version 3.47

Merge pull request #979 from fenglui/master
增加chatGLM int4配置支持小显存也可以选择chatGLM
2023-07-24 19:58:47 +08:00 · 2023-07-24 19:52:27 +08:00 · 2023-07-24 18:50:29 +08:00 · 2023-07-24 18:19:57 +08:00 · 2023-07-24 18:06:15 +08:00 · 2023-07-24 17:48:35 +08:00
36 changed files with 2218 additions and 680 deletions
--- a/.github/workflows/build-with-jittorllms.yml
+++ b/.github/workflows/build-with-jittorllms.yml
@ -1,5 +1,5 @@
 # https://docs.github.com/en/actions/publishing-packages/publishing-docker-images#publishing-images-to-github-packages
-name: Create and publish a Docker image for ChatGLM support
+name: build-with-jittorllms

 on:
  push:
--- a/README.md
+++ b/README.md
@ -5,7 +5,7 @@
 > `pip install -r requirements.txt`


-# <div align=center><img src="docs/logo.png" width="40" > GPT 学术优化 (GPT Academic)</div>
+# <div align=center><img src="docs/logo.png" width="40"> GPT 学术优化 (GPT Academic)</div>

 **如果喜欢这个项目，请给它一个Star；如果您发明了好用的快捷键或函数插件，欢迎发pull requests！**

@ -18,14 +18,14 @@ To translate this project to arbitary language with GPT, read and run [`multi_la
 >
 > 2.本项目中每个文件的功能都在自译解[`self_analysis.md`](https://github.com/binary-husky/gpt_academic/wiki/chatgpt-academic%E9%A1%B9%E7%9B%AE%E8%87%AA%E8%AF%91%E8%A7%A3%E6%8A%A5%E5%91%8A)详细说明。随着版本的迭代，您也可以随时自行点击相关函数插件，调用GPT重新生成项目的自我解析报告。常见问题汇总在[`wiki`](https://github.com/binary-husky/gpt_academic/wiki/%E5%B8%B8%E8%A7%81%E9%97%AE%E9%A2%98)当中。[安装方法](#installation)。
 > 
-> 3.本项目兼容并鼓励尝试国产大语言模型ChatGLM和Moss等等。支持多个api-key共存，可在配置文件中填写如`API_KEY="openai-key1,openai-key2,api2d-key3"`。需要临时更换`API_KEY`时，在输入区输入临时的`API_KEY`然后回车键提交后即可生效。
+> 3.本项目兼容并鼓励尝试国产大语言模型ChatGLM和Moss等等。支持多个api-key共存，可在配置文件中填写如`API_KEY="openai-key1,openai-key2,azure-key3,api2d-key4"`。需要临时更换`API_KEY`时，在输入区输入临时的`API_KEY`然后回车键提交后即可生效。


 

 <div align="center">

-功能 | 描述
+功能（⭐= 近期新增功能） | 描述
 --- | ---
 一键润色 | 支持一键润色、一键查找论文语法错误
 一键中英互译 | 一键中英互译
@ -44,12 +44,13 @@ chat分析报告生成 | [函数插件] 运行后自动生成总结汇报
 Latex论文一键校对 | [函数插件] 仿Grammarly对Latex文章进行语法、拼写纠错+输出对照PDF
 [谷歌学术统合小助手](https://www.bilibili.com/video/BV19L411U7ia) | [函数插件] 给定任意谷歌学术搜索页面URL，让gpt帮你[写relatedworks](https://www.bilibili.com/video/BV1GP411U7Az/)
 互联网信息聚合+GPT | [函数插件] 一键[让GPT从互联网获取信息](https://www.bilibili.com/video/BV1om4y127ck)回答问题，让信息永不过时
-⭐Arxiv论文精细翻译 | [函数插件] 一键[以超高质量翻译arxiv论文](https://www.bilibili.com/video/BV1dz4y1v77A/)，目前最好的论文翻译工具
+⭐Arxiv论文精细翻译 ([Docker](https://github.com/binary-husky/gpt_academic/pkgs/container/gpt_academic_with_latex)) | [函数插件] 一键[以超高质量翻译arxiv论文](https://www.bilibili.com/video/BV1dz4y1v77A/)，目前最好的论文翻译工具
+⭐[实时语音对话输入](https://github.com/binary-husky/gpt_academic/blob/master/docs/use_audio.md) | [函数插件] 异步[监听音频](https://www.bilibili.com/video/BV1AV4y187Uy/)，自动断句，自动寻找回答时机
 公式/图片/表格显示 | 可以同时显示公式的[tex形式和渲染形式](https://user-images.githubusercontent.com/96192199/230598842-1d7fcddd-815d-40ee-af60-baf488a199df.png)，支持公式、代码高亮
 多线程函数插件支持 | 支持多线调用chatgpt，一键处理[海量文本](https://www.bilibili.com/video/BV1FT411H7c5/)或程序
 启动暗色[主题](https://github.com/binary-husky/gpt_academic/issues/173) | 在浏览器url后面添加```/?__theme=dark```可以切换dark主题
 [多LLM模型](https://www.bilibili.com/video/BV1wT411p7yf)支持 | 同时被GPT3.5、GPT4、[清华ChatGLM2](https://github.com/THUDM/ChatGLM2-6B)、[复旦MOSS](https://github.com/OpenLMLab/MOSS)同时伺候的感觉一定会很不错吧？
-ChatGLM2微调模型 | 支持加载ChatGLM2微调模型，提供ChatGLM2微调插件
+⭐ChatGLM2微调模型 | 支持加载ChatGLM2微调模型，提供ChatGLM2微调辅助插件
 更多LLM模型接入，支持[huggingface部署](https://huggingface.co/spaces/qingxu98/gpt-academic) | 加入Newbing接口(新必应)，引入清华[Jittorllms](https://github.com/Jittor/JittorLLMs)支持[LLaMA](https://github.com/facebookresearch/llama)和[盘古α](https://openi.org.cn/pangu/)
 更多新功能展示 (图像生成等) …… | 见本文档结尾处 ……

@ -92,7 +93,7 @@ ChatGLM2微调模型 | 支持加载ChatGLM2微调模型，提供ChatGLM2微调

 1. 下载项目
 ```sh
-git clone https://github.com/binary-husky/gpt_academic.git
+git clone --depth=1 https://github.com/binary-husky/gpt_academic.git
 cd gpt_academic
 ```

@ -125,7 +126,7 @@ python -m pip install -r request_llm/requirements_chatglm.txt

 # 【可选步骤II】支持复旦MOSS
 python -m pip install -r request_llm/requirements_moss.txt
-git clone https://github.com/OpenLMLab/MOSS.git request_llm/moss  # 注意执行此行代码时，必须处于项目根路径
+git clone --depth=1 https://github.com/OpenLMLab/MOSS.git request_llm/moss  # 注意执行此行代码时，必须处于项目根路径

 # 【可选步骤III】确保config.py配置文件的AVAIL_LLM_MODELS包含了期望的模型，目前支持的全部模型如下(jittorllms系列目前仅支持docker方案)：
 AVAIL_LLM_MODELS = ["gpt-3.5-turbo", "api2d-gpt-3.5-turbo", "gpt-4", "api2d-gpt-4", "chatglm", "newbing", "moss"] # + ["jittorllms_rwkv", "jittorllms_pangualpha", "jittorllms_llama"]
@ -145,10 +146,10 @@ python main.py

 1. 仅ChatGPT（推荐大多数人选择，等价于docker-compose方案1）
 [![basic](https://github.com/binary-husky/gpt_academic/actions/workflows/build-without-local-llms.yml/badge.svg?branch=master)](https://github.com/binary-husky/gpt_academic/actions/workflows/build-without-local-llms.yml)
-[![basic](https://github.com/binary-husky/gpt_academic/actions/workflows/build-with-latex.yml/badge.svg?branch=master)](https://github.com/binary-husky/gpt_academic/actions/workflows/build-with-latex.yml)
+[![basiclatex](https://github.com/binary-husky/gpt_academic/actions/workflows/build-with-latex.yml/badge.svg?branch=master)](https://github.com/binary-husky/gpt_academic/actions/workflows/build-with-latex.yml)

 ``` sh
-git clone https://github.com/binary-husky/gpt_academic.git  # 下载项目
+git clone --depth=1 https://github.com/binary-husky/gpt_academic.git  # 下载项目
 cd gpt_academic                                 # 进入路径
 nano config.py                                      # 用任意文本编辑器编辑config.py, 配置 “Proxy”， “API_KEY” 以及 “WEB_PORT” (例如50923) 等
 docker build -t gpt-academic .                      # 安装
@ -169,6 +170,8 @@ docker-compose up
 ```

