Merge branch 'master' into HEAD

Co-authored-by: 柯仕锋 <12029064@zju.edu.cn>

.github/workflows/conda-pack-windows.yml

@@ -0,0 +1,56 @@
+name: Create Conda Environment Package
+
+on:
+  workflow_dispatch:
+
+jobs:
+  build:
+    runs-on: windows-latest
+    
+    steps:
+    - name: Checkout repository
+      uses: actions/checkout@v4
+      
+    - name: Setup Miniconda
+      uses: conda-incubator/setup-miniconda@v3
+      with:
+        auto-activate-base: true
+        activate-environment: ""
+        
+    - name: Create new Conda environment
+      shell: bash -l {0}
+      run: |
+        conda create -n gpt python=3.11 -y
+        conda activate gpt
+        
+    - name: Install requirements
+      shell: bash -l {0}
+      run: |
+        conda activate gpt
+        pip install -r requirements.txt
+        
+    - name: Install conda-pack
+      shell: bash -l {0}
+      run: |
+        conda activate gpt
+        conda install conda-pack -y
+        
+    - name: Pack conda environment
+      shell: bash -l {0}
+      run: |
+        conda activate gpt
+        conda pack -n gpt -o gpt.tar.gz
+      
+    - name: Create workspace zip
+      shell: pwsh
+      run: |
+        mkdir workspace
+        Get-ChildItem -Exclude "workspace" | Copy-Item -Destination workspace -Recurse
+        Remove-Item -Path workspace/.git* -Recurse -Force -ErrorAction SilentlyContinue
+        Copy-Item gpt.tar.gz workspace/ -Force
+    
+    - name: Upload packed files
+      uses: actions/upload-artifact@v4
+      with:
+        name: gpt-academic-package
+        path: workspace

.github/workflows/stale.yml

@@ -7,7 +7,7 @@
 name: 'Close stale issues and PRs'
 on:
   schedule:
-    - cron: '*/5 * * * *'
+    - cron: '*/30 * * * *'
 
 jobs:
   stale:
@@ -19,7 +19,6 @@ jobs:
     steps:
       - uses: actions/stale@v8
         with:
-          stale-issue-message: 'This issue is stale because it has been open 100 days with no activity. Remove stale label or comment or this will be closed in 1 days.'
+          stale-issue-message: 'This issue is stale because it has been open 100 days with no activity. Remove stale label or comment or this will be closed in 7 days.'
           days-before-stale: 100
-          days-before-close: 1
-          debug-only: true
+          days-before-close: 7

.gitignore

@@ -161,4 +161,5 @@ temp.*
 objdump*
 *.min.*.js
 TODO
-*.cursorrules
+experimental_mods
+search_results

Dockerfile

@@ -3,37 +3,36 @@
 # - 如何构建: 先修改 `config.py`， 然后 `docker build -t gpt-academic . `
 # - 如何运行(Linux下): `docker run --rm -it --net=host gpt-academic `
 # - 如何运行(其他操作系统，选择任意一个固定端口50923): `docker run --rm -it -e WEB_PORT=50923 -p 50923:50923 gpt-academic `
-FROM python:3.11
 
+FROM ghcr.io/astral-sh/uv:python3.12-bookworm
 
 # 非必要步骤，更换pip源 （以下三行，可以删除）
 RUN echo '[global]' > /etc/pip.conf && \
     echo 'index-url = https://mirrors.aliyun.com/pypi/simple/' >> /etc/pip.conf && \
     echo 'trusted-host = mirrors.aliyun.com' >> /etc/pip.conf
 
-
-# 语音输出功能（以下两行，第一行更换阿里源，第二行安装ffmpeg，都可以删除）
-RUN UBUNTU_VERSION=$(awk -F= '/^VERSION_CODENAME=/{print $2}' /etc/os-release); echo "deb https://mirrors.aliyun.com/debian/ $UBUNTU_VERSION main non-free contrib" > /etc/apt/sources.list; apt-get update
+# 语音输出功能（以下1,2行更换阿里源，第3,4行安装ffmpeg，都可以删除） 
+RUN sed -i 's/deb.debian.org/mirrors.aliyun.com/g' /etc/apt/sources.list.d/debian.sources && \
+    sed -i 's/security.debian.org/mirrors.aliyun.com/g' /etc/apt/sources.list.d/debian.sources && \
+    apt-get update
 RUN apt-get install ffmpeg -y
-
+RUN apt-get clean
 
 # 进入工作路径（必要）
 WORKDIR /gpt
 
-
 # 安装大部分依赖，利用Docker缓存加速以后的构建 （以下两行，可以删除）
 COPY requirements.txt ./
-RUN pip3 install -r requirements.txt
-
+RUN uv venv --python=3.12 && uv pip install --verbose -r requirements.txt -i https://mirrors.aliyun.com/pypi/simple/
+ENV PATH="/gpt/.venv/bin:$PATH"
+RUN python -c 'import loguru'
 
 # 装载项目文件，安装剩余依赖（必要）
 COPY . .
-RUN pip3 install -r requirements.txt
-
-
-# 非必要步骤，用于预热模块（可以删除）
-RUN python3  -c 'from check_proxy import warm_up_modules; warm_up_modules()'
+RUN uv venv --python=3.12 && uv pip install -r requirements.txt -i https://mirrors.aliyun.com/pypi/simple/
 
+# # 非必要步骤，用于预热模块（可以删除）
+RUN python -c 'from check_proxy import warm_up_modules; warm_up_modules()'
 
 # 启动（必要）
-CMD ["python3", "-u", "main.py"]
+CMD ["bash", "-c", "python main.py"]

README.md

@@ -1,9 +1,15 @@
 > [!IMPORTANT]
-> 2024.10.10: 突发停电，紧急恢复了提供[whl包](https://drive.google.com/file/d/19U_hsLoMrjOlQSzYS3pzWX9fTzyusArP/view?usp=sharing)的文件服务器  
-> 2024.10.8: 版本3.90加入对llama-index的初步支持，版本3.80加入插件二级菜单功能（详见wiki）  
+> `master主分支`最新动态(2025.7.31): 新GUI前端，Coming Soon
+> `master主分支`最新动态(2025.3.2): 修复大量代码typo / 联网组件支持Jina的api / 增加deepseek-r1支持  
+> `frontier开发分支`最新动态(2024.12.9): 更新对话时间线功能，优化xelatex论文翻译  
+> `wiki文档`最新动态(2024.12.5): 更新ollama接入指南  
+>
+> 2025.2.2: 三分钟快速接入最强qwen2.5-max[视频](https://www.bilibili.com/video/BV1LeFuerEG4)  
+> 2025.2.1: 支持自定义字体  
+> 2024.10.10: 突发停电，紧急恢复了提供[whl包](https://drive.google.com/drive/folders/14kR-3V-lIbvGxri4AHc8TpiA1fqsw7SK?usp=sharing)的文件服务器  
 > 2024.5.1: 加入Doc2x翻译PDF论文的功能，[查看详情](https://github.com/binary-husky/gpt_academic/wiki/Doc2x)  
 > 2024.3.11: 全力支持Qwen、GLM、DeepseekCoder等中文大语言模型！ SoVits语音克隆模块，[查看详情](https://www.bilibili.com/video/BV1Rp421S7tF/) 
-> 2024.1.17: 安装依赖时，请选择`requirements.txt`中**指定的版本**。 安装命令：`pip install -r requirements.txt`。本项目完全开源免费，您可通过订阅[在线服务](https://github.com/binary-husky/gpt_academic/wiki/online)的方式鼓励本项目的发展。
+> 2024.1.17: 安装依赖时，请选择`requirements.txt`中**指定的版本**。 安装命令：`pip install -r requirements.txt`。
 
