘制脑图": "Summarize mind mapping",
+    "禁止杜撰不符合我选择的剧情": "Prohibit making up plots that do not match my choice",
+    "正在生成向量库": "Generating vector library",
+    "是LLM的内部调优参数": "Is an internal tuning parameter of LLM",
+    "请你选择一个合适的图表类型": "Please choose an appropriate chart type",
+    "请在“输入区”输入图像生成提示": "Please enter image generation prompts in the 'input area'",
+    "经测试设置为小于500时": "After testing, set it to less than 500",
+    "当然": "Certainly",
+    "必要": "Necessary",
+    "从左到右": "From left to right",
+    "接下来调用本地Latex翻译插件即可": "Next, call the local Latex translation plugin",
+    "如果相同则返回": "If the same, return",
+    "根据语言": "According to the language",
+    "使用mermaid语法": "Use mermaid syntax",
+    "这是游戏的第一步": "This is the first step of the game",
+    "构建后续剧情引导": "Building subsequent plot guidance",
+    "以满足 token 限制": "To meet the token limit",
+    "也就是说": "That is to say",
+    "mermaid语法举例": "Mermaid syntax example",
+    "发送": "Send",
+    "那么就只显示英文提示词": "Then only display English prompts",
+    "正在检查": "Checking",
+    "返回处理后的字符串": "Return the processed string",
+    "2 序列图": "Sequence diagram 2",
+    "yi-34b-chat-0205只有4k上下文": "yi-34b-chat-0205 has only 4k context",
+    "请检查配置": "Please check the configuration",
+    "请你给出围绕“{subject}”的象限图": "Please provide a quadrant diagram around '{subject}'",
+    "故事该结束了": "The story should end",
+    "修复缩进": "Fix indentation",
+    "请描述给出的图片": "Please describe the given image",
+    "启用插件热加载": "Enable plugin hot reload",
+    "通义-在线模型 -=-=-=-=-=-=-": "Tongyi - Online Model",
+    "比较页数是否相同": "Compare if the number of pages is the same",
+    "正式开始服务": "Officially start the service",
+    "使用mermaid flowchart对以上文本进行总结": "Summarize the above text using a mermaid flowchart",
+    "不是vision 才处理history": "Not only vision but also handle history",
+    "来定义了一个正则表达式模式": "Defined a regular expression pattern",
+    "IP地址等": "IP addresses, etc.",
+    "那么双引号才是句子的终点": "Then the double quotes mark the end of the sentence",
+    "输入1": "Input 1",
+    "/「1792x1024」/「1024x1792」 || 质量支持 「-standard」": "/'1792x1024'/ '1024x1792' || Quality support '-standard'",
+    "为了避免索引错误将其更改为大写": "To avoid indexing errors, change it to uppercase",
+    "搜索网页": "Search the web",
+    "用于控制生成文本的随机性和创造性": "Used to control the randomness and creativity of generated text",
+    "不能等于 0": "Cannot equal 0",
+    "在距地球五万光年的远方": "At a distance of fifty thousand light-years from Earth",
+    ". 表示任意单一字符": ". represents any single character",
+    "选择预测值最大的k个token进行采样": "Select the k tokens with the largest predicted values for sampling",
+    "输出2": "Output 2",
+    "函数示意图": "Function Diagram",
+    "You are associated with a deactivated account. Cohere以账户失效为由": "You are associated with a deactivated account. Cohere due to account deactivation",
+    "3. 后续剧情发展3": "3. Subsequent Plot Development",
+    "并以“剧情收尾”四个字提示程序": "And use the four characters 'Plot Conclusion' as a prompt for the program",
+    "中文省略号": "Chinese Ellipsis",
+    "则不生效": "Will not take effect",
+    "目前是两位小数": "Currently is two decimal places",
+    "Incorrect API key. Cohere以提供了不正确的API_KEY为由": "Incorrect API key. Cohere reports an incorrect API_KEY."
+}

docs/translate_japanese.json

@@ -44,7 +44,7 @@
     "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批量翻译": "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结果": "LatexOutputPDFResult",
+    "Latex输出PDF": "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

@@ -6,7 +6,7 @@
     "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",
+    "PDF批量翻译": "BatchTranslatePDFDocuments_MultiThreaded",
     "下载arxiv论文翻译摘要": "DownloadArxivPaperTranslateAbstract",
     "解析一个Python项目": "ParsePythonProject",
     "解析一个Golang项目": "ParseGolangProject",
@@ -16,7 +16,7 @@
     "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结果": "OutputPDFFromLatex",
+    "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",
@@ -97,5 +97,12 @@
     "多智能体": "MultiAgent",
     "图片生成_DALLE2": "ImageGeneration_DALLE2",
     "图片生成_DALLE3": "ImageGeneration_DALLE3",
-    "图片修改_DALLE2": "ImageModification_DALLE2"
-}
+    "图片修改_DALLE2": "ImageModification_DALLE2",
+    "生成多种Mermaid图表": "GenerateMultipleMermaidCharts",
+    "知识库文件注入": "InjectKnowledgeBaseFiles",
+    "PDF翻译中文并重新编译PDF": "TranslatePDFToChineseAndRecompilePDF",
+    "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"
+}

docs/translate_traditionalchinese.json

@@ -43,7 +43,7 @@
     "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批量翻译": "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结果": "OutputPDFFromLatex",
+    "Latex输出PDF": "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
+```

docs/waifu_plugin/autoload.js

@@ -1,30 +0,0 @@
-try {
-    $("<link>").attr({href: "file=docs/waifu_plugin/waifu.css", rel: "stylesheet", type: "text/css"}).appendTo('head');
-    $('body').append('<div class="waifu"><div class="waifu-tips"></div><canvas id="live2d" class="live2d"></canvas><div class="waifu-tool"><span class="fui-home"></span> <span class="fui-chat"></span> <span class="fui-eye"></span> <span class="fui-user"></span> <span class="fui-photo"></span> <span class="fui-info-circle"></span> <span class="fui-cross"></span></div></div>');
-    $.ajax({url: "file=docs/waifu_plugin/waifu-tips.js", dataType:"script", cache: true, success: function() {
-        $.ajax({url: "file=docs/waifu_plugin/live2d.js", dataType:"script", cache: true, success: function() {
-            /* 可直接修改部分参数 */
-            live2d_settings['hitokotoAPI'] = "hitokoto.cn";  // 一言 API
-            live2d_settings['modelId'] = 5;                  // 默认模型 ID
-            live2d_settings['modelTexturesId'] = 1;          // 默认材质 ID
-            live2d_settings['modelStorage'] = false;         // 不储存模型 ID
-            live2d_settings['waifuSize']            = '210x187';
-            live2d_settings['waifuTipsSize']        = '187x52';
-            live2d_settings['canSwitchModel']       = true;
-            live2d_settings['canSwitchTextures']    = true;
-            live2d_settings['canSwitchHitokoto']    = false;
-            live2d_settings['canTakeScreenshot']    = false;
-            live2d_settings['canTurnToHomePage']    = false;
-            live2d_settings['canTurnToAboutPage']   = false;
-            live2d_settings['showHitokoto']         = false;         // 显示一言
-            live2d_settings['showF12Status']        = false;         // 显示加载状态
-            live2d_settings['showF12Message']       = false;        // 显示看板娘消息
-            live2d_settings['showF12OpenMsg']       = false;         // 显示控制台打开提示
-            live2d_settings['showCopyMessage']      = false;         // 显示 复制内容 提示
-            live2d_settings['showWelcomeMessage']   = true;         // 显示进入面页欢迎词
-
-            /* 在 initModel 前添加 */
-            initModel("file=docs/waifu_plugin/waifu-tips.json");
-        }});
-    }});
-} catch(err) { console.log("[Error] JQuery is not defined.") }

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),
@@ -13,35 +13,41 @@ help_menu_description = \
 </br></br>如何语音对话: 请阅读Wiki
 </br></br>如何临时更换API_KEY: 在输入区输入临时API_KEY后提交（网页刷新后失效）"""
 
+def enable_log(PATH_LOGGING):
+    import logging
+    admin_log_path = os.path.join(PATH_LOGGING, "admin")
+    os.makedirs(admin_log_path, exist_ok=True)
+    log_dir = os.path.join(admin_log_path, "chat_secrets.log")
+    try:logging.basicConfig(filename=log_dir, level=logging.INFO, encoding="utf-8", format="%(asctime)s %(levelname)-8s %(message)s", datefmt="%Y-%m-%d %H:%M:%S")
+    except:logging.basicConfig(filename=log_dir, level=logging.INFO,  format="%(asctime)s %(levelname)-8s %(message)s", datefmt="%Y-%m-%d %H:%M:%S")
+    # Disable logging output from the 'httpx' logger
+    logging.getLogger("httpx").setLevel(logging.WARNING)
+    print(f"所有对话记录将自动保存在本地目录{log_dir}, 请注意自我隐私保护哦！")
+
 def main():
     import gradio as gr
-    if gr.__version__ not in ['3.32.6', '3.32.7', '3.32.8']:
+    if gr.__version__ not in ['3.32.9']:
         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
     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 = get_conf('ENABLE_AUDIO', 'AUTO_CLEAR_TXT', 'PATH_LOGGING', 'AVAIL_THEMES', 'THEME')
-    DARK_MODE, NUM_CUSTOM_BASIC_BTN, SSL_KEYFILE, SSL_CERTFILE = get_conf('DARK_MODE', 'NUM_CUSTOM_BASIC_BTN', 'SSL_KEYFILE', 'SSL_CERTFILE')
-    INIT_SYS_PROMPT = get_conf('INIT_SYS_PROMPT')
+    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, 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
-    from themes.theme import js_code_for_css_changing, js_code_for_darkmode_init, js_code_for_toggle_darkmode, js_code_for_persistent_cookie_init
-    from themes.theme import load_dynamic_theme, to_cookie_str, from_cookie_str, init_cookie
+    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 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}"
 
-    # 问询记录, python 版本建议3.9+（越新越好）
-    import logging, uuid
-    os.makedirs(PATH_LOGGING, exist_ok=True)
-    try:logging.basicConfig(filename=f"{PATH_LOGGING}/chat_secrets.log", level=logging.INFO, encoding="utf-8", format="%(asctime)s %(levelname)-8s %(message)s", datefmt="%Y-%m-%d %H:%M:%S")
-    except:logging.basicConfig(filename=f"{PATH_LOGGING}/chat_secrets.log", level=logging.INFO,  format="%(asctime)s %(levelname)-8s %(message)s", datefmt="%Y-%m-%d %H:%M:%S")
-    # Disable logging output from the 'httpx' logger
-    logging.getLogger("httpx").setLevel(logging.WARNING)
-    print(f"所有问询记录将自动保存在本地目录./{PATH_LOGGING}/chat_secrets.log, 请注意自我隐私保护哦！")
+    # 对话、日志记录
+    enable_log(PATH_LOGGING)
 
     # 一些普通功能模块
     from core_functional import get_core_functions
@@ -65,7 +71,7 @@ def main():
     proxy_info = check_proxy(proxies)
 
     gr_L1 = lambda: gr.Row().style()
-    gr_L2 = lambda scale, elem_id: gr.Column(scale=scale, elem_id=elem_id)
+    gr_L2 = lambda scale, elem_id: gr.Column(scale=scale, elem_id=elem_id, min_width=400)
     if LAYOUT == "TOP-DOWN":
         gr_L1 = lambda: DummyWith()
         gr_L2 = lambda scale, elem_id: gr.Row()
@@ -74,15 +80,18 @@ def main():
     cancel_handles = []
     customize_btns = {}
     predefined_btns = {}
-    with gr.Blocks(title="GPT 学术优化", theme=set_theme, analytics_enabled=False, css=advanced_css) as demo:
+    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, dark_mode, persistent_cookie = gr.Textbox(visible=False), gr.Textbox(DARK_MODE, visible=False), gr.Textbox(visible=False)
-        cookies = gr.State(load_chat_cookies())
+        secret_css = gr.Textbox(visible=False, elem_id="secret_css")
+
+
+        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():
@@ -98,6 +107,7 @@ def main():
                             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")
+
                 with gr.Accordion("基础功能区", open=True, elem_id="basic-panel") as area_basic_fn:
                     with gr.Row():
                         for k in range(NUM_CUSTOM_BASIC_BTN):
@@ -142,7 +152,6 @@ def main():
                         with gr.Accordion("点击展开“文件下载区”。", open=False) as area_file_up:
                             file_upload = gr.Files(label="任何文件, 推荐上传压缩文件(zip, tar)", file_count="multiple", elem_id="elem_upload")
 
-
         with gr.Floating(init_x="0%", init_y="0%", visible=True, width=None, drag="forbidden", elem_id="tooltip"):
             with gr.Row():
                 with gr.Tab("上传文件", elem_id="interact-panel"):
@@ -150,18 +159,25 @@ def main():
                     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)
+                    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",)
+                    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)
+                    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)
-                    checkboxes_2 = gr.CheckboxGroup(["自定义菜单"],
-                                                  value=[], label="显示/隐藏自定义菜单", elem_id='cbsc').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"):
@@ -178,7 +194,7 @@ def main():
                         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", variant="secondary", visible=False); clearBtn2.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:
@@ -192,69 +208,31 @@ def main():
                         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_load    = gr.Button("加载已保存", variant="primary"); basic_fn_load.style(size="sm")
-                        def assign_btn(persistent_cookie_, cookies_, basic_btn_dropdown_, basic_fn_title, basic_fn_prefix, basic_fn_suffix):
-                            ret = {}
-                            customize_fn_overwrite_ = cookies_['customize_fn_overwrite']
-                            customize_fn_overwrite_.update({
-                                basic_btn_dropdown_:
-                                    {
-                                        "Title":basic_fn_title,
-                                        "Prefix":basic_fn_prefix,
-                                        "Suffix":basic_fn_suffix,
-                                    }
-                                }
-                            )
-                            cookies_.update(customize_fn_overwrite_)
-                            if basic_btn_dropdown_ in customize_btns:
-                                ret.update({customize_btns[basic_btn_dropdown_]: gr.update(visible=True, value=basic_fn_title)})
-                            else:
-                                ret.update({predefined_btns[basic_btn_dropdown_]: gr.update(visible=True, value=basic_fn_title)})
-                            ret.update({cookies: cookies_})
-                            try: persistent_cookie_ = from_cookie_str(persistent_cookie_)   # persistent cookie to dict
-                            except: persistent_cookie_ = {}
-                            persistent_cookie_["custom_bnt"] = customize_fn_overwrite_      # dict update new value
-                            persistent_cookie_ = to_cookie_str(persistent_cookie_)          # persistent cookie to dict
-                            ret.update({persistent_cookie: persistent_cookie_})             # write persistent cookie
-                            return ret
+                        basic_fn_clean   = gr.Button("恢复默认", variant="primary"); basic_fn_clean.style(size="sm")
 
-                        def reflesh_btn(persistent_cookie_, cookies_):
-                            ret = {}
-                            for k in customize_btns:
-                                ret.update({customize_btns[k]: gr.update(visible=False, value="")})
+                        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);}""")
 
-                            try: persistent_cookie_ = from_cookie_str(persistent_cookie_)    # persistent cookie to dict
-                            except: return ret
 
-                            customize_fn_overwrite_ = persistent_cookie_.get("custom_bnt", {})
-                            cookies_['customize_fn_overwrite'] = customize_fn_overwrite_
-                            ret.update({cookies: cookies_})
-
-                            for k,v in persistent_cookie_["custom_bnt"].items():
-                                if v['Title'] == "": continue
-                                if k in customize_btns: ret.update({customize_btns[k]: gr.update(visible=True, value=v['Title'])})
-                                else: ret.update({predefined_btns[k]: gr.update(visible=True, value=v['Title'])})
-                            return ret
-
-                        basic_fn_load.click(reflesh_btn, [persistent_cookie, cookies], [cookies, *customize_btns.values(), *predefined_btns.values()])
-                        h = basic_fn_confirm.click(assign_btn, [persistent_cookie, cookies, basic_btn_dropdown, basic_fn_title, basic_fn_prefix, basic_fn_suffix],
-                                                   [persistent_cookie, cookies, *customize_btns.values(), *predefined_btns.values()])
-                        # save persistent cookie
-                        h.then(None, [persistent_cookie], None, _js="""(persistent_cookie)=>{setCookie("persistent_cookie", persistent_cookie, 5);}""")
 
         # 功能区显示开关与功能区的互动
         def fn_area_visibility(a):
             ret = {}
-            ret.update({area_basic_fn: gr.update(visible=("基础功能区" in a))})
-            ret.update({area_crazy_fn: gr.update(visible=("函数插件区" in a))})
             ret.update({area_input_primary: gr.update(visible=("浮动输入区" not in a))})
             ret.update({area_input_secondary: gr.update(visible=("浮动输入区" in a))})
-            ret.update({clearBtn: gr.update(visible=("输入清除键" in a))})
-            ret.update({clearBtn2: gr.update(visible=("输入清除键" in a))})
             ret.update({plugin_advanced_arg: gr.update(visible=("插件参数区" in a))})
             if "浮动输入区" in a: ret.update({txt: gr.update(value="")})
             return ret
-        checkboxes.select(fn_area_visibility, [checkboxes], [area_basic_fn, area_crazy_fn, area_input_primary, area_input_secondary, txt, txt2, clearBtn, clearBtn2, plugin_advanced_arg] )
+        checkboxes.select(fn_area_visibility, [checkboxes], [area_basic_fn, area_crazy_fn, area_input_primary, area_input_secondary, txt, txt2, plugin_advanced_arg] )
+        checkboxes.select(None, [checkboxes], None, _js=js_code_show_or_hide)
 
         # 功能区显示开关与功能区的互动
         def fn_area_visibility_2(a):
@@ -262,6 +240,7 @@ def main():
             ret.update({area_customize: gr.update(visible=("自定义菜单" in a))})
             return ret
         checkboxes_2.select(fn_area_visibility_2, [checkboxes_2], [area_customize] )
+        checkboxes_2.select(None, [checkboxes_2], None, _js=js_code_show_or_hide_group2)
 