 3. ChatGPT + LLAMA + 盘古 + RWKV（需要熟悉Docker）
+[![jittorllms](https://github.com/binary-husky/gpt_academic/actions/workflows/build-with-jittorllms.yml/badge.svg?branch=master)](https://github.com/binary-husky/gpt_academic/actions/workflows/build-with-jittorllms.yml)
+
 ``` sh
 # 修改docker-compose.yml，保留方案3并删除其他方案。修改docker-compose.yml中方案3的配置，参考其中注释即可
 docker-compose up
@ -287,6 +290,7 @@ Tip：不指定文件直接点击 `载入对话历史存档` 可以查看历史h

 ### II：版本:
 - version 3.5(Todo): 使用自然语言调用本项目的所有函数插件（高优先级）
+- version 3.46: 支持完全脱手操作的实时语音对话
 - version 3.45: 支持自定义ChatGLM2微调模型
 - version 3.44: 正式支持Azure，优化界面易用性
 - version 3.4: +arxiv论文翻译、latex论文批改功能
@ -310,7 +314,7 @@ gpt_academic开发者QQ群-2：610599535
    - 官方Gradio目前有很多兼容性Bug，请务必使用`requirement.txt`安装Gradio

 ### III：主题
-
+可以通过修改`THEME`选项（config.py）变更主题
 1. `Chuanhu-Small-and-Beautiful` [网址](https://github.com/GaiZhenbiao/ChuanhuChatGPT/)


--- a/check_proxy.py
+++ b/check_proxy.py
@ -117,7 +117,7 @@ def auto_update(raise_error=False):
        with open('./version', 'r', encoding='utf8') as f:
            current_version = f.read()
            current_version = json.loads(current_version)['version']
-        if (remote_version - current_version) >= 0.01:
+        if (remote_version - current_version) >= 0.01-1e-5:
            from colorful import print亮黄
            print亮黄(
                f'\n新版本可用。新版本:{remote_version}，当前版本:{current_version}。{new_feature}')
--- a/config.py
+++ b/config.py
@ -32,9 +32,9 @@ else:

 # ------------------------------------ 以下配置可以优化体验, 但大部分场合下并不需要修改 ------------------------------------

-# 重新URL重新定向，实现更换API_URL的作用（常规情况下，不要修改!! 高危设置！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"} 
-# 例如 API_URL_REDIRECT = {"https://api.openai.com/v1/chat/completions":"https://reverse-proxy-url/v1/chat/completions"}
+# 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"}
 API_URL_REDIRECT = {}


@ -71,7 +71,7 @@ MAX_RETRY = 2
 # 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" # 可选 ↓↓↓
 AVAIL_LLM_MODELS = ["gpt-3.5-turbo-16k", "gpt-3.5-turbo", "azure-gpt-3.5", "api2d-gpt-3.5-turbo", "gpt-4", "api2d-gpt-4", "chatglm", "moss", "newbing", "stack-claude"]
-# P.S. 其他可用的模型还包括 ["gpt-3.5-turbo-0613", "gpt-3.5-turbo-16k-0613", "newbing-free", "jittorllms_rwkv", "jittorllms_pangualpha", "jittorllms_llama"]
+# P.S. 其他可用的模型还包括 ["gpt-3.5-turbo-0613", "gpt-3.5-turbo-16k-0613", "claude-1-100k", "claude-2", "internlm", "jittorllms_rwkv", "jittorllms_pangualpha", "jittorllms_llama"]


 # ChatGLM(2) Finetune Model Path （如果使用ChatGLM2微调模型，需要把"chatglmft"加入AVAIL_LLM_MODELS中）
@ -80,6 +80,7 @@ ChatGLM_PTUNING_CHECKPOINT = "" # 例如"/home/hmp/ChatGLM2-6B/ptuning/output/6b

 # 本地LLM模型如ChatGLM的执行方式 CPU/GPU
 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）
@ -89,9 +90,11 @@ CONCURRENT_COUNT = 100
 # 是否在提交时自动清空输入框
 AUTO_CLEAR_TXT = False

+
 # 色彩主体，可选 ["Default", "Chuanhu-Small-and-Beautiful"]
 THEME = "Default"

+
 # 加一个live2d装饰
 ADD_WAIFU = False

@ -127,7 +130,15 @@ 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://help.aliyun.com/document_detail/450255.html
+# 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
 ENABLE_AUDIO = False
 ALIYUN_TOKEN=""    # 例如 f37f30e0f9934c34a992f6f64f7eba4f
-ALIYUN_APPKEY=""   # 例如 RoPlZrM88DnAFkZK
+ALIYUN_APPKEY=""   # 例如 RoPlZrM88DnAFkZK
+
+
+# Claude API KEY
+ANTHROPIC_API_KEY = ""
+
+
+# 自定义API KEY格式
+CUSTOM_API_KEY_PATTERN = ""
--- a/crazy_functions/Latex输出PDF结果.py
+++ b/crazy_functions/Latex输出PDF结果.py
@ -157,7 +157,7 @@ def Latex英文纠错加PDF对比(txt, llm_kwargs, plugin_kwargs, chatbot, histo
    try:
        import glob, os, time, subprocess
        subprocess.Popen(['pdflatex', '-version'])
-        from .latex_utils import Latex精细分解与转化, 编译Latex
+        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"])
@ -234,7 +234,7 @@ def Latex翻译中文并重新编译PDF(txt, llm_kwargs, plugin_kwargs, chatbot,
    try:
        import glob, os, time, subprocess
        subprocess.Popen(['pdflatex', '-version'])
-        from .latex_utils import Latex精细分解与转化, 编译Latex
+        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"])
--- a/crazy_functions/crazy_functions_test.py
+++ b/crazy_functions/crazy_functions_test.py
@ -195,9 +195,12 @@ def test_Latex():
    # txt = r"https://arxiv.org/abs/2303.08774"
    # txt = r"https://arxiv.org/abs/2303.12712"
    # txt = r"C:\Users\fuqingxu\arxiv_cache\2303.12712\workfolder"
-    txt = r"2306.17157" # 这个paper有个input命令文件名大小写错误！
-    
-
+    # txt = r"2306.17157" # 这个paper有个input命令文件名大小写错误！
+    # txt = "https://arxiv.org/abs/2205.14135"
+    # txt = r"C:\Users\fuqingxu\arxiv_cache\2205.14135\workfolder"
+    # txt = r"C:\Users\fuqingxu\arxiv_cache\2205.14135\workfolder"
+    txt = r"2210.03629"
+    txt = r"2307.04964"
    for cookies, cb, hist, msg in (Latex翻译中文并重新编译PDF)(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
        cli_printer.print(cb)   #  print(cb)

@ -240,7 +243,7 @@ if __name__ == "__main__":
    # test_数学动画生成manim()
    # test_Langchain知识库()
    # test_Langchain知识库读取()
-    # test_Latex()
-    test_chatglm_finetune()
+    test_Latex()
+    # test_chatglm_finetune()
    input("程序完成，回车退出。")
    print("退出。")
--- a/crazy_functions/latex_fns/latex_actions.py
+++ b/crazy_functions/latex_fns/latex_actions.py
@ -1,320 +1,16 @@
 from toolbox import update_ui, update_ui_lastest_msg    # 刷新Gradio前端界面
 from toolbox import zip_folder, objdump, objload, 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
+
 import os, shutil
 import re
 import numpy as np
+
 pj = os.path.join

-"""
-========================================================================
-Part One
-Latex segmentation with a binary mask (PRESERVE=0, TRANSFORM=1)
-========================================================================
-"""
-PRESERVE = 0
-TRANSFORM = 1
-
-def set_forbidden_text(text, mask, pattern, flags=0):
-    """
-    Add a preserve text area in this paper
-    e.g. with pattern = r"\\begin\{algorithm\}(.*?)\\end\{algorithm\}"
-    you can mask out (mask = PRESERVE so that text become untouchable for GPT) 
-    everything between "\begin{equation}" and "\end{equation}"
-    """
-    if isinstance(pattern, list): pattern = '|'.join(pattern)
-    pattern_compile = re.compile(pattern, flags)
-    for res in pattern_compile.finditer(text):
-        mask[res.span()[0]:res.span()[1]] = PRESERVE
-    return text, mask
-
-def reverse_forbidden_text(text, mask, pattern, flags=0, forbid_wrapper=True):
-    """
-    Move area out of preserve area (make text editable for GPT)
-    count the number of the braces so as to catch compelete text area. 
-    e.g.
-    \begin{abstract} blablablablablabla. \end{abstract} 
-    """
-    if isinstance(pattern, list): pattern = '|'.join(pattern)
-    pattern_compile = re.compile(pattern, flags)
-    for res in pattern_compile.finditer(text):
-        if not forbid_wrapper:
-            mask[res.span()[0]:res.span()[1]] = TRANSFORM
-        else:
-            mask[res.regs[0][0]: res.regs[1][0]] = PRESERVE   # '\\begin{abstract}'
-            mask[res.regs[1][0]: res.regs[1][1]] = TRANSFORM   # abstract
-            mask[res.regs[1][1]: res.regs[0][1]] = PRESERVE   # abstract
-    return text, mask
-
-def set_forbidden_text_careful_brace(text, mask, pattern, flags=0):
-    """
-    Add a preserve text area in this paper (text become untouchable for GPT).
-    count the number of the braces so as to catch compelete text area. 
-    e.g.
-    \caption{blablablablabla\texbf{blablabla}blablabla.} 
-    """
-    pattern_compile = re.compile(pattern, flags)
-    for res in pattern_compile.finditer(text):
-        brace_level = -1
-        p = begin = end = res.regs[0][0]
-        for _ in range(1024*16):
-            if text[p] == '}' and brace_level == 0: break
-            elif text[p] == '}':  brace_level -= 1
-            elif text[p] == '{':  brace_level += 1
-            p += 1
-        end = p+1
-        mask[begin:end] = PRESERVE
-    return text, mask
-
-def reverse_forbidden_text_careful_brace(text, mask, pattern, flags=0, forbid_wrapper=True):
-    """
-    Move area out of preserve area (make text editable for GPT)
-    count the number of the braces so as to catch compelete text area. 
-    e.g.
-    \caption{blablablablabla\texbf{blablabla}blablabla.} 
-    """
-    pattern_compile = re.compile(pattern, flags)
-    for res in pattern_compile.finditer(text):
-        brace_level = 0
-        p = begin = end = res.regs[1][0]
-        for _ in range(1024*16):
-            if text[p] == '}' and brace_level == 0: break
-            elif text[p] == '}':  brace_level -= 1
-            elif text[p] == '{':  brace_level += 1
-            p += 1
-        end = p
-        mask[begin:end] = TRANSFORM
-        if forbid_wrapper:
-            mask[res.regs[0][0]:begin] = PRESERVE
-            mask[end:res.regs[0][1]] = PRESERVE
-    return text, mask
-
-def set_forbidden_text_begin_end(text, mask, pattern, flags=0, limit_n_lines=42):
-    """
-    Find all \begin{} ... \end{} text block that with less than limit_n_lines lines.
-    Add it to preserve area
-    """
-    pattern_compile = re.compile(pattern, flags)
-    def search_with_line_limit(text, mask):
-        for res in pattern_compile.finditer(text):
-            cmd = res.group(1)  # begin{what}
-            this = res.group(2) # content between begin and end
-            this_mask = mask[res.regs[2][0]:res.regs[2][1]]
-            white_list = ['document', 'abstract', 'lemma', 'definition', 'sproof', 
-                          'em', 'emph', 'textit', 'textbf', 'itemize', 'enumerate']
-            if (cmd in white_list) or this.count('\n') >= limit_n_lines: # use a magical number 42
-                this, this_mask = search_with_line_limit(this, this_mask)
-                mask[res.regs[2][0]:res.regs[2][1]] = this_mask
-            else:
-                mask[res.regs[0][0]:res.regs[0][1]] = PRESERVE
-        return text, mask
-    return search_with_line_limit(text, mask) 
-
-class LinkedListNode():
-    """
-    Linked List Node
-    """
-    def __init__(self, string, preserve=True) -> None:
-        self.string = string
-        self.preserve = preserve
-        self.next = None
-        # self.begin_line = 0
-        # self.begin_char = 0
-
-def convert_to_linklist(text, mask):
-    root = LinkedListNode("", preserve=True)
-    current_node = root
-    for c, m, i in zip(text, mask, range(len(text))):
-        if (m==PRESERVE and current_node.preserve) \
-            or (m==TRANSFORM and not current_node.preserve):
-            # add
-            current_node.string += c
-        else:
-            current_node.next = LinkedListNode(c, preserve=(m==PRESERVE))
-            current_node = current_node.next
-    return root
-"""
-========================================================================
-Latex Merge File
-========================================================================
-"""
-
-def 寻找Latex主文件(file_manifest, mode):
-    """
-    在多Tex文档中，寻找主文件，必须包含documentclass，返回找到的第一个。
-    P.S. 但愿没人把latex模板放在里面传进来 (6.25 加入判定latex模板的代码)
-    """
-    canidates = []
-    for texf in file_manifest:
-        if os.path.basename(texf).startswith('merge'):
-            continue
-        with open(texf, 'r', encoding='utf8') as f:
-            file_content = f.read()
-        if r'\documentclass' in file_content:
-            canidates.append(texf)
-        else:
-            continue
-
-    if len(canidates) == 0:
-        raise RuntimeError('无法找到一个主Tex文件（包含documentclass关键字）')
-    elif len(canidates) == 1:
-        return canidates[0]
-    else: # if len(canidates) >= 2 通过一些Latex模板中常见（但通常不会出现在正文）的单词，对不同latex源文件扣分，取评分最高者返回
-        canidates_score = []
-        # 给出一些判定模板文档的词作为扣分项
-        unexpected_words = ['\LaTeX', 'manuscript', 'Guidelines', 'font', 'citations', 'rejected', 'blind review', 'reviewers']
-        expected_words = ['\input', '\ref', '\cite']
-        for texf in canidates:
-            canidates_score.append(0)
-            with open(texf, 'r', encoding='utf8') as f:
-                file_content = f.read()
-            for uw in unexpected_words:
-                if uw in file_content:
-                    canidates_score[-1] -= 1
-            for uw in expected_words:
-                if uw in file_content:
-                    canidates_score[-1] += 1
-        select = np.argmax(canidates_score) # 取评分最高者返回
-        return canidates[select]
-    
-def rm_comments(main_file):
-    new_file_remove_comment_lines = []
-    for l in main_file.splitlines():
-        # 删除整行的空注释
-        if l.lstrip().startswith("%"):
-            pass
-        else:
-            new_file_remove_comment_lines.append(l)
-    main_file = '\n'.join(new_file_remove_comment_lines)
-    # main_file = re.sub(r"\\include{(.*?)}", r"\\input{\1}", main_file)  # 将 \include 命令转换为 \input 命令
-    main_file = re.sub(r'(?<!\\)%.*', '', main_file)  # 使用正则表达式查找半行注释, 并替换为空字符串
-    return main_file
-
-def find_tex_file_ignore_case(fp):
-    dir_name = os.path.dirname(fp)
-    base_name = os.path.basename(fp)
-    if not base_name.endswith('.tex'): base_name+='.tex'
-    if os.path.exists(pj(dir_name, base_name)): return pj(dir_name, base_name)
-    # go case in-sensitive
-    import glob
-    for f in glob.glob(dir_name+'/*.tex'):
-        base_name_s = os.path.basename(fp)
-        if base_name_s.lower() == base_name.lower(): return f
-    return None
-
-def merge_tex_files_(project_foler, main_file, mode):
-    """
-    Merge Tex project recrusively
-    """
-    main_file = rm_comments(main_file)
-    for s in reversed([q for q in re.finditer(r"\\input\{(.*?)\}", main_file, re.M)]):
-        f = s.group(1)
-        fp = os.path.join(project_foler, f)
-        fp = find_tex_file_ignore_case(fp)
-        if fp:
-            with open(fp, 'r', encoding='utf-8', errors='replace') as fx: c = fx.read()
-        else:
-            raise RuntimeError(f'找不到{fp}，Tex源文件缺失！')
-        c = merge_tex_files_(project_foler, c, mode)
-        main_file = main_file[:s.span()[0]] + c + main_file[s.span()[1]:]
-    return main_file
-
-def merge_tex_files(project_foler, main_file, mode):
-    """
-    Merge Tex project recrusively
-    P.S. 顺便把CTEX塞进去以支持中文
-    P.S. 顺便把Latex的注释去除
-    """
-    main_file = merge_tex_files_(project_foler, main_file, mode)
-    main_file = rm_comments(main_file)
-
-    if mode == 'translate_zh':
-        # find paper documentclass
-        pattern = re.compile(r'\\documentclass.*\n')
-        match = pattern.search(main_file)
-        assert match is not None, "Cannot find documentclass statement!"
-        position = match.end()
-        add_ctex = '\\usepackage{ctex}\n'
-        add_url = '\\usepackage{url}\n' if '{url}' not in main_file else ''
-        main_file = main_file[:position] + add_ctex + add_url + main_file[position:]
-        # fontset=windows
-        import platform
-        main_file = re.sub(r"\\documentclass\[(.*?)\]{(.*?)}", r"\\documentclass[\1,fontset=windows,UTF8]{\2}",main_file)
-        main_file = re.sub(r"\\documentclass{(.*?)}", r"\\documentclass[fontset=windows,UTF8]{\1}",main_file)
-        # find paper abstract
-        pattern_opt1 = re.compile(r'\\begin\{abstract\}.*\n')
-        pattern_opt2 = re.compile(r"\\abstract\{(.*?)\}", flags=re.DOTALL)
-        match_opt1 = pattern_opt1.search(main_file)
-        match_opt2 = pattern_opt2.search(main_file)
-        assert (match_opt1 is not None) or (match_opt2 is not None), "Cannot find paper abstract section!"
-    return main_file
-
-
-
-"""
-========================================================================
-Post process
-========================================================================
-"""
-def mod_inbraket(match):
-    """
-    为啥chatgpt会把cite里面的逗号换成中文逗号呀 
-    """
-    # get the matched string
-    cmd = match.group(1)
-    str_to_modify = match.group(2)
-    # modify the matched string
-    str_to_modify = str_to_modify.replace('：', ':')    # 前面是中文冒号，后面是英文冒号
-    str_to_modify = str_to_modify.replace('，', ',')    # 前面是中文逗号，后面是英文逗号
-    # str_to_modify = 'BOOM'
-    return "\\" + cmd + "{" + str_to_modify + "}"
-
-def fix_content(final_tex, node_string):
-    """
-    Fix common GPT errors to increase success rate
-    """
-    final_tex = re.sub(r"(?<!\\)%", "\\%", final_tex)
-    final_tex = re.sub(r"\\([a-z]{2,10})\ \{", r"\\\1{", string=final_tex)
-    final_tex = re.sub(r"\\\ ([a-z]{2,10})\{", r"\\\1{", string=final_tex)
-    final_tex = re.sub(r"\\([a-z]{2,10})\{([^\}]*?)\}", mod_inbraket, string=final_tex)
-
-    if "Traceback" in final_tex and "[Local Message]" in final_tex:
-        final_tex = node_string # 出问题了，还原原文
-    if node_string.count('\\begin') != final_tex.count('\\begin'):
-        final_tex = node_string # 出问题了，还原原文
-    if node_string.count('\_') > 0 and node_string.count('\_') > final_tex.count('\_'):
-        # walk and replace any _ without \
-        final_tex = re.sub(r"(?<!\\)_", "\\_", final_tex)
-
-    def compute_brace_level(string):
-        # this function count the number of { and }
-        brace_level = 0
-        for c in string:
-            if c == "{": brace_level += 1
-            elif c == "}": brace_level -= 1
-        return brace_level
-    def join_most(tex_t, tex_o):
-        # this function join translated string and original string when something goes wrong
-        p_t = 0
-        p_o = 0
-        def find_next(string, chars, begin):
-            p = begin
-            while p < len(string):
-                if string[p] in chars: return p, string[p]
-                p += 1
-            return None, None
-        while True:
-            res1, char = find_next(tex_o, ['{','}'], p_o)
-            if res1 is None: break
-            res2, char = find_next(tex_t, [char], p_t)
-            if res2 is None: break
-            p_o = res1 + 1
-            p_t = res2 + 1
-        return tex_t[:p_t] + tex_o[p_o:]
-
-    if compute_brace_level(final_tex) != compute_brace_level(node_string):
-        # 出问题了，还原部分原文，保证括号正确
-        final_tex = join_most(final_tex, node_string)
-    return final_tex

 def split_subprocess(txt, project_folder, return_dict, opts):
    """
@ -326,7 +22,8 @@ def split_subprocess(txt, project_folder, return_dict, opts):
    mask = np.zeros(len(txt), dtype=np.uint8) + TRANSFORM

    # 吸收title与作者以上的部分
-    text, mask = set_forbidden_text(text, mask, r"(.*?)\\maketitle", re.DOTALL)
+    text, mask = set_forbidden_text(text, mask, r"^(.*?)\\maketitle", re.DOTALL)
+    text, mask = set_forbidden_text(text, mask, r"^(.*?)\\begin{document}", re.DOTALL)
    # 吸收iffalse注释
    text, mask = set_forbidden_text(text, mask, r"\\iffalse(.*?)\\fi", re.DOTALL)
    # 吸收在42行以内的begin-end组合
@ -356,77 +53,9 @@ def split_subprocess(txt, project_folder, return_dict, opts):
    text, mask = reverse_forbidden_text(text, mask, r"\\begin\{abstract\}(.*?)\\end\{abstract\}", re.DOTALL, forbid_wrapper=True)
    root = convert_to_linklist(text, mask)

-    # 修复括号
-    node = root
-    while True:
-        string = node.string
-        if node.preserve: 
-            node = node.next
-            if node is None: break
-            continue
-        def break_check(string):
-            str_stack = [""] # (lv, index)
-            for i, c in enumerate(string):
-                if c == '{':
-                    str_stack.append('{')
-                elif c == '}':
-                    if len(str_stack) == 1:
-                        print('stack fix')
-                        return i
-                    str_stack.pop(-1)
-                else:
-                    str_stack[-1] += c
-            return -1
-        bp = break_check(string)
+    # 最后一步处理，增强稳健性
+    root = post_process(root)

-        if bp == -1:
-            pass
-        elif bp == 0:
-            node.string = string[:1]
-            q = LinkedListNode(string[1:], False)
-            q.next = node.next
-            node.next = q
-        else:
-            node.string = string[:bp]
-            q = LinkedListNode(string[bp:], False)
-            q.next = node.next
-            node.next = q
-
-        node = node.next
-        if node is None: break
-
-    # 屏蔽空行和太短的句子
-    node = root
-    while True:
-        if len(node.string.strip('\n').strip(''))==0: node.preserve = True
-        if len(node.string.strip('\n').strip(''))<42: node.preserve = True
-        node = node.next
-        if node is None: break
-    node = root
-    while True:
-        if node.next and node.preserve and node.next.preserve:
-            node.string += node.next.string
-            node.next = node.next.next
-        node = node.next
-        if node is None: break
-
-    # 将前后断行符脱离
-    node = root
-    prev_node = None
-    while True:
-        if not node.preserve:
-            lstriped_ = node.string.lstrip().lstrip('\n')
-            if (prev_node is not None) and (prev_node.preserve) and (len(lstriped_)!=len(node.string)):
-                prev_node.string += node.string[:-len(lstriped_)]
-                node.string = lstriped_
-            rstriped_ = node.string.rstrip().rstrip('\n')
-            if (node.next is not None) and (node.next.preserve) and (len(rstriped_)!=len(node.string)):
-                node.next.string = node.string[len(rstriped_):] + node.next.string
-                node.string = rstriped_
-        # =====
-        prev_node = node
-        node = node.next
-        if node is None: break
    # 输出html调试文件，用红色标注处保留区（PRESERVE），用黑色标注转换区（TRANSFORM）
    with open(pj(project_folder, 'debug_log.html'), 'w', encoding='utf8') as f:
        segment_parts_for_gpt = []
@ -437,7 +66,7 @@ def split_subprocess(txt, project_folder, return_dict, opts):
            show_html = node.string.replace('\n','<br/>')
            if not node.preserve:
                segment_parts_for_gpt.append(node.string)
-                f.write(f'<p style="color:black;">#{show_html}#</p>')
+                f.write(f'<p style="color:black;">#{node.range}{show_html}#</p>')
            else:
                f.write(f'<p style="color:red;">{show_html}</p>')
            node = node.next
@ -448,8 +77,6 @@ def split_subprocess(txt, project_folder, return_dict, opts):
    return_dict['segment_parts_for_gpt'] = segment_parts_for_gpt
    return return_dict

-
-
 class LatexPaperSplit():
    """
    break down latex file to a linked list,
@ -464,18 +91,32 @@ class LatexPaperSplit():
        # 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。}}\\\\" 

-    def merge_result(self, arr, mode, msg):
+
+    def merge_result(self, arr, mode, msg, buggy_lines=[], buggy_line_surgery_n_lines=10):
        """
        Merge the result after the GPT process completed
        """
        result_string = ""
-        p = 0
+        node_cnt = 0
+        line_cnt = 0
+        
        for node in self.nodes:
            if node.preserve:
+                line_cnt += node.string.count('\n')
                result_string += node.string
            else:
-                result_string += fix_content(arr[p], node.string)
-                p += 1
+                translated_txt = fix_content(arr[node_cnt], node.string)
+                begin_line = line_cnt
+                end_line = line_cnt + translated_txt.count('\n')
+
+                # reverse translation if any error
+                if any([begin_line-buggy_line_surgery_n_lines <= b_line <= end_line+buggy_line_surgery_n_lines for b_line in buggy_lines]):
+                    translated_txt = node.string
+
+                result_string += translated_txt
+                node_cnt += 1
+                line_cnt += translated_txt.count('\n')
+
        if mode == 'translate_zh':
            pattern = re.compile(r'\\begin\{abstract\}.*\n')
            match = pattern.search(result_string)
@ -490,6 +131,7 @@ class LatexPaperSplit():
            result_string = result_string[:position] + self.msg + msg + self.msg_declare + result_string[position:]
        return result_string

+
    def split(self, txt, project_folder, opts): 
        """
        break down latex file to a linked list,
@ -511,7 +153,6 @@ class LatexPaperSplit():
        return self.sp


-
 class LatexPaperFileGroup():
    """
    use tokenizer to break down text according to max_token_limit
@ -539,7 +180,7 @@ class LatexPaperFileGroup():
                self.sp_file_index.append(index)
                self.sp_file_tag.append(self.file_paths[index])
            else:
-                from .crazy_utils import breakdown_txt_to_satisfy_token_limit_for_pdf
+                from ..crazy_utils import breakdown_txt_to_satisfy_token_limit_for_pdf
                segments = breakdown_txt_to_satisfy_token_limit_for_pdf(file_content, self.get_token_num, max_token_limit)
                for j, segment in enumerate(segments):
                    self.sp_file_contents.append(segment)
@ -560,41 +201,14 @@ class LatexPaperFileGroup():
                f.write(res)
        return manifest

-def write_html(sp_file_contents, sp_file_result, chatbot, project_folder):
-
-    # write html
-    try:
-        import shutil
-        from .crazy_utils import construct_html
-        from toolbox import gen_time_str
-        ch = construct_html() 
-        orig = ""
-        trans = ""
-        final = []
-        for c,r in zip(sp_file_contents, sp_file_result): 
-            final.append(c)
-            final.append(r)
-        for i, k in enumerate(final): 
-            if i%2==0:
-                orig = k
-            if i%2==1:
-                trans = k
-                ch.add_row(a=orig, b=trans)
-        create_report_file_name = f"{gen_time_str()}.trans.html"
-        ch.save_file(create_report_file_name)
-        shutil.copyfile(pj('./gpt_log/', create_report_file_name), pj(project_folder, create_report_file_name))
-        promote_file_to_downloadzone(file=f'./gpt_log/{create_report_file_name}', chatbot=chatbot)
-    except:
-        from toolbox import trimmed_format_exc
-        print('writing html result failed:', trimmed_format_exc())

 def Latex精细分解与转化(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, mode='proofread', switch_prompt=None, opts=[]):
    import time, os, re
-    from .crazy_utils import request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency
-    from .latex_utils import LatexPaperFileGroup, merge_tex_files, LatexPaperSplit, 寻找Latex主文件
+    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 ----------> 
-    maintex = 寻找Latex主文件(file_manifest, mode)
+    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)
@ -668,54 +282,51 @@ def Latex精细分解与转化(file_manifest, project_folder, llm_kwargs, plugin
    #  <-------- 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 ----------> 
-    chatbot.append((f"完成了吗？", 'GPT结果已输出, 正在编译PDF'))
+    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 ----------> 
    return project_folder + f'/merge_{mode}.tex'


-
-def remove_buggy_lines(file_path, log_path, tex_name, tex_name_pure, n_fix, work_folder_modified):
+def remove_buggy_lines(file_path, log_path, tex_name, tex_name_pure, n_fix, work_folder_modified, fixed_line=[]):
    try:
        with open(log_path, 'r', encoding='utf-8', errors='replace') as f:
            log = f.read()
-        with open(file_path, 'r', encoding='utf-8', errors='replace') as f:
-            file_lines = f.readlines()
        import re
        buggy_lines = re.findall(tex_name+':([0-9]{1,5}):', log)
        buggy_lines = [int(l) for l in buggy_lines]
        buggy_lines = sorted(buggy_lines)
-        print("removing lines that has errors", buggy_lines)
-        file_lines.pop(buggy_lines[0]-1)
+        buggy_line = buggy_lines[0]-1
+        print("reversing tex line that has errors", buggy_line)
+
+        # 重组，逆转出错的段落
+        if buggy_line not in fixed_line:
+            fixed_line.append(buggy_line)
+
+        lps, file_result, mode, msg = objload(file=pj(work_folder_modified,'merge_result.pkl'))
+        final_tex = lps.merge_result(file_result, mode, msg, buggy_lines=fixed_line, buggy_line_surgery_n_lines=5*n_fix)
+
        with open(pj(work_folder_modified, f"{tex_name_pure}_fix_{n_fix}.tex"), 'w', encoding='utf-8', errors='replace') as f:
-            f.writelines(file_lines)
+            f.write(final_tex)
+
        return True, f"{tex_name_pure}_fix_{n_fix}", buggy_lines
    except:
        print("Fatal error occurred, but we cannot identify error, please download zip, read latex log, and compile manually.")
        return False, -1, [-1]
-    
-def compile_latex_with_timeout(command, cwd, timeout=60):
-    import subprocess
-    process = subprocess.Popen(command, shell=True, stdout=subprocess.PIPE, stderr=subprocess.PIPE, cwd=cwd)
-    try:
-        stdout, stderr = process.communicate(timeout=timeout)
-    except subprocess.TimeoutExpired:
-        process.kill()
-        stdout, stderr = process.communicate()
-        print("Process timed out!")
-        return False
-    return True
+

 def 编译Latex(chatbot, history, main_file_original, main_file_modified, work_folder_original, work_folder_modified, work_folder, mode='default'):
    import os, time
-    current_dir = os.getcwd()
    n_fix = 1
+    fixed_line = []
    max_try = 32
    chatbot.append([f"正在编译PDF文档", f'编译已经开始。当前工作路径为{work_folder}，如果程序停顿5分钟以上，请直接去该路径下取回翻译结果，或者重启之后再度尝试 ...']); yield from update_ui(chatbot=chatbot, history=history)
    chatbot.append([f"正在编译PDF文档", '...']); yield from update_ui(chatbot=chatbot, history=history); time.sleep(1); chatbot[-1] = list(chatbot[-1]) # 刷新界面
@ -723,6 +334,10 @@ def 编译Latex(chatbot, history, main_file_original, main_file_modified, work_f

    while True:
        import os
+        may_exist_bbl = pj(work_folder_modified, f'merge.bbl')
+        target_bbl = pj(work_folder_modified, f'{main_file_modified}.bbl')
+        if os.path.exists(may_exist_bbl) and not os.path.exists(target_bbl):
+            shutil.copyfile(may_exist_bbl, target_bbl)

        # https://stackoverflow.com/questions/738755/dont-make-me-manually-abort-a-latex-compile-when-theres-an-error
        yield from update_ui_lastest_msg(f'尝试第 {n_fix}/{max_try} 次编译, 编译原始PDF ...', chatbot, history)   # 刷新Gradio前端界面
@ -756,7 +371,6 @@ def 编译Latex(chatbot, history, main_file_original, main_file_modified, work_f
                ok = compile_latex_with_timeout(f'pdflatex  -interaction=batchmode -file-line-error merge_diff.tex', work_folder)
                ok = compile_latex_with_timeout(f'pdflatex  -interaction=batchmode -file-line-error merge_diff.tex', work_folder)

-
        # <---------- 检查结果 ----------->
        results_ = ""
        original_pdf_success = os.path.exists(pj(work_folder_original, f'{main_file_original}.pdf'))
@ -773,9 +387,19 @@ def 编译Latex(chatbot, history, main_file_original, main_file_modified, work_f
        if modified_pdf_success:
            yield from update_ui_lastest_msg(f'转化PDF编译已经成功, 即将退出 ...', chatbot, history)    # 刷新Gradio前端界面
            result_pdf = pj(work_folder_modified, f'{main_file_modified}.pdf') # get pdf path
+            origin_pdf = pj(work_folder_original, f'{main_file_original}.pdf') # get pdf path
            if os.path.exists(pj(work_folder, '..', 'translation')):
                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: 
+                try:
+                    from .latex_toolbox import merge_pdfs
+                    concat_pdf = pj(work_folder_modified, f'comparison.pdf')
+                    merge_pdfs(origin_pdf, result_pdf, concat_pdf)
+                    promote_file_to_downloadzone(concat_pdf, rename_file=None, chatbot=chatbot)  # promote file to web UI
+                except Exception as e:
+                    pass
            return True # 成功啦
        else:
            if n_fix>=max_try: break
@ -787,6 +411,7 @@ def 编译Latex(chatbot, history, main_file_original, main_file_modified, work_f
                tex_name_pure=f'{main_file_modified}',
                n_fix=n_fix,
                work_folder_modified=work_folder_modified,
+                fixed_line=fixed_line
            )
            yield from update_ui_lastest_msg(f'由于最为关键的转化PDF编译失败, 将根据报错信息修正tex源文件并重试, 当前报错的latex代码处于第{buggy_lines}行 ...', chatbot, history)   # 刷新Gradio前端界面
            if not can_retry: break
@ -794,4 +419,29 @@ def 编译Latex(chatbot, history, main_file_original, main_file_modified, work_f
    return False # 失败啦


-
+def write_html(sp_file_contents, sp_file_result, chatbot, project_folder):
+    # write html
+    try:
+        import shutil
+        from ..crazy_utils import construct_html
+        from toolbox import gen_time_str
+        ch = construct_html() 
+        orig = ""
+        trans = ""
+        final = []
+        for c,r in zip(sp_file_contents, sp_file_result): 
+            final.append(c)
+            final.append(r)
+        for i, k in enumerate(final): 
+            if i%2==0:
+                orig = k
+            if i%2==1:
+                trans = k
+                ch.add_row(a=orig, b=trans)
+        create_report_file_name = f"{gen_time_str()}.trans.html"
+        ch.save_file(create_report_file_name)
+        shutil.copyfile(pj('./gpt_log/', create_report_file_name), pj(project_folder, create_report_file_name))
+        promote_file_to_downloadzone(file=f'./gpt_log/{create_report_file_name}', chatbot=chatbot)
+    except:
+        from toolbox import trimmed_format_exc
+        print('writing html result failed:', trimmed_format_exc())
--- a/crazy_functions/latex_fns/latex_toolbox.py
+++ b/crazy_functions/latex_fns/latex_toolbox.py
@ -0,0 +1,456 @@
+import os, shutil
+import re
+import numpy as np
+PRESERVE = 0
+TRANSFORM = 1
+
+pj = os.path.join
+
+class LinkedListNode():
+    """
+    Linked List Node
+    """
+    def __init__(self, string, preserve=True) -> None:
+        self.string = string
+        self.preserve = preserve
+        self.next = None
+        self.range = None
+        # self.begin_line = 0
+        # self.begin_char = 0
+
+def convert_to_linklist(text, mask):
+    root = LinkedListNode("", preserve=True)
+    current_node = root
+    for c, m, i in zip(text, mask, range(len(text))):
+        if (m==PRESERVE and current_node.preserve) \
+            or (m==TRANSFORM and not current_node.preserve):
+            # add
+            current_node.string += c
+        else:
+            current_node.next = LinkedListNode(c, preserve=(m==PRESERVE))
+            current_node = current_node.next
+    return root
+
+def post_process(root):
+    # 修复括号
+    node = root
+    while True:
+        string = node.string
+        if node.preserve: 
+            node = node.next
+            if node is None: break
+            continue
+        def break_check(string):
+            str_stack = [""] # (lv, index)
+            for i, c in enumerate(string):
+                if c == '{':
+                    str_stack.append('{')
+                elif c == '}':
+                    if len(str_stack) == 1:
+                        print('stack fix')
+                        return i
+                    str_stack.pop(-1)
+                else:
+                    str_stack[-1] += c
+            return -1
+        bp = break_check(string)
+
+        if bp == -1:
+            pass
+        elif bp == 0:
+            node.string = string[:1]
+            q = LinkedListNode(string[1:], False)
+            q.next = node.next
+            node.next = q
+        else:
+            node.string = string[:bp]
+            q = LinkedListNode(string[bp:], False)
+            q.next = node.next
+            node.next = q
+
+        node = node.next
+        if node is None: break
+
+    # 屏蔽空行和太短的句子
+    node = root
+    while True:
+        if len(node.string.strip('\n').strip(''))==0: node.preserve = True
+        if len(node.string.strip('\n').strip(''))<42: node.preserve = True
+        node = node.next
+        if node is None: break
+    node = root
+    while True:
+        if node.next and node.preserve and node.next.preserve:
+            node.string += node.next.string
+            node.next = node.next.next
+        node = node.next
+        if node is None: break
+
+    # 将前后断行符脱离
+    node = root
+    prev_node = None
+    while True:
+        if not node.preserve:
+            lstriped_ = node.string.lstrip().lstrip('\n')
+            if (prev_node is not None) and (prev_node.preserve) and (len(lstriped_)!=len(node.string)):
+                prev_node.string += node.string[:-len(lstriped_)]
+                node.string = lstriped_
+            rstriped_ = node.string.rstrip().rstrip('\n')
+            if (node.next is not None) and (node.next.preserve) and (len(rstriped_)!=len(node.string)):
+                node.next.string = node.string[len(rstriped_):] + node.next.string
+                node.string = rstriped_
+        # =====
+        prev_node = node
+        node = node.next
+        if node is None: break
+
+    # 标注节点的行数范围
+    node = root
+    n_line = 0
+    expansion = 2
+    while True:
+        n_l = node.string.count('\n')
+        node.range = [n_line-expansion, n_line+n_l+expansion]   # 失败时，扭转的范围
+        n_line = n_line+n_l
+        node = node.next
+        if node is None: break
+    return root
+
+
+"""
+=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
+Latex segmentation with a binary mask (PRESERVE=0, TRANSFORM=1)
+=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
+"""
+
+
+def set_forbidden_text(text, mask, pattern, flags=0):
+    """
+    Add a preserve text area in this paper
+    e.g. with pattern = r"\\begin\{algorithm\}(.*?)\\end\{algorithm\}"
+    you can mask out (mask = PRESERVE so that text become untouchable for GPT) 
+    everything between "\begin{equation}" and "\end{equation}"
+    """
+    if isinstance(pattern, list): pattern = '|'.join(pattern)
+    pattern_compile = re.compile(pattern, flags)
+    for res in pattern_compile.finditer(text):
+        mask[res.span()[0]:res.span()[1]] = PRESERVE
+    return text, mask
+
+def reverse_forbidden_text(text, mask, pattern, flags=0, forbid_wrapper=True):
+    """
+    Move area out of preserve area (make text editable for GPT)
+    count the number of the braces so as to catch compelete text area. 
+    e.g.
+    \begin{abstract} blablablablablabla. \end{abstract} 
+    """
+    if isinstance(pattern, list): pattern = '|'.join(pattern)
+    pattern_compile = re.compile(pattern, flags)
+    for res in pattern_compile.finditer(text):
+        if not forbid_wrapper:
+            mask[res.span()[0]:res.span()[1]] = TRANSFORM
+        else:
+            mask[res.regs[0][0]: res.regs[1][0]] = PRESERVE   # '\\begin{abstract}'
+            mask[res.regs[1][0]: res.regs[1][1]] = TRANSFORM   # abstract
+            mask[res.regs[1][1]: res.regs[0][1]] = PRESERVE   # abstract
+    return text, mask
+
+def set_forbidden_text_careful_brace(text, mask, pattern, flags=0):
+    """
+    Add a preserve text area in this paper (text become untouchable for GPT).
+    count the number of the braces so as to catch compelete text area. 
+    e.g.
+    \caption{blablablablabla\texbf{blablabla}blablabla.} 
+    """
+    pattern_compile = re.compile(pattern, flags)
+    for res in pattern_compile.finditer(text):
+        brace_level = -1
+        p = begin = end = res.regs[0][0]
+        for _ in range(1024*16):
+            if text[p] == '}' and brace_level == 0: break
+            elif text[p] == '}':  brace_level -= 1
+            elif text[p] == '{':  brace_level += 1
+            p += 1
+        end = p+1
+        mask[begin:end] = PRESERVE
+    return text, mask
+
+def reverse_forbidden_text_careful_brace(text, mask, pattern, flags=0, forbid_wrapper=True):
+    """
+    Move area out of preserve area (make text editable for GPT)
+    count the number of the braces so as to catch compelete text area. 
+    e.g.
+    \caption{blablablablabla\texbf{blablabla}blablabla.} 
+    """
+    pattern_compile = re.compile(pattern, flags)
+    for res in pattern_compile.finditer(text):
+        brace_level = 0
+        p = begin = end = res.regs[1][0]
+        for _ in range(1024*16):
+            if text[p] == '}' and brace_level == 0: break
+            elif text[p] == '}':  brace_level -= 1
+            elif text[p] == '{':  brace_level += 1
+            p += 1
+        end = p
+        mask[begin:end] = TRANSFORM
+        if forbid_wrapper:
+            mask[res.regs[0][0]:begin] = PRESERVE
+            mask[end:res.regs[0][1]] = PRESERVE
+    return text, mask
+
+def set_forbidden_text_begin_end(text, mask, pattern, flags=0, limit_n_lines=42):
+    """
+    Find all \begin{} ... \end{} text block that with less than limit_n_lines lines.
+    Add it to preserve area
+    """
+    pattern_compile = re.compile(pattern, flags)
+    def search_with_line_limit(text, mask):
+        for res in pattern_compile.finditer(text):
+            cmd = res.group(1)  # begin{what}
+            this = res.group(2) # content between begin and end
+            this_mask = mask[res.regs[2][0]:res.regs[2][1]]
+            white_list = ['document', 'abstract', 'lemma', 'definition', 'sproof', 
+                          'em', 'emph', 'textit', 'textbf', 'itemize', 'enumerate']
+            if (cmd in white_list) or this.count('\n') >= limit_n_lines: # use a magical number 42
+                this, this_mask = search_with_line_limit(this, this_mask)
+                mask[res.regs[2][0]:res.regs[2][1]] = this_mask
+            else:
+                mask[res.regs[0][0]:res.regs[0][1]] = PRESERVE
+        return text, mask
+    return search_with_line_limit(text, mask) 
+
+
+
+"""
+=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
+Latex Merge File
+=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
+"""
+
+def find_main_tex_file(file_manifest, mode):
+    """
+    在多Tex文档中，寻找主文件，必须包含documentclass，返回找到的第一个。
+    P.S. 但愿没人把latex模板放在里面传进来 (6.25 加入判定latex模板的代码)
+    """
+    canidates = []
+    for texf in file_manifest:
+        if os.path.basename(texf).startswith('merge'):
+            continue
+        with open(texf, 'r', encoding='utf8', errors='ignore') as f:
+            file_content = f.read()
+        if r'\documentclass' in file_content:
+            canidates.append(texf)
+        else:
+            continue
+
+    if len(canidates) == 0:
+        raise RuntimeError('无法找到一个主Tex文件（包含documentclass关键字）')
+    elif len(canidates) == 1:
+        return canidates[0]
+    else: # if len(canidates) >= 2 通过一些Latex模板中常见（但通常不会出现在正文）的单词，对不同latex源文件扣分，取评分最高者返回
+        canidates_score = []
+        # 给出一些判定模板文档的词作为扣分项
+        unexpected_words = ['\LaTeX', 'manuscript', 'Guidelines', 'font', 'citations', 'rejected', 'blind review', 'reviewers']
+        expected_words = ['\input', '\ref', '\cite']
+        for texf in canidates:
+            canidates_score.append(0)
+            with open(texf, 'r', encoding='utf8', errors='ignore') as f:
+                file_content = f.read()
+            for uw in unexpected_words:
+                if uw in file_content:
+                    canidates_score[-1] -= 1
+            for uw in expected_words:
+                if uw in file_content:
+                    canidates_score[-1] += 1
+        select = np.argmax(canidates_score) # 取评分最高者返回
+        return canidates[select]
+    
+def rm_comments(main_file):
+    new_file_remove_comment_lines = []
+    for l in main_file.splitlines():
+        # 删除整行的空注释
+        if l.lstrip().startswith("%"):
+            pass
+        else:
+            new_file_remove_comment_lines.append(l)
+    main_file = '\n'.join(new_file_remove_comment_lines)
+    # main_file = re.sub(r"\\include{(.*?)}", r"\\input{\1}", main_file)  # 将 \include 命令转换为 \input 命令
+    main_file = re.sub(r'(?<!\\)%.*', '', main_file)  # 使用正则表达式查找半行注释, 并替换为空字符串
+    return main_file
+
+def find_tex_file_ignore_case(fp):
+    dir_name = os.path.dirname(fp)
+    base_name = os.path.basename(fp)
+    if not base_name.endswith('.tex'): base_name+='.tex'
+    if os.path.exists(pj(dir_name, base_name)): return pj(dir_name, base_name)
+    # go case in-sensitive
+    import glob
+    for f in glob.glob(dir_name+'/*.tex'):
+        base_name_s = os.path.basename(fp)
+        if base_name_s.lower() == base_name.lower(): return f
+    return None
+
+def merge_tex_files_(project_foler, main_file, mode):
+    """
+    Merge Tex project recrusively
+    """
+    main_file = rm_comments(main_file)
+    for s in reversed([q for q in re.finditer(r"\\input\{(.*?)\}", main_file, re.M)]):
+        f = s.group(1)
+        fp = os.path.join(project_foler, f)
+        fp = find_tex_file_ignore_case(fp)
+        if fp:
+            with open(fp, 'r', encoding='utf-8', errors='replace') as fx: c = fx.read()
+        else:
+            raise RuntimeError(f'找不到{fp}，Tex源文件缺失！')
+        c = merge_tex_files_(project_foler, c, mode)
+        main_file = main_file[:s.span()[0]] + c + main_file[s.span()[1]:]
+    return main_file
+
+def merge_tex_files(project_foler, main_file, mode):
+    """
+    Merge Tex project recrusively
+    P.S. 顺便把CTEX塞进去以支持中文
+    P.S. 顺便把Latex的注释去除
+    """
+    main_file = merge_tex_files_(project_foler, main_file, mode)
+    main_file = rm_comments(main_file)
+
+    if mode == 'translate_zh':
+        # find paper documentclass
+        pattern = re.compile(r'\\documentclass.*\n')
+        match = pattern.search(main_file)
+        assert match is not None, "Cannot find documentclass statement!"
+        position = match.end()
+        add_ctex = '\\usepackage{ctex}\n'
+        add_url = '\\usepackage{url}\n' if '{url}' not in main_file else ''
+        main_file = main_file[:position] + add_ctex + add_url + main_file[position:]
+        # fontset=windows
+        import platform
+        main_file = re.sub(r"\\documentclass\[(.*?)\]{(.*?)}", r"\\documentclass[\1,fontset=windows,UTF8]{\2}",main_file)
+        main_file = re.sub(r"\\documentclass{(.*?)}", r"\\documentclass[fontset=windows,UTF8]{\1}",main_file)
+        # find paper abstract
+        pattern_opt1 = re.compile(r'\\begin\{abstract\}.*\n')
+        pattern_opt2 = re.compile(r"\\abstract\{(.*?)\}", flags=re.DOTALL)
+        match_opt1 = pattern_opt1.search(main_file)
+        match_opt2 = pattern_opt2.search(main_file)
+        assert (match_opt1 is not None) or (match_opt2 is not None), "Cannot find paper abstract section!"
+    return main_file
+
+
+"""
+=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
+Post process
+=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
+"""
+def mod_inbraket(match):
+    """
+    为啥chatgpt会把cite里面的逗号换成中文逗号呀 
+    """
+    # get the matched string
+    cmd = match.group(1)
+    str_to_modify = match.group(2)
+    # modify the matched string
+    str_to_modify = str_to_modify.replace('：', ':')    # 前面是中文冒号，后面是英文冒号
+    str_to_modify = str_to_modify.replace('，', ',')    # 前面是中文逗号，后面是英文逗号
+    # str_to_modify = 'BOOM'
+    return "\\" + cmd + "{" + str_to_modify + "}"
+
+def fix_content(final_tex, node_string):
+    """
+    Fix common GPT errors to increase success rate
+    """
+    final_tex = re.sub(r"(?<!\\)%", "\\%", final_tex)
+    final_tex = re.sub(r"\\([a-z]{2,10})\ \{", r"\\\1{", string=final_tex)
+    final_tex = re.sub(r"\\\ ([a-z]{2,10})\{", r"\\\1{", string=final_tex)
+    final_tex = re.sub(r"\\([a-z]{2,10})\{([^\}]*?)\}", mod_inbraket, string=final_tex)
+
+    if "Traceback" in final_tex and "[Local Message]" in final_tex:
+        final_tex = node_string # 出问题了，还原原文
+    if node_string.count('\\begin') != final_tex.count('\\begin'):
+        final_tex = node_string # 出问题了，还原原文
+    if node_string.count('\_') > 0 and node_string.count('\_') > final_tex.count('\_'):
+        # walk and replace any _ without \
+        final_tex = re.sub(r"(?<!\\)_", "\\_", final_tex)
+
+    def compute_brace_level(string):
+        # this function count the number of { and }
+        brace_level = 0
+        for c in string:
+            if c == "{": brace_level += 1
+            elif c == "}": brace_level -= 1
+        return brace_level
+    def join_most(tex_t, tex_o):
+        # this function join translated string and original string when something goes wrong
+        p_t = 0
+        p_o = 0
+        def find_next(string, chars, begin):
+            p = begin
+            while p < len(string):
+                if string[p] in chars: return p, string[p]
+                p += 1
+            return None, None
+        while True:
+            res1, char = find_next(tex_o, ['{','}'], p_o)
+            if res1 is None: break
+            res2, char = find_next(tex_t, [char], p_t)
+            if res2 is None: break
+            p_o = res1 + 1
+            p_t = res2 + 1
+        return tex_t[:p_t] + tex_o[p_o:]
+
+    if compute_brace_level(final_tex) != compute_brace_level(node_string):
+        # 出问题了，还原部分原文，保证括号正确
+        final_tex = join_most(final_tex, node_string)
+    return final_tex
+    
+def compile_latex_with_timeout(command, cwd, timeout=60):
+    import subprocess
+    process = subprocess.Popen(command, shell=True, stdout=subprocess.PIPE, stderr=subprocess.PIPE, cwd=cwd)
+    try:
+        stdout, stderr = process.communicate(timeout=timeout)
+    except subprocess.TimeoutExpired:
+        process.kill()
+        stdout, stderr = process.communicate()
+        print("Process timed out!")
+        return False
+    return True
+
+
+
+def merge_pdfs(pdf1_path, pdf2_path, output_path):
+    import PyPDF2
+    Percent = 0.8
+    # Open the first PDF file
+    with open(pdf1_path, 'rb') as pdf1_file:
+        pdf1_reader = PyPDF2.PdfFileReader(pdf1_file)
+        # Open the second PDF file
+        with open(pdf2_path, 'rb') as pdf2_file:
+            pdf2_reader = PyPDF2.PdfFileReader(pdf2_file)
+            # Create a new PDF file to store the merged pages
+            output_writer = PyPDF2.PdfFileWriter()
+            # Determine the number of pages in each PDF file
+            num_pages = max(pdf1_reader.numPages, pdf2_reader.numPages)
+            # Merge the pages from the two PDF files
+            for page_num in range(num_pages):
+                # Add the page from the first PDF file
+                if page_num < pdf1_reader.numPages:
+                    page1 = pdf1_reader.getPage(page_num)
+                else:
+                    page1 = PyPDF2.PageObject.createBlankPage(pdf1_reader)
+                # Add the page from the second PDF file
+                if page_num < pdf2_reader.numPages:
+                    page2 = pdf2_reader.getPage(page_num)
+                else:
+                    page2 = PyPDF2.PageObject.createBlankPage(pdf1_reader)
+                # Create a new empty page with double width
+                new_page = PyPDF2.PageObject.createBlankPage(
+                    width = int(int(page1.mediaBox.getWidth()) + int(page2.mediaBox.getWidth()) * Percent),
+                    height = max(page1.mediaBox.getHeight(), page2.mediaBox.getHeight())
+                )
+                new_page.mergeTranslatedPage(page1, 0, 0)
+                new_page.mergeTranslatedPage(page2, int(int(page1.mediaBox.getWidth())-int(page2.mediaBox.getWidth())* (1-Percent)), 0)
+                output_writer.addPage(new_page)
+            # Save the merged PDF file
+            with open(output_path, 'wb') as output_file:
+                output_writer.write(output_file)
--- a/crazy_functions/live_audio/aliyunASR.py
+++ b/crazy_functions/live_audio/aliyunASR.py
@ -23,7 +23,7 @@ class AliyunASR():
        pass

    def test_on_close(self, *args):
-        # print("on_close: args=>{}".format(args))
+        self.aliyun_service_ok = False
        pass

    def test_on_result_chg(self, message, *args):
@ -50,7 +50,7 @@ class AliyunASR():
        rad.clean_up()
        temp_folder = tempfile.gettempdir()
        TOKEN, APPKEY = get_conf('ALIYUN_TOKEN', 'ALIYUN_APPKEY')
-
+        self.aliyun_service_ok = True
        URL="wss://nls-gateway.aliyuncs.com/ws/v1"
        sr = nls.NlsSpeechTranscriber(
                    url=URL,
@ -86,4 +86,8 @@ class AliyunASR():
                for i in slices: sr.send_audio(bytes(i))
            else:
                time.sleep(0.1)
+
+            if not self.aliyun_service_ok:
+                self.stop = True
+                self.stop_msg = 'Aliyun音频服务异常，请检查ALIYUN_TOKEN和ALIYUN_APPKEY是否过期。'
        r = sr.stop()
--- a/crazy_functions/下载arxiv论文翻译摘要.py
+++ b/crazy_functions/下载arxiv论文翻译摘要.py
@ -144,11 +144,11 @@ def 下载arxiv论文并翻译摘要(txt, llm_kwargs, plugin_kwargs, chatbot, hi

    # 尝试导入依赖，如果缺少依赖，则给出安装建议
    try:
-        import pdfminer, bs4
+        import bs4
    except:
        report_execption(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```。")
+            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

--- a/crazy_functions/对话历史存档.py
+++ b/crazy_functions/对话历史存档.py
@ -12,7 +12,7 @@ def write_chat_to_file(chatbot, history=None, file_name=None):
        file_name = 'chatGPT对话历史' + time.strftime("%Y-%m-%d-%H-%M-%S", time.localtime()) + '.html'
    os.makedirs('./gpt_log/', exist_ok=True)
    with open(f'./gpt_log/{file_name}', 'w', encoding='utf8') as f:
-        from theme.theme import advanced_css
+        from themes.theme import advanced_css
        f.write(f'<!DOCTYPE html><head><meta charset="utf-8"><title>对话历史</title><style>{advanced_css}</style></head>')
        for i, contents in enumerate(chatbot):
            for j, content in enumerate(contents):
--- a/crazy_functions/语音助手.py
+++ b/crazy_functions/语音助手.py
@ -14,9 +14,11 @@ class WatchDog():
        self.bark_fn = bark_fn
        self.interval = interval
        self.msg = msg
+        self.kill_dog = False
    
    def watch(self):
        while True:
+            if self.kill_dog: break
            if time.time() - self.last_feed > self.timeout:
                if len(self.msg) > 0: print(self.msg)
                self.bark_fn()
@ -87,6 +89,9 @@ class InterviewAssistant(AliyunASR):

    def __del__(self):
        self.stop = True
+        self.stop_msg = ""
+        self.commit_wd.kill_dog = True
+        self.plugin_wd.kill_dog = True

    def init(self, chatbot):
        # 初始化音频采集线程
@ -119,7 +124,7 @@ class InterviewAssistant(AliyunASR):
        self.commit_wd = WatchDog(timeout=self.commit_after_pause_n_second, bark_fn=self.no_audio_for_a_while, interval=0.2)
        self.commit_wd.begin_watch()

-        while True:
+        while not self.stop:
            self.event_on_result_chg.wait(timeout=0.25)  # run once every 0.25 second
            chatbot = self.agt.update_chatbot(chatbot)   # 将子线程的gpt结果写入chatbot
            history = chatbot2history(chatbot)
@ -158,6 +163,8 @@ class InterviewAssistant(AliyunASR):
                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

+        if len(self.stop_msg) != 0:
+            raise RuntimeError(self.stop_msg)



--- a/docker-compose.yml
+++ b/docker-compose.yml
@ -63,7 +63,7 @@ services:
 version: '3'
 services:
  gpt_academic_with_rwkv:
-    image: fuqingxu/gpt_academic:jittorllms
+    image: ghcr.io/binary-husky/gpt_academic_jittorllms:master
    environment:
      # 请查阅 `config.py` 以查看所有的配置信息
      API_KEY:                  '    sk-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx,fkxxxxxx-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx  '
@ -85,28 +85,13 @@ services:
    # 与宿主的网络融合
    network_mode: "host"

-    # 使用代理网络拉取最新代码
-    # command: >
-    #   bash -c "       truncate -s -1 /etc/proxychains.conf &&
-    #                   echo \"socks5 127.0.0.1 10880\" >> /etc/proxychains.conf &&
-    #                   echo '[gpt-academic] 正在从github拉取最新代码...' &&
-    #                   proxychains git pull &&
-    #                   echo '[jittorllms] 正在从github拉取最新代码...' &&
-    #                   proxychains git --git-dir=request_llm/jittorllms/.git --work-tree=request_llm/jittorllms pull --force &&
-    #                   python3 -u main.py"
-
    # 不使用代理网络拉取最新代码
    command: >
-      bash -c "       echo '[gpt-academic] 正在从github拉取最新代码...' &&
-                      git pull &&
-                      pip install -r requirements.txt &&
-                      echo '[jittorllms] 正在从github拉取最新代码...' &&
-                      git --git-dir=request_llm/jittorllms/.git --work-tree=request_llm/jittorllms pull --force &&
-                      python3 -u main.py"
+      python3 -u main.py


 ## ===================================================
-## 【方案四】 chatgpt + Latex
+## 【方案四】 ChatGPT + Latex
 ## ===================================================
 version: '3'
 services:
--- a/docs/Dockerfile+JittorLLM
+++ b/docs/Dockerfile+JittorLLM
@ -26,7 +26,7 @@ RUN curl -sS https://bootstrap.pypa.io/get-pip.py | python3.8
 RUN $useProxyNetwork python3 -m pip install torch --extra-index-url https://download.pytorch.org/whl/cu113
 # 下载分支
 WORKDIR /gpt
-RUN $useProxyNetwork git clone https://github.com/binary-husky/chatgpt_academic.git -b jittor
+RUN $useProxyNetwork git clone https://github.com/binary-husky/chatgpt_academic.git
 WORKDIR /gpt/chatgpt_academic
 RUN $useProxyNetwork python3 -m pip install -r requirements.txt
 RUN $useProxyNetwork python3 -m pip install -r request_llm/requirements_chatglm.txt
--- a/docs/GithubAction+JittorLLMs
+++ b/docs/GithubAction+JittorLLMs
@ -13,7 +13,7 @@ RUN python3 -m pip install torch --extra-index-url https://download.pytorch.org/

 # 下载分支
 WORKDIR /gpt
-RUN git clone https://github.com/binary-husky/chatgpt_academic.git -b jittor
+RUN git clone https://github.com/binary-husky/chatgpt_academic.git
 WORKDIR /gpt/chatgpt_academic
 RUN python3 -m pip install -r requirements.txt
 RUN python3 -m pip install -r request_llm/requirements_chatglm.txt
--- a/docs/gradio-3.32.2-py3-none-any.whl
+++ b/docs/gradio-3.32.2-py3-none-any.whl
--- a/docs/translate_english.json
+++ b/docs/translate_english.json
@ -1956,5 +1956,134 @@
    "填入ENGINE": "Fill in ENGINE",
    "填入api版本": "Fill in the API version",
    "中文Bing版": "Chinese Bing version",
-    "当前支持的格式包括": "Currently supported formats include"
+    "当前支持的格式包括": "Currently supported formats include",
+    "交互功能模板函数": "InteractiveFunctionTemplateFunction",
+    "交互功能函数模板": "InteractiveFunctionFunctionTemplate",
+    "语音助手": "VoiceAssistant",
+    "微调数据集生成": "FineTuneDatasetGeneration",
+    "chatglm微调工具": "ChatGLMFineTuningTool",
+    "启动微调": "StartFineTuning",
+    "请讲话": "Please speak",
+    "正在听您讲话": "Listening to you",
+    "对这个人外貌、身处的环境、内心世界、过去经历进行描写": "Describe the appearance, environment, inner world, and past experiences of this person",
+    "请向下翻": "Please scroll down",
+    "实时音频采集": "Real-time audio collection",
+    "找不到": "Not found",
+    "在一个异步线程中采集音频": "Collect audio in an asynchronous thread",
+    "azure和api2d请求源": "Azure and API2D request source",
+    "等待ChatGLMFT响应中": "Waiting for ChatGLMFT response",
+    "如果使用ChatGLM2微调模型": "If using ChatGLM2 fine-tuning model",
+    "把文件复制过去": "Copy the file over",
+    "可选": "Optional",
+    "ChatGLMFT响应异常": "ChatGLMFT response exception",
+    "上传本地文件/压缩包供函数插件调用": "Upload local files/compressed packages for function plugin calls",
+    "例如 f37f30e0f9934c34a992f6f64f7eba4f": "For example, f37f30e0f9934c34a992f6f64f7eba4f",
+    "正在等您说完问题": "Waiting for you to finish the question",
+    "解除插件状态": "Release plugin status",
+    "详情见https": "See details at https",
+    "避免线程阻塞": "Avoid thread blocking",
+    "先上传数据集": "Upload dataset first",
+    "请直接提交即可": "Submit directly",
+    "Call ChatGLMFT fail 不能正常加载ChatGLMFT的参数": "Call ChatGLMFT fail, cannot load ChatGLMFT parameters",
+    "插件可读取“输入区”文本/路径作为参数": "The plugin can read text/path in the input area as parameters",
+    "给出指令": "Give instructions",
+    "暂不提交": "Do not submit for now",
+    "如 绿帽子*深蓝色衬衫*黑色运动裤": "E.g. green hat * dark blue shirt * black sports pants",
+    "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": "Aliyun real-time speech recognition has high configuration difficulty and is only recommended for advanced users. Refer to https",
+    "ChatGLMFT尚未加载": "ChatGLMFT has not been loaded yet",
+    "输入 clear 以清空对话历史": "Enter 'clear' to clear the conversation history",
+    "可以将自身的状态存储到cookie中": "You can store your own status in cookies",
+    "填入你亲手写的部署名": "Fill in the deployment name you wrote by yourself",
+    "该选项即将被弃用": "This option will be deprecated soon",
+    "代理网络配置": "Proxy network configuration",
+    "每秒采样数量": "Number of samples per second",
+    "使用时": "When using",
+    "想象一个穿着者": "Imagine a wearer",
+    "如果已经存在": "If it already exists",
+    "例如您可以将以下命令复制到下方": "For example, you can copy the following command below",
+    "正在锁定插件": "Locking plugin",
+    "使用": "Use",
+    "读 docs\\use_azure.md": "Read docs\\use_azure.md",
+    "开始最终总结": "Start final summary",
+    "openai的官方KEY需要伴随组织编码": "Openai's official KEY needs to be accompanied by organizational code",
+    "将子线程的gpt结果写入chatbot": "Write the GPT result of the sub-thread into the chatbot",
+    "Arixv论文精细翻译": "Fine translation of Arixv paper",
+    "开始接收chatglmft的回复": "Start receiving replies from chatglmft",
+    "请先将.doc文档转换为.docx文档": "Please convert .doc documents to .docx documents first",
+    "避免多用户干扰": "Avoid multiple user interference",
+    "清空label": "Clear label",
+    "解除插件锁定": "Unlock plugin",
+    "请以以下方式load模型！！！": "Please load the model in the following way!!!",
+    "没给定指令": "No instruction given",
+    "100字以内": "Within 100 words",
+    "获取关键词": "Get keywords",
+    "欢迎使用 MOSS 人工智能助手！": "Welcome to use MOSS AI assistant!",
+    "音频助手": "Audio assistant",
+    "上传Latex项目": "Upload Latex project",
+    "对话助手函数插件": "Chat assistant function plugin",
+    "如果一句话小于7个字": "If a sentence is less than 7 words",
+    "640个字节为一组": "640 bytes per group",
+    "右下角更换模型菜单中可切换openai": "OpenAI can be switched in the model menu in the lower right corner",
+    "双手离开鼠标键盘吧": "Take your hands off the mouse and keyboard",
+    "先删除": "Delete first",
+    "如果要使用ChatGLMFT": "If you want to use ChatGLMFT",
+    "例如 RoPlZrM88DnAFkZK": "For example, RoPlZrM88DnAFkZK",
+    "提取总结": "Extract summary",
+    "ChatGLMFT消耗大量的内存": "ChatGLMFT consumes a lot of memory",
+    "格式如org-123456789abcdefghijklmno的": "In the format of org-123456789abcdefghijklmno",
+    "在执行完成之后": "After execution is complete",
+    "此处填API密钥": "Fill in the API key here",
+    "chatglmft 没有 sys_prompt 接口": "ChatGLMFT does not have a sys_prompt interface",
+    "用第二人称": "Use the second person",
+    "Chuanhu-Small-and-Beautiful主题": "Chuanhu-Small-and-Beautiful theme",
+    "请检查ALIYUN_TOKEN和ALIYUN_APPKEY是否过期": "Please check if ALIYUN_TOKEN and ALIYUN_APPKEY have expired",
+    "还需要填写组织": "You also need to fill in the organization",
+    "会直接转到该函数": "Will directly jump to the function",
+    "初始化插件状态": "Initializing plugin status",
+    "插件锁定中": "Plugin is locked",
+    "如果这里报错": "If there is an error here",
+    "本地Latex论文精细翻译": "Local Latex paper fine translation",
+    "极少数情况下": "In very few cases",
+    "首先你在中文语境下通读整篇论文": "First, read the entire paper in a Chinese context",
+    "点击“停止”键可终止程序": "Click the 'Stop' button to terminate the program",
+    "建议排查": "Suggested troubleshooting",
+    "没有阿里云语音识别APPKEY和TOKEN": "No Aliyun voice recognition APPKEY and TOKEN",
+    "避免遗忘导致死锁": "Avoid forgetting to cause deadlock",
+    "第一次调用": "First call",
+    "解决插件锁定时的界面显示问题": "Solve the interface display problem when the plugin is locked",
+    "初始化音频采集线程": "Initialize audio capture thread",
+    "找不到微调模型检查点": "Cannot find fine-tuning model checkpoint",
+    "色彩主体": "Color theme",
+    "上传文件自动修正路径": "Automatically correct the path when uploading files",
+    "将文件添加到chatbot cookie中": "Add files to chatbot cookie",
+    "正常状态": "Normal state",
+    "建议使用英文单词": "Suggest using English words",
+    "Aliyun音频服务异常": "Aliyun audio service exception",
+    "格式如org-xxxxxxxxxxxxxxxxxxxxxxxx": "Format like org-xxxxxxxxxxxxxxxxxxxxxxxx",
+    "GPT 学术优化": "GPT academic optimization",
+    "要求": "Requirement",
+    "赋予插件状态": "Assign plugin status",
+    "等待GPT响应": "Waiting for GPT response",
+    "MOSS can understand and communicate fluently in the language chosen by the user such as English and 中文. MOSS can perform any language-based tasks.": "MOSS can understand and communicate fluently in the language chosen by the user such as English and Chinese. MOSS can perform any language-based tasks.",
+    "我将为您查找相关壁纸": "I will search for related wallpapers for you",
+    "当下一次用户提交时": "When the next user submits",
+    "赋予插件锁定 锁定插件回调路径": "Assign plugin lock, lock plugin callback path",
+    "处理个别特殊插件的锁定状态": "Handle the lock status of individual special plugins",
+    "add gpt task 创建子线程请求gpt": "Add GPT task, create sub-thread to request GPT",
+    "等待用户的再次调用": "Waiting for the user to call again",
+    "只读": "Read-only",
+    "用于灵活调整复杂功能的各种参数": "Various parameters used to flexibly adjust complex functions",
+    "输入 stop 以终止对话": "Enter stop to terminate the conversation",