 <br>
 
@@ -124,20 +130,20 @@ Latex论文一键校对 | [插件] 仿Grammarly对Latex文章进行语法、拼
 
 ```mermaid
 flowchart TD
-    A{"安装方法"} --> W1("I. 🔑直接运行 (Windows, Linux or MacOS)")
-    W1 --> W11["1. Python pip包管理依赖"]
-    W1 --> W12["2. Anaconda包管理依赖（推荐⭐）"]
+    A{"安装方法"} --> W1("I 🔑直接运行 (Windows, Linux or MacOS)")
+    W1 --> W11["1 Python pip包管理依赖"]
+    W1 --> W12["2 Anaconda包管理依赖（推荐⭐）"]
 
-    A --> W2["II. 🐳使用Docker (Windows, Linux or MacOS)"]
+    A --> W2["II 🐳使用Docker (Windows, Linux or MacOS)"]
 
-    W2 --> k1["1. 部署项目全部能力的大镜像（推荐⭐）"]
-    W2 --> k2["2. 仅在线模型（GPT, GLM4等）镜像"]
-    W2 --> k3["3. 在线模型 + Latex的大镜像"]
+    W2 --> k1["1 部署项目全部能力的大镜像（推荐⭐）"]
+    W2 --> k2["2 仅在线模型（GPT, GLM4等）镜像"]
+    W2 --> k3["3 在线模型 + Latex的大镜像"]
 
-    A --> W4["IV. 🚀其他部署方法"]
-    W4 --> C1["1. Windows/MacOS 一键安装运行脚本（推荐⭐）"]
-    W4 --> C2["2. Huggingface, Sealos远程部署"]
-    W4 --> C4["3. ... 其他 ..."]
+    A --> W4["IV 🚀其他部署方法"]
+    W4 --> C1["1 Windows/MacOS 一键安装运行脚本（推荐⭐）"]
+    W4 --> C2["2 Huggingface, Sealos远程部署"]
+    W4 --> C4["3 其他 ..."]
 ```
 
 ### 安装方法I：直接运行 (Windows, Linux or MacOS)
@@ -170,26 +176,32 @@ flowchart TD
     ```
 
 
-<details><summary>如果需要支持清华ChatGLM2/复旦MOSS/RWKV作为后端，请点击展开此处</summary>
+<details><summary>如果需要支持清华ChatGLM系列/复旦MOSS/RWKV作为后端，请点击展开此处</summary>
 <p>
 