         # 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]
@@ -272,15 +251,19 @@ def main():
         cancel_handles.append(txt2.submit(**predict_args))
         cancel_handles.append(submitBtn.click(**predict_args))
         cancel_handles.append(submitBtn2.click(**predict_args))
-        resetBtn.click(lambda: ([], [], "已重置"), None, [chatbot, history, status])
-        resetBtn2.click(lambda: ([], [], "已重置"), None, [chatbot, history, status])
-        clearBtn.click(lambda: ("",""), None, [txt, txt2])
-        clearBtn2.click(lambda: ("",""), None, [txt, txt2])
+        resetBtn.click(None, None, [chatbot, history, status], _js=js_code_reset)   # 先在前端快速清除chatbot&status
+        resetBtn2.click(None, None, [chatbot, history, status], _js=js_code_reset)  # 先在前端快速清除chatbot&status
+        reset_server_side_args = (lambda history: ([], [], "已重置", json.dumps(history)),
+                                  [history], [chatbot, history, status, history_cache])
+        resetBtn.click(*reset_server_side_args)    # 再在后端清除history，把history转存history_cache备用
+        resetBtn2.click(*reset_server_side_args)   # 再在后端清除history，把history转存history_cache备用
+        clearBtn.click(None, None, [txt, txt2], _js=js_code_clear)
+        clearBtn2.click(None, None, [txt, txt2], _js=js_code_clear)
         if AUTO_CLEAR_TXT:
-            submitBtn.click(lambda: ("",""), None, [txt, txt2])
-            submitBtn2.click(lambda: ("",""), None, [txt, txt2])
-            txt.submit(lambda: ("",""), None, [txt, txt2])
-            txt2.submit(lambda: ("",""), None, [txt, txt2])
+            submitBtn.click(None, None, [txt, txt2], _js=js_code_clear)
+            submitBtn2.click(None, None, [txt, txt2], _js=js_code_clear)
+            txt.submit(None, None, [txt, txt2], _js=js_code_clear)
+            txt2.submit(None, None, [txt, txt2], _js=js_code_clear)
         # 基础功能区的回调函数注册
         for k in functional:
             if ("Visible" in functional[k]) and (not functional[k]["Visible"]): continue
@@ -296,7 +279,7 @@ def main():
         for k in plugins:
             if not plugins[k].get("AsButton", True): continue
             click_handle = plugins[k]["Button"].click(ArgsGeneralWrapper(plugins[k]["Function"]), [*input_combo], output_combo)
-            click_handle.then(on_report_generated, [cookies, file_upload, chatbot], [cookies, file_upload, chatbot])
+            click_handle.then(on_report_generated, [cookies, file_upload, chatbot], [cookies, file_upload, chatbot]).then(None, [plugins[k]["Button"]], None, _js=r"(fn)=>on_plugin_exe_complete(fn)")
             cancel_handles.append(click_handle)
         # 函数插件-下拉菜单与随变按钮的互动
         def on_dropdown_changed(k):
@@ -334,7 +317,7 @@ def main():
             if k in [r"打开插件列表", r"请先从插件列表中选择"]: return
             yield from ArgsGeneralWrapper(plugins[k]["Function"])(request, *args, **kwargs)
         click_handle = switchy_bt.click(route,[switchy_bt, *input_combo], output_combo)
-        click_handle.then(on_report_generated, [cookies, file_upload, chatbot], [cookies, file_upload, chatbot])
+        click_handle.then(on_report_generated, [cookies, file_upload, chatbot], [cookies, file_upload, chatbot]).then(None, [switchy_bt], None, _js=r"(fn)=>on_plugin_exe_complete(fn)")
         cancel_handles.append(click_handle)
         # 终止按钮的回调函数注册
         stopBtn.click(fn=None, inputs=None, outputs=None, cancels=cancel_handles)
@@ -360,11 +343,14 @@ def main():
             audio_mic.stream(deal_audio, inputs=[audio_mic, cookies])
 
 
-        demo.load(init_cookie, inputs=[cookies, chatbot], outputs=[cookies])
-        darkmode_js = js_code_for_darkmode_init
-        demo.load(None, inputs=None, outputs=[persistent_cookie], _js=js_code_for_persistent_cookie_init)
-        demo.load(None, inputs=[dark_mode], outputs=None, _js=darkmode_js)    # 配置暗色主题或亮色主题
-        demo.load(None, inputs=[gr.Textbox(LAYOUT, visible=False)], outputs=None, _js='(LAYOUT)=>{GptAcademicJavaScriptInit(LAYOUT);}')
+        app_block.load(assign_user_uuid, inputs=[cookies], outputs=[cookies])
+
+        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
 
     # 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():
@@ -379,28 +365,15 @@ def main():
 
         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
+        threading.Thread(target=warm_up_mods, name="warm-up",      daemon=True).start() # 预热tiktoken模块
 
+    # 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()
-    demo.queue(concurrency_count=CONCURRENT_COUNT).launch(
-        quiet=True,
-        server_name="0.0.0.0",
-        ssl_keyfile=None if SSL_KEYFILE == "" else SSL_KEYFILE,
-        ssl_certfile=None if SSL_CERTFILE == "" else SSL_CERTFILE,
-        ssl_verify=False,
-        server_port=PORT,
-        favicon_path=os.path.join(os.path.dirname(__file__), "docs/logo.png"),
-        auth=AUTHENTICATION if len(AUTHENTICATION) != 0 else None,
-        blocked_paths=["config.py","config_private.py","docker-compose.yml","Dockerfile",f"{PATH_LOGGING}/admin"])
 
-    # 如果需要在二级路径下运行
-    # CUSTOM_PATH = get_conf('CUSTOM_PATH')
-    # if CUSTOM_PATH != "/":
-    #     from toolbox import run_gradio_in_subpath
-    #     run_gradio_in_subpath(demo, auth=AUTHENTICATION, port=PORT, custom_path=CUSTOM_PATH)
-    # else:
-    #     demo.launch(server_name="0.0.0.0", server_port=PORT, auth=AUTHENTICATION, favicon_path="docs/logo.png",
-    #                 blocked_paths=["config.py","config_private.py","docker-compose.yml","Dockerfile",f"{PATH_LOGGING}/admin"])
+    # 最后，正式开始服务
+    from shared_utils.fastapi_server import start_app
+    start_app(app_block, CONCURRENT_COUNT, AUTHENTICATION, PORT, SSL_KEYFILE, SSL_CERTFILE)
+
 
 if __name__ == "__main__":
     main()

multi_language.py

@@ -1,7 +1,7 @@
 """
     Translate this project to other languages (experimental, please open an issue if there is any bug)
-    
-    
+
+
     Usage:
         1. modify config.py, set your LLM_MODEL and API_KEY(s) to provide access to OPENAI (or any other LLM model provider)
 
@@ -11,20 +11,20 @@
         3. modify TransPrompt (below ↓)
             TransPrompt = f"Replace each json value `#` with translated results in English, e.g., \"原始文本\":\"TranslatedText\". Keep Json format. Do not answer #."
 
-        4. Run `python multi_language.py`. 
+        4. Run `python multi_language.py`.
             Note: You need to run it multiple times to increase translation coverage because GPT makes mistakes sometimes.
            (You can also run `CACHE_ONLY=True python multi_language.py` to use cached translation mapping)
 
         5. Find the translated program in `multi-language\English\*`
-   
+
     P.S.
-    
+
         - The translation mapping will be stored in `docs/translation_xxxx.json`, you can revised mistaken translation there.
-        
+
         - If you would like to share your `docs/translation_xxxx.json`, (so that everyone can use the cached & revised translation mapping), please open a Pull Request
 
         - If there is any translation error in `docs/translation_xxxx.json`, please open a Pull Request
-        
+
         - Welcome any Pull Request, regardless of language
 """
 
@@ -58,7 +58,7 @@ if not os.path.exists(CACHE_FOLDER):
 
 def lru_file_cache(maxsize=128, ttl=None, filename=None):
     """
-    Decorator that caches a function's return value after being called with given arguments. 
+    Decorator that caches a function's return value after being called with given arguments.
     It uses a Least Recently Used (LRU) cache strategy to limit the size of the cache.
     maxsize: Maximum size of the cache. Defaults to 128.
     ttl: Time-to-Live of the cache. If a value hasn't been accessed for `ttl` seconds, it will be evicted from the cache.
@@ -151,7 +151,7 @@ def map_to_json(map, language):
 
 def read_map_from_json(language):
     if os.path.exists(f'docs/translate_{language.lower()}.json'):
-        with open(f'docs/translate_{language.lower()}.json', 'r', encoding='utf8') as f: 
+        with open(f'docs/translate_{language.lower()}.json', 'r', encoding='utf8') as f:
             res = json.load(f)
             res = {k:v for k, v in res.items() if v is not None and contains_chinese(k)}
             return res
@@ -168,7 +168,7 @@ def advanced_split(splitted_string, spliter, include_spliter=False):
                         splitted[i] += spliter
                 splitted[i] = splitted[i].strip()
             for i in reversed(range(len(splitted))):
-                if not contains_chinese(splitted[i]): 
+                if not contains_chinese(splitted[i]):
                     splitted.pop(i)
             splitted_string_tmp.extend(splitted)
         else:
@@ -183,12 +183,12 @@ def trans(word_to_translate, language, special=False):
     if len(word_to_translate) == 0: return {}
     from crazy_functions.crazy_utils import request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency
     from toolbox import get_conf, ChatBotWithCookies, load_chat_cookies
-    
+
     cookies = load_chat_cookies()
     llm_kwargs = {
         'api_key': cookies['api_key'],
         'llm_model': cookies['llm_model'],
-        'top_p':1.0, 
+        'top_p':1.0,
         'max_length': None,
         'temperature':0.4,
     }
@@ -204,12 +204,12 @@ def trans(word_to_translate, language, special=False):
         sys_prompt_array = [f"Translate following sentences to {LANG}. E.g., You should translate sentences to the following format ['translation of sentence 1', 'translation of sentence 2']. Do NOT answer with Chinese!" for _ in inputs_array]
     chatbot = ChatBotWithCookies(llm_kwargs)
     gpt_say_generator = 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, 
+        inputs_array,
+        inputs_show_user_array,
+        llm_kwargs,
+        chatbot,
+        history_array,
+        sys_prompt_array,
     )
     while True:
         try:
@@ -224,7 +224,7 @@ def trans(word_to_translate, language, special=False):
             try:
                 res_before_trans = eval(result[i-1])
                 res_after_trans = eval(result[i])
-                if len(res_before_trans) != len(res_after_trans): 
+                if len(res_before_trans) != len(res_after_trans):
                     raise RuntimeError
                 for a,b in zip(res_before_trans, res_after_trans):
                     translated_result[a] = b
@@ -246,12 +246,12 @@ def trans_json(word_to_translate, language, special=False):
     if len(word_to_translate) == 0: return {}
     from crazy_functions.crazy_utils import request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency
     from toolbox import get_conf, ChatBotWithCookies, load_chat_cookies
-    
+
     cookies = load_chat_cookies()
     llm_kwargs = {
         'api_key': cookies['api_key'],
         'llm_model': cookies['llm_model'],
-        'top_p':1.0, 
+        'top_p':1.0,
         'max_length': None,
         'temperature':0.4,
     }
@@ -261,18 +261,18 @@ def trans_json(word_to_translate, language, special=False):
     word_to_translate_split = split_list(word_to_translate, N_EACH_REQ)
     inputs_array = [{k:"#" for k in s} for s in word_to_translate_split]
     inputs_array = [ json.dumps(i, ensure_ascii=False)  for i in inputs_array]
-    
+
     inputs_show_user_array = inputs_array
     history_array = [[] for _ in inputs_array]
     sys_prompt_array = [TransPrompt for _ in inputs_array]
     chatbot = ChatBotWithCookies(llm_kwargs)
     gpt_say_generator = 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, 
+        inputs_array,
+        inputs_show_user_array,
+        llm_kwargs,
+        chatbot,
+        history_array,
+        sys_prompt_array,
     )
     while True:
         try:
@@ -336,7 +336,7 @@ def step_1_core_key_translate():
     cached_translation = read_map_from_json(language=LANG_STD)
     cached_translation_keys = list(cached_translation.keys())
     for d in chinese_core_keys_norepeat:
-        if d not in cached_translation_keys: 
+        if d not in cached_translation_keys:
             need_translate.append(d)
 
     if CACHE_ONLY:
@@ -379,7 +379,7 @@ def step_1_core_key_translate():
                 # read again
                 with open(file_path, 'r', encoding='utf-8') as f:
                     content = f.read()
-                
+
                 for k, v in chinese_core_keys_norepeat_mapping.items():
                     content = content.replace(k, v)
 
@@ -390,7 +390,7 @@ def step_1_core_key_translate():
 def step_2_core_key_translate():
 
     # =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
-    # step2 
+    # step2
     # =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
 
     def load_string(strings, string_input):
@@ -423,7 +423,7 @@ def step_2_core_key_translate():
         splitted_string = advanced_split(splitted_string, spliter="   ", include_spliter=False)
         splitted_string = advanced_split(splitted_string, spliter="- ", include_spliter=False)
         splitted_string = advanced_split(splitted_string, spliter="---", include_spliter=False)
-        
+
         # --------------------------------------
         for j, s in enumerate(splitted_string): # .com
             if '.com' in s: continue
@@ -457,7 +457,7 @@ def step_2_core_key_translate():
                     comments_arr = []
                     for code_sp in content.splitlines():
                         comments = re.findall(r'#.*$', code_sp)
-                        for comment in comments: 
+                        for comment in comments:
                             load_string(strings=comments_arr, string_input=comment)
                     string_literals.extend(comments_arr)
 
@@ -479,7 +479,7 @@ def step_2_core_key_translate():
     cached_translation = read_map_from_json(language=LANG)
     cached_translation_keys = list(cached_translation.keys())
     for d in chinese_literal_names_norepeat:
-        if d not in cached_translation_keys: 
+        if d not in cached_translation_keys:
             need_translate.append(d)
 
     if CACHE_ONLY:
@@ -504,18 +504,18 @@ def step_2_core_key_translate():
                 # read again
                 with open(file_path, 'r', encoding='utf-8') as f:
                     content = f.read()
-                
+
                 for k, v in cached_translation.items():
                     if v is None: continue
-                    if '"' in v: 
+                    if '"' in v:
                         v = v.replace('"', "`")
-                    if '\'' in v: 
+                    if '\'' in v:
                         v = v.replace('\'', "`")
                     content = content.replace(k, v)
 
                 with open(file_path, 'w', encoding='utf-8') as f:
                     f.write(content)
-                
+
                 if file.strip('.py') in cached_translation:
                     file_new = cached_translation[file.strip('.py')] + '.py'
                     file_path_new = os.path.join(root, file_new)

request_llms/bridge_all.py

@@ -8,10 +8,10 @@
     具备多线程调用能力的函数：在函数插件中被调用，灵活而简洁
     2. predict_no_ui_long_connection(...)
 """
-import tiktoken, copy
+import tiktoken, copy, re
 from functools import lru_cache
 from concurrent.futures import ThreadPoolExecutor
-from toolbox import get_conf, trimmed_format_exc, apply_gpt_academic_string_mask
+from toolbox import get_conf, trimmed_format_exc, apply_gpt_academic_string_mask, read_one_api_model_name
 
 from .bridge_chatgpt import predict_no_ui_long_connection as chatgpt_noui
 from .bridge_chatgpt import predict as chatgpt_ui
@@ -31,6 +31,12 @@ from .bridge_qianfan import predict as qianfan_ui
 from .bridge_google_gemini import predict as genai_ui
 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_cohere import predict as cohere_ui
+from .bridge_cohere import predict_no_ui_long_connection as cohere_noui
+
 colors = ['#FF00FF', '#00FFFF', '#FF0000', '#990099', '#009999', '#990044']
 
 class LazyloadTiktoken(object):
@@ -44,13 +50,13 @@ class LazyloadTiktoken(object):
         tmp = tiktoken.encoding_for_model(model)
         print('加载tokenizer完毕')
         return tmp
-    
+
     def encode(self, *args, **kwargs):
-        encoder = self.get_encoder(self.model) 
+        encoder = self.get_encoder(self.model)
         return encoder.encode(*args, **kwargs)
-    
+
     def decode(self, *args, **kwargs):
-        encoder = self.get_encoder(self.model) 
+        encoder = self.get_encoder(self.model)
         return encoder.decode(*args, **kwargs)
 
 # Endpoint 重定向
@@ -58,12 +64,18 @@ API_URL_REDIRECT, AZURE_ENDPOINT, AZURE_ENGINE = get_conf("API_URL_REDIRECT", "A
 openai_endpoint = "https://api.openai.com/v1/chat/completions"
 api2d_endpoint = "https://openai.api2d.net/v1/chat/completions"
 newbing_endpoint = "wss://sydney.bing.com/sydney/ChatHub"
+gemini_endpoint = "https://generativelanguage.googleapis.com/v1beta/models"
+claude_endpoint = "https://api.anthropic.com/v1/messages"
+yimodel_endpoint = "https://api.lingyiwanwu.com/v1/chat/completions"
+cohere_endpoint = "https://api.cohere.ai/v1/chat"
+ollama_endpoint = "http://localhost:11434/api/chat"
+
 if not AZURE_ENDPOINT.endswith('/'): AZURE_ENDPOINT += '/'
 azure_endpoint = AZURE_ENDPOINT + f'openai/deployments/{AZURE_ENGINE}/chat/completions?api-version=2023-05-15'
 # 兼容旧版的配置
 try:
     API_URL = get_conf("API_URL")
-    if API_URL != "https://api.openai.com/v1/chat/completions": 
+    if API_URL != "https://api.openai.com/v1/chat/completions":
         openai_endpoint = API_URL
         print("警告！API_URL配置选项将被弃用，请更换为API_URL_REDIRECT配置")
 except:
@@ -72,7 +84,11 @@ except:
 if openai_endpoint in API_URL_REDIRECT: openai_endpoint = API_URL_REDIRECT[openai_endpoint]
 if api2d_endpoint in API_URL_REDIRECT: api2d_endpoint = API_URL_REDIRECT[api2d_endpoint]
 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]
 
 # 获取tokenizer
 tokenizer_gpt35 = LazyloadTiktoken("gpt-3.5-turbo")
@@ -91,11 +107,11 @@ model_info = {
         "fn_with_ui": chatgpt_ui,
         "fn_without_ui": chatgpt_noui,
         "endpoint": openai_endpoint,
-        "max_token": 4096,
+        "max_token": 16385,
         "tokenizer": tokenizer_gpt35,
         "token_cnt": get_token_num_gpt35,
     },
-    
+
     "gpt-3.5-turbo-16k": {
         "fn_with_ui": chatgpt_ui,
         "fn_without_ui": chatgpt_noui,
@@ -123,7 +139,16 @@ model_info = {
         "token_cnt": get_token_num_gpt35,
     },
 
-    "gpt-3.5-turbo-1106": {#16k
+    "gpt-3.5-turbo-1106": { #16k
+        "fn_with_ui": chatgpt_ui,
+        "fn_without_ui": chatgpt_noui,
+        "endpoint": openai_endpoint,
+        "max_token": 16385,
+        "tokenizer": tokenizer_gpt35,
+        "token_cnt": get_token_num_gpt35,
+    },
+
+    "gpt-3.5-turbo-0125": { #16k
         "fn_with_ui": chatgpt_ui,
         "fn_without_ui": chatgpt_noui,
         "endpoint": openai_endpoint,
@@ -177,6 +202,25 @@ model_info = {
         "token_cnt": get_token_num_gpt4,
     },
 
+    "gpt-4-turbo": {
+        "fn_with_ui": chatgpt_ui,
+        "fn_without_ui": chatgpt_noui,
+        "endpoint": openai_endpoint,
+        "max_token": 128000,
+        "tokenizer": tokenizer_gpt4,
+        "token_cnt": get_token_num_gpt4,
+    },
+
+    "gpt-4-turbo-2024-04-09": {
+        "fn_with_ui": chatgpt_ui,
+        "fn_without_ui": chatgpt_noui,
+        "endpoint": openai_endpoint,
+        "max_token": 128000,
+        "tokenizer": tokenizer_gpt4,
+        "token_cnt": get_token_num_gpt4,
+    },
+
+
     "gpt-3.5-random": {
         "fn_with_ui": chatgpt_ui,
         "fn_without_ui": chatgpt_noui,
@@ -185,7 +229,7 @@ model_info = {
         "tokenizer": tokenizer_gpt4,
         "token_cnt": get_token_num_gpt4,
     },
-    
+
     "gpt-4-vision-preview": {
         "fn_with_ui": chatgpt_vision_ui,
         "fn_without_ui": chatgpt_vision_noui,
@@ -215,16 +259,33 @@ model_info = {
         "token_cnt": get_token_num_gpt4,
     },
 