+    "缺少ChatGLMFT的依赖": "Missing dependency of ChatGLMFT",
+    "找 API_ORG 设置项": "Find API_ORG setting item",
+    "检查config中的AVAIL_LLM_MODELS选项": "Check the AVAIL_LLM_MODELS option in config",
+    "对这个人外貌、身处的环境、内心世界、人设进行描写": "Describe the appearance, environment, inner world, and character of this person.",
+    "请输入关键词": "Please enter a keyword.",
+    "！！！如果需要运行量化版本": "!!! If you need to run the quantitative version.",
+    "为每一位访问的用户赋予一个独一无二的uuid编码": "Assign a unique uuid code to each visiting user.",
+    "由于提问含不合规内容被Azure过滤": "Due to Azure filtering out questions containing non-compliant content.",
+    "欢迎使用 MOSS 人工智能助手！输入内容即可进行对话": "Welcome to use MOSS AI assistant! Enter the content to start the conversation.",
+    "记住当前的label": "Remember the current label.",
+    "不能正常加载ChatGLMFT的参数！": "Cannot load ChatGLMFT parameters normally!",
+    "建议直接在API_KEY处填写": "It is recommended to fill in directly at API_KEY."
 }
--- a/docs/translate_traditionalchinese.json
+++ b/docs/translate_traditionalchinese.json
@ -150,26 +150,7 @@
    "使用中文回答我的问题": "使用中文回答我的問題",
    "备份一个文件": "備份一個文件",
    "未知": "未知",
-    "如.md": "#",
-    "**输入参数说明**": "#",
-    "如果这裡拋出異常": "#",
-    "多線程操作已經開始": "#",
-    "備份和下載": "#",
-    "新版本可用": "#",
-    "將要忽略匹配的文件後綴": "#",
-    "可調節線程池的大小避免openai的流量限制錯誤": "#",
-    "使用Unsplash API": "#",
-    "ChatGPT綜合": "#",
-    "從摘要中提取高價值信息": "#",
-    "借助此參數": "#",
-    "知乎": "#",
-    "其他錯誤": "#",
-    "退出": "#",
-    "對話歷史寫入": "#",
-    "問詢記錄": "#",
-    "依次訪問網頁": "#",
-    "NewBing響應異常": "#",
-    "jittorllms尚未加載": "#",
+    "其他錯誤": "其他錯誤",
    "等待NewBing响应": "等待NewBing回應",
    "找不到任何CSharp文件": "找不到任何CSharp檔案",
    "插件demo": "插件範例",
@ -300,12 +281,12 @@
    "上傳本地文件可供紅色函數插件調用": "上傳本地文件供紅色函數插件調用",
    "生成圖像": "生成圖像",
    "追加歷史": "追加歷史",
-    "網絡代理狀態": "網路代理狀態",
+    "網絡代理狀態": "網絡代理狀態",
    "不需要再次轉化": "不需要再次轉換",
    "帶超時倒計時": "帶有超時倒數計時",
    "保存當前對話": "儲存目前對話",
    "等待響應": "等待回應",
-    "依賴檢測通過": "依賴檢查通過",
+    "依賴檢測通過": "依賴檢測通過",
    "如果要使用ChatGLM": "如果要使用ChatGLM",
    "對IPynb文件進行解析": "對IPynb檔案進行解析",
    "先切換模型到openai或api2d": "先切換模型到openai或api2d",
@ -411,7 +392,7 @@
    "中转网址预览": "中轉網址預覽",
    "自动截断": "自動截斷",
    "当無法用標點、空行分割時": "當無法用標點、空行分割時",
-    "意外Json結構": "意外的Json結構",
+    "意外Json結構": "意外Json結構",
    "需要讀取和清理文本的pdf文件路徑": "需要讀取和清理文本的pdf文件路徑",
    "HotReload的裝飾器函數": "HotReload的裝飾器函數",
    "chatGPT 分析報告": "chatGPT 分析報告",
@ -423,7 +404,7 @@
    "這個bug沒找到觸發條件": "這個bug沒找到觸發條件",
    "喚起高級參數輸入區": "喚起高級參數輸入區",
    "但大部分場合下並不需要修改": "但大部分場合下並不需要修改",
-    "盡量是完整的一個section": "盡量是完整的一個section",
+    "盡量是完整的一個section": "盡量選擇完整的一個章節",
    "如果OpenAI不響應": "如果OpenAI不響應",
    "等文本特殊符號轉換為其基本形式來對文本進行歸一化處理": "等文本特殊符號轉換為其基本形式來對文本進行歸一化處理",
    "你的回答必須簡單明了": "你的回答必須簡單明了",
@ -517,7 +498,7 @@
    "正在提取摘要並下載PDF文檔……": "正在提取摘要並下載PDF文件……",
    "1. 對原始文本進行歸一化處理": "1. 正規化原始文本",
    "問題": "問題",
-    "用於基礎的對話功能": "基本對話功能",
+    "用於基礎的對話功能": "用於基礎的對話功能",
    "獲取設置": "獲取設置",
    "如果缺少依賴": "如果缺少依賴項",
    "第6步": "第6步",
@ -1111,26 +1092,9 @@
    "清理规则包括": "清理規則包括",
    "新版配置": "新版配置",
    "如果有": "如果有",
-    "高級參數輸入區": "#",
-    "您提供的api-key不滿足要求": "#",
-    "“喂狗”": "#",
-    "有線程鎖": "#",
-    "解析整個CSharp項目": "#",
-    "上下文管理器必須實現兩個方法": "#",
-    "Call MOSS fail 不能正常加載MOSS的參數": "#",
-    "獲取圖片URL": "#",
-    "輸入部分太自由": "#",
-    "Not enough point. API2D賬戶點數不足": "#",
-    "網絡錯誤": "#",
-    "請開始多線程操作": "#",
-    "authors獲取失敗": "#",
-    "、地址": "#",
-    "根據以上分析": "#",
-    "1、英文題目；2、中文題目翻譯；3、作者；4、arxiv公開": "#",
-    "一些普通功能模塊": "#",
-    "參數簡單": "#",
-    "具備以下功能": "#",
-    "優先級2. 獲取config_private中的配置": "#",
+    "Call MOSS fail 不能正常加載MOSS的參數": "Call MOSS fail 不能正常加載MOSS的參數",
+    "根據以上分析": "根據以上分析",
+    "一些普通功能模塊": "一些普通功能模塊",
    "汇总报告如何远程获取": "如何遠程獲取匯總報告",
    "热更新prompt": "熱更新提示",
    "插件调度异常": "插件調度異常",
@ -1191,26 +1155,9 @@
    "函数插件区": "函數插件區",
    "*** API_KEY 导入成功": "*** API_KEY 導入成功",
    "请对下面的程序文件做一个概述文件名是": "請對下面的程序文件做一個概述文件名是",
-    "替換跨行的連詞": "#",
-    "內容太長了都會觸發token數量溢出的錯誤": "#",
-    "尚未完成全部響應": "#",
-    "生成帶有段落標籤的HTML代碼": "#",
-    "函數熱更新是指在不停止程序運行的情況下": "#",
-    "將Unsplash API中的PUT_YOUR_QUERY_HERE替換成描述該事件的一個最重要的單詞": "#",
-    "沒有提供高級參數功能說明": "#",
-    "條": "#",
-    "請刷新界面重試": "#",
-    "和openai的連接容易斷掉": "#",
-    "使用 Unsplash API": "#",
-    "完成情況": "#",
-    "迭代上一次的結果": "#",
-    "每個線程都要“餵狗”": "#",
-    "最多收納多少個網頁的結果": "#",
-    "日": "#",
-    "第4步": "#",
-    "找不到任何python文件": "#",
-    "經過充分測試": "#",
-    "缺少的依賴": "#",
+    "內容太長了都會觸發token數量溢出的錯誤": "內容太長了都會觸發token數量溢出的錯誤",
+    "沒有提供高級參數功能說明": "未提供高級參數功能說明",
+    "和openai的連接容易斷掉": "和openai的連接容易斷掉",
    "分组+迭代处理": "分組+迭代處理",
    "安装Newbing的依赖": "安裝Newbing的依賴",
    "批": "批",
@ -1511,5 +1458,760 @@
    "包括": "包括",
    "或者": "或者",
    "并执行函数的新版本": "並執行函數的新版本",
-    "论文": "論文"
+    "论文": "論文",
+    "解析一个Golang项目": "ParseAGolangProject",
+    "Latex英文纠错": "LatexEnglishCorrection",
+    "连接bing搜索回答问题": "ConnectToBingSearchForAnswer",
+    "联网的ChatGPT_bing版": "ChatGPT_BingVersionOnline",
+    "总结音视频": "SummarizeAudioAndVideo",
+    "动画生成": "GenerateAnimations",
+    "数学动画生成manim": "GenerateMathematicalAnimationsWithManim",
+    "Markdown翻译指定语言": "TranslateMarkdownToSpecifiedLanguage",
+    "知识库问答": "KnowledgeBaseQA",
+    "Langchain知识库": "LangchainKnowledgeBase",
+    "读取知识库作答": "ReadKnowledgeBaseAndAnswerQuestions",
+    "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翻译中文并重新编译PDF": "TranslateLatexToChineseAndRecompilePDF",
+    "语音助手": "VoiceAssistant",
+    "微调数据集生成": "FineTuneDatasetGeneration",
+    "chatglm微调工具": "ChatGLM_FineTuningTool",
+    "启动微调": "StartFineTuning",
+    "sprint亮靛": "SprintLiangDian",
+    "寻找Latex主文件": "FindLatexMainFile",
+    "专业词汇声明": "ProfessionalTerminologyDeclaration",
+    "Latex精细分解与转化": "LatexFineDecompositionAndConversion",
+    "编译Latex": "CompileLatex",
+    "正在等您说完问题": "正在等您說完問題",
+    "最多同时执行5个": "最多同時執行5個",
+    "将文件复制一份到下载区": "將檔案複製一份到下載區",
+    "您接下来不能再使用其他插件了": "您接下來不能再使用其他插件了",
+    "如 绿帽子*深蓝色衬衫*黑色运动裤": "如 綠帽子*深藍色襯衫*黑色運動褲",
+    "首先你在中文语境下通读整篇论文": "首先您在中文語境下通讀整篇論文",
+    "根据给定的切割时长将音频文件切割成多个片段": "根據給定的切割時長將音訊檔切割成多個片段",
+    "接下来两句话只显示在界面上": "接下來兩句話只顯示在介面上",
+    "清空label": "清空標籤",
+    "正在尝试自动安装": "正在嘗試自動安裝",
+    "MOSS消耗大量的内存": "MOSS消耗大量的記憶體",
+    "如果这里报错": "如果這裡報錯",
+    "其他类型文献转化效果未知": "其他類型文獻轉換效果未知",
+    "ChatGPT综合": "ChatGPT綜合",
+    "音频文件的路径": "音訊檔案的路徑",
+    "执行错误": "執行錯誤",
+    "因此选择GenerateImage函数": "因此選擇GenerateImage函數",
+    "从摘要中提取高价值信息": "從摘要中提取高價值資訊",
+    "使用英文": "使用英文",
+    "是否在提交时自动清空输入框": "是否在提交時自動清空輸入框",
+    "生成数学动画": "生成數學動畫",
+    "正在加载Claude组件": "正在載入Claude元件",
+    "参数说明": "參數說明",
+    "建议排查": "建議排查",
+    "将消耗较长时间下载中文向量化模型": "將消耗較長時間下載中文向量化模型",
+    "test_LangchainKnowledgeBase读取": "test_LangchainKnowledgeBase讀取",
+    "安装Claude的依赖": "安裝Claude的相依性",
+    "以下所有配置也都支持利用环境变量覆写": "以下所有配置也都支持利用環境變數覆寫",
+    "需要被切割的音频文件名": "需要被切割的音頻文件名",
+    "保存当前对话": "保存當前對話",
+    "功能、贡献者": "功能、貢獻者",
+    "Chuanhu-Small-and-Beautiful主题": "Chuanhu-小而美主題",
+    "等待Claude响应": "等待Claude響應",
+    "其他模型转化效果未知": "其他模型轉換效果未知",
+    "版权归原文作者所有": "版權歸原文作者所有",
+    "回答完问题后": "回答完問題後",
+    "请先上传文件素材": "請先上傳文件素材",
+    "上传本地文件/压缩包供函数插件调用": "上傳本地文件/壓縮包供函數插件調用",
+    "P.S. 顺便把Latex的注释去除": "P.S. 順便把Latex的註釋去除",
+    "您提供的api-key不满足要求": "您提供的api-key不滿足要求",
+    "切割音频文件": "切割音頻文件",
+    "对不同latex源文件扣分": "對不同latex源文件扣分",
+    "以下是一篇学术论文的基础信息": "以下是一篇學術論文的基礎信息",
+    "问题": "問題",
+    "待注入的知识库名称id": "待注入的知識庫名稱id",
+    "”的主要内容": "”的主要內容",
+    "获取设置": "獲取設置",
+    "str类型": "str類型",
+    "多线程": "多線程",
+    "尝试执行Latex指令失败": "嘗試執行Latex指令失敗",
+    "然后再写一段英文摘要": "然後再寫一段英文摘要",
+    "段音频的主要内容": "段音頻的主要內容",
+    "临时地激活代理网络": "臨時地激活代理網絡",
+    "网络的远程文件": "網絡的遠程文件",
+    "不能正常加载ChatGLMFT的参数！": "無法正常載入ChatGLMFT的參數！",
+    "正在编译PDF文档": "正在編譯PDF文件",
+    "等待ChatGLMFT响应中": "等待ChatGLMFT回應中",
+    "将": "將",
+    "片段": "片段",
+    "修复括号": "修復括號",
+    "条": "條",
+    "建议直接在API_KEY处填写": "建議直接在API_KEY處填寫",
+    "根据需要切换prompt": "根據需要切換prompt",
+    "使用": "使用",
+    "请输入要翻译成哪种语言": "請輸入要翻譯成哪種語言",
+    "实际得到格式": "實際得到格式",
+    "例如 f37f30e0f9934c34a992f6f64f7eba4f": "例如 f37f30e0f9934c34a992f6f64f7eba4f",
+    "请切换至“KnowledgeBaseQA”插件进行知识库访问": "請切換至“KnowledgeBaseQA”插件進行知識庫訪問",
+    "用户填3": "用戶填3",
+    "远程云服务器部署": "遠程雲服務器部署",
+    "未知指令": "未知指令",
+    "每个线程都要“喂狗”": "每個線程都要“喂狗”",
+    "该项目的Latex主文件是": "該項目的Latex主文件是",
+    "设置OpenAI密钥和模型": "設置OpenAI密鑰和模型",
+    "填入你亲手写的部署名": "填入你親手寫的部署名",
+    "仅调试": "僅調試",
+    "依赖不足": "依賴不足",
+    "右下角更换模型菜单中可切换openai": "右下角更換模型菜單中可切換openai",
+    "解析整个CSharp项目": "解析整個CSharp項目",
+    "唤起高级参数输入区": "喚起高級參數輸入區",
+    "这个bug没找到触发条件": "這個bug沒找到觸發條件",
+    "========================================= 插件主程序2 =====================================================": "========================================= 插件主程序2 =====================================================",
+    "经过充分测试": "經過充分測試",
+    "该文件中主要包含三个函数": "該文件中主要包含三個函數",
+    "您可以到Github Issue区": "您可以到Github Issue區",
+    "避免线程阻塞": "避免線程阻塞",
+    "吸收iffalse注释": "吸收iffalse註釋",
+    "from crazy_functions.虚空终端 import 终端": "from crazy_functions.虛空終端 import 終端",
+    "异步方法": "異步方法",
+    "块元提取": "塊元提取",
+    "Your account is not active. OpenAI以账户失效为由": "您的帳戶未啟用。OpenAI以帳戶失效為由",
+    "还原部分原文": "還原部分原文",
+    "如果要使用Claude": "如果要使用Claude",
+    "把文件复制过去": "把文件複製過去",
+    "解压失败! 需要安装pip install rarfile来解压rar文件": "解壓失敗！需要安裝pip install rarfile來解壓rar文件",
+    "正在锁定插件": "正在鎖定插件",
+    "输入 clear 以清空对话历史": "輸入 clear 以清空對話歷史",
+    "P.S. 但愿没人把latex模板放在里面传进来": "P.S. 但願沒人把latex模板放在裡面傳進來",
+    "实时音频采集": "實時音頻採集",
+    "开始最终总结": "開始最終總結",
+    "拒绝服务": "拒絕服務",
+    "配置教程&视频教程": "配置教程&視頻教程",
+    "所有音频都总结完成了吗": "所有音頻都總結完成了嗎",
+    "返回": "返回",
+    "避免不小心传github被别人看到": "避免不小心傳github被別人看到",
+    "否则将导致每个人的Claude问询历史互相渗透": "否則將導致每個人的Claude問詢歷史互相滲透",
+    "提问吧! 但注意": "提問吧！但注意",
+    "待处理的word文档路径": "待處理的word文檔路徑",
+    "欢迎加REAME中的QQ联系开发者": "歡迎加REAME中的QQ聯繫開發者",
+    "建议暂时不要使用": "建議暫時不要使用",
+    "Latex没有安装": "Latex沒有安裝",
+    "在这里放一些网上搜集的demo": "在這裡放一些網上搜集的demo",
+    "实现消息发送、接收等功能": "實現消息發送、接收等功能",
+    "用于与with语句一起使用": "用於與with語句一起使用",
+    "解压失败! 需要安装pip install py7zr来解压7z文件": "解壓失敗! 需要安裝pip install py7zr來解壓7z文件",
+    "借助此参数": "借助此參數",
+    "判定为数据流的结束": "判定為數據流的結束",
+    "提取文件扩展名": "提取文件擴展名",
+    "GPT结果已输出": "GPT結果已輸出",
+    "读取文件": "讀取文件",
+    "如果OpenAI不响应": "如果OpenAI不響應",
+    "输入部分太自由": "輸入部分太自由",
+    "用于给一小段代码上代理": "用於給一小段代碼上代理",
+    "输入 stop 以终止对话": "輸入 stop 以終止對話",
+    "这个paper有个input命令文件名大小写错误！": "這個paper有個input命令文件名大小寫錯誤！",
+    "等待Claude回复的片段": "等待Claude回復的片段",
+    "开始": "開始",
+    "将根据报错信息修正tex源文件并重试": "將根據報錯信息修正tex源文件並重試",
+    "建议更换代理协议": "建議更換代理協議",
+    "递归地切割PDF文件": "遞歸地切割PDF文件",
+    "读 docs\\use_azure.md": "讀 docs\\use_azure.md",
+    "参数": "參數",
+    "屏蔽空行和太短的句子": "屏蔽空行和太短的句子",
+    "分析上述回答": "分析上述回答",
+    "因为在同一个频道里存在多人使用时历史消息渗透问题": "因為在同一個頻道裡存在多人使用時歷史消息滲透問題",
+    "使用latexdiff生成論文轉化前後對比": "使用latexdiff生成論文轉化前後對比",
+    "檢查結果": "檢查結果",
+    "請在此處追加更細緻的校錯指令": "請在此處追加更細緻的校錯指令",
+    "報告如何遠程獲取": "報告如何遠程獲取",
+    "發現已經存在翻譯好的PDF文檔": "發現已經存在翻譯好的PDF文檔",
+    "插件鎖定中": "插件鎖定中",
+    "正在精細切分latex文件": "正在精細切分latex文件",
+    "數學GenerateAnimations": "數學GenerateAnimations",
+    "上傳文件自動修正路徑": "上傳文件自動修正路徑",
+    "請檢查ALIYUN_TOKEN和ALIYUN_APPKEY是否過期": "請檢查ALIYUN_TOKEN和ALIYUN_APPKEY是否過期",
+    "上傳Latex項目": "上傳LaTeX項目",
+    "Aliyun音頻服務異常": "Aliyun音頻服務異常",
+    "為了防止大語言模型的意外謬誤產生擴散影響": "為了防止大語言模型的意外謬誤產生擴散影響",
+    "調用Claude時": "調用Claude時",
+    "解除插件鎖定": "解除插件鎖定",
+    "暗色模式 / 亮色模式": "暗色模式 / 亮色模式",
+    "只有第二步成功": "只有第二步成功",
+    "分析结果": "分析結果",
+    "用第二人称": "使用第二人稱",
+    "详情见https": "詳情請見https",
+    "记住当前的label": "記住當前的標籤",
+    "当无法用标点、空行分割时": "當無法用標點符號、空行分割時",
+    "如果分析错误": "如果分析錯誤",
+    "如果有必要": "如果有必要",
+    "不要修改!! 高危设置！通过修改此设置": "不要修改!! 高危設置！通過修改此設置",
+    "ChatGLMFT消耗大量的内存": "ChatGLMFT消耗大量的內存",
+    "摘要生成后的文档路径": "摘要生成後的文件路徑",
+    "对全文进行概括": "對全文進行概述",
+    "LLM_MODEL是默认选中的模型": "LLM_MODEL是默認選中的模型",
+    "640个字节为一组": "640個字節為一組",
+    "获取关键词": "獲取關鍵詞",
+    "解析为简体中文": "解析為簡體中文",
+    "将 \\include 命令转换为 \\input 命令": "將 \\include 命令轉換為 \\input 命令",
+    "默认值为1000": "默認值為1000",
+    "手动指定语言": "手動指定語言",
+    "请登录OpenAI查看详情 https": "請登錄OpenAI查看詳情 https",
+    "尝试第": "嘗試第",
+    "每秒采样数量": "每秒採樣數量",
+    "加载失败!": "加載失敗!",
+    "方法": "方法",
+    "对这个人外貌、身处的环境、内心世界、过去经历进行描写": "對這個人外貌、身處的環境、內心世界、過去經歷進行描寫",
+    "请先将.doc文档转换为.docx文档": "請先將.doc文檔轉換為.docx文檔",
+    "定位主Latex文件": "定位主Latex文件",
+    "批量SummarizeAudioAndVideo": "批量摘要音视频",
+    "终端": "終端",
+    "即将退出": "即將退出",
+    "找不到": "找不到",
+    "正在听您讲话": "正在聆聽您講話",
+    "请您不要删除或修改这行警告": "請勿刪除或修改此警告",
+    "没有阿里云语音识别APPKEY和TOKEN": "沒有阿里雲語音識別APPKEY和TOKEN",
+    "临时地启动代理网络": "臨時啟動代理網絡",
+    "请尝试把以下指令复制到高级参数区": "請將以下指令複製到高級參數區",
+    "中文Bing版": "中文Bing版",
+    "计算文件总时长和切割点": "計算文件總時長和切割點",
+    "寻找主文件": "尋找主文件",
+    "jittorllms尚未加载": "jittorllms尚未加載",
+    "使用正则表达式查找半行注释": "使用正則表達式查找半行註釋",
+    "文档越长耗时越长": "文檔越長耗時越長",
+    "生成中文PDF": "生成中文PDF",
+    "写入文件": "寫入文件",
+    "第三组插件": "第三組插件",
+    "开始接收chatglmft的回复": "開始接收chatglmft的回覆",
+    "由于提问含不合规内容被Azure过滤": "由於提問含不合規內容被Azure過濾",
+    "安装方法https": "安裝方法https",
+    "是否自动处理token溢出的情况": "是否自動處理token溢出的情況",
+    "如果需要使用AZURE 详情请见额外文档 docs\\use_azure.md": "如果需要使用AZURE 詳情請見額外文檔 docs\\use_azure.md",
+    "将要忽略匹配的文件后缀": "將要忽略匹配的文件後綴",
+    "authors获取失败": "authors獲取失敗",
+    "发送到openai音频解析终端": "發送到openai音頻解析終端",
+    "请开始多线程操作": "請開始多線程操作",
+    "对这个人外貌、身处的环境、内心世界、人设进行描写": "對這個人外貌、身處的環境、內心世界、人設進行描寫",
+    "MOSS can understand and communicate fluently in the language chosen by the user such as English and 中文. MOSS can perform any language-based tasks.": "MOSS可以流利地理解和使用用戶選擇的語言，例如英語和中文。MOSS可以執行任何基於語言的任務。",
+    "work_folder = Latex預處理": "設置工作目錄為Latex預處理",
+    "然後轉移到指定的另一個路徑中": "然後轉移到指定的另一個路徑中",
+    "使用Newbing": "使用Newbing",
+    "詳情信息見requirements.txt": "詳細信息請參閱requirements.txt",
+    "開始下載": "開始下載",
+    "多線程翻譯開始": "多線程翻譯開始",
+    "當前大語言模型": "當前大語言模型",
+    "格式如org-123456789abcdefghijklmno的": "格式如org-123456789abcdefghijklmno的",
+    "當下一次用戶提交時": "當下一次用戶提交時",
+    "需要特殊依賴": "需要特殊依賴",
+    "次編譯": "次編譯",
+    "先上傳數據集": "先上傳數據集",
+    "gpt寫的": "gpt寫的",
+    "調用緩存": "調用緩存",
+    "优先级1. 获取环境变量作为配置": "優先級1. 獲取環境變量作為配置",
+    "检查config中的AVAIL_LLM_MODELS选项": "檢查config中的AVAIL_LLM_MODELS選項",
+    "并且对于网络上的文件": "並且對於網絡上的文件",
+    "根据文本使用GPT模型生成相应的图像": "根據文本使用GPT模型生成相應的圖像",
+    "功能描述": "功能描述",
+    "翻译结果": "翻譯結果",
+    "需要预先pip install rarfile": "需要預先pip install rarfile",
+    "等待响应": "等待響應",
+    "我们剥离Introduction之后的部分": "我們剝離Introduction之後的部分",
+    "函数插件-固定按钮区": "函數插件-固定按鈕區",
+    "临时存储用于调试": "臨時存儲用於調試",
+    "比正文字体小": "比正文字體小",
+    "会直接转到该函数": "會直接轉到該函數",
+    "请以以下方式load模型！！！": "請以以下方式load模型！！！",
+    "请输入关键词": "請輸入關鍵詞",
+    "返回找到的第一个": "返回找到的第一個",
+    "高级参数输入区": "高級參數輸入區",
+    "精细切分latex文件": "精細切分latex文件",
+    "赋予插件锁定 锁定插件回调路径": "賦予插件鎖定 鎖定插件回調路徑",
+    "尝试下载": "嘗試下載",
+    "包含documentclass关键字": "包含documentclass關鍵字",
+    "在一个异步线程中采集音频": "在一個異步線程中採集音頻",
+    "先删除": "先刪除",
+    "则跳过GPT请求环节": "則跳過GPT請求環節",
+    "Not enough point. API2D账户点数不足": "Not enough point. API2D帳戶點數不足",
+    "如果一句话小于7个字": "如果一句話小於7個字",
+    "具备以下功能": "具備以下功能",
+    "请查看终端的输出或耐心等待": "請查看終端的輸出或耐心等待",
+    "对输入的word文档进行摘要生成": "對輸入的word文檔進行摘要生成",
+    "只读": "只讀",
+    "文本碎片重组为完整的tex文件": "文本碎片重組為完整的tex文件",
+    "通过调用conversations_open方法打开一个频道": "通過調用conversations_open方法打開一個頻道",
+    "对话历史文件损坏！": "對話歷史文件損壞！",
+    "再失败就没办法了": "再失敗就沒辦法了",
+    "原始PDF编译是否成功": "原始PDF編譯是否成功",
+    "不能正常加载jittorllms的参数！": "不能正常加載jittorllms的參數！",
+    "正在编译对比PDF": "正在編譯對比PDF",
+    "找不到微调模型检查点": "找不到微調模型檢查點",
+    "将生成的报告自动投射到文件上传区": "將生成的報告自動投射到文件上傳區",
+    "请对这部分内容进行语法矫正": "請對這部分內容進行語法校正",
+    "编译已经开始": "編譯已經開始",
+    "需要读取和清理文本的pdf文件路径": "需要讀取和清理文本的pdf文件路徑",
+    "读取文件内容到内存": "讀取文件內容到內存",
+    "用&符号分隔": "用&符號分隔",
+    "输入arxivID": "輸入arxivID",
+    "找 API_ORG 设置项": "找API_ORG設置項",
+    "分析用户提供的谷歌学术": "分析用戶提供的谷歌學術",
+    "欢迎使用 MOSS 人工智能助手！输入内容即可进行对话": "歡迎使用 MOSS 人工智能助手！輸入內容即可進行對話",
+    "段音频的第": "段音頻的第",
+    "没有找到任何可读取文件": "沒有找到任何可讀取文件",
+    "目前仅支持GPT3.5/GPT4": "目前僅支持GPT3.5/GPT4",
+    "为每一位访问的用户赋予一个独一无二的uuid编码": "為每一位訪問的用戶賦予一個獨一無二的uuid編碼",
+    "内含已经翻译的Tex文档": "內含已經翻譯的Tex文檔",
+    "消耗时间的函数": "消耗時間的函數",
+    "成功啦": "成功啦",
+    "环境变量配置格式见docker-compose.yml": "環境變量配置格式見docker-compose.yml",
+    "将每次对话记录写入Markdown格式的文件中": "將每次對話記錄寫入Markdown格式的文件中",
+    "报告已经添加到右侧“文件上传区”": "報告已經添加到右側“文件上傳區”",
+    "此处可以输入解析提示": "此處可以輸入解析提示",
+    "缺少MOSS的依赖": "缺少MOSS的依賴",
+    "仅在Windows系统进行了测试": "僅在Windows系統進行了測試",
+    "然后重启程序": "然後重啟程序",
+    "此处不修改": "此處不修改",
+    "输出html调试文件": "輸出html調試文件",
+    "6.25 加入判定latex模板的代码": "6.25 加入判定latex模板的代碼",
+    "提取总结": "提取總結",
+    "要求": "要求",
+    "由于最为关键的转化PDF编译失败": "由於最為關鍵的轉化PDF編譯失敗",
+    "除非您是论文的原作者": "除非您是論文的原作者",
+    "输入问题后点击该插件": "輸入問題後點擊該插件",
+    "该选项即将被弃用": "該選項即將被棄用",
+    "再列出用户可能提出的三个问题": "再列出用戶可能提出的三個問題",
+    "所有文件都总结完成了吗": "所有文件都總結完成了嗎",
+    "请稍候": "請稍候",
+    "向chatbot中添加简单的意外错误信息": "向chatbot中添加簡單的意外錯誤信息",
+    "快捷的调试函数": "快捷的調試函數",
+    "LatexEnglishCorrection+高亮修正位置": "Latex英文校正+高亮修正位置",
+    "循环监听已打开频道的消息": "循環監聽已打開頻道的消息",
+    "将指定目录下的PDF文件从英文翻译成中文": "將指定目錄下的PDF文件從英文翻譯成中文",
+    "请对下面的音频片段做概述": "請對下面的音頻片段做概述",
+    "openai的官方KEY需要伴隨组织编码": "openai的官方KEY需要伴隨組織編碼",
+    "表示频道ID": "頻道ID",
+    "当前支持的格式包括": "目前支援的格式包括",
+    "只有GenerateImage和生成图像相关": "僅限GenerateImage和生成圖像相關",
+    "删除中间文件夹": "刪除中間資料夾",
+    "解除插件状态": "解除插件狀態",
+    "正在预热文本向量化模组": "正在預熱文本向量化模組",
+    "100字以内": "限制100字內",
+    "如果缺少依赖": "如果缺少相依性",
+    "寻找主tex文件": "尋找主要tex檔案",
+    "gpt 多线程请求": "gpt 多線程請求",
+    "已知某些代码的局部作用是": "已知某些程式碼的局部作用是",
+    "--读取文件": "--讀取檔案",
+    "前面是中文冒号": "前面是中文冒號",
+    "*{\\scriptsize\\textbf{警告": "*{\\scriptsize\\textbf{警告",
+    "OpenAI所允许的最大并行过载": "OpenAI所允許的最大並行過載",
+    "请直接去该路径下取回翻译结果": "請直接前往該路徑取回翻譯結果",
+    "以免输入溢出": "以免輸入溢出",
+    "把某个路径下所有文件压缩": "壓縮某個路徑下的所有檔案",
+    "问询记录": "詢問記錄",
+    "Tex源文件缺失！": "Tex原始檔案遺失！",
+    "当前参数": "目前參數",
+    "处理markdown文本格式的转变": "處理markdown文本格式的轉換",
+    "尝试加载": "嘗試載入",
+    "请在此处给出自定义翻译命令": "請在此處提供自訂翻譯命令",
+    "这需要一段时间计算": "這需要一段時間計算",
+    "-构建知识库": "-建立知識庫",
+    "还需要填写组织": "還需要填寫組織",
+    "当前知识库内的有效文件": "當前知識庫內的有效文件",
+    "第一次调用": "第一次調用",
+    "从一批文件": "從一批文件",
+    "json等": "json等",
+    "翻译-": "翻譯-",
+    "编译文献交叉引用": "編譯文獻交叉引用",
+    "优先级2. 获取config_private中的配置": "優先級2. 獲取config_private中的配置",
+    "可选": "可選",
+    "我们": "我們",
+    "编译结束": "編譯結束",
+    "或代理节点": "或代理節點",
+    "chatGPT 分析报告": "chatGPT 分析報告",
+    "调用openai api 使用whisper-1模型": "調用openai api 使用whisper-1模型",
+    "这段代码定义了一个名为TempProxy的空上下文管理器": "這段代碼定義了一個名為TempProxy的空上下文管理器",
+    "生成的视频文件路径": "生成的視頻文件路徑",
+    "请直接提交即可": "請直接提交即可",
+    "=================================== 工具函数 ===============================================": "=================================== 工具函數 ===============================================",
+    "报错信息如下. 如果是与网络相关的问题": "報錯信息如下. 如果是與網絡相關的問題",
+    "python 版本建议3.9+": "python 版本建議3.9+",
+    "多线程函数插件中": "多線程函數插件中",
+    "对话助手函数插件": "對話助手函數插件",
+    "或者重启之后再度尝试": "或者重啟之後再度嘗試",
+    "拆分过长的latex片段": "拆分過長的latex片段",
+    "调用whisper模型音频转文字": "調用whisper模型音頻轉文字",
+    "失败啦": "失敗啦",
+    "正在编译PDF": "正在編譯PDF",
+    "请刷新界面重试": "請刷新界面重試",
+    "模型参数": "模型參數",
+    "写出文件": "寫出文件",
+    "第二组插件": "第二組插件",
+    "在多Tex文档中": "在多Tex文檔中",
+    "有线程锁": "有線程鎖",
+    "释放线程锁": "釋放線程鎖",
+    "读取优先级": "讀取優先級",
+    "Linux下必须使用Docker安装": "Linux下必須使用Docker安裝",
+    "例如您可以将以下命令复制到下方": "例如您可以將以下命令複製到下方",
+    "导入依赖失败": "導入依賴失敗",
+    "给出一些判定模板文档的词作为扣分项": "給出一些判定模板文檔的詞作為扣分項",
+    "等待Claude响应中": "等待Claude響應中",
+    "Call ChatGLMFT fail 不能正常加载ChatGLMFT的参数": "Call ChatGLMFT fail 不能正常加載ChatGLMFT的參數",
+    "但本地存储了以下历史文件": "但本地存儲了以下歷史文件",
+    "如果存在调试缓存文件": "如果存在調試緩存文件",
+    "如果这里抛出异常": "如果這裡拋出異常",
+    "详见项目主README.md": "詳見項目主README.md",
+    "作者": "作者",
+    "现在您点击任意“红颜色”标识的函数插件时": "現在您點擊任意“紅顏色”標識的函數插件時",
+    "上下文管理器必须实现两个方法": "上下文管理器必須實現兩個方法",
+    "匹配^数字^": "匹配^數字^",
+    "也是可读的": "也是可讀的",
+    "将音频解析为简体中文": "將音頻解析為簡體中文",
+    "依次访问网页": "依次訪問網頁",
+    "P.S. 顺便把CTEX塞进去以支持中文": "P.S. 順便把CTEX塞進去以支持中文",
+    "NewBing响应异常": "NewBing響應異常",
+    "获取已打开频道的最新消息并返回消息列表": "獲取已打開頻道的最新消息並返回消息列表",
+    "请使用Markdown": "請使用Markdown",
+    "例如 RoPlZrM88DnAFkZK": "例如 RoPlZrM88DnAFkZK",
+    "编译BibTex": "編譯BibTex",
+    "Claude失败": "Claude失敗",
+    "请更换为API_URL_REDIRECT配置": "請更換為API_URL_REDIRECT配置",
+    "P.S. 其他可用的模型还包括": "P.S. 其他可用的模型還包括",
+    "色彩主体": "色彩主體",
+    "后面是英文逗号": "後面是英文逗號",
+    "下载pdf文件未成功": "下載pdf文件未成功",
+    "删除整行的空注释": "刪除整行的空注釋",
+    "吸收匿名公式": "吸收匿名公式",
+    "从而更全面地理解项目的整体功能": "從而更全面地理解項目的整體功能",
+    "不需要再次转化": "不需要再次轉化",
+    "可以将自身的状态存储到cookie中": "可以將自身的狀態存儲到cookie中",
+    "1、英文题目；2、中文题目翻译；3、作者；4、arxiv公开": "1、英文題目；2、中文題目翻譯；3、作者；4、arxiv公開",
+    "GPT 学术优化": "GPT 學術優化",
+    "解析整个Python项目": "解析整個Python項目",
+    "吸收其他杂项": "吸收其他雜項",
+    "-预热文本向量化模组": "-預熱文本向量化模組",
+    "Claude组件初始化成功": "Claude組件初始化成功",
+    "此处填API密钥": "此處填API密鑰",
+    "请继续分析其他源代码": "請繼續分析其他源代碼",
+    "质能方程式": "質能方程式",
+    "功能尚不稳定": "功能尚不穩定",
+    "使用教程详情见 request_llm/README.md": "使用教程詳情見 request_llm/README.md",
+    "从以上搜索结果中抽取信息": "從以上搜索結果中抽取信息",
+    "虽然PDF生成失败了": "雖然PDF生成失敗了",
+    "找图片": "尋找圖片",
+    "还原原文": "還原原文",
+    "可调节线程池的大小避免openai的流量限制错误": "可調整線程池大小以避免openai流量限制錯誤",
+    "正在提取摘要并下载PDF文档……": "正在提取摘要並下載PDF文件......",
+    "缺少ChatGLMFT的依赖": "缺少ChatGLMFT的依賴",
+    "不会实时显示在界面上": "不會即時顯示在界面上",
+    "解决部分词汇翻译不准确的问题": "解決部分詞彙翻譯不準確的問題",
+    "等待多线程操作": "等待多線程操作",
+    "吸收title与作者以上的部分": "吸收標題與作者以上的部分",
+    "如果需要使用Slack Claude": "如果需要使用Slack Claude",
+    "一、论文概况": "一、論文概況",
+    "默认为Chinese": "默認為中文",
+    "图像生成所用到的提示文本": "圖像生成所用到的提示文本",
+    "向已打开的频道发送一条文本消息": "向已打開的頻道發送一條文本消息",
+    "如果某个子任务出错": "如果某個子任務出錯",
+    "chatglmft 没有 sys_prompt 接口": "chatglmft沒有sys_prompt接口",
+    "对比PDF编译是否成功": "對比PDF編譯是否成功",
+    "免费": "免費",
+    "请讲话": "請講話",
+    "安装ChatGLM的依赖": "安裝ChatGLM的依賴",
+    "对IPynb文件进行解析": "對IPynb文件進行解析",
+    "文件路径列表": "文件路徑列表",
+    "或者使用此插件继续上传更多文件": "或者使用此插件繼續上傳更多文件",
+    "随机负载均衡": "隨機負載均衡",
+    "！！！如果需要运行量化版本": "！！！如果需要運行量化版本",
+    "注意目前不能多人同时调用Claude接口": "注意目前不能多人同時調用Claude接口",
+    "文件读取完成": "文件讀取完成",
+    "用于灵活调整复杂功能的各种参数": "用於靈活調整複雜功能的各種參數",
+    "**函数功能**": "**函數功能**",
+    "先切换模型到openai或api2d": "先切換模型到openai或api2d",
+    "You are associated with a deactivated account. OpenAI以账户失效为由": "您的帳戶已停用。OpenAI以帳戶失效為由",
+    "你的回答必须简单明了": "您的回答必須簡單明了",
+    "是否丢弃掉 不是正文的内容": "是否丟棄掉 不是正文的內容",
+    "但请查收结果": "但請查收結果",
+    "Claude响应缓慢": "Claude響應緩慢",
+    "需Latex": "需Latex",
+    "Claude回复的片段": "Claude回復的片段",
+    "如果要使用ChatGLMFT": "如果要使用ChatGLMFT",
+    "它*必须*被包含在AVAIL_LLM_MODELS列表中": "它*必須*被包含在AVAIL_LLM_MODELS列表中",
+    "前面是中文逗号": "前面是中文逗號",
+    "需要预先pip install py7zr": "需要預先pip install py7zr",
+    "将前后断行符脱离": "將前後斷行符脫離",
+    "防止丢失最后一条消息": "防止丟失最後一條消息",
+    "初始化插件状态": "初始化插件狀態",
+    "以秒为单位": "以秒為單位",
+    "中文Latex项目全文润色": "中文Latex項目全文潤色",
+    "对整个Latex项目进行纠错": "對整個Latex項目進行校對",
+    "NEWBING_COOKIES未填写或有格式错误": "NEWBING_COOKIES未填寫或有格式錯誤",
+    "函数插件作者": "函數插件作者",
+    "结束": "結束",
+    "追加历史": "追加歷史",
+    "您需要首先调用构建知识库": "您需要首先調用構建知識庫",
+    "如果程序停顿5分钟以上": "如果程序停頓5分鐘以上",
+    "ChatGLMFT响应异常": "ChatGLMFT響應異常",
+    "根据当前的模型类别": "根據當前的模型類別",
+    "才能继续下面的步骤": "才能繼續下面的步驟",
+    "并将返回的频道ID保存在属性CHANNEL_ID中": "並將返回的頻道ID保存在屬性CHANNEL_ID中",
+    "请查收结果": "請查收結果",
+    "解决插件锁定时的界面显示问题": "解決插件鎖定時的界面顯示問題",
+    "待提取的知识库名称id": "待提取的知識庫名稱id",
+    "Claude响应异常": "Claude響應異常",
+    "当前代理可用性": "當前代理可用性",
+    "代理网络配置": "代理網絡配置",
+    "我将为您查找相关壁纸": "我將為您查找相關壁紙",
+    "没给定指令": "沒給定指令",
+    "音频内容是": "音頻內容是",
+    "用该压缩包+ConversationHistoryArchive进行反馈": "用該壓縮包+ConversationHistoryArchive進行反饋",
+    "总结音频": "總結音頻",
+    "等待用户的再次调用": "等待用戶的再次調用",
+    "永远给定None": "永遠給定None",
+    "论文概况": "論文概況",
+    "建议使用英文单词": "建議使用英文單詞",
+    "刷新Gradio前端界面": "刷新Gradio前端界面",
+    "列表递归接龙": "列表遞歸接龍",
+    "赋予插件状态": "賦予插件狀態",
+    "构建完成": "構建完成",
+    "避免多用户干扰": "避免多用戶干擾",
+    "当前工作路径为": "當前工作路徑為",
+    "用黑色标注转换区": "用黑色標注轉換區",
+    "压缩包": "壓縮包",
+    "刷新页面即可以退出KnowledgeBaseQA模式": "刷新頁面即可以退出KnowledgeBaseQA模式",
+    "拆分过长的Markdown文件": "拆分過長的Markdown文件",
+    "生成时间戳": "生成時間戳",
+    "尚未完成全部响应": "尚未完成全部響應",
+    "HotReload的装饰器函数": "HotReload的裝飾器函數",
+    "请务必用 pip install -r requirements.txt 指令安装依赖": "請務必用 pip install -r requirements.txt 指令安裝依賴",
+    "TGUI不支持函数插件的实现": "TGUI不支持函數插件的實現",
+    "音频文件名": "音頻文件名",
+    "找不到任何音频或视频文件": "找不到任何音頻或視頻文件",
+    "音频解析结果": "音頻解析結果",
+    "如果使用ChatGLM2微调模型": "如果使用ChatGLM2微調模型",
+    "限制的3/4时": "限制的3/4時",
+    "获取回复": "獲取回復",
+    "对话历史写入": "對話歷史寫入",
+    "记录删除注释后的文本": "記錄刪除註釋後的文本",
+    "整理结果为压缩包": "整理結果為壓縮包",
+    "注意事项": "注意事項",
+    "请耐心等待": "請耐心等待",
+    "在执行完成之后": "在執行完成之後",
+    "参数简单": "參數簡單",
+    "Arixv论文精细翻译": "Arixv論文精細翻譯",
+    "备份和下载": "備份和下載",
+    "当前报错的latex代码处于第": "當前報錯的latex代碼處於第",
+    "Markdown翻译": "Markdown翻譯",
+    "英文Latex项目全文纠错": "英文Latex項目全文校對",
+    "获取预处理函数": "獲取預處理函數",
+    "add gpt task 创建子线程请求gpt": "add gpt task 創建子線程請求gpt",
+    "一个包含所有切割音频片段文件路径的列表": "一個包含所有切割音頻片段文件路徑的列表",
+    "解析arxiv网址失败": "解析arxiv網址失敗",
+    "PDF文件所在的路径": "PDF文件所在路徑",
+    "取评分最高者返回": "取評分最高者返回",
+    "此插件处于开发阶段": "此插件處於開發階段",
+    "如果已经存在": "如果已經存在",
+    "或者不在环境变量PATH中": "或者不在環境變量PATH中",
+    "目前支持的格式": "目前支持的格式",
+    "将多文件tex工程融合为一个巨型tex": "將多文件tex工程融合為一個巨型tex",
+    "暂不提交": "暫不提交",
+    "调用函数": "調用函數",
+    "编译转化后的PDF": "編譯轉化後的PDF",
+    "将代码转为动画": "將代碼轉為動畫",
+    "本地Latex论文精细翻译": "本地Latex論文精細翻譯",
+    "删除或修改歧义文件": "刪除或修改歧義文件",
+    "其他操作系统表现未知": "其他操作系統表現未知",
+    "此插件Windows支持最佳": "此插件Windows支持最佳",
+    "构建知识库": "構建知識庫",
+    "每个切割音频片段的时长": "每個切割音頻片段的時長",
+    "用latex编译为PDF对修正处做高亮": "用latex編譯為PDF對修正處做高亮",
+    "行": "行",
+    "= 2 通过一些Latex模板中常见": "= 2 通過一些Latex模板中常見",
+    "如参考文献、脚注、图注等": "如參考文獻、腳註、圖註等",
+    "期望格式例如": "期望格式例如",
+    "翻译内容可靠性无保障": "翻譯內容可靠性無保障",
+    "请用一句话概括这些文件的整体功能": "請用一句話概括這些文件的整體功能",
+    "段音频完成了吗": "段音頻完成了嗎",
+    "填入azure openai api的密钥": "填入azure openai api的密鑰",
+    "文本碎片重组为完整的tex片段": "文本碎片重組為完整的tex片段",
+    "吸收在42行以內的begin-end組合": "吸收在42行以內的begin-end組合",
+    "屬性": "屬性",
+    "必須包含documentclass": "必須包含documentclass",
+    "等待GPT響應": "等待GPT響應",
+    "當前語言模型溫度設定": "當前語言模型溫度設定",
+    "模型選擇是": "選擇的模型為",
+    "reverse 操作必須放在最後": "reverse 操作必須放在最後",
+    "將子線程的gpt結果寫入chatbot": "將子線程的gpt結果寫入chatbot",
+    "默認為default": "默認為default",
+    "目前對機器學習類文獻轉化效果最好": "目前對機器學習類文獻轉化效果最好",
+    "主程序即將開始": "主程序即將開始",
+    "點擊“停止”鍵可終止程序": "點擊“停止”鍵可終止程序",
+    "正在處理": "正在處理",
+    "請立即終止程序": "請立即停止程序",
+    "將 chatglm 直接對齊到 chatglm2": "將 chatglm 直接對齊到 chatglm2",
+    "音頻助手": "音頻助手",
+    "正在構建知識庫": "正在構建知識庫",
+    "請向下翻": "請向下滾動頁面",
+    "後面是英文冒號": "後面是英文冒號",
+    "無法找到一個主Tex文件": "無法找到一個主Tex文件",
+    "使用中文总结音频“": "使用中文總結音頻",
+    "该PDF由GPT-Academic开源项目调用大语言模型+Latex翻译插件一键生成": "該PDF由GPT-Academic開源項目調用大語言模型+Latex翻譯插件一鍵生成",
+    "开始生成动画": "開始生成動畫",
+    "完成情况": "完成情況",
+    "然后进行问答": "然後進行問答",
+    "为啥chatgpt会把cite里面的逗号换成中文逗号呀": "為啥chatgpt會把cite裡面的逗號換成中文逗號呀",
+    "暂时不支持历史消息": "暫時不支持歷史消息",
+    "项目Github地址 \\url{https": "項目Github地址 \\url{https",
+    "Newbing 请求失败": "Newbing 請求失敗",
+    "根据自然语言执行插件命令": "根據自然語言執行插件命令",
+    "迭代上一次的结果": "迭代上一次的結果",
+    "azure和api2d请求源": "azure和api2d請求源",
+    "格式如org-xxxxxxxxxxxxxxxxxxxxxxxx": "格式如org-xxxxxxxxxxxxxxxxxxxxxxxx",
+    "推荐http": "推薦http",
+    "将要匹配的模式": "將要匹配的模式",
+    "代理数据解析失败": "代理數據解析失敗",
+    "创建存储切割音频的文件夹": "創建存儲切割音頻的文件夾",
+    "用红色标注处保留区": "用紅色標注處保留區",
+    "至少一个线程任务Token溢出而失败": "至少一個線程任務Token溢出而失敗",
+    "获取Slack消息失败": "獲取Slack消息失敗",
+    "极少数情况下": "極少數情況下",
+    "辅助gpt生成代码": "輔助gpt生成代碼",
+    "生成图像": "生成圖像",
+    "最多收纳多少个网页的结果": "最多收納多少個網頁的結果",
+    "获取图片URL": "獲取圖片URL",
+    "正常状态": "正常狀態",
+    "编译原始PDF": "編譯原始PDF",
+    "SummarizeAudioAndVideo内容": "音視頻摘要內容",
+    "Latex文件融合完成": "Latex文件融合完成",
+    "获取线程锁": "獲取線程鎖",
+    "SlackClient类用于与Slack API进行交互": "SlackClient類用於與Slack API進行交互",
+    "检测到arxiv文档连接": "檢測到arxiv文檔連接",
+    "--读取参数": "--讀取參數",
+    "如果您是论文原作者": "如果您是論文原作者",
+    "5刀": "5美元",
+    "转化PDF编译是否成功": "轉換PDF編譯是否成功",
+    "生成带有段落标签的HTML代码": "生成帶有段落標籤的HTML代碼",
+    "目前不支持历史消息查询": "目前不支持歷史消息查詢",
+    "将文件添加到chatbot cookie中": "將文件添加到chatbot cookie中",
+    "多线程操作已经开始": "多線程操作已經開始",
+    "请求子进程": "請求子進程",
+    "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": "將Unsplash API中的PUT_YOUR_QUERY_HERE替換成描述該事件的一個最重要的單詞",
+    "不能加载Claude组件": "不能加載Claude組件",
+    "请仔细鉴别并以原文为准": "請仔細鑒別並以原文為準",
+    "否则结束循环": "否則結束循環",
+    "插件可读取“输入区”文本/路径作为参数": "插件可讀取“輸入區”文本/路徑作為參數",
+    "网络错误": "網絡錯誤",
+    "想象一个穿着者": "想像一個穿著者",
+    "避免遗忘导致死锁": "避免遺忘導致死鎖",
+    "保证括号正确": "保證括號正確",
+    "报错信息": "錯誤信息",
+    "提取视频中的音频": "提取視頻中的音頻",
+    "初始化音频采集线程": "初始化音頻採集線程",
+    "参考文献转Bib": "參考文獻轉Bib",
+    "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": "阿里云即時語音識別配置難度較高，僅建議高手用戶使用，參考 https",
+    "使用时": "使用時",
+    "处理个别特殊插件的锁定状态": "處理個別特殊插件的鎖定狀態",
+    "但通常不会出现在正文": "但通常不會出現在正文",
+    "此函数逐渐地搜索最长的条目进行剪辑": "此函數逐漸地搜索最長的條目進行剪輯",
+    "给出指令": "給出指令",
+    "读取音频文件": "讀取音頻文件",
+    "========================================= 插件主程序1 =====================================================": "========================================= 插件主程序1 =====================================================",
+    "带超时倒计时": "帶超時倒計時",
+    "禁止移除或修改此警告": "禁止移除或修改此警告",
+    "ChatGLMFT尚未加载": "ChatGLMFT尚未加載",
+    "双手离开鼠标键盘吧": "雙手離開鼠標鍵盤吧",
+    "缺少的依赖": "缺少的依賴",
+    "的单词": "的單詞",
+    "中读取数据构建知识库": "中讀取數據構建知識庫",
+    "函数热更新是指在不停止程序运行的情况下": "函數熱更新是指在不停止程序運行的情況下",
+    "建议低于1": "建議低於1",
+    "转化PDF编译已经成功": "轉換PDF編譯已經成功",
+    "出问题了": "出問題了",
+    "欢迎使用 MOSS 人工智能助手！": "歡迎使用 MOSS 人工智能助手！",
+    "正在精细切分latex文件": "正在精細切分LaTeX文件",
+    "”补上": "”補上",
+    "网络代理状态": "網路代理狀態",
+    "依赖检测通过": "依賴檢測通過",
+    "默认为default": "預設為default",
+    "Call MOSS fail 不能正常加载MOSS的参数": "呼叫MOSS失敗，無法正常載入MOSS參數",
+    "音频助手": "音頻助手",
+    "次编译": "次編譯",
+    "其他错误": "其他錯誤",
+    "属性": "屬性",
+    "主程序即将开始": "主程式即將開始",
+    "Aliyun音频服务异常": "Aliyun音頻服務異常",
+    "response中会携带traceback报错信息": "response中會攜帶traceback錯誤信息",
+    "一些普通功能模块": "一些普通功能模組",
+    "和openai的连接容易断掉": "和openai的連線容易斷掉",
+    "请检查ALIYUN_TOKEN和ALIYUN_APPKEY是否过期": "請檢查ALIYUN_TOKEN和ALIYUN_APPKEY是否過期",
+    "调用Claude时": "呼叫Claude時",
+    "插件锁定中": "插件鎖定中",
+    "将子线程的gpt结果写入chatbot": "將子線程的gpt結果寫入chatbot",
+    "当下一次用户提交时": "當下一次使用者提交時",
+    "先上传数据集": "先上傳資料集",
+    "请在此处追加更细致的矫错指令": "請在此處追加更細緻的矯錯指令",
+    "无法找到一个主Tex文件": "無法找到一個主Tex文件",
+    "gpt写的": "gpt寫的",
+    "预处理": "預處理",
+    "但大部分场合下并不需要修改": "但大部分場合下並不需要修改",
+    "正在构建知识库": "正在建構知識庫",
+    "开始请求": "開始請求",
+    "根据以上分析": "根據以上分析",
+    "需要特殊依赖": "需要特殊依賴",
+    "用于基础的对话功能": "用於基礎的對話功能",
+    "且没有代码段": "且沒有程式碼段",
+    "取决于": "取決於",
+    "openai的官方KEY需要伴隨組織編碼": "請填入組織編碼",
+    "等待newbing回覆的片段": "等待newbing回覆的片段",
+    "调用缓存": "呼叫快取",
+    "模型选择是": "模型選擇為",
+    "当前大语言模型": "當前大語言模型",
+    "然后转移到指定的另一个路径中": "然後轉移到指定的另一個路徑中",
+    "请向下翻": "請向下滾動",
+    "内容太长了都会触发token数量溢出的错误": "內容太長會觸發token數量溢出的錯誤",
+    "每一块": "每一塊",
+    "详情信息见requirements.txt": "詳細信息見requirements.txt",
+    "没有提供高级参数功能说明": "沒有提供高級參數功能說明",
+    "上传Latex项目": "上傳Latex項目",
+    "请立即终止程序": "請立即終止程式",
+    "解除插件锁定": "解除插件鎖定",
+    "意外Json结构": "意外Json結構",
+    "必须包含documentclass": "必須包含documentclass",
+    "10个文件为一组": "10個文件為一組",
+    "openai的官方KEY需要伴随组织编码": "openai的官方KEY需要伴隨組織編碼",
+    "重置文件的创建时间": "重置文件的創建時間",
+    "尽量是完整的一个section": "盡量是完整的一個section",
+    "报告如何远程获取": "報告如何遠程獲取",
+    "work_folder = Latex预处理": "work_folder = Latex預處理",
+    "吸收在42行以内的begin-end组合": "吸收在42行以內的begin-end組合",
+    "后面是英文冒号": "後面是英文冒號",
+    "使用latexdiff生成论文转化前后对比": "使用latexdiff生成論文轉化前後對比",
+    "首先你在英文语境下通读整篇论文": "首先你在英文語境下通讀整篇論文",
+    "为了防止大语言模型的意外谬误产生扩散影响": "為了防止大語言模型的意外謬誤產生擴散影響",
+    "发现已经存在翻译好的PDF文档": "發現已經存在翻譯好的PDF文檔",
+    "点击“停止”键可终止程序": "點擊“停止”鍵可終止程序",
+    "数学GenerateAnimations": "數學GenerateAnimations",
+    "随变按钮的回调函数注册": "隨變按鈕的回調函數註冊",
+    "history至少释放二分之一": "history至少釋放二分之一",
+    "当前语言模型温度设定": "當前語言模型溫度設定",
+    "等待GPT响应": "等待GPT響應",
+    "正在处理": "正在處理",
+    "多线程翻译开始": "多線程翻譯開始",
+    "reverse 操作必须放在最后": "reverse 操作必須放在最後",
+    "等待newbing回复的片段": "等待newbing回覆的片段",
+    "开始下载": "開始下載",
+    "将 chatglm 直接对齐到 chatglm2": "將 chatglm 直接對齊到 chatglm2",
+    "以上材料已经被写入": "以上材料已經被寫入",
+    "上传文件自动修正路径": "上傳文件自動修正路徑",
+    "然后请使用Markdown格式封装": "然後請使用Markdown格式封裝",
+    "目前对机器学习类文献转化效果最好": "目前對機器學習類文獻轉化效果最好",
+    "检查结果": "檢查結果",
+    "、地址": "地址",
+    "如.md": "如.md",
+    "使用Unsplash API": "使用Unsplash API",
+    "**输入参数说明**": "**輸入參數說明**",
+    "新版本可用": "新版本可用",
+    "找不到任何python文件": "找不到任何python文件",
+    "知乎": "知乎",
+    "日": "日",
+    "“喂狗”": "“喂狗”",
+    "第4步": "第4步",
+    "退出": "退出",
+    "使用 Unsplash API": "使用 Unsplash API"
 }
--- a/docs/use_audio.md
+++ b/docs/use_audio.md
@ -6,17 +6,23 @@
 pip install --upgrade pyOpenSSL scipy git+https://github.com/aliyun/alibabacloud-nls-python-sdk.git
 ```