-【可选步骤】如果需要支持清华ChatGLM3/复旦MOSS作为后端，需要额外安装更多依赖（前提条件：熟悉Python + 用过Pytorch + 电脑配置够强）：
+【可选步骤】如果需要支持清华ChatGLM系列/复旦MOSS作为后端，需要额外安装更多依赖（前提条件：熟悉Python + 用过Pytorch + 电脑配置够强）：
 
 ```sh
 # 【可选步骤I】支持清华ChatGLM3。清华ChatGLM备注：如果遇到"Call ChatGLM fail 不能正常加载ChatGLM的参数" 错误，参考如下： 1：以上默认安装的为torch+cpu版，使用cuda需要卸载torch重新安装torch+cuda； 2：如因本机配置不够无法加载模型，可以修改request_llm/bridge_chatglm.py中的模型精度, 将 AutoTokenizer.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True) 都修改为 AutoTokenizer.from_pretrained("THUDM/chatglm-6b-int4", trust_remote_code=True)
 python -m pip install -r request_llms/requirements_chatglm.txt
 
-# 【可选步骤II】支持复旦MOSS
+# 【可选步骤II】支持清华ChatGLM4 注意：此模型至少需要24G显存
+python -m pip install -r request_llms/requirements_chatglm4.txt
+# 可使用modelscope下载ChatGLM4模型
+# pip install modelscope
+# modelscope download --model ZhipuAI/glm-4-9b-chat --local_dir ./THUDM/glm-4-9b-chat
+
+# 【可选步骤III】支持复旦MOSS
 python -m pip install -r request_llms/requirements_moss.txt
 git clone --depth=1 https://github.com/OpenLMLab/MOSS.git request_llms/moss  # 注意执行此行代码时，必须处于项目根路径
 
-# 【可选步骤III】支持RWKV Runner
+# 【可选步骤IV】支持RWKV Runner
 参考wiki：https://github.com/binary-husky/gpt_academic/wiki/%E9%80%82%E9%85%8DRWKV-Runner
 
-# 【可选步骤IV】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)：
+# 【可选步骤V】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", "moss"] # + ["jittorllms_rwkv", "jittorllms_pangualpha", "jittorllms_llama"]
 
-# 【可选步骤V】支持本地模型INT8,INT4量化（这里所指的模型本身不是量化版本，目前deepseek-coder支持，后面测试后会加入更多模型量化选择）
+# 【可选步骤VI】支持本地模型INT8,INT4量化（这里所指的模型本身不是量化版本，目前deepseek-coder支持，后面测试后会加入更多模型量化选择）
 pip install bitsandbyte
 # windows用户安装bitsandbytes需要使用下面bitsandbytes-windows-webui
 python -m pip install bitsandbytes --prefer-binary --extra-index-url=https://jllllll.github.io/bitsandbytes-windows-webui
@@ -417,7 +429,6 @@ timeline LR
 1. `master` 分支: 主分支，稳定版
 2. `frontier` 分支: 开发分支，测试版
 3. 如何[接入其他大模型](request_llms/README.md)
-4. 访问GPT-Academic的[在线服务并支持我们](https://github.com/binary-husky/gpt_academic/wiki/online)
 
 ### V：参考与学习
 

config.py

@@ -7,11 +7,16 @@
     Configuration reading priority: environment variable > config_private.py > config.py
 """
 
-# [step 1]>> API_KEY = "sk-123456789xxxxxxxxxxxxxxxxxxxxxxxxxxxxxx123456789"。极少数情况下，还需要填写组织（格式如org-123456789abcdefghijklmno的），请向下翻，找 API_ORG 设置项
-API_KEY = "此处填API密钥"    # 可同时填写多个API-KEY，用英文逗号分割，例如API_KEY = "sk-openaikey1,sk-openaikey2,fkxxxx-api2dkey3,azure-apikey4"
+# [step 1-1]>> ( 接入OpenAI模型家族 ) API_KEY = "sk-123456789xxxxxxxxxxxxxxxxxxxxxxxxxxxxxx123456789"。极少数情况下，还需要填写组织（格式如org-123456789abcdefghijklmno的），请向下翻，找 API_ORG 设置项
+API_KEY = "在此处填写APIKEY"    # 可同时填写多个API-KEY，用英文逗号分割，例如API_KEY = "sk-openaikey1,sk-openaikey2,fkxxxx-api2dkey3,azure-apikey4"
 
+# [step 1-2]>> ( 强烈推荐！接入通义家族 & 大模型服务平台百炼 ) 接入通义千问在线大模型，api-key获取地址 https://dashscope.console.aliyun.com/
+DASHSCOPE_API_KEY = "" # 阿里灵积云API_KEY（用于接入qwen-max，dashscope-qwen3-14b，dashscope-deepseek-r1等）
 
-# [step 2]>> 改为True应用代理，如果直接在海外服务器部署，此处不修改；如果使用本地或无地域限制的大模型时，此处也不需要修改
+# [step 1-3]>> ( 接入 deepseek-reasoner, 即 deepseek-r1 ) 深度求索(DeepSeek) API KEY，默认请求地址为"https://api.deepseek.com/v1/chat/completions"
+DEEPSEEK_API_KEY = ""
+
+# [step 2]>> 改为True应用代理。如果使用本地或无地域限制的大模型时，此处不修改；如果直接在海外服务器部署，此处不修改
 USE_PROXY = False
 if USE_PROXY:
     """
@@ -32,11 +37,16 @@ else:
 
 # [step 3]>> 模型选择是 (注意: LLM_MODEL是默认选中的模型, 它*必须*被包含在AVAIL_LLM_MODELS列表中 )
 LLM_MODEL = "gpt-3.5-turbo-16k" # 可选 ↓↓↓
-AVAIL_LLM_MODELS = ["gpt-4-1106-preview", "gpt-4-turbo-preview", "gpt-4-vision-preview",
+AVAIL_LLM_MODELS = ["qwen-max", "o1-mini", "o1-mini-2024-09-12", "o1", "o1-2024-12-17", "o1-preview", "o1-preview-2024-09-12",
+                    "gpt-4-1106-preview", "gpt-4-turbo-preview", "gpt-4-vision-preview",
                     "gpt-4o", "gpt-4o-mini", "gpt-4-turbo", "gpt-4-turbo-2024-04-09",
                     "gpt-3.5-turbo-1106", "gpt-3.5-turbo-16k", "gpt-3.5-turbo", "azure-gpt-3.5",
                     "gpt-4", "gpt-4-32k", "azure-gpt-4", "glm-4", "glm-4v", "glm-3-turbo",
-                    "gemini-1.5-pro", "chatglm3"
+                    "gemini-1.5-pro", "chatglm3", "chatglm4",
+                    "deepseek-chat", "deepseek-coder", "deepseek-reasoner", 
+                    "volcengine-deepseek-r1-250120", "volcengine-deepseek-v3-241226",
+                    "dashscope-deepseek-r1", "dashscope-deepseek-v3",
+                    "dashscope-qwen3-14b", "dashscope-qwen3-235b-a22b", "dashscope-qwen3-32b",
                     ]
 
 EMBEDDING_MODEL = "text-embedding-3-small"
@@ -47,7 +57,7 @@ EMBEDDING_MODEL = "text-embedding-3-small"
 #   "glm-4-0520", "glm-4-air", "glm-4-airx", "glm-4-flash",
 #   "qianfan", "deepseekcoder",
 #   "spark", "sparkv2", "sparkv3", "sparkv3.5", "sparkv4",
-#   "qwen-turbo", "qwen-plus", "qwen-max", "qwen-local",
+#   "qwen-turbo", "qwen-plus", "qwen-local",