-    # api_2d (此后不需要在此处添加api2d的接口了，因为下面的代码会自动添加)
-    "api2d-gpt-3.5-turbo": {
-        "fn_with_ui": chatgpt_ui,
-        "fn_without_ui": chatgpt_noui,
-        "endpoint": api2d_endpoint,
-        "max_token": 4096,
+    # 智谱AI
+    "glm-4": {
+        "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,
+        "endpoint": None,
+        "max_token": 10124 * 4,
         "tokenizer": tokenizer_gpt35,
         "token_cnt": get_token_num_gpt35,
     },
 
+    # api_2d (此后不需要在此处添加api2d的接口了，因为下面的代码会自动添加)
     "api2d-gpt-4": {
         "fn_with_ui": chatgpt_ui,
         "fn_without_ui": chatgpt_noui,
@@ -270,7 +331,7 @@ model_info = {
     "gemini-pro": {
         "fn_with_ui": genai_ui,
         "fn_without_ui": genai_noui,
-        "endpoint": None,
+        "endpoint": gemini_endpoint,
         "max_token": 1024 * 32,
         "tokenizer": tokenizer_gpt35,
         "token_cnt": get_token_num_gpt35,
@@ -278,13 +339,56 @@ model_info = {
     "gemini-pro-vision": {
         "fn_with_ui": genai_ui,
         "fn_without_ui": genai_noui,
+        "endpoint": gemini_endpoint,
+        "max_token": 1024 * 32,
+        "tokenizer": tokenizer_gpt35,
+        "token_cnt": get_token_num_gpt35,
+    },
+
+    # cohere
+    "cohere-command-r-plus": {
+        "fn_with_ui": cohere_ui,
+        "fn_without_ui": cohere_noui,
+        "can_multi_thread": True,
+        "endpoint": cohere_endpoint,
+        "max_token": 1024 * 4,
+        "tokenizer": tokenizer_gpt35,
+        "token_cnt": get_token_num_gpt35,
+    },
+
+}
+# -=-=-=-=-=-=- 月之暗面 -=-=-=-=-=-=-
+from request_llms.bridge_moonshot import predict as moonshot_ui
+from request_llms.bridge_moonshot import predict_no_ui_long_connection as moonshot_no_ui
+model_info.update({
+    "moonshot-v1-8k": {
+        "fn_with_ui": moonshot_ui,
+        "fn_without_ui": moonshot_no_ui,
+        "can_multi_thread": True,
+        "endpoint": None,
+        "max_token": 1024 * 8,
+        "tokenizer": tokenizer_gpt35,
+        "token_cnt": get_token_num_gpt35,
+    },
+    "moonshot-v1-32k": {
+        "fn_with_ui": moonshot_ui,
+        "fn_without_ui": moonshot_no_ui,
+        "can_multi_thread": True,
         "endpoint": None,
         "max_token": 1024 * 32,
         "tokenizer": tokenizer_gpt35,
         "token_cnt": get_token_num_gpt35,
     },
-}
-
+    "moonshot-v1-128k": {
+        "fn_with_ui": moonshot_ui,
+        "fn_without_ui": moonshot_no_ui,
+        "can_multi_thread": True,
+        "endpoint": None,
+        "max_token": 1024 * 128,
+        "tokenizer": tokenizer_gpt35,
+        "token_cnt": get_token_num_gpt35,
+    }
+})
 # -=-=-=-=-=-=- api2d 对齐支持 -=-=-=-=-=-=-
 for model in AVAIL_LLM_MODELS:
     if model.startswith('api2d-') and (model.replace('api2d-','') in model_info.keys()):
@@ -300,25 +404,67 @@ for model in AVAIL_LLM_MODELS:
         model_info.update({model: mi})
 
 # -=-=-=-=-=-=- 以下部分是新加入的模型，可能附带额外依赖 -=-=-=-=-=-=-
-if "claude-1-100k" in AVAIL_LLM_MODELS or "claude-2" in AVAIL_LLM_MODELS:
+# claude家族
+claude_models = ["claude-instant-1.2","claude-2.0","claude-2.1","claude-3-haiku-20240307","claude-3-sonnet-20240229","claude-3-opus-20240229"]
+if any(item in claude_models for item in AVAIL_LLM_MODELS):
     from .bridge_claude import predict_no_ui_long_connection as claude_noui
     from .bridge_claude import predict as claude_ui
     model_info.update({
-        "claude-1-100k": {
+        "claude-instant-1.2": {
             "fn_with_ui": claude_ui,
             "fn_without_ui": claude_noui,
-            "endpoint": None,
-            "max_token": 8196,
+            "endpoint": claude_endpoint,
+            "max_token": 100000,
             "tokenizer": tokenizer_gpt35,
             "token_cnt": get_token_num_gpt35,
         },
     })
     model_info.update({
-        "claude-2": {
+        "claude-2.0": {
             "fn_with_ui": claude_ui,
             "fn_without_ui": claude_noui,
-            "endpoint": None,
-            "max_token": 8196,
+            "endpoint": claude_endpoint,
+            "max_token": 100000,
+            "tokenizer": tokenizer_gpt35,
+            "token_cnt": get_token_num_gpt35,
+        },
+    })
+    model_info.update({
+        "claude-2.1": {
+            "fn_with_ui": claude_ui,
+            "fn_without_ui": claude_noui,
+            "endpoint": claude_endpoint,
+            "max_token": 200000,
+            "tokenizer": tokenizer_gpt35,
+            "token_cnt": get_token_num_gpt35,
+        },
+    })
+    model_info.update({
+        "claude-3-haiku-20240307": {
+            "fn_with_ui": claude_ui,
+            "fn_without_ui": claude_noui,
+            "endpoint": claude_endpoint,
+            "max_token": 200000,
+            "tokenizer": tokenizer_gpt35,
+            "token_cnt": get_token_num_gpt35,
+        },
+    })
+    model_info.update({
+        "claude-3-sonnet-20240229": {
+            "fn_with_ui": claude_ui,
+            "fn_without_ui": claude_noui,
+            "endpoint": claude_endpoint,
+            "max_token": 200000,
+            "tokenizer": tokenizer_gpt35,
+            "token_cnt": get_token_num_gpt35,
+        },
+    })
+    model_info.update({
+        "claude-3-opus-20240229": {
+            "fn_with_ui": claude_ui,
+            "fn_without_ui": claude_noui,
+            "endpoint": claude_endpoint,
+            "max_token": 200000,
             "tokenizer": tokenizer_gpt35,
             "token_cnt": get_token_num_gpt35,
         },
@@ -388,22 +534,6 @@ if "stack-claude" in AVAIL_LLM_MODELS:
             "token_cnt": get_token_num_gpt35,
         }
     })
-if "newbing-free" in AVAIL_LLM_MODELS:
-    try:
-        from .bridge_newbingfree import predict_no_ui_long_connection as newbingfree_noui
-        from .bridge_newbingfree import predict as newbingfree_ui
-        model_info.update({
-            "newbing-free": {
-                "fn_with_ui": newbingfree_ui,
-                "fn_without_ui": newbingfree_noui,
-                "endpoint": newbing_endpoint,
-                "max_token": 4096,
-                "tokenizer": tokenizer_gpt35,
-                "token_cnt": get_token_num_gpt35,
-            }
-        })
-    except:
-        print(trimmed_format_exc())
 if "newbing" in AVAIL_LLM_MODELS:   # same with newbing-free
     try:
         from .bridge_newbingfree import predict_no_ui_long_connection as newbingfree_noui
@@ -436,6 +566,7 @@ if "chatglmft" in AVAIL_LLM_MODELS:   # same with newbing-free
         })
     except:
         print(trimmed_format_exc())
+# -=-=-=-=-=-=- 上海AI-LAB书生大模型 -=-=-=-=-=-=-
 if "internlm" in AVAIL_LLM_MODELS:
     try:
         from .bridge_internlm import predict_no_ui_long_connection as internlm_noui
@@ -468,6 +599,7 @@ if "chatglm_onnx" in AVAIL_LLM_MODELS:
         })
     except:
         print(trimmed_format_exc())
+# -=-=-=-=-=-=- 通义-本地模型 -=-=-=-=-=-=-
 if "qwen-local" in AVAIL_LLM_MODELS:
     try:
         from .bridge_qwen_local import predict_no_ui_long_connection as qwen_local_noui
@@ -476,6 +608,7 @@ if "qwen-local" in AVAIL_LLM_MODELS:
             "qwen-local": {
                 "fn_with_ui": qwen_local_ui,
                 "fn_without_ui": qwen_local_noui,
+                "can_multi_thread": False,
                 "endpoint": None,
                 "max_token": 4096,
                 "tokenizer": tokenizer_gpt35,
@@ -484,6 +617,7 @@ if "qwen-local" in AVAIL_LLM_MODELS:
         })
     except:
         print(trimmed_format_exc())
+# -=-=-=-=-=-=- 通义-在线模型 -=-=-=-=-=-=-
 if "qwen-turbo" in AVAIL_LLM_MODELS or "qwen-plus" in AVAIL_LLM_MODELS or "qwen-max" in AVAIL_LLM_MODELS:   # zhipuai
     try:
         from .bridge_qwen import predict_no_ui_long_connection as qwen_noui
@@ -492,6 +626,7 @@ if "qwen-turbo" in AVAIL_LLM_MODELS or "qwen-plus" in AVAIL_LLM_MODELS or "qwen-
             "qwen-turbo": {
                 "fn_with_ui": qwen_ui,
                 "fn_without_ui": qwen_noui,
+                "can_multi_thread": True,
                 "endpoint": None,
                 "max_token": 6144,
                 "tokenizer": tokenizer_gpt35,
@@ -500,6 +635,7 @@ if "qwen-turbo" in AVAIL_LLM_MODELS or "qwen-plus" in AVAIL_LLM_MODELS or "qwen-
             "qwen-plus": {
                 "fn_with_ui": qwen_ui,
                 "fn_without_ui": qwen_noui,
+                "can_multi_thread": True,
                 "endpoint": None,
                 "max_token": 30720,
                 "tokenizer": tokenizer_gpt35,
@@ -508,6 +644,7 @@ if "qwen-turbo" in AVAIL_LLM_MODELS or "qwen-plus" in AVAIL_LLM_MODELS or "qwen-
             "qwen-max": {
                 "fn_with_ui": qwen_ui,
                 "fn_without_ui": qwen_noui,
+                "can_multi_thread": True,
                 "endpoint": None,
                 "max_token": 28672,
                 "tokenizer": tokenizer_gpt35,
@@ -516,7 +653,35 @@ if "qwen-turbo" in AVAIL_LLM_MODELS or "qwen-plus" in AVAIL_LLM_MODELS or "qwen-
         })
     except:
         print(trimmed_format_exc())
-if "spark" in AVAIL_LLM_MODELS:   # 讯飞星火认知大模型
+# -=-=-=-=-=-=- 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
+    try:
+        from .bridge_yimodel import predict_no_ui_long_connection as yimodel_noui
+        from .bridge_yimodel import predict as yimodel_ui
+        model_info.update({
+            "yi-34b-chat-0205": {
+                "fn_with_ui": yimodel_ui,
+                "fn_without_ui": yimodel_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,
+                "tokenizer": tokenizer_gpt35,
+                "token_cnt": get_token_num_gpt35,
+            },
+            "yi-34b-chat-200k": {
+                "fn_with_ui": yimodel_ui,
+                "fn_without_ui": yimodel_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,
+            },
+        })
+    except:
+        print(trimmed_format_exc())
+# -=-=-=-=-=-=- 讯飞星火认知大模型 -=-=-=-=-=-=-
+if "spark" in AVAIL_LLM_MODELS:
     try:
         from .bridge_spark import predict_no_ui_long_connection as spark_noui
         from .bridge_spark import predict as spark_ui
@@ -524,6 +689,7 @@ if "spark" in AVAIL_LLM_MODELS:   # 讯飞星火认知大模型
             "spark": {
                 "fn_with_ui": spark_ui,
                 "fn_without_ui": spark_noui,
+                "can_multi_thread": True,
                 "endpoint": None,
                 "max_token": 4096,
                 "tokenizer": tokenizer_gpt35,
@@ -540,6 +706,7 @@ if "sparkv2" in AVAIL_LLM_MODELS:   # 讯飞星火认知大模型
             "sparkv2": {
                 "fn_with_ui": spark_ui,
                 "fn_without_ui": spark_noui,
+                "can_multi_thread": True,
                 "endpoint": None,
                 "max_token": 4096,
                 "tokenizer": tokenizer_gpt35,
@@ -548,7 +715,7 @@ if "sparkv2" in AVAIL_LLM_MODELS:   # 讯飞星火认知大模型
         })
     except:
         print(trimmed_format_exc())
-if "sparkv3" in AVAIL_LLM_MODELS:   # 讯飞星火认知大模型
+if "sparkv3" in AVAIL_LLM_MODELS or "sparkv3.5" in AVAIL_LLM_MODELS:   # 讯飞星火认知大模型
     try:
         from .bridge_spark import predict_no_ui_long_connection as spark_noui
         from .bridge_spark import predict as spark_ui
@@ -556,6 +723,16 @@ if "sparkv3" in AVAIL_LLM_MODELS:   # 讯飞星火认知大模型
             "sparkv3": {
                 "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,
+            },
+            "sparkv3.5": {
+                "fn_with_ui": spark_ui,
+                "fn_without_ui": spark_noui,
+                "can_multi_thread": True,
                 "endpoint": None,
                 "max_token": 4096,
                 "tokenizer": tokenizer_gpt35,
@@ -580,22 +757,22 @@ if "llama2" in AVAIL_LLM_MODELS:   # llama2
         })
     except:
         print(trimmed_format_exc())
-if "zhipuai" in AVAIL_LLM_MODELS:   # zhipuai
+# -=-=-=-=-=-=- 智谱 -=-=-=-=-=-=-
+if "zhipuai" in AVAIL_LLM_MODELS:   # zhipuai 是glm-4的别名，向后兼容配置
     try:
-        from .bridge_zhipu import predict_no_ui_long_connection as zhipu_noui
-        from .bridge_zhipu import predict as zhipu_ui
         model_info.update({
             "zhipuai": {
                 "fn_with_ui": zhipu_ui,
                 "fn_without_ui": zhipu_noui,
                 "endpoint": None,
-                "max_token": 4096,
+                "max_token": 10124 * 8,
                 "tokenizer": tokenizer_gpt35,
                 "token_cnt": get_token_num_gpt35,
-            }
+            },
         })
     except:
         print(trimmed_format_exc())
+# -=-=-=-=-=-=- 幻方-深度求索大模型 -=-=-=-=-=-=-
 if "deepseekcoder" in AVAIL_LLM_MODELS:   # deepseekcoder
     try:
         from .bridge_deepseekcoder import predict_no_ui_long_connection as deepseekcoder_noui
@@ -612,30 +789,87 @@ if "deepseekcoder" in AVAIL_LLM_MODELS:   # deepseekcoder
         })
     except:
         print(trimmed_format_exc())
-# if "skylark" in AVAIL_LLM_MODELS:
-#     try:
-#         from .bridge_skylark2 import predict_no_ui_long_connection as skylark_noui
-#         from .bridge_skylark2 import predict as skylark_ui
-#         model_info.update({
-#             "skylark": {
-#                 "fn_with_ui": skylark_ui,
-#                 "fn_without_ui": skylark_noui,
-#                 "endpoint": None,
-#                 "max_token": 4096,
-#                 "tokenizer": tokenizer_gpt35,
-#                 "token_cnt": get_token_num_gpt35,
-#             }
-#         })
-#     except:
-#         print(trimmed_format_exc())
 
 
-# <-- 用于定义和切换多个azure模型 -->
-AZURE_CFG_ARRAY = get_conf("AZURE_CFG_ARRAY")
+# -=-=-=-=-=-=- 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)"]
+    # 其中
+    #   "one-api-"          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"one-api模型 {model} 的 max_token 配置不是整数，请检查配置文件。")
+        continue
+    model_info.update({
+        model: {
+            "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,
+        },
+    })
+# -=-=-=-=-=-=- 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 -->
 if len(AZURE_CFG_ARRAY) > 0:
     for azure_model_name, azure_cfg_dict in AZURE_CFG_ARRAY.items():
         # 可能会覆盖之前的配置，但这是意料之中的
-        if not azure_model_name.startswith('azure'): 
+        if not azure_model_name.startswith('azure'):
             raise ValueError("AZURE_CFG_ARRAY中配置的模型必须以azure开头")
         endpoint_ = azure_cfg_dict["AZURE_ENDPOINT"] + \
             f'openai/deployments/{azure_cfg_dict["AZURE_ENGINE"]}/chat/completions?api-version=2023-05-15'
@@ -660,7 +894,7 @@ def LLM_CATCH_EXCEPTION(f):
     """
     装饰器函数，将错误显示出来
     """
-    def decorated(inputs, llm_kwargs, history, sys_prompt, observe_window, console_slience):
+    def decorated(inputs:str, llm_kwargs:dict, history:list, sys_prompt:str, observe_window:list, console_slience:bool):
         try:
             return f(inputs, llm_kwargs, history, sys_prompt, observe_window, console_slience)
         except Exception as e:
@@ -670,9 +904,9 @@ def LLM_CATCH_EXCEPTION(f):
     return decorated
 
 
-def predict_no_ui_long_connection(inputs, llm_kwargs, history, sys_prompt, observe_window=[], console_slience=False):
+def predict_no_ui_long_connection(inputs:str, llm_kwargs:dict, history:list, sys_prompt:str, observe_window:list=[], console_slience:bool=False):
     """
-    发送至LLM，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。
+    发送至LLM，等待回复，一次性完成，不显示中间过程。但内部（尽可能地）用stream的方法避免中途网线被掐。
     inputs：
         是本次问询的输入
     sys_prompt:
@@ -690,7 +924,6 @@ def predict_no_ui_long_connection(inputs, llm_kwargs, history, sys_prompt, obser
     model = llm_kwargs['llm_model']
     n_model = 1
     if '&' not in model:
-        assert not model.startswith("tgui"), "TGUI不支持函数插件的实现"
 
         # 如果只询问1个大语言模型：
         method = model_info[model]["fn_without_ui"]
@@ -701,7 +934,7 @@ def predict_no_ui_long_connection(inputs, llm_kwargs, history, sys_prompt, obser
         executor = ThreadPoolExecutor(max_workers=4)
         models = model.split('&')
         n_model = len(models)
-        
+
         window_len = len(observe_window)
         assert window_len==3
         window_mutex = [["", time.time(), ""] for _ in range(n_model)] + [True]
@@ -720,12 +953,13 @@ def predict_no_ui_long_connection(inputs, llm_kwargs, history, sys_prompt, obser
                 time.sleep(0.25)
                 if not window_mutex[-1]: break
                 # 看门狗（watchdog）
-                for i in range(n_model): 
+                for i in range(n_model):
                     window_mutex[i][1] = observe_window[1]
                 # 观察窗（window）
                 chat_string = []
                 for i in range(n_model):
-                    chat_string.append( f"【{str(models[i])} 说】: <font color=\"{colors[i]}\"> {window_mutex[i][0]} </font>" )
+                    color = colors[i%len(colors)]
+                    chat_string.append( f"【{str(models[i])} 说】: <font color=\"{color}\"> {window_mutex[i][0]} </font>" )
                 res = '<br/><br/>\n\n---\n\n'.join(chat_string)
                 # # # # # # # # # # #
                 observe_window[0] = res
@@ -742,22 +976,30 @@ def predict_no_ui_long_connection(inputs, llm_kwargs, history, sys_prompt, obser
             time.sleep(1)
 
         for i, future in enumerate(futures):  # wait and get
-            return_string_collect.append( f"【{str(models[i])} 说】: <font color=\"{colors[i]}\"> {future.result()} </font>" )
+            color = colors[i%len(colors)]
+            return_string_collect.append( f"【{str(models[i])} 说】: <font color=\"{color}\"> {future.result()} </font>" )
 
         window_mutex[-1] = False # stop mutex thread
         res = '<br/><br/>\n\n---\n\n'.join(return_string_collect)
         return res
 