-如果因为中国特色网络问题导致上述命令无法执行：
+如果因为特色网络问题导致上述命令无法执行：
 1. git clone alibabacloud-nls-python-sdk这个项目（或者直接前往Github对应网址下载压缩包）.
 命令行输入： `git clone https://github.com/aliyun/alibabacloud-nls-python-sdk.git`
 1. 进入alibabacloud-nls-python-sdk目录命令行输入：`python setup.py install`


 ## 2. 配置音频功能开关 和 阿里云APPKEY（config.py/config_private.py/环境变量）
+
+- 注册阿里云账号
+- 开通 智能语音交互 （有免费白嫖时长）
+- 获取token和appkey
+- 未来将逐步用其他更廉价的云服务取代阿里云
+
 ```
 ENABLE_AUDIO = True
-ALIYUN_TOKEN = "554a50fcd0bb476c8d07bb630e94d20c"    # 例如 f37f30e0f9934c34a992f6f64f7eba4f
-ALIYUN_APPKEY = "RoPlZrM88DnAFkZK"   # 例如 RoPlZrM88DnAFkZK
+ALIYUN_TOKEN = "554a50fcd0bb476c8d07bb630e94d20c"    # 此token已经失效
+ALIYUN_APPKEY = "RoPlZrM88DnAFkZK"   # 此appkey已经失效
 ```