 #   "moonshot-v1-128k", "moonshot-v1-32k", "moonshot-v1-8k",
 #   "gpt-3.5-turbo-0613", "gpt-3.5-turbo-16k-0613", "gpt-3.5-turbo-0125", "gpt-4o-2024-05-13"
 #   "claude-3-haiku-20240307","claude-3-sonnet-20240229","claude-3-opus-20240229", "claude-2.1", "claude-instant-1.2",
@@ -55,6 +65,7 @@ EMBEDDING_MODEL = "text-embedding-3-small"
 #   "deepseek-chat" ,"deepseek-coder",
 #   "gemini-1.5-flash",
 #   "yi-34b-chat-0205","yi-34b-chat-200k","yi-large","yi-medium","yi-spark","yi-large-turbo","yi-large-preview",
+#   "grok-beta",
 # ]
 # --- --- --- ---
 # 此外，您还可以在接入one-api/vllm/ollama/Openroute时，
@@ -73,7 +84,7 @@ API_URL_REDIRECT = {}
 
 # 多线程函数插件中，默认允许多少路线程同时访问OpenAI。Free trial users的限制是每分钟3次，Pay-as-you-go users的限制是每分钟3500次
 # 一言以蔽之：免费（5刀）用户填3，OpenAI绑了信用卡的用户可以填 16 或者更高。提高限制请查询：https://platform.openai.com/docs/guides/rate-limits/overview
-DEFAULT_WORKER_NUM = 3
+DEFAULT_WORKER_NUM = 8
 
 
 # 色彩主题, 可选 ["Default", "Chuanhu-Small-and-Beautiful", "High-Contrast"]
@@ -81,6 +92,31 @@ DEFAULT_WORKER_NUM = 3
 THEME = "Default"
 AVAIL_THEMES = ["Default", "Chuanhu-Small-and-Beautiful", "High-Contrast", "Gstaff/Xkcd", "NoCrypt/Miku"]
 
+FONT = "Theme-Default-Font"
+AVAIL_FONTS = [
+    "默认值(Theme-Default-Font)", 
+    "宋体(SimSun)",  
+    "黑体(SimHei)",  
+    "楷体(KaiTi)",  
+    "仿宋(FangSong)",  
+    "华文细黑(STHeiti Light)",
+    "华文楷体(STKaiti)",  
+    "华文仿宋(STFangsong)",  
+    "华文宋体(STSong)",  
+    "华文中宋(STZhongsong)",  
+    "华文新魏(STXinwei)",  
+    "华文隶书(STLiti)", 
+    # 备注：以下字体需要网络支持，您可以自定义任意您喜欢的字体，如下所示，需要满足的格式为 "字体昵称(字体英文真名@字体css下载链接)" 
+    "思源宋体(Source Han Serif CN VF@https://chinese-fonts-cdn.deno.dev/packages/syst/dist/SourceHanSerifCN/result.css)",
+    "月星楷(Moon Stars Kai HW@https://chinese-fonts-cdn.deno.dev/packages/moon-stars-kai/dist/MoonStarsKaiHW-Regular/result.css)",
+    "珠圆体(MaokenZhuyuanTi@https://chinese-fonts-cdn.deno.dev/packages/mkzyt/dist/猫啃珠圆体/result.css)",
+    "平方萌萌哒(PING FANG MENG MNEG DA@https://chinese-fonts-cdn.deno.dev/packages/pfmmd/dist/平方萌萌哒/result.css)",
+    "Helvetica",
+    "ui-sans-serif",
+    "sans-serif",
+    "system-ui"
+]
+
 
 # 默认的系统提示词（system prompt）
 INIT_SYS_PROMPT = "Serve me as a writing and programming assistant."
@@ -132,16 +168,15 @@ MULTI_QUERY_LLM_MODELS = "gpt-3.5-turbo&chatglm3"
 QWEN_LOCAL_MODEL_SELECTION = "Qwen/Qwen-1_8B-Chat-Int8"
 
 
-# 接入通义千问在线大模型 https://dashscope.console.aliyun.com/
-DASHSCOPE_API_KEY = "" # 阿里灵积云API_KEY
-
-
 # 百度千帆（LLM_MODEL="qianfan"）
 BAIDU_CLOUD_API_KEY = ''
 BAIDU_CLOUD_SECRET_KEY = ''
 BAIDU_CLOUD_QIANFAN_MODEL = 'ERNIE-Bot'    # 可选 "ERNIE-Bot-4"(文心大模型4.0), "ERNIE-Bot"(文心一言), "ERNIE-Bot-turbo", "BLOOMZ-7B", "Llama-2-70B-Chat", "Llama-2-13B-Chat", "Llama-2-7B-Chat", "ERNIE-Speed-128K", "ERNIE-Speed-8K", "ERNIE-Lite-8K"
 
 
+# 如果使用ChatGLM3或ChatGLM4本地模型，请把 LLM_MODEL="chatglm3" 或LLM_MODEL="chatglm4"，并在此处指定模型路径
+CHATGLM_LOCAL_MODEL_PATH = "THUDM/glm-4-9b-chat" # 例如"/home/hmp/ChatGLM3-6B/"
+
 # 如果使用ChatGLM2微调模型，请把 LLM_MODEL="chatglmft"，并在此处指定模型路径
 CHATGLM_PTUNING_CHECKPOINT = "" # 例如"/home/hmp/ChatGLM2-6B/ptuning/output/6b-pt-128-1e-2/checkpoint-100"
 
@@ -235,13 +270,15 @@ MOONSHOT_API_KEY = ""
 YIMODEL_API_KEY = ""
 
 
-# 深度求索(DeepSeek) API KEY，默认请求地址为"https://api.deepseek.com/v1/chat/completions"
-DEEPSEEK_API_KEY = ""
+# 接入火山引擎的在线大模型)，api-key获取地址 https://console.volcengine.com/ark/region:ark+cn-beijing/endpoint
+ARK_API_KEY = "00000000-0000-0000-0000-000000000000" # 火山引擎 API KEY
 
 
 # 紫东太初大模型 https://ai-maas.wair.ac.cn
 TAICHU_API_KEY = ""
 
+# Grok API KEY
+GROK_API_KEY = ""
 
 # Mathpix 拥有执行PDF的OCR功能，但是需要注册账号
 MATHPIX_APPID = ""
@@ -273,8 +310,8 @@ GROBID_URLS = [
 ]
 
 
-# Searxng互联网检索服务
-SEARXNG_URL = "https://cloud-1.agent-matrix.com/"
+# Searxng互联网检索服务（这是一个huggingface空间，请前往huggingface复制该空间，然后把自己新的空间地址填在这里）
+SEARXNG_URLS = [ f"https://kaletianlre-beardvs{i}dd.hf.space/" for i in range(1,5) ]
 
 
 # 是否允许通过自然语言描述修改本页的配置，该功能具有一定的危险性，默认关闭
@@ -298,7 +335,7 @@ ARXIV_CACHE_DIR = "gpt_log/arxiv_cache"
 
 
 # 除了连接OpenAI之外，还有哪些场合允许使用代理，请尽量不要修改
-WHEN_TO_USE_PROXY = ["Download_LLM", "Download_Gradio_Theme", "Connect_Grobid",
+WHEN_TO_USE_PROXY = ["Connect_OpenAI", "Download_LLM", "Download_Gradio_Theme", "Connect_Grobid",
                      "Warmup_Modules", "Nougat_Download", "AutoGen", "Connect_OpenAI_Embedding"]
 
 
@@ -310,6 +347,23 @@ PLUGIN_HOT_RELOAD = False
 NUM_CUSTOM_BASIC_BTN = 4
 
 
+# 媒体智能体的服务地址（这是一个huggingface空间，请前往huggingface复制该空间，然后把自己新的空间地址填在这里）
+DAAS_SERVER_URLS = [ f"https://niuziniu-biligpt{i}.hf.space/stream" for i in range(1,5) ]
+
+
+# 在互联网搜索组件中，负责将搜索结果整理成干净的Markdown
+JINA_API_KEY = ""
+
+
+# 是否自动裁剪上下文长度（是否启动，默认不启动）
+AUTO_CONTEXT_CLIP_ENABLE = False
+# 目标裁剪上下文的token长度（如果超过这个长度，则会自动裁剪）
+AUTO_CONTEXT_CLIP_TRIGGER_TOKEN_LEN = 30*1000
+# 无条件丢弃x以上的轮数
+AUTO_CONTEXT_MAX_ROUND = 64
+# 在裁剪上下文时，倒数第x次对话能“最多”保留的上下文token的比例占 AUTO_CONTEXT_CLIP_TRIGGER_TOKEN_LEN 的多少