 
-def predict(inputs, llm_kwargs, *args, **kwargs):
+def predict(inputs:str, llm_kwargs:dict, *args, **kwargs):
     """
     发送至LLM，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LLM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
+
+    完整参数列表：
+        predict(
+            inputs:str,                     # 是本次问询的输入
+            llm_kwargs:dict,                # 是LLM的内部调优参数
+            plugin_kwargs:dict,             # 是插件的内部参数
+            chatbot:ChatBotWithCookies,     # 原样传递，负责向用户前端展示对话，兼顾前端状态的功能
+            history:list=[],                # 是之前的对话列表
+            system_prompt:str='',           # 系统静默prompt
+            stream:bool=True,               # 是否流式输出（已弃用）
+            additional_fn:str=None          # 基础功能区按钮的附加功能
+        ):
     """
 
     inputs = apply_gpt_academic_string_mask(inputs, mode="show_llm")

request_llms/bridge_chatglm.py

@@ -56,15 +56,15 @@ class GetGLM2Handle(LocalLLMHandle):
 
         query, max_length, top_p, temperature, history = adaptor(kwargs)
 
-        for response, history in self._model.stream_chat(self._tokenizer, 
-                                                         query, 
-                                                         history, 
+        for response, history in self._model.stream_chat(self._tokenizer,
+                                                         query,
+                                                         history,
                                                          max_length=max_length,
                                                          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

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
-            _model_name_ = "THUDM/chatglm3-6b-int4"
-        elif LOCAL_MODEL_QUANT == "INT8":       # INT8
-            _model_name_ = "THUDM/chatglm3-6b-int8"
-        else:
-            _model_name_ = "THUDM/chatglm3-6b"  # FP16
-        with ProxyNetworkActivate('Download_LLM'):
-            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()
+        LOCAL_MODEL_QUANT, device = get_conf("LOCAL_MODEL_QUANT", "LOCAL_MODEL_DEVICE")
+        _model_name_ = "THUDM/chatglm3-6b"
+        # if LOCAL_MODEL_QUANT == "INT4":  # INT4
+        #     _model_name_ = "THUDM/chatglm3-6b-int4"
+        # elif LOCAL_MODEL_QUANT == "INT8":  # INT8
+        #     _model_name_ = "THUDM/chatglm3-6b-int8"
+        # else:
+        #     _model_name_ = "THUDM/chatglm3-6b"  # FP16
+        with ProxyNetworkActivate("Download_LLM"):
+            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']
-            max_length = kwargs['max_length']
-            top_p = kwargs['top_p']
-            temperature = kwargs['temperature']
-            history = kwargs['history']
+            query = kwargs["query"]
+            max_length = kwargs["max_length"]
+            top_p = kwargs["top_p"]
+            temperature = kwargs["temperature"]
+            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, 
-                                                         query, 
-                                                         history, 
-                                                         max_length=max_length,
-                                                         top_p=top_p,
-                                                         temperature=temperature,
-                                                         ):
+        for response, history in self._model.stream_chat(
+            self._tokenizer,
+            query,
+            history,
+            max_length=max_length,
+            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_chatglmft.py

@@ -37,7 +37,7 @@ class GetGLMFTHandle(Process):
         self.check_dependency()
         self.start()
         self.threadLock = threading.Lock()
-        
+
     def check_dependency(self):
         try:
             import sentencepiece
@@ -101,7 +101,7 @@ class GetGLMFTHandle(Process):
                     break
             except Exception as e:
                 retry += 1
-                if retry > 3: 
+                if retry > 3:
                     self.child.send('[Local Message] Call ChatGLMFT fail 不能正常加载ChatGLMFT的参数。')
                     raise RuntimeError("不能正常加载ChatGLMFT的参数！")
 
@@ -113,7 +113,7 @@ class GetGLMFTHandle(Process):
                 for response, history in self.chatglmft_model.stream_chat(self.chatglmft_tokenizer, **kwargs):
                     self.child.send(response)
                     # # 中途接收可能的终止指令（如果有的话）
-                    # if self.child.poll(): 
+                    # if self.child.poll():
                     #     command = self.child.recv()
                     #     if command == '[Terminate]': break
             except:
@@ -133,11 +133,12 @@ class GetGLMFTHandle(Process):
             else:
                 break
         self.threadLock.release()
-    
+
 global glmft_handle
 glmft_handle = None
 #################################################################################
-def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="", observe_window=[], console_slience=False):
+def predict_no_ui_long_connection(inputs:str, llm_kwargs:dict, history:list=[], sys_prompt:str="",
+                                  observe_window:list=[], console_slience:bool=False):
     """
         多线程方法
         函数的说明请见 request_llms/bridge_all.py
@@ -146,7 +147,7 @@ def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="",
     if glmft_handle is None:
         glmft_handle = GetGLMFTHandle()
         if len(observe_window) >= 1: observe_window[0] = load_message + "\n\n" + glmft_handle.info
-        if not glmft_handle.success: 
+        if not glmft_handle.success:
             error = glmft_handle.info
             glmft_handle = None
             raise RuntimeError(error)
@@ -161,7 +162,7 @@ def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="",
     response = ""
     for response in glmft_handle.stream_chat(query=inputs, history=history_feedin, max_length=llm_kwargs['max_length'], top_p=llm_kwargs['top_p'], temperature=llm_kwargs['temperature']):
         if len(observe_window) >= 1:  observe_window[0] = response
-        if len(observe_window) >= 2:  
+        if len(observe_window) >= 2:
             if (time.time()-observe_window[1]) > watch_dog_patience:
                 raise RuntimeError("程序终止。")
     return response
@@ -180,7 +181,7 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
         glmft_handle = GetGLMFTHandle()
         chatbot[-1] = (inputs, load_message + "\n\n" + glmft_handle.info)
         yield from update_ui(chatbot=chatbot, history=[])
-        if not glmft_handle.success: 
+        if not glmft_handle.success:
             glmft_handle = None
             return
 

request_llms/bridge_chatglmonnx.py

@@ -59,7 +59,7 @@ class GetONNXGLMHandle(LocalLLMHandle):
             temperature=temperature,
         ):
             yield answer
-        
+
     def try_to_import_special_deps(self, **kwargs):
         # import something that will raise error if the user does not install requirement_*.txt
         # 🏃‍♂️🏃‍♂️🏃‍♂️ 子进程执行

request_llms/bridge_chatgpt.py

@@ -21,7 +21,9 @@ 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, is_any_api_key, select_api_key, what_keys, clip_history, trimmed_format_exc, is_the_upload_folder
+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
 proxies, TIMEOUT_SECONDS, MAX_RETRY, API_ORG, AZURE_CFG_ARRAY = \
     get_conf('proxies', 'TIMEOUT_SECONDS', 'MAX_RETRY', 'API_ORG', 'AZURE_CFG_ARRAY')
 
@@ -47,14 +49,14 @@ def decode_chunk(chunk):
     choice_valid = False
     has_content = False
     has_role = False
-    try: 
+    try:
         chunkjson = json.loads(chunk_decoded[6:])
         has_choices = 'choices' in chunkjson
         if has_choices: choice_valid = (len(chunkjson['choices']) > 0)
         if has_choices and choice_valid: has_content = ("content" in chunkjson['choices'][0]["delta"])
         if has_content: has_content = (chunkjson['choices'][0]["delta"]["content"] is not None)
         if has_choices and choice_valid: has_role = "role" in chunkjson['choices'][0]["delta"]
-    except: 
+    except:
         pass
     return chunk_decoded, chunkjson, has_choices, choice_valid, has_content, has_role
 
@@ -68,7 +70,7 @@ def verify_endpoint(endpoint):
         raise ValueError("Endpoint不正确, 请检查AZURE_ENDPOINT的配置! 当前的Endpoint为:" + endpoint)
     return endpoint
 
-def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="", observe_window=None, console_slience=False):
+def predict_no_ui_long_connection(inputs:str, llm_kwargs:dict, history:list=[], sys_prompt:str="", observe_window:list=None, console_slience:bool=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：
@@ -103,16 +105,18 @@ def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="",
     json_data = None
     while True:
         try: chunk = next(stream_response)
-        except StopIteration: 
+        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。
         chunk_decoded, chunkjson, has_choices, choice_valid, has_content, has_role = decode_chunk(chunk)
         if len(chunk_decoded)==0: continue
-        if not chunk_decoded.startswith('data:'): 
+        if not chunk_decoded.startswith('data:'):
             error_msg = get_full_error(chunk, stream_response).decode()
             if "reduce the length" in error_msg:
                 raise ConnectionAbortedError("OpenAI拒绝了请求:" + error_msg)
+            elif """type":"upstream_error","param":"307""" in error_msg:
+                raise ConnectionAbortedError("正常结束，但显示Token不足，导致输出不完整，请削减单次输入的文本量。")
             else:
                 raise RuntimeError("OpenAI拒绝了请求：" + error_msg)
         if ('data: [DONE]' in chunk_decoded): break # api2d 正常完成
@@ -123,11 +127,12 @@ def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="",
         json_data = chunkjson['choices'][0]
         delta = json_data["delta"]
         if len(delta) == 0: break
-        if "role" in delta: continue
-        if "content" in delta:
+        if (not has_content) and has_role: continue
+        if (not has_content) and (not has_role): continue # raise RuntimeError("发现不标准的第三方接口："+delta)
+        if has_content: # has_role = True/False
             result += delta["content"]
             if not console_slience: print(delta["content"], end='')
-            if observe_window is not None: 
+            if observe_window is not None:
                 # 观测窗，把已经获取的数据显示出去
                 if len(observe_window) >= 1:
                     observe_window[0] += delta["content"]
@@ -143,7 +148,8 @@ def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="",
     return result
 
 
-def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_prompt='', stream = True, additional_fn=None):
+def predict(inputs:str, llm_kwargs:dict, plugin_kwargs:dict, chatbot:ChatBotWithCookies,
+            history:list=[], system_prompt:str='', stream:bool=True, additional_fn:str=None):
     """
     发送至chatGPT，流式获取输出。
     用于基础的对话功能。
@@ -169,7 +175,7 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
         inputs, history = handle_core_functionality(additional_fn, inputs, history, chatbot)
 
     raw_input = inputs
-    logging.info(f'[raw_input] {raw_input}')
+    # logging.info(f'[raw_input] {raw_input}')
     chatbot.append((inputs, ""))
     yield from update_ui(chatbot=chatbot, history=history, msg="等待响应") # 刷新界面
 
@@ -185,7 +191,7 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
         chatbot[-1] = (inputs, f"您提供的api-key不满足要求，不包含任何可用于{llm_kwargs['llm_model']}的api-key。您可能选择了错误的模型或请求源。")
         yield from update_ui(chatbot=chatbot, history=history, msg="api-key不满足要求") # 刷新界面
         return
-        
+
     # 检查endpoint是否合法
     try:
         from .bridge_all import model_info
@@ -195,7 +201,7 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
         chatbot[-1] = (inputs, tb_str)
         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("")
 
     retry = 0
@@ -212,7 +218,7 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
             if retry > MAX_RETRY: raise TimeoutError
 
     gpt_replying_buffer = ""
-    
+
     is_head_of_the_stream = True
     if stream:
         stream_response =  response.iter_lines()
@@ -224,21 +230,21 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
                 chunk_decoded = chunk.decode()
                 error_msg = chunk_decoded
                 # 首先排除一个one-api没有done数据包的第三方Bug情形
-                if len(gpt_replying_buffer.strip()) > 0 and len(error_msg) == 0: 
+                if len(gpt_replying_buffer.strip()) > 0 and len(error_msg) == 0:
                     yield from update_ui(chatbot=chatbot, history=history, msg="检测到有缺陷的非OpenAI官方接口，建议选择更稳定的接口。")
                     break
                 # 其他情况，直接返回报错
                 chatbot, history = handle_error(inputs, llm_kwargs, chatbot, history, chunk_decoded, error_msg)
                 yield from update_ui(chatbot=chatbot, history=history, msg="非OpenAI官方接口返回了错误:" + chunk.decode()) # 刷新界面
                 return
-            
+
             # 提前读取一些信息 （用于判断异常）
             chunk_decoded, chunkjson, has_choices, choice_valid, has_content, has_role = decode_chunk(chunk)
 
             if is_head_of_the_stream and (r'"object":"error"' not in chunk_decoded) and (r"content" not 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 has_choices and not choice_valid:
@@ -250,7 +256,8 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
                     # 前者是API2D的结束条件，后者是OPENAI的结束条件
                     if ('data: [DONE]' in chunk_decoded) or (len(chunkjson['choices'][0]["delta"]) == 0):
                         # 判定为数据流的结束，gpt_replying_buffer也写完了
-                        logging.info(f'[response] {gpt_replying_buffer}')
+                        # logging.info(f'[response] {gpt_replying_buffer}')
+                        log_chat(llm_model=llm_kwargs["llm_model"], input_str=inputs, output_str=gpt_replying_buffer)
                         break
                     # 处理数据流的主体
                     status_text = f"finish_reason: {chunkjson['choices'][0].get('finish_reason', 'null')}"
@@ -262,7 +269,8 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
                         # 一些第三方接口的出现这样的错误，兼容一下吧
                         continue
                     else:
-                        # 一些垃圾第三方接口的出现这样的错误
+                        # 至此已经超出了正常接口应该进入的范围，一些垃圾第三方接口会出现这样的错误
+                        if chunkjson['choices'][0]["delta"]["content"] is None: continue # 一些垃圾第三方接口出现这样的错误，兼容一下吧
                         gpt_replying_buffer = gpt_replying_buffer + chunkjson['choices'][0]["delta"]["content"]
 
                     history[-1] = gpt_replying_buffer
@@ -283,7 +291,7 @@ def handle_error(inputs, llm_kwargs, chatbot, history, chunk_decoded, error_msg)
     openai_website = ' 请登录OpenAI查看详情 https://platform.openai.com/signup'
     if "reduce the length" in error_msg:
         if len(history) >= 2: history[-1] = ""; history[-2] = "" # 清除当前溢出的输入：history[-2] 是本次输入, history[-1] 是本次输出
-        history = clip_history(inputs=inputs, history=history, tokenizer=model_info[llm_kwargs['llm_model']]['tokenizer'], 
+        history = clip_history(inputs=inputs, history=history, tokenizer=model_info[llm_kwargs['llm_model']]['tokenizer'],
                                                max_token_limit=(model_info[llm_kwargs['llm_model']]['max_token'])) # history至少释放二分之一
         chatbot[-1] = (chatbot[-1][0], "[Local Message] Reduce the length. 本次输入过长, 或历史数据过长. 历史缓存数据已部分释放, 您可以请再次尝试. (若再次失败则更可能是因为输入过长.)")
     elif "does not exist" in error_msg:
@@ -315,14 +323,17 @@ def generate_payload(inputs, llm_kwargs, history, system_prompt, stream):
     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",
         "Authorization": f"Bearer {api_key}"
     }
     if API_ORG.startswith('org-'): headers.update({"OpenAI-Organization": API_ORG})
-    if llm_kwargs['llm_model'].startswith('azure-'): 
+    if llm_kwargs['llm_model'].startswith('azure-'):
         headers.update({"api-key": api_key})
         if llm_kwargs['llm_model'] in AZURE_CFG_ARRAY.keys():
             azure_api_key_unshared = AZURE_CFG_ARRAY[llm_kwargs['llm_model']]["AZURE_API_KEY"]
@@ -354,10 +365,15 @@ def generate_payload(inputs, llm_kwargs, history, system_prompt, stream):
     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", 
+            "gpt-3.5-turbo",
             "gpt-3.5-turbo-16k",
             "gpt-3.5-turbo-1106",
             "gpt-3.5-turbo-0613",
@@ -368,7 +384,7 @@ def generate_payload(inputs, llm_kwargs, history, system_prompt, stream):
 
     payload = {
         "model": model,
-        "messages": messages, 
+        "messages": messages,
         "temperature": llm_kwargs['temperature'],  # 1.0,
         "top_p": llm_kwargs['top_p'],  # 1.0,
         "n": 1,

request_llms/bridge_chatgpt_vision.py

@@ -27,7 +27,7 @@ timeout_bot_msg = '[Local Message] Request timeout. Network error. Please check
 
 
 def report_invalid_key(key):
-    if get_conf("BLOCK_INVALID_APIKEY"): 
+    if get_conf("BLOCK_INVALID_APIKEY"):
         # 实验性功能，自动检测并屏蔽失效的KEY，请勿使用
         from request_llms.key_manager import ApiKeyManager
         api_key = ApiKeyManager().add_key_to_blacklist(key)
@@ -51,13 +51,13 @@ def decode_chunk(chunk):
     choice_valid = False
     has_content = False
     has_role = False
-    try: 
+    try:
         chunkjson = json.loads(chunk_decoded[6:])
         has_choices = 'choices' in chunkjson
         if has_choices: choice_valid = (len(chunkjson['choices']) > 0)
         if has_choices and choice_valid: has_content = "content" in chunkjson['choices'][0]["delta"]
         if has_choices and choice_valid: has_role = "role" in chunkjson['choices'][0]["delta"]
-    except: 
+    except:
         pass
     return chunk_decoded, chunkjson, has_choices, choice_valid, has_content, has_role
 