 参考 https://help.aliyun.com/document_detail/450255.html
@ -38,7 +44,9 @@ II 如果需要监听电脑音频（不监听自己说话），需要安装`VB-A
  - 3-2 勾选Listen to this device。
  - 3-3 在playback through this device下拉菜单中选择你的正常耳机或音响。

-III 两种音频监听模式切换时，需要刷新页面才有效。
+III `[把特殊软件（如腾讯会议）的外放声音用VoiceMeeter截留]` 在完成步骤II的基础上，在特殊软件（如腾讯会议）中，打开声音菜单，选择扬声器VoiceMeeter Input，选择麦克风为正常耳机麦。
+
+VI 两种音频监听模式切换时，需要刷新页面才有效。

 ## 5.点击函数插件区“实时音频采集” 或者其他音频交互功能

--- a/main.py
+++ b/main.py
@ -14,7 +14,7 @@ def main():
    if not AUTHENTICATION: AUTHENTICATION = None

    from check_proxy import get_current_version
-    from theme.theme import adjust_theme, advanced_css, theme_declaration
+    from themes.theme import adjust_theme, advanced_css, theme_declaration
    initial_prompt = "Serve me as a writing and programming assistant."
    title_html = f"<h1 align=\"center\">GPT 学术优化 {get_current_version()}</h1>{theme_declaration}"
    description =  """代码开源和更新[地址🚀](https://github.com/binary-husky/chatgpt_academic)，感谢热情的[开发者们❤️](https://github.com/binary-husky/chatgpt_academic/graphs/contributors)"""
@ -22,8 +22,10 @@ def main():
    # 问询记录, python 版本建议3.9+（越新越好）
    import logging, uuid
    os.makedirs("gpt_log", exist_ok=True)
-    try:logging.basicConfig(filename="gpt_log/chat_secrets.log", level=logging.INFO, encoding="utf-8")
-    except:logging.basicConfig(filename="gpt_log/chat_secrets.log", level=logging.INFO)
+    try:logging.basicConfig(filename="gpt_log/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="gpt_log/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("所有问询记录将自动保存在本地目录./gpt_log/chat_secrets.log, 请注意自我隐私保护哦！")