+AUTO_CONTEXT_MAX_CLIP_RATIO = [0.80, 0.60, 0.45, 0.25, 0.20, 0.18, 0.16, 0.14, 0.12, 0.10, 0.08, 0.07, 0.06, 0.05, 0.04, 0.03, 0.02, 0.01]
+
 
 """
 --------------- 配置关联关系说明 ---------------
@@ -369,6 +423,7 @@ NUM_CUSTOM_BASIC_BTN = 4
 
 本地大模型示意图
 │
+├── "chatglm4"
 ├── "chatglm3"
 ├── "chatglm"
 ├── "chatglm_onnx"
@@ -399,7 +454,7 @@ NUM_CUSTOM_BASIC_BTN = 4
 插件在线服务配置依赖关系示意图
 │
 ├── 互联网检索
-│   └── SEARXNG_URL
+│   └── SEARXNG_URLS
 │
 ├── 语音功能
 │   ├── ENABLE_AUDIO

config_private.py

@@ -0,0 +1,444 @@
+"""
+    以下所有配置也都支持利用环境变量覆写，环境变量配置格式见docker-compose.yml。
+    读取优先级：环境变量 > config_private.py > config.py
+    --- --- --- --- --- --- --- --- --- --- --- --- --- --- --- --- --- --- --- --- ---
+    All the following configurations also support using environment variables to override,
+    and the environment variable configuration format can be seen in docker-compose.yml.
+    Configuration reading priority: environment variable > config_private.py > config.py
+"""
+
+# [step 1-1]>> ( 接入GPT等模型 ) API_KEY = "sk-123456789xxxxxxxxxxxxxxxxxxxxxxxxxxxxxx123456789"。极少数情况下，还需要填写组织（格式如org-123456789abcdefghijklmno的），请向下翻，找 API_ORG 设置项
+API_KEY = "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"    # 可同时填写多个API-KEY，用英文逗号分割，例如API_KEY = "sk-openaikey1,sk-openaikey2,fkxxxx-api2dkey1,fkxxxx-api2dkey2"
+
+# [step 1-2]>> ( 接入通义 qwen-max ) 接入通义千问在线大模型，api-key获取地址 https://dashscope.console.aliyun.com/
+DASHSCOPE_API_KEY = "" # 阿里灵积云API_KEY
+
+# [step 1-3]>> ( 接入 deepseek-reasoner, 即 deepseek-r1 ) 深度求索(DeepSeek) API KEY，默认请求地址为"https://api.deepseek.com/v1/chat/completions"
+DEEPSEEK_API_KEY = "sk-d99b8cc6b7414cc88a5d950a3ff7585e"
+
+# [step 2]>> 改为True应用代理。如果使用本地或无地域限制的大模型时，此处不修改；如果直接在海外服务器部署，此处不修改
+USE_PROXY = True
+if USE_PROXY:
+    proxies = {
+        "http":"socks5h://192.168.8.9:1070",  # 再例如  "http":  "http://127.0.0.1:7890",
+        "https":"socks5h://192.168.8.9:1070",  # 再例如  "https": "http://127.0.0.1:7890",
+    }
+else:
+    proxies = None
+DEFAULT_WORKER_NUM = 256
+
+# [step 3]>> 模型选择是 (注意: LLM_MODEL是默认选中的模型, 它*必须*被包含在AVAIL_LLM_MODELS列表中 )
+LLM_MODEL = "gpt-4-32k" # 可选 ↓↓↓
+AVAIL_LLM_MODELS = ["deepseek-chat", "deepseek-coder", "deepseek-reasoner",
+                    "gpt-4-1106-preview", "gpt-4-turbo-preview", "gpt-4-vision-preview",
+                    "gpt-4o", "gpt-4o-mini", "gpt-4-turbo", "gpt-4-turbo-2024-04-09",
+                    "gpt-3.5-turbo-1106", "gpt-3.5-turbo-16k", "gpt-3.5-turbo", "azure-gpt-3.5",
+                    "gpt-4", "gpt-4-32k", "azure-gpt-4", "glm-4", "glm-4v", "glm-3-turbo",
+                    "gemini-1.5-pro", "chatglm3", "chatglm4",
+                    ]
+
+EMBEDDING_MODEL = "text-embedding-3-small"
+
+# --- --- --- ---
+# P.S. 其他可用的模型还包括
+# AVAIL_LLM_MODELS = [
+#   "glm-4-0520", "glm-4-air", "glm-4-airx", "glm-4-flash",
+#   "qianfan", "deepseekcoder",
+#   "spark", "sparkv2", "sparkv3", "sparkv3.5", "sparkv4",
+#   "qwen-turbo", "qwen-plus", "qwen-local",
+#   "moonshot-v1-128k", "moonshot-v1-32k", "moonshot-v1-8k",
+#   "gpt-3.5-turbo-0613", "gpt-3.5-turbo-16k-0613", "gpt-3.5-turbo-0125", "gpt-4o-2024-05-13"
+#   "claude-3-haiku-20240307","claude-3-sonnet-20240229","claude-3-opus-20240229", "claude-2.1", "claude-instant-1.2",
+#   "moss", "llama2", "chatglm_onnx", "internlm", "jittorllms_pangualpha", "jittorllms_llama",
+#   "deepseek-chat" ,"deepseek-coder",
+#   "gemini-1.5-flash",
+#   "yi-34b-chat-0205","yi-34b-chat-200k","yi-large","yi-medium","yi-spark","yi-large-turbo","yi-large-preview",
+#   "grok-beta",
+# ]
+# --- --- --- ---
+# 此外，您还可以在接入one-api/vllm/ollama/Openroute时，
+# 使用"one-api-*","vllm-*","ollama-*","openrouter-*"前缀直接使用非标准方式接入的模型，例如
+# AVAIL_LLM_MODELS = ["one-api-claude-3-sonnet-20240229(max_token=100000)", "ollama-phi3(max_token=4096)","openrouter-openai/gpt-4o-mini","openrouter-openai/chatgpt-4o-latest"]
+# --- --- --- ---
+
+
+# --------------- 以下配置可以优化体验 ---------------
+
+# 重新URL重新定向，实现更换API_URL的作用（高危设置! 常规情况下不要修改! 通过修改此设置，您将把您的API-KEY和对话隐私完全暴露给您设定的中间人！）
+# 格式: API_URL_REDIRECT = {"https://api.openai.com/v1/chat/completions": "在这里填写重定向的api.openai.com的URL"}
+# 举例: API_URL_REDIRECT = {"https://api.openai.com/v1/chat/completions": "https://reverse-proxy-url/v1/chat/completions", "http://localhost:11434/api/chat": "在这里填写您ollama的URL"}
+API_URL_REDIRECT = {}
+
+
+# 多线程函数插件中，默认允许多少路线程同时访问OpenAI。Free trial users的限制是每分钟3次，Pay-as-you-go users的限制是每分钟3500次
+# 一言以蔽之：免费（5刀）用户填3，OpenAI绑了信用卡的用户可以填 16 或者更高。提高限制请查询：https://platform.openai.com/docs/guides/rate-limits/overview
+DEFAULT_WORKER_NUM = 64
+
+
+# 色彩主题, 可选 ["Default", "Chuanhu-Small-and-Beautiful", "High-Contrast"]
+# 更多主题, 请查阅Gradio主题商店: https://huggingface.co/spaces/gradio/theme-gallery 可选 ["Gstaff/Xkcd", "NoCrypt/Miku", ...]
+THEME = "Default"
+AVAIL_THEMES = ["Default", "Chuanhu-Small-and-Beautiful", "High-Contrast", "Gstaff/Xkcd", "NoCrypt/Miku"]