@@ -103,7 +103,7 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
 
     raw_input = inputs
     logging.info(f'[raw_input] {raw_input}')
-    def make_media_input(inputs, image_paths): 
+    def make_media_input(inputs, image_paths):
         for image_path in image_paths:
             inputs = inputs + f'<br/><br/><div align="center"><img src="file={os.path.abspath(image_path)}"></div>'
         return inputs
@@ -122,7 +122,7 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
         chatbot[-1] = (inputs, f"您提供的api-key不满足要求，不包含任何可用于{llm_kwargs['llm_model']}的api-key。您可能选择了错误的模型或请求源。")
         yield from update_ui(chatbot=chatbot, history=history, msg="api-key不满足要求") # 刷新界面
         return
-        
+
     # 检查endpoint是否合法
     try:
         from .bridge_all import model_info
@@ -150,7 +150,7 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
             if retry > MAX_RETRY: raise TimeoutError
 
     gpt_replying_buffer = ""
-    
+
     is_head_of_the_stream = True
     if stream:
         stream_response =  response.iter_lines()
@@ -162,21 +162,21 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
                 chunk_decoded = chunk.decode()
                 error_msg = chunk_decoded
                 # 首先排除一个one-api没有done数据包的第三方Bug情形
-                if len(gpt_replying_buffer.strip()) > 0 and len(error_msg) == 0: 
+                if len(gpt_replying_buffer.strip()) > 0 and len(error_msg) == 0:
                     yield from update_ui(chatbot=chatbot, history=history, msg="检测到有缺陷的非OpenAI官方接口，建议选择更稳定的接口。")
                     break
                 # 其他情况，直接返回报错
                 chatbot, history = handle_error(inputs, llm_kwargs, chatbot, history, chunk_decoded, error_msg, api_key)
                 yield from update_ui(chatbot=chatbot, history=history, msg="非OpenAI官方接口返回了错误:" + chunk.decode()) # 刷新界面
                 return
-            
+
             # 提前读取一些信息 （用于判断异常）
             chunk_decoded, chunkjson, has_choices, choice_valid, has_content, has_role = decode_chunk(chunk)
 
             if is_head_of_the_stream and (r'"object":"error"' not in chunk_decoded) and (r"content" not 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 has_choices and not choice_valid:
@@ -220,7 +220,7 @@ def handle_error(inputs, llm_kwargs, chatbot, history, chunk_decoded, error_msg,
     openai_website = ' 请登录OpenAI查看详情 https://platform.openai.com/signup'
     if "reduce the length" in error_msg:
         if len(history) >= 2: history[-1] = ""; history[-2] = "" # 清除当前溢出的输入：history[-2] 是本次输入, history[-1] 是本次输出
-        history = clip_history(inputs=inputs, history=history, tokenizer=model_info[llm_kwargs['llm_model']]['tokenizer'], 
+        history = clip_history(inputs=inputs, history=history, tokenizer=model_info[llm_kwargs['llm_model']]['tokenizer'],
                                                max_token_limit=(model_info[llm_kwargs['llm_model']]['max_token'])) # history至少释放二分之一
         chatbot[-1] = (chatbot[-1][0], "[Local Message] Reduce the length. 本次输入过长, 或历史数据过长. 历史缓存数据已部分释放, 您可以请再次尝试. (若再次失败则更可能是因为输入过长.)")
     elif "does not exist" in error_msg:
@@ -260,7 +260,7 @@ def generate_payload(inputs, llm_kwargs, history, system_prompt, image_paths):
         "Authorization": f"Bearer {api_key}"
     }
     if API_ORG.startswith('org-'): headers.update({"OpenAI-Organization": API_ORG})
-    if llm_kwargs['llm_model'].startswith('azure-'): 
+    if llm_kwargs['llm_model'].startswith('azure-'):
         headers.update({"api-key": api_key})
         if llm_kwargs['llm_model'] in AZURE_CFG_ARRAY.keys():
             azure_api_key_unshared = AZURE_CFG_ARRAY[llm_kwargs['llm_model']]["AZURE_API_KEY"]
@@ -294,7 +294,7 @@ def generate_payload(inputs, llm_kwargs, history, system_prompt, image_paths):
 
     payload = {
         "model": model,
-        "messages": messages, 
+        "messages": messages,
         "temperature": llm_kwargs['temperature'],   # 1.0,
         "top_p": llm_kwargs['top_p'],               # 1.0,
         "n": 1,

request_llms/bridge_chatgpt_website.py

@@ -73,12 +73,12 @@ def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="",
     result = ''
     while True:
         try: chunk = next(stream_response).decode()
-        except StopIteration: 
+        except StopIteration:
             break
         except requests.exceptions.ConnectionError:
             chunk = next(stream_response).decode() # 失败了，重试一次？再失败就没办法了。
         if len(chunk)==0: continue
-        if not chunk.startswith('data:'): 
+        if not chunk.startswith('data:'):
             error_msg = get_full_error(chunk.encode('utf8'), stream_response).decode()
             if "reduce the length" in error_msg:
                 raise ConnectionAbortedError("OpenAI拒绝了请求:" + error_msg)
@@ -89,14 +89,14 @@ def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="",
         delta = json_data["delta"]
         if len(delta) == 0: break
         if "role" in delta: continue
-        if "content" in delta: 
+        if "content" in delta:
             result += delta["content"]
             if not console_slience: print(delta["content"], end='')
-            if observe_window is not None: 
+            if observe_window is not None:
                 # 观测窗，把已经获取的数据显示出去
                 if len(observe_window) >= 1: observe_window[0] += delta["content"]
                 # 看门狗，如果超过期限没有喂狗，则终止
-                if len(observe_window) >= 2:  
+                if len(observe_window) >= 2:
                     if (time.time()-observe_window[1]) > watch_dog_patience:
                         raise RuntimeError("用户取消了程序。")
         else: raise RuntimeError("意外Json结构："+delta)
@@ -132,7 +132,7 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
         chatbot[-1] = (inputs, f"您提供的api-key不满足要求，不包含任何可用于{llm_kwargs['llm_model']}的api-key。您可能选择了错误的模型或请求源。")
         yield from update_ui(chatbot=chatbot, history=history, msg="api-key不满足要求") # 刷新界面
         return
-        
+
     history.append(inputs); history.append("")
 
     retry = 0
@@ -151,7 +151,7 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
             if retry > MAX_RETRY: raise TimeoutError
 
     gpt_replying_buffer = ""
-    
+
     is_head_of_the_stream = True
     if stream:
         stream_response =  response.iter_lines()
@@ -165,12 +165,12 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
                 chatbot, history = handle_error(inputs, llm_kwargs, chatbot, history, chunk_decoded, error_msg)
                 yield from update_ui(chatbot=chatbot, history=history, msg="非Openai官方接口返回了错误:" + chunk.decode()) # 刷新界面
                 return
-            
+
             # print(chunk.decode()[6:])
             if is_head_of_the_stream and (r'"object":"error"' not in chunk.decode()):
                 # 数据流的第一帧不携带content
                 is_head_of_the_stream = False; continue
-            
+
             if chunk:
                 try:
                     chunk_decoded = chunk.decode()
@@ -203,7 +203,7 @@ def handle_error(inputs, llm_kwargs, chatbot, history, chunk_decoded, error_msg)
     openai_website = ' 请登录OpenAI查看详情 https://platform.openai.com/signup'
     if "reduce the length" in error_msg:
         if len(history) >= 2: history[-1] = ""; history[-2] = "" # 清除当前溢出的输入：history[-2] 是本次输入, history[-1] 是本次输出
-        history = clip_history(inputs=inputs, history=history, tokenizer=model_info[llm_kwargs['llm_model']]['tokenizer'], 
+        history = clip_history(inputs=inputs, history=history, tokenizer=model_info[llm_kwargs['llm_model']]['tokenizer'],
                                                max_token_limit=(model_info[llm_kwargs['llm_model']]['max_token'])) # history至少释放二分之一
         chatbot[-1] = (chatbot[-1][0], "[Local Message] Reduce the length. 本次输入过长, 或历史数据过长. 历史缓存数据已部分释放, 您可以请再次尝试. (若再次失败则更可能是因为输入过长.)")
                         # history = []    # 清除历史
@@ -264,7 +264,7 @@ def generate_payload(inputs, llm_kwargs, history, system_prompt, stream):
 
     payload = {
         "model": llm_kwargs['llm_model'].strip('api2d-'),
-        "messages": messages, 
+        "messages": messages,
         "temperature": llm_kwargs['temperature'],  # 1.0,
         "top_p": llm_kwargs['top_p'],  # 1.0,
         "n": 1,

request_llms/bridge_claude.py

@@ -9,15 +9,15 @@
     具备多线程调用能力的函数
     2. predict_no_ui_long_connection：支持多线程
 """
-
-import os
-import json
-import time
-import gradio as gr
 import logging
+import os
+import time
 import traceback
+import json
 import requests
-import importlib
+from toolbox import get_conf, update_ui, trimmed_format_exc, encode_image, every_image_file_in_path, log_chat
+picture_system_prompt = "\n当回复图像时,必须说明正在回复哪张图像。所有图像仅在最后一个问题中提供,即使它们在历史记录中被提及。请使用'这是第X张图像:'的格式来指明您正在描述的是哪张图像。"
+Claude_3_Models = ["claude-3-haiku-20240307", "claude-3-sonnet-20240229", "claude-3-opus-20240229"]
 
 # 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
@@ -39,6 +39,34 @@ def get_full_error(chunk, stream_response):
             break
     return chunk
 
+def decode_chunk(chunk):
+    # 提前读取一些信息（用于判断异常）
+    chunk_decoded = chunk.decode()
+    chunkjson = None
+    is_last_chunk = False
+    need_to_pass = False
+    if chunk_decoded.startswith('data:'):
+        try:
+            chunkjson = json.loads(chunk_decoded[6:])
+        except:
+            need_to_pass = True
+            pass
+    elif chunk_decoded.startswith('event:'):
+        try:
+            event_type = chunk_decoded.split(':')[1].strip()
+            if event_type == 'content_block_stop' or event_type == 'message_stop':
+                is_last_chunk = True
+            elif event_type == 'content_block_start' or event_type == 'message_start':
+                need_to_pass = True
+                pass
+        except:
+            need_to_pass = True
+            pass
+    else:
+        need_to_pass = True
+        pass
+    return need_to_pass, chunkjson, is_last_chunk
+
 
 def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="", observe_window=None, console_slience=False):
     """
@@ -54,50 +82,67 @@ def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="",
     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
     """
-    from anthropic import Anthropic
     watch_dog_patience = 5 # 看门狗的耐心, 设置5秒即可
-    prompt = generate_payload(inputs, llm_kwargs, history, system_prompt=sys_prompt, stream=True)
-    retry = 0
     if len(ANTHROPIC_API_KEY) == 0:
         raise RuntimeError("没有设置ANTHROPIC_API_KEY选项")
+    if inputs == "":     inputs = "空空如也的输入栏"
+    headers, message = generate_payload(inputs, llm_kwargs, history, sys_prompt, image_paths=None)
+    retry = 0
+
 
     while True:
         try:
             # make a POST request to the API endpoint, stream=False
             from .bridge_all import model_info
-            anthropic = Anthropic(api_key=ANTHROPIC_API_KEY)
-            # endpoint = model_info[llm_kwargs['llm_model']]['endpoint']
-            # with ProxyNetworkActivate()
-            stream = anthropic.completions.create(
-                prompt=prompt,
-                max_tokens_to_sample=4096,       # The maximum number of tokens to generate before stopping.
-                model=llm_kwargs['llm_model'],
-                stream=True,
-                temperature = llm_kwargs['temperature']
-            )
-            break
-        except Exception as e:
+            endpoint = model_info[llm_kwargs['llm_model']]['endpoint']
+            response = requests.post(endpoint, headers=headers, json=message,
+                                     proxies=proxies, stream=True, timeout=TIMEOUT_SECONDS);break
+        except requests.exceptions.ReadTimeout as e:
             retry += 1
             traceback.print_exc()
             if retry > MAX_RETRY: raise TimeoutError
             if MAX_RETRY!=0: print(f'请求超时，正在重试 ({retry}/{MAX_RETRY}) ……')
+    stream_response = response.iter_lines()
     result = ''
-    try: 
-        for completion in stream:
-            result += completion.completion
-            if not console_slience: print(completion.completion, 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] += completion.completion
-                # 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:
-        traceback.print_exc()
+    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。
+        need_to_pass, chunkjson, is_last_chunk = decode_chunk(chunk)
+        if chunk:
+            try:
+                if need_to_pass:
+                    pass
+                elif is_last_chunk:
+                    # logging.info(f'[response] {result}')
+                    break
+                else:
+                    if chunkjson and chunkjson['type'] == 'content_block_delta':
+                        result += chunkjson['delta']['text']
+                        print(chunkjson['delta']['text'], end='')
+                        if observe_window is not None:
+                            # 观测窗，把已经获取的数据显示出去
+                            if len(observe_window) >= 1:
+                                observe_window[0] += chunkjson['delta']['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 make_media_input(history,inputs,image_paths):
+    for image_path in image_paths:
+        inputs = inputs + f'<br/><br/><div align="center"><img src="file={os.path.abspath(image_path)}"></div>'
+    return inputs
 
 def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_prompt='', stream = True, additional_fn=None):
     """
@@ -109,23 +154,33 @@ 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
     """
-    from anthropic import Anthropic
+    if inputs == "":     inputs = "空空如也的输入栏"
     if len(ANTHROPIC_API_KEY) == 0:
         chatbot.append((inputs, "没有设置ANTHROPIC_API_KEY"))
         yield from update_ui(chatbot=chatbot, history=history, msg="等待响应") # 刷新界面
         return
-    
+
     if additional_fn is not None:
         from core_functional import handle_core_functionality
         inputs, history = handle_core_functionality(additional_fn, inputs, history, chatbot)
 
-    raw_input = inputs
-    logging.info(f'[raw_input] {raw_input}')
-    chatbot.append((inputs, ""))
-    yield from update_ui(chatbot=chatbot, history=history, msg="等待响应") # 刷新界面
+    have_recent_file, image_paths = every_image_file_in_path(chatbot)
+    if len(image_paths) > 20:
+        chatbot.append((inputs, "图片数量超过api上限(20张)"))
+        yield from update_ui(chatbot=chatbot, history=history, msg="等待响应")
+        return
+
+    if any([llm_kwargs['llm_model'] == model for model in Claude_3_Models]) and have_recent_file:
+        if inputs == "" or inputs == "空空如也的输入栏":     inputs = "请描述给出的图片"
+        system_prompt += picture_system_prompt  # 由于没有单独的参数保存包含图片的历史，所以只能通过提示词对第几张图片进行定位
+        chatbot.append((make_media_input(history,inputs, image_paths), ""))
+        yield from update_ui(chatbot=chatbot, history=history, msg="等待响应") # 刷新界面
+    else:
+        chatbot.append((inputs, ""))
+        yield from update_ui(chatbot=chatbot, history=history, msg="等待响应") # 刷新界面
 
     try:
-        prompt = generate_payload(inputs, llm_kwargs, history, system_prompt, stream)
+        headers, message = generate_payload(inputs, llm_kwargs, history, system_prompt, image_paths)
     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
@@ -138,91 +193,117 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
         try:
             # make a POST request to the API endpoint, stream=True
             from .bridge_all import model_info
-            anthropic = Anthropic(api_key=ANTHROPIC_API_KEY)
-            # endpoint = model_info[llm_kwargs['llm_model']]['endpoint']
-            # with ProxyNetworkActivate()
-            stream = anthropic.completions.create(
-                prompt=prompt,
-                max_tokens_to_sample=4096,       # The maximum number of tokens to generate before stopping.
-                model=llm_kwargs['llm_model'],
-                stream=True,
-                temperature = llm_kwargs['temperature']
-            )
-            
-            break
-        except:
+            endpoint = model_info[llm_kwargs['llm_model']]['endpoint']
+            response = requests.post(endpoint, headers=headers, json=message,
+                                     proxies=proxies, stream=True, timeout=TIMEOUT_SECONDS);break
+        except requests.exceptions.ReadTimeout as e:
             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
+            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()
     gpt_replying_buffer = ""
-    
-    for completion in stream:
-        try:
-            gpt_replying_buffer = gpt_replying_buffer + completion.completion
-            history[-1] = gpt_replying_buffer
-            chatbot[-1] = (history[-2], history[-1])
-            yield from update_ui(chatbot=chatbot, history=history, msg='正常') # 刷新界面
 
-        except Exception as e:
-            from toolbox import regular_txt_to_markdown
-            tb_str = '```\n' + trimmed_format_exc() + '```'
-            chatbot[-1] = (chatbot[-1][0], f"[Local Message] 异常 \n\n{tb_str}")
-            yield from update_ui(chatbot=chatbot, history=history, msg="Json异常" + tb_str) # 刷新界面
-            return
-        
+    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。
+        need_to_pass, chunkjson, is_last_chunk = decode_chunk(chunk)
+        if chunk:
+            try:
+                if need_to_pass:
+                    pass
+                elif is_last_chunk:
+                    log_chat(llm_model=llm_kwargs["llm_model"], input_str=inputs, output_str=gpt_replying_buffer)
+                    # logging.info(f'[response] {gpt_replying_buffer}')
+                    break
+                else:
+                    if chunkjson and chunkjson['type'] == 'content_block_delta':
+                        gpt_replying_buffer += chunkjson['delta']['text']
+                        history[-1] = gpt_replying_buffer
+                        chatbot[-1] = (history[-2], history[-1])
+                        yield from update_ui(chatbot=chatbot, history=history, msg='正常') # 刷新界面
 
+            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")
 
+def multiple_picture_types(image_paths):
+    """
+    根据图片类型返回image/jpeg, image/png, image/gif, image/webp，无法判断则返回image/jpeg
+    """
+    for image_path in image_paths:
+        if image_path.endswith('.jpeg') or image_path.endswith('.jpg'):
+            return 'image/jpeg'
+        elif image_path.endswith('.png'):
+            return 'image/png'
+        elif image_path.endswith('.gif'):
+            return 'image/gif'
+        elif image_path.endswith('.webp'):
+            return 'image/webp'
+    return 'image/jpeg'
 
-# https://github.com/jtsang4/claude-to-chatgpt/blob/main/claude_to_chatgpt/adapter.py
-def convert_messages_to_prompt(messages):
-    prompt = ""
-    role_map = {
-        "system": "Human",
-        "user": "Human",
-        "assistant": "Assistant",
-    }
-    for message in messages:
-        role = message["role"]
-        content = message["content"]
-        transformed_role = role_map[role]
-        prompt += f"\n\n{transformed_role.capitalize()}: {content}"
-    prompt += "\n\nAssistant: "
-    return prompt
-
-def generate_payload(inputs, llm_kwargs, history, system_prompt, stream):
+def generate_payload(inputs, llm_kwargs, history, system_prompt, image_paths):
     """
     整合所有信息，选择LLM模型，生成http请求，为发送请求做准备
     """
-    from anthropic import Anthropic, HUMAN_PROMPT, AI_PROMPT
 
     conversation_cnt = len(history) // 2
 
-    messages = [{"role": "system", "content": system_prompt}]
+    messages = []
+
     if conversation_cnt:
         for index in range(0, 2*conversation_cnt, 2):
             what_i_have_asked = {}
             what_i_have_asked["role"] = "user"
-            what_i_have_asked["content"] = history[index]
+            what_i_have_asked["content"] = [{"type": "text", "text": 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
+            what_gpt_answer["content"] = [{"type": "text", "text": history[index+1]}]
+            if what_i_have_asked["content"][0]["text"] != "":
+                if what_i_have_asked["content"][0]["text"] == "": continue
+                if what_i_have_asked["content"][0]["text"] == timeout_bot_msg: continue
                 messages.append(what_i_have_asked)
                 messages.append(what_gpt_answer)
             else:
-                messages[-1]['content'] = what_gpt_answer['content']
+                messages[-1]['content'][0]['text'] = what_gpt_answer['content'][0]['text']
 