    # 一些普通功能模块
--- a/request_llm/bridge_all.py
+++ b/request_llm/bridge_all.py
@ -170,6 +170,29 @@ model_info = {

 AVAIL_LLM_MODELS, LLM_MODEL = get_conf("AVAIL_LLM_MODELS", "LLM_MODEL")
 AVAIL_LLM_MODELS = AVAIL_LLM_MODELS + [LLM_MODEL]
+if "claude-1-100k" in AVAIL_LLM_MODELS or "claude-2" 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": {
+            "fn_with_ui": claude_ui,
+            "fn_without_ui": claude_noui,
+            "endpoint": None,
+            "max_token": 8196,
+            "tokenizer": tokenizer_gpt35,
+            "token_cnt": get_token_num_gpt35,
+        },
+    })
+    model_info.update({
+        "claude-2": {
+            "fn_with_ui": claude_ui,
+            "fn_without_ui": claude_noui,
+            "endpoint": None,
+            "max_token": 8196,
+            "tokenizer": tokenizer_gpt35,
+            "token_cnt": get_token_num_gpt35,
+        },
+    })
 if "jittorllms_rwkv" in AVAIL_LLM_MODELS:
    from .bridge_jittorllms_rwkv import predict_no_ui_long_connection as rwkv_noui
    from .bridge_jittorllms_rwkv import predict as rwkv_ui
@ -225,7 +248,6 @@ if "moss" in AVAIL_LLM_MODELS:
 if "stack-claude" in AVAIL_LLM_MODELS:
    from .bridge_stackclaude import predict_no_ui_long_connection as claude_noui
    from .bridge_stackclaude import predict as claude_ui
-    # claude
    model_info.update({
        "stack-claude": {
            "fn_with_ui": claude_ui,
@ -240,7 +262,6 @@ 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
-        # claude
        model_info.update({
            "newbing-free": {
                "fn_with_ui": newbingfree_ui,
@ -257,7 +278,6 @@ if "newbing" in AVAIL_LLM_MODELS:   # same with newbing-free
    try:
        from .bridge_newbingfree import predict_no_ui_long_connection as newbingfree_noui
        from .bridge_newbingfree import predict as newbingfree_ui
-        # claude
        model_info.update({
            "newbing": {
                "fn_with_ui": newbingfree_ui,
@ -274,7 +294,6 @@ if "chatglmft" in AVAIL_LLM_MODELS:   # same with newbing-free
    try:
        from .bridge_chatglmft import predict_no_ui_long_connection as chatglmft_noui
        from .bridge_chatglmft import predict as chatglmft_ui
-        # claude
        model_info.update({
            "chatglmft": {
                "fn_with_ui": chatglmft_ui,
@ -287,7 +306,22 @@ if "chatglmft" in AVAIL_LLM_MODELS:   # same with newbing-free
        })
    except:
        print(trimmed_format_exc())
-
+if "internlm" in AVAIL_LLM_MODELS:
+    try:
+        from .bridge_internlm import predict_no_ui_long_connection as internlm_noui
+        from .bridge_internlm import predict as internlm_ui
+        model_info.update({
+            "internlm": {
+                "fn_with_ui": internlm_ui,
+                "fn_without_ui": internlm_noui,
+                "endpoint": None,
+                "max_token": 4096,
+                "tokenizer": tokenizer_gpt35,
+                "token_cnt": get_token_num_gpt35,
+            }
+        })
+    except:
+        print(trimmed_format_exc())

 def LLM_CATCH_EXCEPTION(f):
    """
--- a/request_llm/bridge_chatglm.py
+++ b/request_llm/bridge_chatglm.py
@ -37,15 +37,23 @@ class GetGLMHandle(Process):
        # 子进程执行
        # 第一次运行，加载参数
        retry = 0
+        LOCAL_MODEL_QUANT, device = get_conf('LOCAL_MODEL_QUANT', 'LOCAL_MODEL_DEVICE')
+
+        if LOCAL_MODEL_QUANT == "INT4":         # INT4
+            _model_name_ = "THUDM/chatglm2-6b-int4"
+        elif LOCAL_MODEL_QUANT == "INT8":       # INT8
+            _model_name_ = "THUDM/chatglm2-6b-int8"
+        else:
+            _model_name_ = "THUDM/chatglm2-6b"  # FP16
+
        while True:
            try:
                if self.chatglm_model is None:
-                    self.chatglm_tokenizer = AutoTokenizer.from_pretrained("THUDM/chatglm2-6b", trust_remote_code=True)
-                    device, = get_conf('LOCAL_MODEL_DEVICE')
+                    self.chatglm_tokenizer = AutoTokenizer.from_pretrained(_model_name_, trust_remote_code=True)
                    if device=='cpu':
-                        self.chatglm_model = AutoModel.from_pretrained("THUDM/chatglm2-6b", trust_remote_code=True).float()
+                        self.chatglm_model = AutoModel.from_pretrained(_model_name_, trust_remote_code=True).float()
                    else:
-                        self.chatglm_model = AutoModel.from_pretrained("THUDM/chatglm2-6b", trust_remote_code=True).half().cuda()
+                        self.chatglm_model = AutoModel.from_pretrained(_model_name_, trust_remote_code=True).half().cuda()
                    self.chatglm_model = self.chatglm_model.eval()
                    break
                else:
--- a/request_llm/bridge_chatgpt.py
+++ b/request_llm/bridge_chatgpt.py
@ -174,9 +174,10 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
                chunk = next(stream_response)
            except StopIteration:
                # 非OpenAI官方接口的出现这样的报错，OpenAI和API2D不会走这里
-                from toolbox import regular_txt_to_markdown; tb_str = '```\n' + trimmed_format_exc() + '```'
-                chatbot[-1] = (chatbot[-1][0], f"[Local Message] 远程返回错误: \n\n{tb_str} \n\n{regular_txt_to_markdown(chunk.decode())}")
-                yield from update_ui(chatbot=chatbot, history=history, msg="远程返回错误:" + chunk.decode()) # 刷新界面
+                chunk_decoded = chunk.decode()
+                error_msg = chunk_decoded
+                chatbot, history = handle_error(inputs, llm_kwargs, chatbot, history, chunk_decoded, error_msg)
+                yield from update_ui(chatbot=chatbot, history=history, msg="非Openai官方接口返回了错误:" + chunk.decode()) # 刷新界面
                return
            
            # print(chunk.decode()[6:])
@ -187,7 +188,7 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
            if chunk:
                try:
                    chunk_decoded = chunk.decode()
-                    # 前者API2D的
+                    # 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(json.loads(chunk_decoded[6:])['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}')
@ -200,41 +201,45 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
                    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:
-                    traceback.print_exc()
                    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
-                    openai_website = ' 请登录OpenAI查看详情 https://platform.openai.com/signup'
-                    if "reduce the length" in error_msg:
-                        if len(history) >= 2: history[-1] = ""; history[-2] = "" # 清除当前溢出的输入：history[-2] 是本次输入, history[-1] 是本次输出
-                        history = clip_history(inputs=inputs, history=history, tokenizer=model_info[llm_kwargs['llm_model']]['tokenizer'], 
-                                               max_token_limit=(model_info[llm_kwargs['llm_model']]['max_token'])) # history至少释放二分之一
-                        chatbot[-1] = (chatbot[-1][0], "[Local Message] Reduce the length. 本次输入过长, 或历史数据过长. 历史缓存数据已部分释放, 您可以请再次尝试. (若再次失败则更可能是因为输入过长.)")
-                        # history = []    # 清除历史
-                    elif "does not exist" in error_msg:
-                        chatbot[-1] = (chatbot[-1][0], f"[Local Message] Model {llm_kwargs['llm_model']} does not exist. 模型不存在, 或者您没有获得体验资格.")
-                    elif "Incorrect API key" in error_msg:
-                        chatbot[-1] = (chatbot[-1][0], "[Local Message] Incorrect API key. OpenAI以提供了不正确的API_KEY为由, 拒绝服务. " + openai_website)
-                    elif "exceeded your current quota" in error_msg:
-                        chatbot[-1] = (chatbot[-1][0], "[Local Message] You exceeded your current quota. OpenAI以账户额度不足为由, 拒绝服务." + openai_website)
-                    elif "account is not active" in error_msg:
-                        chatbot[-1] = (chatbot[-1][0], "[Local Message] Your account is not active. OpenAI以账户失效为由, 拒绝服务." + openai_website)
-                    elif "associated with a deactivated account" in error_msg:
-                        chatbot[-1] = (chatbot[-1][0], "[Local Message] You are associated with a deactivated account. OpenAI以账户失效为由, 拒绝服务." + openai_website)
-                    elif "bad forward key" in error_msg:
-                        chatbot[-1] = (chatbot[-1][0], "[Local Message] Bad forward key. API2D账户额度不足.")
-                    elif "Not enough point" in error_msg:
-                        chatbot[-1] = (chatbot[-1][0], "[Local Message] Not enough point. API2D账户点数不足.")
-                    else:
-                        from toolbox import regular_txt_to_markdown
-                        tb_str = '```\n' + trimmed_format_exc() + '```'
-                        chatbot[-1] = (chatbot[-1][0], f"[Local Message] 异常 \n\n{tb_str} \n\n{regular_txt_to_markdown(chunk_decoded)}")
+                    chatbot, history = handle_error(inputs, llm_kwargs, chatbot, history, chunk_decoded, error_msg)
                    yield from update_ui(chatbot=chatbot, history=history, msg="Json异常" + error_msg) # 刷新界面
+                    print(error_msg)
                    return

+def handle_error(inputs, llm_kwargs, chatbot, history, chunk_decoded, error_msg):
+    from .bridge_all import model_info
+    openai_website = ' 请登录OpenAI查看详情 https://platform.openai.com/signup'
+    if "reduce the length" in error_msg:
+        if len(history) >= 2: history[-1] = ""; history[-2] = "" # 清除当前溢出的输入：history[-2] 是本次输入, history[-1] 是本次输出
+        history = clip_history(inputs=inputs, history=history, tokenizer=model_info[llm_kwargs['llm_model']]['tokenizer'], 
+                                               max_token_limit=(model_info[llm_kwargs['llm_model']]['max_token'])) # history至少释放二分之一
+        chatbot[-1] = (chatbot[-1][0], "[Local Message] Reduce the length. 本次输入过长, 或历史数据过长. 历史缓存数据已部分释放, 您可以请再次尝试. (若再次失败则更可能是因为输入过长.)")
+                        # history = []    # 清除历史
+    elif "does not exist" in error_msg:
+        chatbot[-1] = (chatbot[-1][0], f"[Local Message] Model {llm_kwargs['llm_model']} does not exist. 模型不存在, 或者您没有获得体验资格.")
+    elif "Incorrect API key" in error_msg:
+        chatbot[-1] = (chatbot[-1][0], "[Local Message] Incorrect API key. OpenAI以提供了不正确的API_KEY为由, 拒绝服务. " + openai_website)
+    elif "exceeded your current quota" in error_msg:
+        chatbot[-1] = (chatbot[-1][0], "[Local Message] You exceeded your current quota. OpenAI以账户额度不足为由, 拒绝服务." + openai_website)
+    elif "account is not active" in error_msg:
+        chatbot[-1] = (chatbot[-1][0], "[Local Message] Your account is not active. OpenAI以账户失效为由, 拒绝服务." + openai_website)
+    elif "associated with a deactivated account" in error_msg:
+        chatbot[-1] = (chatbot[-1][0], "[Local Message] You are associated with a deactivated account. OpenAI以账户失效为由, 拒绝服务." + openai_website)
+    elif "bad forward key" in error_msg:
+        chatbot[-1] = (chatbot[-1][0], "[Local Message] Bad forward key. API2D账户额度不足.")
+    elif "Not enough point" in error_msg:
+        chatbot[-1] = (chatbot[-1][0], "[Local Message] Not enough point. API2D账户点数不足.")
+    else:
+        from toolbox import regular_txt_to_markdown
+        tb_str = '```\n' + trimmed_format_exc() + '```'
+        chatbot[-1] = (chatbot[-1][0], f"[Local Message] 异常 \n\n{tb_str} \n\n{regular_txt_to_markdown(chunk_decoded)}")
+    return chatbot, history
+
 def generate_payload(inputs, llm_kwargs, history, system_prompt, stream):
    """
    整合所有信息，选择LLM模型，生成http请求，为发送请求做准备
--- a/request_llm/bridge_claude.py
+++ b/request_llm/bridge_claude.py
@ -0,0 +1,231 @@
+# 借鉴了 https://github.com/GaiZhenbiao/ChuanhuChatGPT 项目
+
+"""
+    该文件中主要包含2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：在实验过程中发现调用predict_no_ui处理长文档时，和openai的连接容易断掉，这个函数用stream的方式解决这个问题，同样支持多线程
+"""
+
+import os
+import json
+import time
+import gradio as gr
+import logging
+import traceback
+import requests
+import importlib
+
+# config_private.py放自己的秘密如API和代理网址
+# 读取时首先看是否存在私密的config_private配置文件（不受git管控），如果有，则覆盖原config文件
+from toolbox import get_conf, update_ui, trimmed_format_exc, ProxyNetworkActivate
+proxies, TIMEOUT_SECONDS, MAX_RETRY, ANTHROPIC_API_KEY = \
+    get_conf('proxies', 'TIMEOUT_SECONDS', 'MAX_RETRY', 'ANTHROPIC_API_KEY')
+
+timeout_bot_msg = '[Local Message] Request timeout. Network error. Please check proxy settings in config.py.' + \
+                  '网络错误，检查代理服务器是否可用，以及代理设置的格式是否正确，格式须是[协议]://[地址]:[端口]，缺一不可。'
+
+def get_full_error(chunk, stream_response):
+    """
+        获取完整的从Openai返回的报错
+    """
+    while True:
+        try:
+            chunk += next(stream_response)
+        except:
+            break
+    return chunk
+
+
+def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="", observe_window=None, console_slience=False):
+    """
+    发送至chatGPT，等待回复，一次性完成，不显示中间过程。但内部用stream的方法避免中途网线被掐。
+    inputs：
+        是本次问询的输入
+    sys_prompt:
+        系统静默prompt
+    llm_kwargs：
+        chatGPT的内部调优参数
+    history：
+        是之前的对话列表
+    observe_window = None：
+        用于负责跨越线程传递已经输出的部分，大部分时候仅仅为了fancy的视觉效果，留空即可。observe_window[0]：观测窗。observe_window[1]：看门狗
+    """
+    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")
+
+    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:
+            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}) ……')
+    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()
+
+    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
+    """
+    from anthropic import Anthropic
+    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:
+        import core_functional
+        importlib.reload(core_functional)    # 热更新prompt
+        core_functional = core_functional.get_core_functions()
+        if "PreProcess" in core_functional[additional_fn]: inputs = core_functional[additional_fn]["PreProcess"](inputs)  # 获取预处理函数（如果有的话）
+        inputs = core_functional[additional_fn]["Prefix"] + inputs + core_functional[additional_fn]["Suffix"]
+
+    raw_input = inputs
+    logging.info(f'[raw_input] {raw_input}')
+    chatbot.append((inputs, ""))
+    yield from update_ui(chatbot=chatbot, history=history, msg="等待响应") # 刷新界面
+
+    try:
+        prompt = generate_payload(inputs, llm_kwargs, history, system_prompt, stream)
+    except RuntimeError as e:
+        chatbot[-1] = (inputs, f"您提供的api-key不满足要求，不包含任何可用于{llm_kwargs['llm_model']}的api-key。您可能选择了错误的模型或请求源。")
+        yield from update_ui(chatbot=chatbot, history=history, msg="api-key不满足要求") # 刷新界面
+        return
+
+    history.append(inputs); history.append("")
+
+    retry = 0
+    while True:
+        try:
+            # make a POST request to the API endpoint, stream=True
+            from .bridge_all import model_info
+            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:
+            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 = ""
+    
+    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
+        
+
+
+
+# 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):
+    """
+    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}]
+    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)
+    prompt = convert_messages_to_prompt(messages)
+
+    return prompt
+
+
--- a/request_llm/bridge_internlm.py
+++ b/request_llm/bridge_internlm.py
@ -0,0 +1,315 @@
+
+from transformers import AutoModel, AutoTokenizer
+import time
+import threading
+import importlib
+from toolbox import update_ui, get_conf, Singleton
+from multiprocessing import Process, Pipe
+
+model_name = "InternLM"
+cmd_to_install = "`pip install ???`"
+load_message = f"{model_name}尚未加载，加载需要一段时间。注意，取决于`config.py`的配置，{model_name}消耗大量的内存（CPU）或显存（GPU），也许会导致低配计算机卡死 ……"
+def try_to_import_special_deps():
+    import sentencepiece
+
+user_prompt = "<|User|>:{user}<eoh>\n"
+robot_prompt = "<|Bot|>:{robot}<eoa>\n"
+cur_query_prompt = "<|User|>:{user}<eoh>\n<|Bot|>:"
+
+
+def combine_history(prompt, hist):
+    messages = hist
+    total_prompt = ""
+    for message in messages:
+        cur_content = message
+        cur_prompt = user_prompt.replace("{user}", cur_content[0])
+        total_prompt += cur_prompt
+        cur_prompt = robot_prompt.replace("{robot}", cur_content[1])
+        total_prompt += cur_prompt
+    total_prompt = total_prompt + cur_query_prompt.replace("{user}", prompt)
+    return total_prompt
+
+
+@Singleton
+class GetInternlmHandle(Process):
+    def __init__(self):
+        # ⭐主进程执行
+        super().__init__(daemon=True)
+        self.parent, self.child = Pipe()
+        self._model = None
+        self._tokenizer = None
+        self.info = ""
+        self.success = True
+        self.check_dependency()
+        self.start()
+        self.threadLock = threading.Lock()
+
+    def ready(self):
+        # ⭐主进程执行
+        return self._model is not None
+
+    def load_model_and_tokenizer(self):
+        # 🏃‍♂️🏃‍♂️🏃‍♂️ 子进程执行
+        import torch
+        from transformers import AutoModelForCausalLM, AutoTokenizer
+        device, = get_conf('LOCAL_MODEL_DEVICE')
+        if self._model is None:
+            tokenizer = AutoTokenizer.from_pretrained("internlm/internlm-chat-7b", trust_remote_code=True)
+            if device=='cpu':
+                model = AutoModelForCausalLM.from_pretrained("internlm/internlm-chat-7b", trust_remote_code=True).to(torch.bfloat16)
+            else:
+                model = AutoModelForCausalLM.from_pretrained("internlm/internlm-chat-7b", trust_remote_code=True).to(torch.bfloat16).cuda()
+
+            model = model.eval()
+        return model, tokenizer
+
+    def llm_stream_generator(self, **kwargs):
+        import torch
+        import logging
+        import copy
+        import warnings
+        import torch.nn as nn
+        from transformers.generation.utils import LogitsProcessorList, StoppingCriteriaList, GenerationConfig
+
+        # 🏃‍♂️🏃‍♂️🏃‍♂️ 子进程执行
+        def adaptor():
+            model = self._model
+            tokenizer = self._tokenizer
+            prompt = kwargs['query']
+            max_length = kwargs['max_length']
+            top_p = kwargs['top_p']
+            temperature = kwargs['temperature']
+            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
+        stopping_criteria = None
+        additional_eos_token_id = 103028
+        generation_config = None
+        # 🏃‍♂️🏃‍♂️🏃‍♂️ 子进程执行
+        # 🏃‍♂️🏃‍♂️🏃‍♂️ https://github.com/InternLM/InternLM/blob/efbf5335709a8c8faeac6eaf07193973ff1d56a1/web_demo.py#L25
+
+        inputs = tokenizer([prompt], padding=True, return_tensors="pt")
+        input_length = len(inputs["input_ids"][0])
+        for k, v in inputs.items():
+            inputs[k] = v.cuda()
+        input_ids = inputs["input_ids"]
+        batch_size, input_ids_seq_length = input_ids.shape[0], input_ids.shape[-1]
+        if generation_config is None:
+            generation_config = model.generation_config
+        generation_config = copy.deepcopy(generation_config)
+        model_kwargs = generation_config.update(**kwargs)
+        bos_token_id, eos_token_id = generation_config.bos_token_id, generation_config.eos_token_id
+        if isinstance(eos_token_id, int):
+            eos_token_id = [eos_token_id]
+        if additional_eos_token_id is not None:
+            eos_token_id.append(additional_eos_token_id)
+        has_default_max_length = kwargs.get("max_length") is None and generation_config.max_length is not None
+        if has_default_max_length and generation_config.max_new_tokens is None:
+            warnings.warn(
+                f"Using `max_length`'s default ({generation_config.max_length}) to control the generation length. "
+                "This behaviour is deprecated and will be removed from the config in v5 of Transformers -- we"
+                " recommend using `max_new_tokens` to control the maximum length of the generation.",
+                UserWarning,
+            )
+        elif generation_config.max_new_tokens is not None:
+            generation_config.max_length = generation_config.max_new_tokens + input_ids_seq_length
+            if not has_default_max_length:
+                logging.warn(
+                    f"Both `max_new_tokens` (={generation_config.max_new_tokens}) and `max_length`(="
+                    f"{generation_config.max_length}) seem to have been set. `max_new_tokens` will take precedence. "
+                    "Please refer to the documentation for more information. "
+                    "(https://huggingface.co/docs/transformers/main/en/main_classes/text_generation)",
+                    UserWarning,
+                )
+
+        if input_ids_seq_length >= generation_config.max_length:
+            input_ids_string = "input_ids"
+            logging.warning(
+                f"Input length of {input_ids_string} is {input_ids_seq_length}, but `max_length` is set to"
+                f" {generation_config.max_length}. This can lead to unexpected behavior. You should consider"
+                " increasing `max_new_tokens`."
+            )
+
+        # 2. Set generation parameters if not already defined
+        logits_processor = logits_processor if logits_processor is not None else LogitsProcessorList()
+        stopping_criteria = stopping_criteria if stopping_criteria is not None else StoppingCriteriaList()
+
+        logits_processor = model._get_logits_processor(
+            generation_config=generation_config,
+            input_ids_seq_length=input_ids_seq_length,
+            encoder_input_ids=input_ids,
+            prefix_allowed_tokens_fn=prefix_allowed_tokens_fn,
+            logits_processor=logits_processor,
+        )
+
+        stopping_criteria = model._get_stopping_criteria(
+            generation_config=generation_config, stopping_criteria=stopping_criteria
+        )
+        logits_warper = model._get_logits_warper(generation_config)
+
+        unfinished_sequences = input_ids.new(input_ids.shape[0]).fill_(1)
+        scores = None
+        while True:
+            model_inputs = model.prepare_inputs_for_generation(input_ids, **model_kwargs)
+            # forward pass to get next token
+            outputs = model(
+                **model_inputs,
+                return_dict=True,
+                output_attentions=False,
+                output_hidden_states=False,
+            )
+
+            next_token_logits = outputs.logits[:, -1, :]
+
+            # pre-process distribution
+            next_token_scores = logits_processor(input_ids, next_token_logits)
+            next_token_scores = logits_warper(input_ids, next_token_scores)
+
+            # sample
+            probs = nn.functional.softmax(next_token_scores, dim=-1)
+            if generation_config.do_sample:
+                next_tokens = torch.multinomial(probs, num_samples=1).squeeze(1)
+            else:
+                next_tokens = torch.argmax(probs, dim=-1)
+
+            # update generated ids, model inputs, and length for next step
+            input_ids = torch.cat([input_ids, next_tokens[:, None]], dim=-1)
+            model_kwargs = model._update_model_kwargs_for_generation(
+                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:
+                if output_token_ids[-1] == each_eos_token_id:
+                    output_token_ids = output_token_ids[:-1]
+            response = tokenizer.decode(output_token_ids)
+
+            yield response
+            # stop when each sentence is finished, or if we exceed the maximum length
+            if unfinished_sequences.max() == 0 or stopping_criteria(input_ids, scores):
+                return
+
+
+
+    def check_dependency(self):
+        # 🏃‍♂️🏃‍♂️🏃‍♂️ 子进程执行
+        try:
+            try_to_import_special_deps()
+            self.info = "依赖检测通过"
+            self.success = True
+        except:
+            self.info = f"缺少{model_name}的依赖，如果要使用{model_name}，除了基础的pip依赖以外，您还需要运行{cmd_to_install}安装{model_name}的依赖。"
+            self.success = False
+
+    def run(self):
+        # 🏃‍♂️🏃‍♂️🏃‍♂️ 子进程执行
+        # 第一次运行，加载参数
+        try:
+            self._model, self._tokenizer = self.load_model_and_tokenizer()
+        except:
+            from toolbox import trimmed_format_exc
+            self.child.send(f'[Local Message] 不能正常加载{model_name}的参数.' + '\n```\n' + trimmed_format_exc() + '\n```\n')
+            raise RuntimeError(f"不能正常加载{model_name}的参数！")
+
+        while True:
+            # 进入任务等待状态
+            kwargs = self.child.recv()
+            # 收到消息，开始请求
+            try:
+                for response_full in self.llm_stream_generator(**kwargs):
+                    self.child.send(response_full)
+            except:
+                from toolbox import trimmed_format_exc
+                self.child.send(f'[Local Message] 调用{model_name}失败.' + '\n```\n' + trimmed_format_exc() + '\n```\n')
+            # 请求处理结束，开始下一个循环
+            self.child.send('[Finish]')
+
+    def stream_chat(self, **kwargs):
+        # ⭐主进程执行
+        self.threadLock.acquire()
+        self.parent.send(kwargs)
+        while True:
+            res = self.parent.recv()
+            if res != '[Finish]':
+                yield res
+            else:
+                break
+        self.threadLock.release()
+    
+    
+# ------------------------------------------------------------------------------------------------------------------------
+# 🔌💻 GPT-Academic
+# ------------------------------------------------------------------------------------------------------------------------
+def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="", observe_window=[], console_slience=False):
+    """
+        ⭐多线程方法
+        函数的说明请见 request_llm/bridge_all.py
+    """
+    _llm_handle = GetInternlmHandle()
+    if len(observe_window) >= 1: observe_window[0] = load_message + "\n\n" + _llm_handle.info
+    if not _llm_handle.success: 
+        error = _llm_handle.info
+        _llm_handle = None
+        raise RuntimeError(error)
+
+    # chatglm 没有 sys_prompt 接口，因此把prompt加入 history
+    history_feedin = []
+    history_feedin.append(["What can I do?", sys_prompt])
+    for i in range(len(history)//2):
+        history_feedin.append([history[2*i], history[2*i+1]] )
+
+    watch_dog_patience = 5 # 看门狗 (watchdog) 的耐心, 设置5秒即可
+    response = ""
+    for response in _llm_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 (time.time()-observe_window[1]) > watch_dog_patience:
+                raise RuntimeError("程序终止。")
+    return response
+
+
+
+def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_prompt='', stream = True, additional_fn=None):
+    """
+        ⭐单线程方法
+        函数的说明请见 request_llm/bridge_all.py
+    """
+    chatbot.append((inputs, ""))
+
+    _llm_handle = GetInternlmHandle()
+    chatbot[-1] = (inputs, load_message + "\n\n" + _llm_handle.info)
+    yield from update_ui(chatbot=chatbot, history=[])
+    if not _llm_handle.success: 
+        _llm_handle = None
+        return
+
+    if additional_fn is not None:
+        import core_functional
+        importlib.reload(core_functional)    # 热更新prompt
+        core_functional = core_functional.get_core_functions()
+        if "PreProcess" in core_functional[additional_fn]: inputs = core_functional[additional_fn]["PreProcess"](inputs)  # 获取预处理函数（如果有的话）
+        inputs = core_functional[additional_fn]["Prefix"] + inputs + core_functional[additional_fn]["Suffix"]
+
+    # 处理历史信息
+    history_feedin = []
+    history_feedin.append(["What can I do?", system_prompt] )
+    for i in range(len(history)//2):
+        history_feedin.append([history[2*i], history[2*i+1]] )
+
+    # 开始接收chatglm的回复
+    response = f"[Local Message]: 等待{model_name}响应中 ..."
+    for response in _llm_handle.stream_chat(query=inputs, history=history_feedin, max_length=llm_kwargs['max_length'], top_p=llm_kwargs['top_p'], temperature=llm_kwargs['temperature']):
+        chatbot[-1] = (inputs, response)
+        yield from update_ui(chatbot=chatbot, history=history)
+
+    # 总结输出
+    if response == f"[Local Message]: 等待{model_name}响应中 ...":
+        response = f"[Local Message]: {model_name}响应异常 ..."
+    history.extend([inputs, response])
+    yield from update_ui(chatbot=chatbot, history=history)
--- a/request_llm/edge_gpt_free.py
+++ b/request_llm/edge_gpt_free.py
@ -447,6 +447,15 @@ class _ChatHub:
        """
        Ask a question to the bot
        """
+        req_header = HEADERS
+        if self.cookies is not None:
+            ws_cookies = []
+            for cookie in self.cookies:
+                ws_cookies.append(f"{cookie['name']}={cookie['value']}")
+            req_header.update({
+                'Cookie': ';'.join(ws_cookies),
+            })
+            
        timeout = aiohttp.ClientTimeout(total=30)
        self.session = aiohttp.ClientSession(timeout=timeout)