+
+FONT = "Theme-Default-Font"
+AVAIL_FONTS = [
+    "默认值(Theme-Default-Font)",
+    "宋体(SimSun)",
+    "黑体(SimHei)",
+    "楷体(KaiTi)",
+    "仿宋(FangSong)",
+    "华文细黑(STHeiti Light)",
+    "华文楷体(STKaiti)",
+    "华文仿宋(STFangsong)",
+    "华文宋体(STSong)",
+    "华文中宋(STZhongsong)",
+    "华文新魏(STXinwei)",
+    "华文隶书(STLiti)",
+    "思源宋体(Source Han Serif CN VF@https://chinese-fonts-cdn.deno.dev/packages/syst/dist/SourceHanSerifCN/result.css)",
+    "月星楷(Moon Stars Kai HW@https://chinese-fonts-cdn.deno.dev/packages/moon-stars-kai/dist/MoonStarsKaiHW-Regular/result.css)",
+    "珠圆体(MaokenZhuyuanTi@https://chinese-fonts-cdn.deno.dev/packages/mkzyt/dist/猫啃珠圆体/result.css)",
+    "平方萌萌哒(PING FANG MENG MNEG DA@https://chinese-fonts-cdn.deno.dev/packages/pfmmd/dist/平方萌萌哒/result.css)",
+    "Helvetica",
+    "ui-sans-serif",
+    "sans-serif",
+    "system-ui"
+]
+
+
+# 默认的系统提示词（system prompt）
+INIT_SYS_PROMPT = " "
+
+
+# 对话窗的高度 （仅在LAYOUT="TOP-DOWN"时生效）
+CHATBOT_HEIGHT = 1115
+
+
+# 代码高亮
+CODE_HIGHLIGHT = True
+
+
+# 窗口布局
+LAYOUT = "LEFT-RIGHT"   # "LEFT-RIGHT"（左右布局） # "TOP-DOWN"（上下布局）
+
+
+# 暗色模式 / 亮色模式
+DARK_MODE = True
+
+
+# 发送请求到OpenAI后，等待多久判定为超时
+TIMEOUT_SECONDS = 60
+
+
+# 网页的端口, -1代表随机端口
+WEB_PORT = 19998
+
+# 是否自动打开浏览器页面
+AUTO_OPEN_BROWSER = True
+
+
+# 如果OpenAI不响应（网络卡顿、代理失败、KEY失效），重试的次数限制
+MAX_RETRY = 5
+
+
+# 插件分类默认选项
+DEFAULT_FN_GROUPS = ['对话', '编程', '学术', '智能体']
+
+
+# 定义界面上“询问多个GPT模型”插件应该使用哪些模型，请从AVAIL_LLM_MODELS中选择，并在不同模型之间用`&`间隔，例如"gpt-3.5-turbo&chatglm3&azure-gpt-4"
+MULTI_QUERY_LLM_MODELS = "gpt-3.5-turbo&chatglm3"
+
+
+# 选择本地模型变体（只有当AVAIL_LLM_MODELS包含了对应本地模型时，才会起作用）
+# 如果你选择Qwen系列的模型，那么请在下面的QWEN_MODEL_SELECTION中指定具体的模型
+# 也可以是具体的模型路径
+QWEN_LOCAL_MODEL_SELECTION = "Qwen/Qwen-1_8B-Chat-Int8"
+
+
+# 百度千帆（LLM_MODEL="qianfan"）
+BAIDU_CLOUD_API_KEY = ''
+BAIDU_CLOUD_SECRET_KEY = ''
+BAIDU_CLOUD_QIANFAN_MODEL = 'ERNIE-Bot'    # 可选 "ERNIE-Bot-4"(文心大模型4.0), "ERNIE-Bot"(文心一言), "ERNIE-Bot-turbo", "BLOOMZ-7B", "Llama-2-70B-Chat", "Llama-2-13B-Chat", "Llama-2-7B-Chat", "ERNIE-Speed-128K", "ERNIE-Speed-8K", "ERNIE-Lite-8K"
+
+
+# 如果使用ChatGLM3或ChatGLM4本地模型，请把 LLM_MODEL="chatglm3" 或LLM_MODEL="chatglm4"，并在此处指定模型路径
+CHATGLM_LOCAL_MODEL_PATH = "THUDM/glm-4-9b-chat" # 例如"/home/hmp/ChatGLM3-6B/"
+
+# 如果使用ChatGLM2微调模型，请把 LLM_MODEL="chatglmft"，并在此处指定模型路径
+CHATGLM_PTUNING_CHECKPOINT = "" # 例如"/home/hmp/ChatGLM2-6B/ptuning/output/6b-pt-128-1e-2/checkpoint-100"
+
+
+# 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）
+CONCURRENT_COUNT = 100
+
+
+# 是否在提交时自动清空输入框
+AUTO_CLEAR_TXT = False
+
+
+# 加一个live2d装饰
+ADD_WAIFU = False
+
+
+# 设置用户名和密码（不需要修改）（相关功能不稳定，与gradio版本和网络都相关，如果本地使用不建议加这个）
+# [("username", "password"), ("username2", "password2"), ...]
+AUTHENTICATION = [("van", "L807878712"),("林", "L807878712"),("源", "L807878712"),("欣", "L807878712"),("z", "czh123456789")]
+
+
+# 如果需要在二级路径下运行（常规情况下，不要修改!!）
+# （举例 CUSTOM_PATH = "/gpt_academic"，可以让软件运行在 http://ip:port/gpt_academic/ 下。）
+CUSTOM_PATH = "/"
+
+
+# HTTPS 秘钥和证书（不需要修改）
+SSL_KEYFILE = ""
+SSL_CERTFILE = ""
+
+
+# 极少数情况下，openai的官方KEY需要伴随组织编码（格式如org-xxxxxxxxxxxxxxxxxxxxxxxx）使用
+API_ORG = ""
+
+
+# 如果需要使用Slack Claude，使用教程详情见 request_llms/README.md
+SLACK_CLAUDE_BOT_ID = ''
+SLACK_CLAUDE_USER_TOKEN = ''
+
+
+# 如果需要使用AZURE（方法一：单个azure模型部署）详情请见额外文档 docs\use_azure.md
+AZURE_ENDPOINT = "https://你亲手写的api名称.openai.azure.com/"
+AZURE_API_KEY = "填入azure openai api的密钥"    # 建议直接在API_KEY处填写，该选项即将被弃用
+AZURE_ENGINE = "填入你亲手写的部署名"            # 读 docs\use_azure.md
+
+
+# 如果需要使用AZURE（方法二：多个azure模型部署+动态切换）详情请见额外文档 docs\use_azure.md
+AZURE_CFG_ARRAY = {}
+
+
+# 阿里云实时语音识别 配置难度较高
+# 参考 https://github.com/binary-husky/gpt_academic/blob/master/docs/use_audio.md
+ENABLE_AUDIO = False
+ALIYUN_TOKEN=""     # 例如 f37f30e0f9934c34a992f6f64f7eba4f
+ALIYUN_APPKEY=""    # 例如 RoPlZrM88DnAFkZK
+ALIYUN_ACCESSKEY="" # （无需填写）
+ALIYUN_SECRET=""    # （无需填写）
+
+
+# GPT-SOVITS 文本转语音服务的运行地址（将语言模型的生成文本朗读出来）
+TTS_TYPE = "DISABLE" # EDGE_TTS / LOCAL_SOVITS_API / DISABLE
+GPT_SOVITS_URL = ""
+EDGE_TTS_VOICE = "zh-CN-XiaoxiaoNeural"
+
+
+# 接入讯飞星火大模型 https://console.xfyun.cn/services/iat
+XFYUN_APPID = "00000000"
+XFYUN_API_SECRET = "bbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbb"
+XFYUN_API_KEY = "aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa"
+
+
+# 接入智谱大模型
+ZHIPUAI_API_KEY = ""
+ZHIPUAI_MODEL = "" # 此选项已废弃，不再需要填写
+
+
+# Claude API KEY
+ANTHROPIC_API_KEY = ""
+
+
+# 月之暗面 API KEY
+MOONSHOT_API_KEY = ""
+
+
+# 零一万物(Yi Model) API KEY
+YIMODEL_API_KEY = ""
+
+
+# 紫东太初大模型 https://ai-maas.wair.ac.cn
+TAICHU_API_KEY = ""
+
+# Grok API KEY
+GROK_API_KEY = ""
+
+# Mathpix 拥有执行PDF的OCR功能，但是需要注册账号
+MATHPIX_APPID = ""
+MATHPIX_APPKEY = ""
+
+
+# DOC2X的PDF解析服务，注册账号并获取API KEY: https://doc2x.noedgeai.com/login
+DOC2X_API_KEY = ""
+
+
+# 自定义API KEY格式
+CUSTOM_API_KEY_PATTERN = ""
+
+
+# Google Gemini API-Key
+GEMINI_API_KEY = ''
+
+