-    what_i_ask_now = {}
-    what_i_ask_now["role"] = "user"
-    what_i_ask_now["content"] = inputs
+    if any([llm_kwargs['llm_model'] == model for model in Claude_3_Models]) and image_paths:
+        what_i_ask_now = {}
+        what_i_ask_now["role"] = "user"
+        what_i_ask_now["content"] = []
+        for image_path in image_paths:
+            what_i_ask_now["content"].append({
+                "type": "image",
+                "source": {
+                    "type": "base64",
+                    "media_type": multiple_picture_types(image_paths),
+                    "data": encode_image(image_path),
+                }
+            })
+        what_i_ask_now["content"].append({"type": "text", "text": inputs})
+    else:
+        what_i_ask_now = {}
+        what_i_ask_now["role"] = "user"
+        what_i_ask_now["content"] = [{"type": "text", "text": inputs}]
     messages.append(what_i_ask_now)
-    prompt = convert_messages_to_prompt(messages)
-
-    return prompt
-
-
+    # 开始整理headers与message
+    headers = {
+        'x-api-key': ANTHROPIC_API_KEY,
+        'anthropic-version': '2023-06-01',
+        'content-type': 'application/json'
+    }
+    payload = {
+        'model': llm_kwargs['llm_model'],
+        'max_tokens': 4096,
+        'messages': messages,
+        'temperature': llm_kwargs['temperature'],
+        'stream': True,
+        'system': system_prompt
+    }
+    return headers, payload

request_llms/bridge_cohere.py

@@ -0,0 +1,328 @@
+# 借鉴了 https://github.com/GaiZhenbiao/ChuanhuChatGPT 项目
+
+"""
+    该文件中主要包含三个函数
+
+    不具备多线程能力的函数：
+    1. predict: 正常对话时使用，具备完备的交互功能，不可多线程
+
+    具备多线程调用能力的函数
+    2. predict_no_ui_long_connection：支持多线程
+"""
+
+import json
+import time
+import gradio as gr
+import logging
+import traceback
+import requests
+import importlib
+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
+proxies, TIMEOUT_SECONDS, MAX_RETRY, API_ORG, AZURE_CFG_ARRAY = \
+    get_conf('proxies', 'TIMEOUT_SECONDS', 'MAX_RETRY', 'API_ORG', 'AZURE_CFG_ARRAY')
+
+timeout_bot_msg = '[Local Message] Request timeout. Network error. Please check proxy settings in config.py.' + \
+                  '网络错误，检查代理服务器是否可用，以及代理设置的格式是否正确，格式须是[协议]://[地址]:[端口]，缺一不可。'
+
+def get_full_error(chunk, stream_response):
+    """
+        获取完整的从Cohere返回的报错
+    """
+    while True:
+        try:
+            chunk += next(stream_response)
+        except:
+            break
+    return chunk
+
+def decode_chunk(chunk):
+    # 提前读取一些信息 （用于判断异常）
+    chunk_decoded = chunk.decode()
+    chunkjson = None
+    has_choices = False
+    choice_valid = False
+    has_content = False
+    has_role = False
+    try:
+        chunkjson = json.loads(chunk_decoded)
+        has_choices = 'choices' in chunkjson
+        if has_choices: choice_valid = (len(chunkjson['choices']) > 0)
+        if has_choices and choice_valid: has_content = ("content" in chunkjson['choices'][0]["delta"])
+        if has_content: has_content = (chunkjson['choices'][0]["delta"]["content"] is not None)
+        if has_choices and choice_valid: has_role = "role" in chunkjson['choices'][0]["delta"]
+    except:
+        pass
+    return chunk_decoded, chunkjson, has_choices, choice_valid, has_content, has_role
+
+from functools import lru_cache
+@lru_cache(maxsize=32)
+def verify_endpoint(endpoint):
+    """
+        检查endpoint是否可用
+    """
+    if "你亲手写的api名称" in endpoint:
+        raise ValueError("Endpoint不正确, 请检查AZURE_ENDPOINT的配置! 当前的Endpoint为:" + endpoint)
+    return endpoint
+
+def predict_no_ui_long_connection(inputs:str, llm_kwargs:dict, history:list=[], sys_prompt:str="", observe_window:list=None, console_slience:bool=False):
+    """
+    发送，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：
+        内部调优参数
+    history：
+        是之前的对话列表
+    observe_window = None：
+        用于负责跨越线程传递已经输出的部分，大部分时候仅仅为了fancy的视觉效果，留空即可。observe_window[0]：观测窗。observe_window[1]：看门狗
+    """
+    watch_dog_patience = 5 # 看门狗的耐心, 设置5秒即可
+    headers, payload = generate_payload(inputs, llm_kwargs, history, system_prompt=sys_prompt, stream=True)
+    retry = 0
+    while True:
+        try:
+            # make a POST request to the API endpoint, stream=False
+            from .bridge_all import model_info
+            endpoint = verify_endpoint(model_info[llm_kwargs['llm_model']]['endpoint'])
+            response = requests.post(endpoint, headers=headers, proxies=proxies,
+                                    json=payload, stream=True, timeout=TIMEOUT_SECONDS); break
+        except requests.exceptions.ReadTimeout as e:
+            retry += 1
+            traceback.print_exc()
+            if retry > MAX_RETRY: raise TimeoutError
+            if MAX_RETRY!=0: print(f'请求超时，正在重试 ({retry}/{MAX_RETRY}) ……')
+
+    stream_response = response.iter_lines()
+    result = ''
+    json_data = None
+    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。
+        chunk_decoded, chunkjson, has_choices, choice_valid, has_content, has_role = decode_chunk(chunk)
+        if chunkjson['event_type'] == 'stream-start': continue
+        if chunkjson['event_type'] == 'text-generation':
+            result += chunkjson["text"]
+            if not console_slience: print(chunkjson["text"], end='')
+            if 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["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。")
+        if chunkjson['event_type'] == 'stream-end': break
+    return result
+
+
+def predict(inputs:str, llm_kwargs:dict, plugin_kwargs:dict, chatbot:ChatBotWithCookies,
+            history:list=[], system_prompt:str='', stream:bool=True, additional_fn:str=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 is_any_api_key(inputs):
+    #     chatbot._cookies['api_key'] = inputs
+    #     chatbot.append(("输入已识别为Cohere的api_key", what_keys(inputs)))
+    #     yield from update_ui(chatbot=chatbot, history=history, msg="api_key已导入") # 刷新界面
+    #     return
+    # elif not is_any_api_key(chatbot._cookies['api_key']):
+    #     chatbot.append((inputs, "缺少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。"))
+    #     yield from update_ui(chatbot=chatbot, history=history, msg="缺少api_key") # 刷新界面
+    #     return
+
+    user_input = inputs
+    if additional_fn is not None:
+        from core_functional import handle_core_functionality
+        inputs, history = handle_core_functionality(additional_fn, inputs, history, chatbot)
+
+    raw_input = inputs
+    # logging.info(f'[raw_input] {raw_input}')
+    chatbot.append((inputs, ""))
+    yield from update_ui(chatbot=chatbot, history=history, msg="等待响应") # 刷新界面
+
+    # check mis-behavior
+    if is_the_upload_folder(user_input):
+        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)
+
+    try:
+        headers, payload = generate_payload(inputs, llm_kwargs, history, system_prompt, stream)
+    except RuntimeError as e:
+        chatbot[-1] = (inputs, f"您提供的api-key不满足要求，不包含任何可用于{llm_kwargs['llm_model']}的api-key。您可能选择了错误的模型或请求源。")
+        yield from update_ui(chatbot=chatbot, history=history, msg="api-key不满足要求") # 刷新界面
+        return
+
+    # 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() + '```'
+        chatbot[-1] = (inputs, tb_str)
+        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("")
+
+    retry = 0
+    while True:
+        try:
+            # make a POST request to the API endpoint, stream=True
+            response = requests.post(endpoint, headers=headers, proxies=proxies,
+                                    json=payload, stream=True, timeout=TIMEOUT_SECONDS);break
+        except:
+            retry += 1
+            chatbot[-1] = ((chatbot[-1][0], timeout_bot_msg))
+            retry_msg = f"，正在重试 ({retry}/{MAX_RETRY}) ……" if MAX_RETRY > 0 else ""
+            yield from update_ui(chatbot=chatbot, history=history, msg="请求超时"+retry_msg) # 刷新界面
+            if retry > MAX_RETRY: raise TimeoutError
+
+    gpt_replying_buffer = ""
+
+    is_head_of_the_stream = True
+    if stream:
+        stream_response =  response.iter_lines()
+        while True:
+            try:
+                chunk = next(stream_response)
+            except StopIteration:
+                # 非Cohere官方接口的出现这样的报错，Cohere和API2D不会走这里
+                chunk_decoded = chunk.decode()
+                error_msg = chunk_decoded
+                # 其他情况，直接返回报错
+                chatbot, history = handle_error(inputs, llm_kwargs, chatbot, history, chunk_decoded, error_msg)
+                yield from update_ui(chatbot=chatbot, history=history, msg="非Cohere官方接口返回了错误:" + chunk.decode()) # 刷新界面
+                return
+
+            # 提前读取一些信息 （用于判断异常）
+            chunk_decoded, chunkjson, has_choices, choice_valid, has_content, has_role = decode_chunk(chunk)
+
+            if chunkjson:
+                try:
+                    if chunkjson['event_type'] == 'stream-start':
+                        continue
+                    if chunkjson['event_type'] == 'text-generation':
+                        gpt_replying_buffer = gpt_replying_buffer + chunkjson["text"]
+                        history[-1] = gpt_replying_buffer
+                        chatbot[-1] = (history[-2], history[-1])
+                        yield from update_ui(chatbot=chatbot, history=history, msg="正常") # 刷新界面
+                    if chunkjson['event_type'] == 'stream-end':
+                        log_chat(llm_model=llm_kwargs["llm_model"], input_str=inputs, output_str=gpt_replying_buffer)
+                        history[-1] = gpt_replying_buffer
+                        chatbot[-1] = (history[-2], history[-1])
+                        yield from update_ui(chatbot=chatbot, history=history, msg="正常") # 刷新界面
+                        break
+                except Exception as e:
+                    yield from update_ui(chatbot=chatbot, history=history, msg="Json解析不合常规") # 刷新界面
+                    chunk = get_full_error(chunk, stream_response)
+                    chunk_decoded = chunk.decode()
+                    error_msg = chunk_decoded
+                    chatbot, history = handle_error(inputs, llm_kwargs, chatbot, history, chunk_decoded, error_msg)
+                    yield from update_ui(chatbot=chatbot, history=history, msg="Json异常" + error_msg) # 刷新界面
+                    print(error_msg)
+                    return
+
+def handle_error(inputs, llm_kwargs, chatbot, history, chunk_decoded, error_msg):
+    from .bridge_all import model_info
+    Cohere_website = ' 请登录Cohere查看详情 https://platform.Cohere.com/signup'
+    if "reduce the length" in error_msg:
+        if len(history) >= 2: history[-1] = ""; history[-2] = "" # 清除当前溢出的输入：history[-2] 是本次输入, history[-1] 是本次输出
+        history = clip_history(inputs=inputs, history=history, tokenizer=model_info[llm_kwargs['llm_model']]['tokenizer'],
+                                               max_token_limit=(model_info[llm_kwargs['llm_model']]['max_token'])) # history至少释放二分之一
+        chatbot[-1] = (chatbot[-1][0], "[Local Message] Reduce the length. 本次输入过长, 或历史数据过长. 历史缓存数据已部分释放, 您可以请再次尝试. (若再次失败则更可能是因为输入过长.)")
+    elif "does not exist" in error_msg:
+        chatbot[-1] = (chatbot[-1][0], f"[Local Message] Model {llm_kwargs['llm_model']} does not exist. 模型不存在, 或者您没有获得体验资格.")
+    elif "Incorrect API key" in error_msg:
+        chatbot[-1] = (chatbot[-1][0], "[Local Message] Incorrect API key. Cohere以提供了不正确的API_KEY为由, 拒绝服务. " + Cohere_website)
+    elif "exceeded your current quota" in error_msg:
+        chatbot[-1] = (chatbot[-1][0], "[Local Message] You exceeded your current quota. Cohere以账户额度不足为由, 拒绝服务." + Cohere_website)
+    elif "account is not active" in error_msg:
+        chatbot[-1] = (chatbot[-1][0], "[Local Message] Your account is not active. Cohere以账户失效为由, 拒绝服务." + Cohere_website)
+    elif "associated with a deactivated account" in error_msg:
+        chatbot[-1] = (chatbot[-1][0], "[Local Message] You are associated with a deactivated account. Cohere以账户失效为由, 拒绝服务." + Cohere_website)
+    elif "API key has been deactivated" in error_msg:
+        chatbot[-1] = (chatbot[-1][0], "[Local Message] API key has been deactivated. Cohere以账户失效为由, 拒绝服务." + Cohere_website)
+    elif "bad forward key" in error_msg:
+        chatbot[-1] = (chatbot[-1][0], "[Local Message] Bad forward key. API2D账户额度不足.")
+    elif "Not enough point" in error_msg:
+        chatbot[-1] = (chatbot[-1][0], "[Local Message] Not enough point. API2D账户点数不足.")
+    else:
+        from toolbox import regular_txt_to_markdown
+        tb_str = '```\n' + trimmed_format_exc() + '```'
+        chatbot[-1] = (chatbot[-1][0], f"[Local Message] 异常 \n\n{tb_str} \n\n{regular_txt_to_markdown(chunk_decoded)}")
+    return chatbot, history
+
+def generate_payload(inputs, llm_kwargs, history, system_prompt, stream):
+    """
+    整合所有信息，选择LLM模型，生成http请求，为发送请求做准备
+    """
+    # if not is_any_api_key(llm_kwargs['api_key']):
+    #     raise AssertionError("你提供了错误的API_KEY。\n\n1. 临时解决方案：直接在输入区键入api_key，然后回车提交。\n\n2. 长效解决方案：在config.py中配置。")
+
+    api_key = select_api_key(llm_kwargs['api_key'], llm_kwargs['llm_model'])
+
+    headers = {
+        "Content-Type": "application/json",
+        "Authorization": f"Bearer {api_key}"
+    }
+    if API_ORG.startswith('org-'): headers.update({"Cohere-Organization": API_ORG})
+    if llm_kwargs['llm_model'].startswith('azure-'):
+        headers.update({"api-key": api_key})
+        if llm_kwargs['llm_model'] in AZURE_CFG_ARRAY.keys():
+            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
+
+    messages = [{"role": "SYSTEM", "message": 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["message"] = history[index]
+            what_gpt_answer = {}
+            what_gpt_answer["role"] = "CHATBOT"
+            what_gpt_answer["message"] = history[index+1]
+            if what_i_have_asked["message"] != "":
+                if what_gpt_answer["message"] == "": continue
+                if what_gpt_answer["message"] == timeout_bot_msg: continue
+                messages.append(what_i_have_asked)
+                messages.append(what_gpt_answer)
+            else:
+                messages[-1]['message'] = what_gpt_answer['message']
+
+    model = llm_kwargs['llm_model']
+    if model.startswith('cohere-'): model = model[len('cohere-'):]
+    payload = {
+        "model": model,
+        "message": inputs,
+        "chat_history": messages,
+        "temperature": llm_kwargs['temperature'],  # 1.0,
+        "top_p": llm_kwargs['top_p'],  # 1.0,
+        "n": 1,
+        "stream": stream,
+        "presence_penalty": 0,
+        "frequency_penalty": 0,
+    }
+
+    return headers,payload
+
+

request_llms/bridge_deepseekcoder.py

@@ -88,7 +88,7 @@ class GetCoderLMHandle(LocalLLMHandle):
             temperature = kwargs['temperature']
             history = kwargs['history']
             return query, max_length, top_p, temperature, history
-        
+
         query, max_length, top_p, temperature, history = adaptor(kwargs)
         history.append({ 'role': 'user', 'content': query})
         messages = history
@@ -97,14 +97,14 @@ class GetCoderLMHandle(LocalLLMHandle):
             inputs = inputs[:, -max_length:]
         inputs = inputs.to(self._model.device)
         generation_kwargs = dict(
-                                    inputs=inputs, 
+                                    inputs=inputs,
                                     max_new_tokens=max_length,
                                     do_sample=False,
                                     top_p=top_p,
                                     streamer = self._streamer,
                                     top_k=50,
                                     temperature=temperature,
-                                    num_return_sequences=1, 
+                                    num_return_sequences=1,
                                     eos_token_id=32021,
                                 )
         thread = Thread(target=self._model.generate, kwargs=generation_kwargs, daemon=True)

request_llms/bridge_google_gemini.py

@@ -7,7 +7,8 @@ import re
 import os
 import time
 from request_llms.com_google import GoogleChatInit
-from toolbox import get_conf, update_ui, update_ui_lastest_msg, have_any_recent_upload_image_files, trimmed_format_exc
+from toolbox import ChatBotWithCookies
+from toolbox import get_conf, update_ui, update_ui_lastest_msg, have_any_recent_upload_image_files, trimmed_format_exc, log_chat
 
 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.' + \
@@ -20,7 +21,7 @@ def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="",
     if get_conf("GEMINI_API_KEY") == "":
         raise ValueError(f"请配置 GEMINI_API_KEY。")
 
-    genai = GoogleChatInit()
+    genai = GoogleChatInit(llm_kwargs)
     watch_dog_patience = 5  # 看门狗的耐心, 设置5秒即可
     gpt_replying_buffer = ''
     stream_response = genai.generate_chat(inputs, llm_kwargs, history, sys_prompt)
@@ -44,7 +45,8 @@ def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="",
     return gpt_replying_buffer
 
 
-def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_prompt='', stream=True, additional_fn=None):
+def predict(inputs:str, llm_kwargs:dict, plugin_kwargs:dict, chatbot:ChatBotWithCookies,
+            history:list=[], system_prompt:str='', stream:bool=True, additional_fn:str=None):
     # 检查API_KEY
     if get_conf("GEMINI_API_KEY") == "":
         yield from update_ui_lastest_msg(f"请配置 GEMINI_API_KEY。", chatbot=chatbot, history=history, delay=0)
@@ -57,7 +59,11 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
 
     if "vision" in llm_kwargs["llm_model"]:
         have_recent_file, image_paths = have_any_recent_upload_image_files(chatbot)
-        def make_media_input(inputs, image_paths): 
+        if not have_recent_file:
+            chatbot.append((inputs, "没有检测到任何近期上传的图像文件，请上传jpg格式的图片，此外，请注意拓展名需要小写"))
+            yield from update_ui(chatbot=chatbot, history=history, msg="等待图片") # 刷新界面
+            return
+        def make_media_input(inputs, image_paths):
             for image_path in image_paths:
                 inputs = inputs + f'<br/><br/><div align="center"><img src="file={os.path.abspath(image_path)}"></div>'
             return inputs
@@ -66,7 +72,7 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
 
     chatbot.append((inputs, ""))
     yield from update_ui(chatbot=chatbot, history=history)
-    genai = GoogleChatInit()
+    genai = GoogleChatInit(llm_kwargs)
     retry = 0
     while True:
         try:
@@ -93,6 +99,7 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
             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_internlm.py

@@ -82,7 +82,7 @@ class GetInternlmHandle(LocalLLMHandle):
             history = kwargs['history']
             real_prompt = combine_history(prompt, history)
             return model, tokenizer, real_prompt, max_length, top_p, temperature
-        
+
         model, tokenizer, prompt, max_length, top_p, temperature = adaptor()
         prefix_allowed_tokens_fn = None
         logits_processor = None
@@ -183,7 +183,7 @@ class GetInternlmHandle(LocalLLMHandle):
                 outputs, model_kwargs, is_encoder_decoder=False
             )
             unfinished_sequences = unfinished_sequences.mul((min(next_tokens != i for i in eos_token_id)).long())
-            
+
             output_token_ids = input_ids[0].cpu().tolist()
             output_token_ids = output_token_ids[input_length:]
             for each_eos_token_id in eos_token_id:
@@ -196,7 +196,7 @@ class GetInternlmHandle(LocalLLMHandle):
             if unfinished_sequences.max() == 0 or stopping_criteria(input_ids, scores):
                 return
 