@ -455,7 +464,7 @@ class _ChatHub:
        # Check if websocket is closed
        self.wss = await self.session.ws_connect(
            wss_link,
-            headers=HEADERS,
+            headers=req_header,
            ssl=ssl_context,
            proxy=self.proxy,
            autoping=False,
@ -510,7 +519,11 @@ class _ChatHub:
        resp_txt_no_link = ""
        while not final:
            msg = await self.wss.receive()
-            objects = msg.data.split(DELIMITER)
+            try:
+                objects = msg.data.split(DELIMITER)
+            except :
+                continue
+            
            for obj in objects:
                if obj is None or not obj:
                    continue
@ -1109,4 +1122,4 @@ class ImageQuery(Query):


 if __name__ == "__main__":
-    main()
+    main()
--- a/request_llm/test_llms.py
+++ b/request_llm/test_llms.py
@ -10,10 +10,12 @@ def validate_path():
    
 validate_path() # validate path so you can run from base directory
 if __name__ == "__main__":
-    from request_llm.bridge_newbingfree import predict_no_ui_long_connection
+    # from request_llm.bridge_newbingfree import predict_no_ui_long_connection
    # from request_llm.bridge_moss import predict_no_ui_long_connection
    # from request_llm.bridge_jittorllms_pangualpha import predict_no_ui_long_connection
    # from request_llm.bridge_jittorllms_llama import predict_no_ui_long_connection
+    # from request_llm.bridge_claude import predict_no_ui_long_connection
+    from request_llm.bridge_internlm import predict_no_ui_long_connection

    llm_kwargs = {
        'max_length': 512,
@ -21,58 +23,8 @@ if __name__ == "__main__":
        'temperature': 1,
    }

-    result = predict_no_ui_long_connection(inputs="你好", 
-                                        llm_kwargs=llm_kwargs,
-                                        history=[],
-                                        sys_prompt="")
+    result = predict_no_ui_long_connection( inputs="请问什么是质子？", 
+                                            llm_kwargs=llm_kwargs,
+                                            history=["你好", "我好！"],
+                                            sys_prompt="")
    print('final result:', result)
-
-
-    result = predict_no_ui_long_connection(inputs="what is a hero?", 
-                                        llm_kwargs=llm_kwargs,
-                                        history=["hello world"],
-                                        sys_prompt="")
-    print('final result:', result)
-
-    result = predict_no_ui_long_connection(inputs="如何理解传奇?", 
-                                        llm_kwargs=llm_kwargs,
-                                        history=[],
-                                        sys_prompt="")
-    print('final result:', result)
-
-    # # print(result)
-    # from multiprocessing import Process, Pipe
-    # class GetGLMHandle(Process):
-    #     def __init__(self):
-    #         super().__init__(daemon=True)
-    #         pass
-    #     def run(self):
-    #         # 子进程执行
-    #         # 第一次运行，加载参数
-    #         def validate_path():
-    #             import os, sys
-    #             dir_name = os.path.dirname(__file__)
-    #             root_dir_assume = os.path.abspath(os.path.dirname(__file__) +  '/..')
-    #             os.chdir(root_dir_assume + '/request_llm/jittorllms')
-    #             sys.path.append(root_dir_assume + '/request_llm/jittorllms')
-    #         validate_path() # validate path so you can run from base directory
-
-    #         jittorllms_model = None
-    #         import types
-    #         try:
-    #             if jittorllms_model is None:
-    #                 from models import get_model
-    #                 # availabel_models = ["chatglm", "pangualpha", "llama", "chatrwkv"]
-    #                 args_dict = {'model': 'chatrwkv'}
-    #                 print('self.jittorllms_model = get_model(types.SimpleNamespace(**args_dict))')
-    #                 jittorllms_model = get_model(types.SimpleNamespace(**args_dict))
-    #                 print('done get model')
-    #         except:
-    #             # self.child.send('[Local Message] Call jittorllms fail 不能正常加载jittorllms的参数。')
-    #             raise RuntimeError("不能正常加载jittorllms的参数！")
-            
-    # x = GetGLMHandle()
-    # x.start()
-
-
-    # input()
--- a/requirements.txt
+++ b/requirements.txt
@ -9,6 +9,7 @@ prompt_toolkit
 latex2mathml
 python-docx
 mdtex2html
+anthropic
 colorama
 Markdown
 pygments
@ -17,3 +18,4 @@ openai
 numpy
 arxiv
 rich
+pypdf2==2.12.1
--- a/themes/common.js
+++ b/themes/common.js
--- a/themes/default.css
+++ b/themes/default.css
--- a/themes/default.py
+++ b/themes/default.py
@ -9,9 +9,8 @@ def adjust_theme():
        set_theme = gr.themes.Default(
            primary_hue=gr.themes.utils.colors.orange,
            neutral_hue=gr.themes.utils.colors.gray,
-            font=["sans-serif", "Microsoft YaHei", "ui-sans-serif", "system-ui",
-                  "sans-serif", gr.themes.utils.fonts.GoogleFont("Source Sans Pro")],
-            font_mono=["ui-monospace", "Consolas", "monospace", gr.themes.utils.fonts.GoogleFont("IBM Plex Mono")])
+            font=["sans-serif", "Microsoft YaHei", "ui-sans-serif", "system-ui"],
+            font_mono=["ui-monospace", "Consolas", "monospace"])
        set_theme.set(
            # Colors
            input_background_fill_dark="*neutral_800",
@ -61,7 +60,7 @@ def adjust_theme():
        if LAYOUT=="TOP-DOWN": 
            js = ""
        else:
-            with open('theme/common.js', 'r', encoding='utf8') as f: 
+            with open('themes/common.js', 'r', encoding='utf8') as f: 
                js = f"<script>{f.read()}</script>"
            
        # 添加一个萌萌的看板娘
@ -83,5 +82,5 @@ def adjust_theme():
        print('gradio版本较旧, 不能自定义字体和颜色')
    return set_theme

-with open("theme/default.css", "r", encoding="utf-8") as f:
+with open("themes/default.css", "r", encoding="utf-8") as f:
    advanced_css = f.read()
--- a/themes/green.css
+++ b/themes/green.css
--- a/themes/green.py
+++ b/themes/green.py
@ -77,7 +77,7 @@ def adjust_theme():
        if LAYOUT=="TOP-DOWN":
            js = ""
        else:
-            with open('theme/common.js', 'r', encoding='utf8') as f:
+            with open('themes/common.js', 'r', encoding='utf8') as f:
                js = f"<script>{f.read()}</script>"

        # 添加一个萌萌的看板娘
@ -100,5 +100,5 @@ def adjust_theme():
    return set_theme


-with open("theme/green.css", "r", encoding="utf-8") as f:
+with open("themes/green.css", "r", encoding="utf-8") as f:
    advanced_css = f.read()
--- a/themes/theme.py
+++ b/themes/theme.py
--- a/toolbox.py
+++ b/toolbox.py
@ -538,7 +538,11 @@ def load_chat_cookies():
    return {'api_key': API_KEY, 'llm_model': LLM_MODEL}

 def is_openai_api_key(key):
-    API_MATCH_ORIGINAL = re.match(r"sk-[a-zA-Z0-9]{48}$", key)
+    CUSTOM_API_KEY_PATTERN, = get_conf('CUSTOM_API_KEY_PATTERN')
+    if len(CUSTOM_API_KEY_PATTERN) != 0:
+        API_MATCH_ORIGINAL = re.match(CUSTOM_API_KEY_PATTERN, key)
+    else:
+        API_MATCH_ORIGINAL = re.match(r"sk-[a-zA-Z0-9]{48}$", key)
    return bool(API_MATCH_ORIGINAL)

 def is_azure_api_key(key):
@ -594,7 +598,7 @@ def select_api_key(keys, llm_model):
            if is_azure_api_key(k): avail_key_list.append(k)

    if len(avail_key_list) == 0:
-        raise RuntimeError(f"您提供的api-key不满足要求，不包含任何可用于{llm_model}的api-key。您可能选择了错误的模型或请求源（右下角更换模型菜单中可切换openai,azure和api2d请求源）")
+        raise RuntimeError(f"您提供的api-key不满足要求，不包含任何可用于{llm_model}的api-key。您可能选择了错误的模型或请求源（右下角更换模型菜单中可切换openai,azure,claude,api2d等请求源）。")

    api_key = random.choice(avail_key_list) # 随机负载均衡
    return api_key
@ -670,13 +674,14 @@ def read_single_conf_with_lru_cache(arg):

    # 在读取API_KEY时，检查一下是不是忘了改config
    if arg == 'API_KEY':
-        print亮蓝(f"[API_KEY] 本项目现已支持OpenAI和API2D的api-key。也支持同时填写多个api-key，如API_KEY=\"openai-key1,openai-key2,api2d-key3\"")
+        print亮蓝(f"[API_KEY] 本项目现已支持OpenAI和Azure的api-key。也支持同时填写多个api-key，如API_KEY=\"openai-key1,openai-key2,azure-key3\"")
        print亮蓝(f"[API_KEY] 您既可以在config.py中修改api-key(s)，也可以在问题输入区输入临时的api-key(s)，然后回车键提交后即可生效。")
        if is_any_api_key(r):
            print亮绿(f"[API_KEY] 您的 API_KEY 是: {r[:15]}*** API_KEY 导入成功")
        else:
-            print亮红( "[API_KEY] 正确的 API_KEY 是'sk'开头的51位密钥（OpenAI），或者 'fk'开头的41位密钥，请在config文件中修改API密钥之后再运行。")
+            print亮红( "[API_KEY] 您的 API_KEY 不满足任何一种已知的密钥格式，请在config文件中修改API密钥之后再运行。")
    if arg == 'proxies':
+        if not read_single_conf_with_lru_cache('USE_PROXY'): r = None   # 检查USE_PROXY，防止proxies单独起作用
        if r is None:
            print亮红('[PROXY] 网络代理状态：未配置。无代理状态下很可能无法访问OpenAI家族的模型。建议：检查USE_PROXY选项是否修改。')
        else:
@ -685,6 +690,7 @@ def read_single_conf_with_lru_cache(arg):
    return r


+@lru_cache(maxsize=128)
 def get_conf(*args):
    # 建议您复制一个config_private.py放自己的秘密, 如API和代理网址, 避免不小心传github被别人看到
    res = []
@ -883,4 +889,16 @@ def objload(file='objdump.tmp'):
        return
    with open(file, 'rb') as f:
        return pickle.load(f)
-    
+    
+def Singleton(cls):
+    """
+    一个单实例装饰器
+    """
+    _instance = {}
+ 
+    def _singleton(*args, **kargs):
+        if cls not in _instance:
+            _instance[cls] = cls(*args, **kargs)
+        return _instance[cls]
+ 
+    return _singleton
--- a/4
+++ b/4
@ -1,5 +1,5 @@
 {
-  "version": 3.45,
+  "version": 3.47,
  "show_feature": true,
-  "new_feature": "支持加载自定义的ChatGLM2微调模型 <-> [改善UI] 动态ChatBot窗口高度 <-> 修复Azure接口的BUG <-> 完善多语言模块 <-> 完善本地Latex矫错和翻译功能 <-> 增加gpt-3.5-16k的支持 <-> 新增最强Arxiv论文翻译插件 <-> 修复gradio复制按钮BUG <-> 修复PDF翻译的BUG, 新增HTML中英双栏对照 <-> 添加了OpenAI图片生成插件"
+  "new_feature": "优化一键升级 <-> 提高arxiv翻译速度和成功率 <-> 支持自定义APIKEY格式 <-> 临时修复theme的文件丢失问题 <-> 新增实时语音对话插件（自动断句，脱手对话） <-> 支持加载自定义的ChatGLM2微调模型 <-> 动态ChatBot窗口高度 <-> 修复Azure接口的BUG <-> 完善多语言模块 <-> 完善本地Latex矫错和翻译功能 <-> 增加gpt-3.5-16k的支持"
 }
Author	SHA1	Message	Date
binary-husky	e4e2430255	version 3.47	2023-07-24 19:58:47 +08:00
binary-husky	1732127a28	Merge pull request #979 from fenglui/master 增加chatGLM int4配置支持小显存也可以选择chatGLM	2023-07-24 19:52:27 +08:00
binary-husky	56bb8b6498	improve re efficiency	2023-07-24 18:50:29 +08:00
binary-husky	e93b6fa3a6	Add GLM INT8	2023-07-24 18:19:57 +08:00
binary-husky	dd4ba0ea22	Merge branch 'master' of https://github.com/fenglui/gpt_academic into fenglui-master	2023-07-24 18:06:15 +08:00
binary-husky	c2701c9ce5	Merge pull request #986 from one-pr/git-clone 默认仅 clone 最新的代码，减小 git clone 的大小	2023-07-24 17:48:35 +08:00
woclass	2f019ce359	优化 README.md 中的其他 git clone	2023-07-24 15:14:48 +08:00
woclass	c5b147aeb7	默认仅 clone 最新的代码，减小 git clone 的大小	2023-07-24 15:14:42 +08:00
fenglui	5813d65e52	增加chatGLM int4配置支持小显存也可以选择chatGLM	2023-07-22 08:29:15 +08:00
binary-husky	a393edfaa4	ALLOW CUSTOM API KEY PATTERN	2023-07-21 22:49:07 +08:00
binary-husky	dd7a01cda5	Merge pull request #976 from fenglui/master fix msg.data.split(DELIMITER) exception when msg.data is int	2023-07-21 17:02:29 +08:00
fenglui	00a3b91f95	fix msg.data.split(DELIMITER) exception when msg.data is int	2023-07-21 03:51:33 +08:00
qingxu fu	61ba544282	add latex test samples	2023-07-20 19:49:23 +08:00
qingxu fu	b5b8c123e4	latex plugin stability improvement	2023-07-20 19:39:22 +08:00
qingxu fu	d9ceba959f	expand range after failure	2023-07-20 18:39:02 +08:00
qingxu fu	6b5b040701	remove pdf merge	2023-07-20 18:29:06 +08:00
qingxu fu	4f4c09a5f3	增强Latex修复能力	2023-07-20 18:08:22 +08:00
qingxu fu	067bc97cce	Merge branch 'interface-interlm' of https://github.com/binary-husky/chatgpt_academic into interface-interlm	2023-07-20 12:46:52 +08:00
qingxu fu	7368580cd6	concat pdf after translation	2023-07-20 12:46:48 +08:00
binary-husky	df90db210c	Merge branch 'master' into interface-interlm	2023-07-20 11:40:45 +08:00
binary-husky	0927ed20a2	edit default configuration	2023-07-20 11:39:35 +08:00
binary-husky	73b22f85be	compat third party gpt error handle	2023-07-20 11:09:22 +08:00
binary-husky	b8d77557b0	Update README.md	2023-07-20 10:12:42 +08:00
binary-husky	99b8fce8f3	Merge pull request #965 from QQisQQ/patch-2 解决new bing 报错200 (fix new bing error code 200 )	2023-07-19 10:15:15 +08:00
binary-husky	16364f1b2d	Merge pull request #966 from doujiang-zheng/master Add timestamp for chat_secrets.log and disable the verbose httpx log.	2023-07-19 10:14:36 +08:00
doujiang-zheng	3b88e00cfb	Add timestamp for chat_secrets.log and disable the verbose httpx log.	2023-07-19 09:43:59 +08:00
QQisQQ	0c8c539e9b	解决new bing 报错200 (fix new bing error code 200 ) modify from `16e00af9d5` works for my issue: ``` Traceback (most recent call last): File "./request_llm/bridge_newbingfree.py", line 152, in run asyncio.run(self.async_run()) File "/root/miniconda3/envs/py311/lib/python3.11/asyncio/runners.py", line 190, in run return runner.run(main) ^^^^^^^^^^^^^^^^ File "/root/miniconda3/envs/py311/lib/python3.11/asyncio/runners.py", line 118, in run return self._loop.run_until_complete(task) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/root/miniconda3/envs/py311/lib/python3.11/asyncio/base_events.py", line 653, in run_until_complete return future.result() ^^^^^^^^^^^^^^^ File "./request_llm/bridge_newbingfree.py", line 98, in async_run async for final, response in self.newbing_model.ask_stream( File "./request_llm/edge_gpt_free.py", line 676, in ask_stream async for response in self.chat_hub.ask_stream( File "./request_llm/edge_gpt_free.py", line 456, in ask_stream self.wss = await self.session.ws_connect( ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/root/miniconda3/envs/py311/lib/python3.11/site-packages/aiohttp/client.py", line 795, in _ws_connect raise WSServerHandshakeError( aiohttp.client_exceptions.WSServerHandshakeError: 200, message='Invalid response status', url=URL('wss://sydney.bing.com/sydney/ChatHub') ```	2023-07-19 04:39:15 +08:00
binary-husky	fd549fb986	merge success	2023-07-18 19:51:13 +08:00
binary-husky	babb775cfb	interface with interlm	2023-07-18 16:33:34 +08:00
qingxu fu	eef9e470c9	Latex解除非UTF8编码错误	2023-07-18 11:00:20 +08:00
binary-husky	3002c6318a	Update README.md	2023-07-17 22:21:39 +08:00
binary-husky	6d0bceaebd	移除插件依赖	2023-07-17 22:00:29 +08:00
binary-husky	aa51d6fde6	up	2023-07-17 21:54:28 +08:00
binary-husky	136479e218	Update README.md	2023-07-17 10:38:46 +08:00
binary-husky	19a2742354	Merge pull request #957 from 1Haschwalth/patch-1 Update README.md	2023-07-17 10:35:15 +08:00
1Haschwalth	45aac96dd3	Update README.md	2023-07-16 21:50:08 +08:00
binary-husky	6f21ae8939	support claude api	2023-07-16 15:03:05 +08:00
binary-husky	add98f4eeb	修复自动版本升级Bug	2023-07-16 13:23:28 +08:00
binary-husky	fe231f72b6	fix theme folder rename problem	2023-07-16 13:15:55 +08:00
binary-husky	b308fde480	update readme	2023-07-15 19:19:39 +08:00
binary-husky	f3e14ff806	更新繁體中文映射詞典	2023-07-15 19:11:00 +08:00
binary-husky	79ef9bdf1c	update English projection dictionary	2023-07-15 19:01:49 +08:00
binary-husky	a3e938aee9	Merge branch 'master' of github.com:binary-husky/chatgpt_academic	2023-07-15 18:41:46 +08:00
binary-husky	b19a6155f4	restore jittor support	2023-07-15 18:41:35 +08:00
binary-husky	801f7342b1	Update config.py	2023-07-15 17:58:34 +08:00
binary-husky	4829fa0f35	Update README.md	2023-07-15 17:46:19 +08:00
binary-husky	3671f4208e	Update README.md	2023-07-15 17:39:04 +08:00
binary-husky	e8c51181ee	进一步提高语音识别的实时性	2023-07-15 17:02:00 +08:00
binary-husky	3ccbb4d6fb	移除google字体	2023-07-15 17:01:37 +08:00
binary-husky	93fe457e99	Merge branch 'master' of github.com:binary-husky/chatgpt_academic	2023-07-15 16:41:46 +08:00
binary-husky	afac657aaa	解决语音助手看门狗线程泄露的问题	2023-07-15 16:41:11 +08:00
binary-husky	3e5c32860a	Update README.md	2023-07-15 14:59:05 +08:00
binary-husky	d577bb38b6	Update use_audio.md	2023-07-15 14:58:27 +08:00
binary-husky	418bc32b39	Update use_audio.md	2023-07-15 14:53:30 +08:00
binary-husky	7148ea0596	更新README	2023-07-15 14:44:07 +08:00
binary-husky	87adb17df4	3.46	2023-07-15 14:38:18 +08:00