+# HUGGINGFACE的TOKEN，下载LLAMA时起作用 https://huggingface.co/docs/hub/security-tokens
+HUGGINGFACE_ACCESS_TOKEN = "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"
+
+
+# GROBID服务器地址（填写多个可以均衡负载），用于高质量地读取PDF文档
+# 获取方法：复制以下空间https://huggingface.co/spaces/qingxu98/grobid，设为public，然后GROBID_URL = "https://(你的hf用户名如qingxu98)-(你的填写的空间名如grobid).hf.space"
+GROBID_URLS = [
+    "https://qingxu98-grobid.hf.space","https://qingxu98-grobid2.hf.space","https://qingxu98-grobid3.hf.space",
+    "https://qingxu98-grobid4.hf.space","https://qingxu98-grobid5.hf.space", "https://qingxu98-grobid6.hf.space",
+    "https://qingxu98-grobid7.hf.space", "https://qingxu98-grobid8.hf.space",
+]
+
+
+# Searxng互联网检索服务（这是一个huggingface空间，请前往huggingface复制该空间，然后把自己新的空间地址填在这里）
+SEARXNG_URLS = [ f"https://kaletianlre-beardvs{i}dd.hf.space/" for i in range(1,5) ]
+
+
+# 是否允许通过自然语言描述修改本页的配置，该功能具有一定的危险性，默认关闭
+ALLOW_RESET_CONFIG = False
+
+
+# 在使用AutoGen插件时，是否使用Docker容器运行代码
+AUTOGEN_USE_DOCKER = False
+
+
+# 临时的上传文件夹位置，请尽量不要修改
+PATH_PRIVATE_UPLOAD = "private_upload"
+
+
+# 日志文件夹的位置，请尽量不要修改
+PATH_LOGGING = "gpt_log"
+
+
+# 存储翻译好的arxiv论文的路径，请尽量不要修改
+ARXIV_CACHE_DIR = "gpt_log/arxiv_cache"
+
+
+# 除了连接OpenAI之外，还有哪些场合允许使用代理，请尽量不要修改
+WHEN_TO_USE_PROXY = ["Connect_OpenAI", "Download_LLM", "Download_Gradio_Theme", "Connect_Grobid",
+                     "Warmup_Modules", "Nougat_Download", "AutoGen", "Connect_OpenAI_Embedding"]
+
+
+# 启用插件热加载
+PLUGIN_HOT_RELOAD = False
+
+
+# 自定义按钮的最大数量限制
+NUM_CUSTOM_BASIC_BTN = 4
+
+
+# 媒体智能体的服务地址（这是一个huggingface空间，请前往huggingface复制该空间，然后把自己新的空间地址填在这里）
+DAAS_SERVER_URLS = [ f"https://niuziniu-biligpt{i}.hf.space/stream" for i in range(1,5) ]
+
+
+
+"""
+--------------- 配置关联关系说明 ---------------
+
+在线大模型配置关联关系示意图
+│
+├── "gpt-3.5-turbo" 等openai模型
+│   ├── API_KEY
+│   ├── CUSTOM_API_KEY_PATTERN（不常用）
+│   ├── API_ORG（不常用）
+│   └── API_URL_REDIRECT（不常用）
+│
+├── "azure-gpt-3.5" 等azure模型（单个azure模型，不需要动态切换）
+│   ├── API_KEY
+│   ├── AZURE_ENDPOINT
+│   ├── AZURE_API_KEY
+│   ├── AZURE_ENGINE
+│   └── API_URL_REDIRECT
+│
+├── "azure-gpt-3.5" 等azure模型（多个azure模型，需要动态切换，高优先级）
+│   └── AZURE_CFG_ARRAY
+│
+├── "spark" 星火认知大模型 spark & sparkv2
+│   ├── XFYUN_APPID
+│   ├── XFYUN_API_SECRET
+│   └── XFYUN_API_KEY
+│
+├── "claude-3-opus-20240229" 等claude模型
+│   └── ANTHROPIC_API_KEY
+│
+├── "stack-claude"
+│   ├── SLACK_CLAUDE_BOT_ID
+│   └── SLACK_CLAUDE_USER_TOKEN
+│
+├── "qianfan" 百度千帆大模型库
+│   ├── BAIDU_CLOUD_QIANFAN_MODEL
+│   ├── BAIDU_CLOUD_API_KEY
+│   └── BAIDU_CLOUD_SECRET_KEY
+│
+├── "glm-4", "glm-3-turbo", "zhipuai" 智谱AI大模型
+│   └── ZHIPUAI_API_KEY
+│
+├── "yi-34b-chat-0205", "yi-34b-chat-200k" 等零一万物(Yi Model)大模型
+│   └── YIMODEL_API_KEY
+│
+├── "qwen-turbo" 等通义千问大模型
+│   └──  DASHSCOPE_API_KEY
+│
+├── "Gemini"
+│   └──  GEMINI_API_KEY
+│
+└── "one-api-...(max_token=...)" 用一种更方便的方式接入one-api多模型管理界面
+    ├── AVAIL_LLM_MODELS
+    ├── API_KEY
+    └── API_URL_REDIRECT
+
+
+本地大模型示意图
+│
+├── "chatglm4"
+├── "chatglm3"
+├── "chatglm"
+├── "chatglm_onnx"
+├── "chatglmft"
+├── "internlm"
+├── "moss"
+├── "jittorllms_pangualpha"
+├── "jittorllms_llama"
+├── "deepseekcoder"
+├── "qwen-local"
+├──  RWKV的支持见Wiki
+└── "llama2"
+
+
+用户图形界面布局依赖关系示意图
+│
+├── CHATBOT_HEIGHT 对话窗的高度
+├── CODE_HIGHLIGHT 代码高亮
+├── LAYOUT 窗口布局
+├── DARK_MODE 暗色模式 / 亮色模式
+├── DEFAULT_FN_GROUPS 插件分类默认选项
+├── THEME 色彩主题
+├── AUTO_CLEAR_TXT 是否在提交时自动清空输入框
+├── ADD_WAIFU 加一个live2d装饰
+└── ALLOW_RESET_CONFIG 是否允许通过自然语言描述修改本页的配置，该功能具有一定的危险性
+
+
+插件在线服务配置依赖关系示意图
+│
+├── 互联网检索
+│   └── SEARXNG_URLS
+│
+├── 语音功能
+│   ├── ENABLE_AUDIO
+│   ├── ALIYUN_TOKEN
+│   ├── ALIYUN_APPKEY
+│   ├── ALIYUN_ACCESSKEY
+│   └── ALIYUN_SECRET
+│
+└── PDF文档精准解析
+    ├── GROBID_URLS
+    ├── MATHPIX_APPID
+    └── MATHPIX_APPKEY
+
+
+"""
+
+
+

crazy_functional.py

@@ -2,7 +2,6 @@ from toolbox import HotReload  # HotReload 的意思是热更新，修改函数
 from toolbox import trimmed_format_exc
 from loguru import logger
 
-
 def get_crazy_functions():
     from crazy_functions.读文章写摘要 import 读文章写摘要
     from crazy_functions.生成函数注释 import 批量生成函数注释
@@ -15,13 +14,13 @@ def get_crazy_functions():
     from crazy_functions.SourceCode_Analyse import 解析一个Rust项目
     from crazy_functions.SourceCode_Analyse import 解析一个Java项目
     from crazy_functions.SourceCode_Analyse import 解析一个前端项目
-    from crazy_functions.Arxiv_论文对话 import Arxiv论文对话
     from crazy_functions.高级功能函数模板 import 高阶功能模板函数
     from crazy_functions.高级功能函数模板 import Demo_Wrap
-    from crazy_functions.Latex全文润色 import Latex英文润色
+    from crazy_functions.Latex_Project_Polish import Latex英文润色
     from crazy_functions.询问多个大语言模型 import 同时问询
     from crazy_functions.SourceCode_Analyse import 解析一个Lua项目
     from crazy_functions.SourceCode_Analyse import 解析一个CSharp项目
+    from crazy_functions.总结word文档 import 总结word文档
     from crazy_functions.解析JupyterNotebook import 解析ipynb文件
     from crazy_functions.Conversation_To_File import 载入对话历史存档