-    
+
 # ------------------------------------------------------------------------------------------------------------------------
 # 🔌💻 GPT-Academic Interface
 # ------------------------------------------------------------------------------------------------------------------------

request_llms/bridge_jittorllms_llama.py

@@ -1,10 +1,10 @@
 
-from transformers import AutoModel, AutoTokenizer
 import time
 import threading
 import importlib
 from toolbox import update_ui, get_conf
 from multiprocessing import Process, Pipe
+from transformers import AutoModel, AutoTokenizer
 
 load_message = "jittorllms尚未加载，加载需要一段时间。注意，请避免混用多种jittor模型，否则可能导致显存溢出而造成卡顿，取决于`config.py`的配置，jittorllms消耗大量的内存（CPU）或显存（GPU），也许会导致低配计算机卡死 ……"
 
@@ -20,7 +20,7 @@ class GetGLMHandle(Process):
         self.check_dependency()
         self.start()
         self.threadLock = threading.Lock()
-        
+
     def check_dependency(self):
         try:
             import pandas
@@ -102,11 +102,12 @@ class GetGLMHandle(Process):
             else:
                 break
         self.threadLock.release()
-    
+
 global llama_glm_handle
 llama_glm_handle = None
 #################################################################################
-def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="", observe_window=[], console_slience=False):
+def predict_no_ui_long_connection(inputs:str, llm_kwargs:dict, history:list=[], sys_prompt:str="",
+                                  observe_window:list=[], console_slience:bool=False):
     """
         多线程方法
         函数的说明请见 request_llms/bridge_all.py
@@ -115,7 +116,7 @@ def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="",
     if llama_glm_handle is None:
         llama_glm_handle = GetGLMHandle()
         if len(observe_window) >= 1: observe_window[0] = load_message + "\n\n" + llama_glm_handle.info
-        if not llama_glm_handle.success: 
+        if not llama_glm_handle.success:
             error = llama_glm_handle.info
             llama_glm_handle = None
             raise RuntimeError(error)
@@ -130,7 +131,7 @@ def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="",
     for response in llama_glm_handle.stream_chat(query=inputs, history=history_feedin, system_prompt=sys_prompt, max_length=llm_kwargs['max_length'], top_p=llm_kwargs['top_p'], temperature=llm_kwargs['temperature']):
         print(response)
         if len(observe_window) >= 1:  observe_window[0] = response
-        if len(observe_window) >= 2:  
+        if len(observe_window) >= 2:
             if (time.time()-observe_window[1]) > watch_dog_patience:
                 raise RuntimeError("程序终止。")
     return response
@@ -149,7 +150,7 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
         llama_glm_handle = GetGLMHandle()
         chatbot[-1] = (inputs, load_message + "\n\n" + llama_glm_handle.info)
         yield from update_ui(chatbot=chatbot, history=[])
-        if not llama_glm_handle.success: 
+        if not llama_glm_handle.success:
             llama_glm_handle = None
             return
 

request_llms/bridge_jittorllms_pangualpha.py

@@ -1,10 +1,10 @@
 
-from transformers import AutoModel, AutoTokenizer
 import time
 import threading
 import importlib
 from toolbox import update_ui, get_conf
 from multiprocessing import Process, Pipe
+from transformers import AutoModel, AutoTokenizer
 
 load_message = "jittorllms尚未加载，加载需要一段时间。注意，请避免混用多种jittor模型，否则可能导致显存溢出而造成卡顿，取决于`config.py`的配置，jittorllms消耗大量的内存（CPU）或显存（GPU），也许会导致低配计算机卡死 ……"
 
@@ -20,7 +20,7 @@ class GetGLMHandle(Process):
         self.check_dependency()
         self.start()
         self.threadLock = threading.Lock()
-        
+
     def check_dependency(self):
         try:
             import pandas
@@ -102,11 +102,12 @@ class GetGLMHandle(Process):
             else:
                 break
         self.threadLock.release()
-    
+
 global pangu_glm_handle
 pangu_glm_handle = None
 #################################################################################
-def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="", observe_window=[], console_slience=False):
+def predict_no_ui_long_connection(inputs:str, llm_kwargs:dict, history:list=[], sys_prompt:str="",
+                                  observe_window:list=[], console_slience:bool=False):
     """
         多线程方法
         函数的说明请见 request_llms/bridge_all.py
@@ -115,7 +116,7 @@ def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="",
     if pangu_glm_handle is None:
         pangu_glm_handle = GetGLMHandle()
         if len(observe_window) >= 1: observe_window[0] = load_message + "\n\n" + pangu_glm_handle.info
-        if not pangu_glm_handle.success: 
+        if not pangu_glm_handle.success:
             error = pangu_glm_handle.info
             pangu_glm_handle = None
             raise RuntimeError(error)
@@ -130,7 +131,7 @@ def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="",
     for response in pangu_glm_handle.stream_chat(query=inputs, history=history_feedin, system_prompt=sys_prompt, max_length=llm_kwargs['max_length'], top_p=llm_kwargs['top_p'], temperature=llm_kwargs['temperature']):
         print(response)
         if len(observe_window) >= 1:  observe_window[0] = response
-        if len(observe_window) >= 2:  
+        if len(observe_window) >= 2:
             if (time.time()-observe_window[1]) > watch_dog_patience:
                 raise RuntimeError("程序终止。")
     return response
@@ -149,7 +150,7 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
         pangu_glm_handle = GetGLMHandle()
         chatbot[-1] = (inputs, load_message + "\n\n" + pangu_glm_handle.info)
         yield from update_ui(chatbot=chatbot, history=[])
-        if not pangu_glm_handle.success: 
+        if not pangu_glm_handle.success:
             pangu_glm_handle = None
             return
 

request_llms/bridge_jittorllms_rwkv.py

@@ -20,7 +20,7 @@ class GetGLMHandle(Process):
         self.check_dependency()
         self.start()
         self.threadLock = threading.Lock()
-        
+
     def check_dependency(self):
         try:
             import pandas
@@ -102,11 +102,12 @@ class GetGLMHandle(Process):
             else:
                 break
         self.threadLock.release()
-    
+
 global rwkv_glm_handle
 rwkv_glm_handle = None
 #################################################################################
-def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="", observe_window=[], console_slience=False):
+def predict_no_ui_long_connection(inputs:str, llm_kwargs:dict, history:list=[], sys_prompt:str="",
+                                  observe_window:list=[], console_slience:bool=False):
     """
         多线程方法
         函数的说明请见 request_llms/bridge_all.py
@@ -115,7 +116,7 @@ def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="",
     if rwkv_glm_handle is None:
         rwkv_glm_handle = GetGLMHandle()
         if len(observe_window) >= 1: observe_window[0] = load_message + "\n\n" + rwkv_glm_handle.info
-        if not rwkv_glm_handle.success: 
+        if not rwkv_glm_handle.success:
             error = rwkv_glm_handle.info
             rwkv_glm_handle = None
             raise RuntimeError(error)
@@ -130,7 +131,7 @@ def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="",
     for response in rwkv_glm_handle.stream_chat(query=inputs, history=history_feedin, system_prompt=sys_prompt, max_length=llm_kwargs['max_length'], top_p=llm_kwargs['top_p'], temperature=llm_kwargs['temperature']):
         print(response)
         if len(observe_window) >= 1:  observe_window[0] = response
-        if len(observe_window) >= 2:  
+        if len(observe_window) >= 2:
             if (time.time()-observe_window[1]) > watch_dog_patience:
                 raise RuntimeError("程序终止。")
     return response
@@ -149,7 +150,7 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
         rwkv_glm_handle = GetGLMHandle()
         chatbot[-1] = (inputs, load_message + "\n\n" + rwkv_glm_handle.info)
         yield from update_ui(chatbot=chatbot, history=[])
-        if not rwkv_glm_handle.success: 
+        if not rwkv_glm_handle.success:
             rwkv_glm_handle = None
             return
 

request_llms/bridge_llama2.py

@@ -48,7 +48,7 @@ class GetLlamaHandle(LocalLLMHandle):
             history = kwargs['history']
             console_slience = kwargs.get('console_slience', True)
             return query, max_length, top_p, temperature, history, console_slience
-        
+
         def convert_messages_to_prompt(query, history):
             prompt = ""
             for a, b in history:
@@ -56,7 +56,7 @@ class GetLlamaHandle(LocalLLMHandle):
                 prompt += "\n{b}" + b
             prompt += f"\n[INST]{query}[/INST]"
             return prompt
-        
+
         query, max_length, top_p, temperature, history, console_slience = adaptor(kwargs)
         prompt = convert_messages_to_prompt(query, history)
         # =-=-=-=-=-=-=-=-=-=-=-=-=-=-=--=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=--=-=-
@@ -70,13 +70,13 @@ class GetLlamaHandle(LocalLLMHandle):
         thread = Thread(target=self._model.generate, kwargs=generation_kwargs)
         thread.start()
         generated_text = ""
-        for new_text in streamer: 
+        for new_text in streamer:
             generated_text += new_text
             if not console_slience: print(new_text, end='')
             yield generated_text.lstrip(prompt_tk_back).rstrip("</s>")
         if not console_slience: print()
         # =-=-=-=-=-=-=-=-=-=-=-=-=-=-=--=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=--=-=-
-        
+
     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

request_llms/bridge_moonshot.py

@@ -0,0 +1,197 @@
+# encoding: utf-8
+# @Time   : 2024/3/3
+# @Author : Spike
+# @Descr   :
+import json
+import os
+import time
+import logging
+
+from toolbox import get_conf, update_ui, log_chat
+from toolbox import ChatBotWithCookies
+
+import requests
+
+
+class MoonShotInit:
+
+    def __init__(self):
+        self.llm_model = None
+        self.url = 'https://api.moonshot.cn/v1/chat/completions'
+        self.api_key = get_conf('MOONSHOT_API_KEY')
+
+    def __converter_file(self, user_input: str):
+        what_ask = []
+        for f in user_input.splitlines():
+            if os.path.exists(f):
+                files = []
+                if os.path.isdir(f):
+                    file_list = os.listdir(f)
+                    files.extend([os.path.join(f, file) for file in file_list])
+                else:
+                    files.append(f)
+                for file in files:
+                    if file.split('.')[-1] in ['pdf']:
+                        with open(file, 'r') as fp:
+                            from crazy_functions.crazy_utils import read_and_clean_pdf_text
+                            file_content, _ = read_and_clean_pdf_text(fp)
+                        what_ask.append({"role": "system", "content": file_content})
+        return what_ask
+
+    def __converter_user(self, user_input: str):
+        what_i_ask_now = {"role": "user", "content": user_input}
+        return what_i_ask_now
+
+    def __conversation_history(self, history):
+        conversation_cnt = len(history) // 2
+        messages = []
+        if conversation_cnt:
+            for index in range(0, 2 * conversation_cnt, 2):
+                what_i_have_asked = {
+                    "role": "user",
+                    "content": str(history[index])
+                }
+                what_gpt_answer = {
+                    "role": "assistant",
+                    "content": str(history[index + 1])
+                }
+                if what_i_have_asked["content"] != "":
+                    if what_gpt_answer["content"] == "": continue
+                    messages.append(what_i_have_asked)
+                    messages.append(what_gpt_answer)
+                else:
+                    messages[-1]['content'] = what_gpt_answer['content']
+        return messages
+
+    def _analysis_content(self, chuck):
+        chunk_decoded = chuck.decode("utf-8")
+        chunk_json = {}
+        content = ""
+        try:
+            chunk_json = json.loads(chunk_decoded[6:])
+            content = chunk_json['choices'][0]["delta"].get("content", "")
+        except:
+            pass
+        return chunk_decoded, chunk_json, content
+
+    def generate_payload(self, inputs, llm_kwargs, history, system_prompt, stream):
+        self.llm_model = llm_kwargs['llm_model']
+        llm_kwargs.update({'use-key': self.api_key})
+        messages = []
+        if system_prompt:
+            messages.append({"role": "system", "content": system_prompt})
+        messages.extend(self.__converter_file(inputs))
+        for i in history[0::2]:    # 历史文件继续上传
+            messages.extend(self.__converter_file(i))
+        messages.extend(self.__conversation_history(history))
+        messages.append(self.__converter_user(inputs))
+        header = {
+            "Content-Type": "application/json",
+            "Authorization": f"Bearer {self.api_key}",
+        }
+        payload = {
+            "model": self.llm_model,
+            "messages": messages,
+            "temperature": llm_kwargs.get('temperature', 0.3),  # 1.0,
+            "top_p": llm_kwargs.get('top_p', 1.0),  # 1.0,
+            "n": llm_kwargs.get('n_choices', 1),
+            "stream": stream
+        }
+        return payload, header
+
+    def generate_messages(self, inputs, llm_kwargs, history, system_prompt, stream):
+        payload, headers = self.generate_payload(inputs, llm_kwargs, history, system_prompt, stream)
+        response = requests.post(self.url, headers=headers, json=payload, stream=stream)
+
+        chunk_content = ""
+        gpt_bro_result = ""
+        for chuck in response.iter_lines():
+            chunk_decoded, check_json, content = self._analysis_content(chuck)
+            chunk_content += chunk_decoded
+            if content:
+                gpt_bro_result += content
+                yield content, gpt_bro_result, ''
+            else:
+                error_msg = msg_handle_error(llm_kwargs, chunk_decoded)
+                if error_msg:
+                    yield error_msg, gpt_bro_result, error_msg
+                    break
+
+
+def msg_handle_error(llm_kwargs, chunk_decoded):
+    use_ket = llm_kwargs.get('use-key', '')
+    api_key_encryption = use_ket[:8] + '****' + use_ket[-5:]
+    openai_website = f' 请登录OpenAI查看详情 https://platform.openai.com/signup  api-key: `{api_key_encryption}`'
+    error_msg = ''
+    if "does not exist" in chunk_decoded:
+        error_msg = f"[Local Message] Model {llm_kwargs['llm_model']} does not exist. 模型不存在, 或者您没有获得体验资格."
+    elif "Incorrect API key" in chunk_decoded:
+        error_msg = f"[Local Message] Incorrect API key. OpenAI以提供了不正确的API_KEY为由, 拒绝服务." + openai_website
+    elif "exceeded your current quota" in chunk_decoded:
+        error_msg = "[Local Message] You exceeded your current quota. OpenAI以账户额度不足为由, 拒绝服务." + openai_website
+    elif "account is not active" in chunk_decoded:
+        error_msg = "[Local Message] Your account is not active. OpenAI以账户失效为由, 拒绝服务." + openai_website
+    elif "associated with a deactivated account" in chunk_decoded:
+        error_msg = "[Local Message] You are associated with a deactivated account. OpenAI以账户失效为由, 拒绝服务." + openai_website
+    elif "API key has been deactivated" in chunk_decoded:
+        error_msg = "[Local Message] API key has been deactivated. OpenAI以账户失效为由, 拒绝服务." + openai_website
+    elif "bad forward key" in chunk_decoded:
+        error_msg = "[Local Message] Bad forward key. API2D账户额度不足."
+    elif "Not enough point" in chunk_decoded:
+        error_msg = "[Local Message] Not enough point. API2D账户点数不足."
+    elif 'error' in str(chunk_decoded).lower():
+        try:
+            error_msg = json.dumps(json.loads(chunk_decoded[:6]), indent=4, ensure_ascii=False)
+        except:
+            error_msg = chunk_decoded
+    return error_msg
+
+
+def predict(inputs:str, llm_kwargs:dict, plugin_kwargs:dict, chatbot:ChatBotWithCookies,
+            history:list=[], system_prompt:str='', stream:bool=True, additional_fn:str=None):
+    chatbot.append([inputs, ""])
+
+    if additional_fn is not None:
+        from core_functional import handle_core_functionality
+        inputs, history = handle_core_functionality(additional_fn, inputs, history, chatbot)
+    yield from update_ui(chatbot=chatbot, history=history, msg="等待响应")  # 刷新界面
+    gpt_bro_init = MoonShotInit()
+    history.extend([inputs, ''])
+    stream_response = gpt_bro_init.generate_messages(inputs, llm_kwargs, history, system_prompt, stream)
+    for content, gpt_bro_result, error_bro_meg in stream_response:
+        chatbot[-1] = [inputs, gpt_bro_result]
+        history[-1] = gpt_bro_result
+        yield from update_ui(chatbot=chatbot, history=history)  # 刷新界面
+        if error_bro_meg:
+            chatbot[-1] = [inputs, error_bro_meg]
+            history = history[:-2]
+            yield from update_ui(chatbot=chatbot, history=history)  # 刷新界面
+            break
+    log_chat(llm_model=llm_kwargs["llm_model"], input_str=inputs, output_str=gpt_bro_result)
+
+def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="", observe_window=None,
+                                  console_slience=False):
+    gpt_bro_init = MoonShotInit()
+    watch_dog_patience = 60  # 看门狗的耐心, 设置10秒即可
+    stream_response = gpt_bro_init.generate_messages(inputs, llm_kwargs, history, sys_prompt, True)
+    moonshot_bro_result = ''
+    for content, moonshot_bro_result, error_bro_meg in stream_response:
+        moonshot_bro_result = moonshot_bro_result
+        if error_bro_meg:
+            if len(observe_window) >= 3:
+                observe_window[2] = error_bro_meg
+            return f'{moonshot_bro_result} 对话错误'
+            # 观测窗
+        if len(observe_window) >= 1:
+            observe_window[0] = moonshot_bro_result
+        if len(observe_window) >= 2:
+            if (time.time() - observe_window[1]) > watch_dog_patience:
+                observe_window[2] = "请求超时，程序终止。"
+                raise RuntimeError(f"{moonshot_bro_result} 程序终止。")
+    return moonshot_bro_result
+
+if __name__ == '__main__':
+    moon_ai = MoonShotInit()
+    for g in moon_ai.generate_messages('hello', {'llm_model': 'moonshot-v1-8k'},
+                                       [], '', True):
+        print(g)

request_llms/bridge_moss.py

@@ -18,7 +18,7 @@ class GetGLMHandle(Process):
         if self.check_dependency():
             self.start()
             self.threadLock = threading.Lock()
-        
+
     def check_dependency(self): # 主进程执行
         try:
             import datasets, os
@@ -54,9 +54,9 @@ class GetGLMHandle(Process):
         from models.tokenization_moss import MossTokenizer
 
         parser = argparse.ArgumentParser()
-        parser.add_argument("--model_name", default="fnlp/moss-moon-003-sft-int4", 
-                            choices=["fnlp/moss-moon-003-sft", 
-                                    "fnlp/moss-moon-003-sft-int8", 
+        parser.add_argument("--model_name", default="fnlp/moss-moon-003-sft-int4",
+                            choices=["fnlp/moss-moon-003-sft",
+                                    "fnlp/moss-moon-003-sft-int8",
                                     "fnlp/moss-moon-003-sft-int4"], type=str)
         parser.add_argument("--gpu", default="0", type=str)
         args = parser.parse_args()
@@ -76,7 +76,7 @@ class GetGLMHandle(Process):
 
         config = MossConfig.from_pretrained(model_path)
         self.tokenizer = MossTokenizer.from_pretrained(model_path)
-        if num_gpus > 1:  
+        if num_gpus > 1:
             print("Waiting for all devices to be ready, it may take a few minutes...")
             with init_empty_weights():
                 raw_model = MossForCausalLM._from_config(config, torch_dtype=torch.float16)
@@ -135,15 +135,15 @@ class GetGLMHandle(Process):
                 inputs = self.tokenizer(self.prompt, return_tensors="pt")
                 with torch.no_grad():
                     outputs = self.model.generate(
-                        inputs.input_ids.cuda(), 
-                        attention_mask=inputs.attention_mask.cuda(), 
-                        max_length=2048, 
-                        do_sample=True, 
-                        top_k=40, 
-                        top_p=0.8, 
+                        inputs.input_ids.cuda(),
+                        attention_mask=inputs.attention_mask.cuda(),
+                        max_length=2048,
+                        do_sample=True,
+                        top_k=40,
+                        top_p=0.8,
                         temperature=0.7,
                         repetition_penalty=1.02,
-                        num_return_sequences=1, 
+                        num_return_sequences=1,
                         eos_token_id=106068,
                         pad_token_id=self.tokenizer.pad_token_id)
                     response = self.tokenizer.decode(outputs[0][inputs.input_ids.shape[1]:], skip_special_tokens=True)
@@ -167,11 +167,12 @@ class GetGLMHandle(Process):
             else:
                 break
         self.threadLock.release()
-    
+
 global moss_handle
 moss_handle = None
 #################################################################################
-def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="", observe_window=[], console_slience=False):
+def predict_no_ui_long_connection(inputs:str, llm_kwargs:dict, history:list=[], sys_prompt:str="",
+                                  observe_window:list=[], console_slience:bool=False):
     """
         多线程方法
         函数的说明请见 request_llms/bridge_all.py
@@ -180,7 +181,7 @@ def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="",
     if moss_handle is None:
         moss_handle = GetGLMHandle()
         if len(observe_window) >= 1: observe_window[0] = load_message + "\n\n" + moss_handle.info
-        if not moss_handle.success: 
+        if not moss_handle.success:
             error = moss_handle.info
             moss_handle = None
             raise RuntimeError(error)
@@ -194,7 +195,7 @@ def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="",
     response = ""
     for response in moss_handle.stream_chat(query=inputs, history=history_feedin, sys_prompt=sys_prompt, max_length=llm_kwargs['max_length'], top_p=llm_kwargs['top_p'], temperature=llm_kwargs['temperature']):
         if len(observe_window) >= 1:  observe_window[0] = response
-        if len(observe_window) >= 2:  
+        if len(observe_window) >= 2:
             if (time.time()-observe_window[1]) > watch_dog_patience:
                 raise RuntimeError("程序终止。")
     return response
@@ -213,7 +214,7 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
         moss_handle = GetGLMHandle()
         chatbot[-1] = (inputs, load_message + "\n\n" + moss_handle.info)
         yield from update_ui(chatbot=chatbot, history=[])
-        if not moss_handle.success: 
+        if not moss_handle.success:
             moss_handle = None
             return
     else:

request_llms/bridge_ollama.py

@@ -0,0 +1,272 @@
+# 借鉴自同目录下的bridge_chatgpt.py
+
+"""
+    该文件中主要包含三个函数
+
+    不具备多线程能力的函数：
+    1. predict: 正常对话时使用，具备完备的交互功能，不可多线程
+
+    具备多线程调用能力的函数
+    2. predict_no_ui_long_connection：支持多线程
+"""
+
+import json
+import time
+import gradio as gr
+import logging
+import traceback
+import requests
+import importlib
+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 = 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):
+    """
+        获取完整的从Openai返回的报错
+    """
+    while True:
+        try:
+            chunk += next(stream_response)
+        except:
+            break
+    return chunk
+
+def decode_chunk(chunk):
+    # 提前读取一些信息（用于判断异常）
+    chunk_decoded = chunk.decode()
+    chunkjson = None
+    is_last_chunk = False
+    try:
+        chunkjson = json.loads(chunk_decoded)
+        is_last_chunk = chunkjson.get("done", False)
+    except:
+        pass
+    return chunk_decoded, chunkjson, is_last_chunk
+
+def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="", observe_window=None, console_slience=False):
+    """
+    发送至chatGPT，等待回复，一次性完成，不显示中间过程。但内部用stream的方法避免中途网线被掐。
+    inputs：
+        是本次问询的输入
+    sys_prompt:
+        系统静默prompt
+    llm_kwargs：
+        chatGPT的内部调优参数
+    history：
+        是之前的对话列表
+    observe_window = None：
+        用于负责跨越线程传递已经输出的部分，大部分时候仅仅为了fancy的视觉效果，留空即可。observe_window[0]：观测窗。observe_window[1]：看门狗
+    """
+    watch_dog_patience = 5 # 看门狗的耐心, 设置5秒即可
+    if inputs == "":     inputs = "空空如也的输入栏"
+    headers, payload = generate_payload(inputs, llm_kwargs, history, system_prompt=sys_prompt, stream=True)
+    retry = 0
+    while True:
+        try:
+            # make a POST request to the API endpoint, stream=False
+            from .bridge_all import model_info
+            endpoint = model_info[llm_kwargs['llm_model']]['endpoint']
+            response = requests.post(endpoint, headers=headers, proxies=proxies,
+                                    json=payload, stream=True, timeout=TIMEOUT_SECONDS); break
+        except requests.exceptions.ReadTimeout as e:
+            retry += 1
+            traceback.print_exc()
+            if retry > MAX_RETRY: raise TimeoutError
+            if MAX_RETRY!=0: print(f'请求超时，正在重试 ({retry}/{MAX_RETRY}) ……')
+
+    stream_response = response.iter_lines()
+    result = ''
+    while True:
+        try: chunk = next(stream_response)
+        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。
+        chunk_decoded, chunkjson, is_last_chunk = decode_chunk(chunk)
+        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['message']["content"]
+                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['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:
+                            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 inputs == "":     inputs = "空空如也的输入栏"
+    user_input = inputs
+    if additional_fn is not None:
+        from core_functional import handle_core_functionality
+        inputs, history = handle_core_functionality(additional_fn, inputs, history, chatbot)
+
+    raw_input = inputs
+    logging.info(f'[raw_input] {raw_input}')
+    chatbot.append((inputs, ""))
+    yield from update_ui(chatbot=chatbot, history=history, msg="等待响应") # 刷新界面
+
+    # check mis-behavior
+    if is_the_upload_folder(user_input):
+        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, payload = generate_payload(inputs, llm_kwargs, history, system_prompt, stream)
+
+    from .bridge_all import model_info
+    endpoint = model_info[llm_kwargs['llm_model']]['endpoint']
+
+    history.append(inputs); history.append("")
+
+    retry = 0
+    while True:
+        try:
+            # make a POST request to the API endpoint, stream=True
+            response = requests.post(endpoint, headers=headers, proxies=proxies,
+                                    json=payload, stream=True, timeout=TIMEOUT_SECONDS);break
+        except:
+            retry += 1
+            chatbot[-1] = ((chatbot[-1][0], timeout_bot_msg))
+            retry_msg = f"，正在重试 ({retry}/{MAX_RETRY}) ……" if MAX_RETRY > 0 else ""
+            yield from update_ui(chatbot=chatbot, history=history, msg="请求超时"+retry_msg) # 刷新界面
+            if retry > MAX_RETRY: raise TimeoutError
+
+    gpt_replying_buffer = ""
+
+    if stream:
+        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。
+
+            # 提前读取一些信息 （用于判断异常）
+            chunk_decoded, chunkjson, is_last_chunk = decode_chunk(chunk)
+
+            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] {gpt_replying_buffer}')
+                        break
+                    # 处理数据流的主体
+                    try:
+                        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])
+                    yield from update_ui(chatbot=chatbot, history=history, msg=status_text) # 刷新界面
+                except Exception as e:
+                    yield from update_ui(chatbot=chatbot, history=history, msg="Json解析不合常规") # 刷新界面
+                    chunk = get_full_error(chunk, stream_response)
+                    chunk_decoded = chunk.decode()
+                    error_msg = chunk_decoded
+                    chatbot, history = handle_error(inputs, llm_kwargs, chatbot, history, chunk_decoded, error_msg)
+                    yield from update_ui(chatbot=chatbot, history=history, msg="Json异常" + error_msg) # 刷新界面
+                    print(error_msg)
+                    return
+
+def handle_error(inputs, llm_kwargs, chatbot, history, chunk_decoded, error_msg):
+    from .bridge_all import model_info
+    if "bad_request" in error_msg:
+        chatbot[-1] = (chatbot[-1][0], "[Local Message] 已经超过了模型的最大上下文或是模型格式错误,请尝试削减单次输入的文本量。")
+    elif "authentication_error" in error_msg:
+        chatbot[-1] = (chatbot[-1][0], "[Local Message] Incorrect API key. 请确保API key有效。")
+    elif "not_found" in error_msg:
+        chatbot[-1] = (chatbot[-1][0], f"[Local Message] {llm_kwargs['llm_model']} 无效，请确保使用小写的模型名称。")
+    elif "rate_limit" in error_msg:
+        chatbot[-1] = (chatbot[-1][0], "[Local Message] 遇到了控制请求速率限制，请一分钟后重试。")
+    elif "system_busy" in error_msg:
+        chatbot[-1] = (chatbot[-1][0], "[Local Message] 系统繁忙，请一分钟后重试。")
+    else:
+        from toolbox import regular_txt_to_markdown
+        tb_str = '```\n' + trimmed_format_exc() + '```'
+        chatbot[-1] = (chatbot[-1][0], f"[Local Message] 异常 \n\n{tb_str} \n\n{regular_txt_to_markdown(chunk_decoded)}")
+    return chatbot, history
+
+def generate_payload(inputs, llm_kwargs, history, system_prompt, stream):
+    """
+    整合所有信息，选择LLM模型，生成http请求，为发送请求做准备
+    """
+
+    headers = {
+        "Content-Type": "application/json",
+    }
+
+    conversation_cnt = len(history) // 2
+
+    messages = [{"role": "system", "content": system_prompt}]
+    if conversation_cnt:
+        for index in range(0, 2*conversation_cnt, 2):
+            what_i_have_asked = {}
+            what_i_have_asked["role"] = "user"
+            what_i_have_asked["content"] = history[index]
+            what_gpt_answer = {}
+            what_gpt_answer["role"] = "assistant"
+            what_gpt_answer["content"] = history[index+1]
+            if what_i_have_asked["content"] != "":
+                if what_gpt_answer["content"] == "": continue
+                if what_gpt_answer["content"] == timeout_bot_msg: continue
+                messages.append(what_i_have_asked)
+                messages.append(what_gpt_answer)
+            else:
+                messages[-1]['content'] = what_gpt_answer['content']
+
+    what_i_ask_now = {}
+    what_i_ask_now["role"] = "user"
+    what_i_ask_now["content"] = inputs
+    messages.append(what_i_ask_now)
+    model = llm_kwargs['llm_model']
+    if llm_kwargs['llm_model'].startswith('ollama-'):
+        model = llm_kwargs['llm_model'][len('ollama-'):]
+        model, _ = read_one_api_model_name(model)
+    options = {"temperature": llm_kwargs['temperature']}
+    payload = {
+        "model": model,
+        "messages": messages,
+        "options": options,
+    }
+    try:
+        print(f" {llm_kwargs['llm_model']} : {conversation_cnt} : {inputs[:100]} ..........")
+    except:
+        print('输入中可能存在乱码。')
+    return headers,payload

request_llms/bridge_qianfan.py

@@ -117,7 +117,8 @@ def generate_from_baidu_qianfan(inputs, llm_kwargs, history, system_prompt):
                 raise RuntimeError(dec['error_msg'])
 
 
-def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="", observe_window=[], console_slience=False):
+def predict_no_ui_long_connection(inputs:str, llm_kwargs:dict, history:list=[], sys_prompt:str="",
+                                  observe_window:list=[], console_slience:bool=False):
     """
         ⭐多线程方法
         函数的说明请见 request_llms/bridge_all.py
@@ -146,21 +147,22 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
     yield from update_ui(chatbot=chatbot, history=history)
     # 开始接收回复
     try:
+        response = f"[Local Message] 等待{model_name}响应中 ..."
         for response in generate_from_baidu_qianfan(inputs, llm_kwargs, history, system_prompt):
             chatbot[-1] = (inputs, response)
             yield from update_ui(chatbot=chatbot, history=history)
+        history.extend([inputs, response])
+        yield from update_ui(chatbot=chatbot, history=history)
     except ConnectionAbortedError as e:
         from .bridge_all import model_info
         if len(history) >= 2: history[-1] = ""; history[-2] = "" # 清除当前溢出的输入：history[-2] 是本次输入, history[-1] 是本次输出
-        history = clip_history(inputs=inputs, history=history, tokenizer=model_info[llm_kwargs['llm_model']]['tokenizer'], 
+        history = clip_history(inputs=inputs, history=history, tokenizer=model_info[llm_kwargs['llm_model']]['tokenizer'],
                     max_token_limit=(model_info[llm_kwargs['llm_model']]['max_token'])) # history至少释放二分之一
         chatbot[-1] = (chatbot[-1][0], "[Local Message] Reduce the length. 本次输入过长, 或历史数据过长. 历史缓存数据已部分释放, 您可以请再次尝试. (若再次失败则更可能是因为输入过长.)")
         yield from update_ui(chatbot=chatbot, history=history, msg="异常") # 刷新界面
         return
-    
-    # 总结输出
-    response = f"[Local Message] {model_name}响应异常 ..."
-    if response == f"[Local Message] 等待{model_name}响应中 ...":
-        response = f"[Local Message] {model_name}响应异常 ..."
-    history.extend([inputs, response])
-    yield from update_ui(chatbot=chatbot, history=history)
+    except RuntimeError as e:
+        tb_str = '```\n' + trimmed_format_exc() + '```'
+        chatbot[-1] = (chatbot[-1][0], tb_str)
+        yield from update_ui(chatbot=chatbot, history=history, msg="异常") # 刷新界面
+        return

request_llms/bridge_qwen.py

@@ -5,7 +5,8 @@ from toolbox import check_packages, report_exception
 
 model_name = 'Qwen'
 
-def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="", observe_window=[], console_slience=False):
+def predict_no_ui_long_connection(inputs:str, llm_kwargs:dict, history:list=[], sys_prompt:str="",
+                                  observe_window:list=[], console_slience:bool=False):
     """
         ⭐多线程方法
         函数的说明请见 request_llms/bridge_all.py
@@ -47,10 +48,13 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
     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)
 
     # 开始接收回复
     from .com_qwenapi import QwenRequestInstance
     sri = QwenRequestInstance()
+    response = f"[Local Message] 等待{model_name}响应中 ..."
     for response in sri.generate(inputs, llm_kwargs, history, system_prompt):
         chatbot[-1] = (inputs, response)
         yield from update_ui(chatbot=chatbot, history=history)

request_llms/bridge_qwen_local.py

@@ -45,7 +45,7 @@ class GetQwenLMHandle(LocalLLMHandle):
 
         for response in self._model.chat_stream(self._tokenizer, query, history=history):
             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

request_llms/bridge_skylark2.py

@@ -9,7 +9,8 @@ def validate_key():
     if YUNQUE_SECRET_KEY == '': return False
     return True
 
-def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="", observe_window=[], console_slience=False):
+def predict_no_ui_long_connection(inputs:str, llm_kwargs:dict, history:list=[], sys_prompt:str="",
+                                  observe_window:list=[], console_slience:bool=False):
     """
         ⭐ 多线程方法
         函数的说明请见 request_llms/bridge_all.py
@@ -56,6 +57,7 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
     # 开始接收回复
     from .com_skylark2api import YUNQUERequestInstance
     sri = YUNQUERequestInstance()
+    response = f"[Local Message] 等待{model_name}响应中 ..."
     for response in sri.generate(inputs, llm_kwargs, history, system_prompt):
         chatbot[-1] = (inputs, response)
         yield from update_ui(chatbot=chatbot, history=history)

request_llms/bridge_spark.py

@@ -9,11 +9,12 @@ model_name = '星火认知大模型'
 
 def validate_key():
     XFYUN_APPID = get_conf('XFYUN_APPID')
-    if XFYUN_APPID == '00000000' or XFYUN_APPID == '': 
+    if XFYUN_APPID == '00000000' or XFYUN_APPID == '':
         return False
     return True
 
-def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="", observe_window=[], console_slience=False):
+def predict_no_ui_long_connection(inputs:str, llm_kwargs:dict, history:list=[], sys_prompt:str="",
+                                  observe_window:list=[], console_slience:bool=False):
     """
         ⭐多线程方法
         函数的说明请见 request_llms/bridge_all.py
@@ -49,9 +50,10 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
         from core_functional import handle_core_functionality
         inputs, history = handle_core_functionality(additional_fn, inputs, history, chatbot)
 
-    # 开始接收回复    
+    # 开始接收回复
     from .com_sparkapi import SparkRequestInstance
     sri = SparkRequestInstance()
+    response = f"[Local Message] 等待{model_name}响应中 ..."
     for response in sri.generate(inputs, llm_kwargs, history, system_prompt, use_image_api=True):
         chatbot[-1] = (inputs, response)
         yield from update_ui(chatbot=chatbot, history=history)

request_llms/bridge_tgui.py

@@ -76,7 +76,7 @@ async def run(context, max_token, temperature, top_p, addr, port):
                 pass
             elif content["msg"] in ["process_generating", "process_completed"]:
                 yield content["output"]["data"][0]
-                # You can search for your desired end indicator and 
+                # You can search for your desired end indicator and
                 #  stop generation by closing the websocket here
                 if (content["msg"] == "process_completed"):
                     break
@@ -117,12 +117,12 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
         async def get_result(mutable):
             # "tgui:galactica-1.3b@localhost:7860"
 
-            async for response in run(context=prompt, max_token=llm_kwargs['max_length'], 
-                                      temperature=llm_kwargs['temperature'], 
+            async for response in run(context=prompt, max_token=llm_kwargs['max_length'],
+                                      temperature=llm_kwargs['temperature'],
                                       top_p=llm_kwargs['top_p'], addr=addr, port=port):
                 print(response[len(mutable[0]):])
                 mutable[0] = response
-                if (time.time() - mutable[1]) > 3: 
+                if (time.time() - mutable[1]) > 3:
                     print('exit when no listener')
                     break
         asyncio.run(get_result(mutable))
@@ -154,12 +154,12 @@ def predict_no_ui_long_connection(inputs, llm_kwargs, history, sys_prompt, obser
 
     def run_coorotine(observe_window):
         async def get_result(observe_window):
-            async for response in run(context=prompt, max_token=llm_kwargs['max_length'], 
-                                      temperature=llm_kwargs['temperature'], 
+            async for response in run(context=prompt, max_token=llm_kwargs['max_length'],
+                                      temperature=llm_kwargs['temperature'],
                                       top_p=llm_kwargs['top_p'], addr=addr, port=port):
                 print(response[len(observe_window[0]):])
                 observe_window[0] = response
-                if (time.time() - observe_window[1]) > 5: 
+                if (time.time() - observe_window[1]) > 5:
                     print('exit when no listener')
                     break
         asyncio.run(get_result(observe_window))