     from crazy_functions.Conversation_To_File import 对话历史存档
@@ -31,12 +30,10 @@ def get_crazy_functions():
     from crazy_functions.Markdown_Translate import Markdown英译中
     from crazy_functions.批量总结PDF文档 import 批量总结PDF文档
     from crazy_functions.PDF_Translate import 批量翻译PDF文档
-    from crazy_functions.批量文件询问 import 批量文件询问
-
     from crazy_functions.谷歌检索小助手 import 谷歌检索小助手
     from crazy_functions.理解PDF文档内容 import 理解PDF文档内容标准文件输入
-    from crazy_functions.Latex全文润色 import Latex中文润色
-    from crazy_functions.Latex全文润色 import Latex英文纠错
+    from crazy_functions.Latex_Project_Polish import Latex中文润色
+    from crazy_functions.Latex_Project_Polish import Latex英文纠错
     from crazy_functions.Markdown_Translate import Markdown中译英
     from crazy_functions.虚空终端 import 虚空终端
     from crazy_functions.生成多种Mermaid图表 import Mermaid_Gen
@@ -52,8 +49,16 @@ def get_crazy_functions():
     from crazy_functions.Image_Generate_Wrap import ImageGen_Wrap
     from crazy_functions.SourceCode_Comment import 注释Python项目
     from crazy_functions.SourceCode_Comment_Wrap import SourceCodeComment_Wrap
+    from crazy_functions.VideoResource_GPT import 多媒体任务
 
     function_plugins = {
+        "多媒体智能体": {
+            "Group": "智能体",
+            "Color": "stop",
+            "AsButton": False,
+            "Info": "【仅测试】多媒体任务",
+            "Function": HotReload(多媒体任务),
+        },
         "虚空终端": {
             "Group": "对话|编程|学术|智能体",
             "Color": "stop",
@@ -61,6 +66,34 @@ def get_crazy_functions():
             "Info": "使用自然语言实现您的想法",
             "Function": HotReload(虚空终端),
         },
+        "解析整个Python项目": {
+            "Group": "编程",
+            "Color": "stop",
+            "AsButton": True,
+            "Info": "解析一个Python项目的所有源文件(.py) | 输入参数为路径",
+            "Function": HotReload(解析一个Python项目),
+        },
+        "注释Python项目": {
+            "Group": "编程",
+            "Color": "stop",
+            "AsButton": False,
+            "Info": "上传一系列python源文件(或者压缩包), 为这些代码添加docstring | 输入参数为路径",
+            "Function": HotReload(注释Python项目),
+            "Class": SourceCodeComment_Wrap,
+        },
+        "载入对话历史存档（先上传存档或输入路径）": {
+            "Group": "对话",
+            "Color": "stop",
+            "AsButton": False,
+            "Info": "载入对话历史存档 | 输入参数为路径",
+            "Function": HotReload(载入对话历史存档),
+        },
+        "删除所有本地对话历史记录（谨慎操作）": {
+            "Group": "对话",
+            "AsButton": False,
+            "Info": "删除所有本地对话历史记录，谨慎操作 | 不需要输入参数",
+            "Function": HotReload(删除所有本地对话历史记录),
+        },
         "清除所有缓存文件（谨慎操作）": {
             "Group": "对话",
             "Color": "stop",
@@ -68,33 +101,107 @@ def get_crazy_functions():
             "Info": "清除所有缓存文件，谨慎操作 | 不需要输入参数",
             "Function": HotReload(清除缓存),
         },
+        "生成多种Mermaid图表(从当前对话或路径(.pdf/.md/.docx)中生产图表）": {
+            "Group": "对话",
+            "Color": "stop",
+            "AsButton": False,
+            "Info" : "基于当前对话或文件生成多种Mermaid图表,图表类型由模型判断",
+            "Function": None,
+            "Class": Mermaid_Gen
+        },
         "Arxiv论文翻译": {
             "Group": "学术",
             "Color": "stop",
             "AsButton": True,
-            "Info": "Arixv论文精细翻译 | 输入参数arxiv论文的ID，比如1812.10695",
+            "Info": "ArXiv论文精细翻译 | 输入参数arxiv论文的ID，比如1812.10695",
             "Function": HotReload(Latex翻译中文并重新编译PDF),  # 当注册Class后，Function旧接口仅会在“虚空终端”中起作用
             "Class": Arxiv_Localize,    # 新一代插件需要注册Class
         },
-        "批量文件询问": {
+        "批量总结Word文档": {
             "Group": "学术",
             "Color": "stop",
             "AsButton": False,
-            "AdvancedArgs": True,
-            "Info": "通过在高级参数区写入prompt，可自定义询问逻辑，默认情况下为总结逻辑 | 输入参数为路径",
-            "ArgsReminder": r"1、请不要更改上方输入框中以“private_upload/...”开头的路径。 "
-                            r"2、请在下方高级参数区中输入你的prompt，文档中的内容将被添加你的prompt后。3、示例：“请总结下面的内容：”，此时，文档内容将添加在“：”后 ",
-            "Function": HotReload(批量文件询问),
+            "Info": "批量总结word文档 | 输入参数为路径",
+            "Function": HotReload(总结word文档),
         },
-        "Arxiv论文对话": {
+        "解析整个Matlab项目": {
+            "Group": "编程",
+            "Color": "stop",
+            "AsButton": False,
+            "Info": "解析一个Matlab项目的所有源文件(.m) | 输入参数为路径",
+            "Function": HotReload(解析一个Matlab项目),
+        },
+        "解析整个C++项目头文件": {
+            "Group": "编程",
+            "Color": "stop",
+            "AsButton": False,  # 加入下拉菜单中
+            "Info": "解析一个C++项目的所有头文件(.h/.hpp) | 输入参数为路径",
+            "Function": HotReload(解析一个C项目的头文件),
+        },
+        "解析整个C++项目（.cpp/.hpp/.c/.h）": {
+            "Group": "编程",
+            "Color": "stop",
+            "AsButton": False,  # 加入下拉菜单中
+            "Info": "解析一个C++项目的所有源文件（.cpp/.hpp/.c/.h）| 输入参数为路径",
+            "Function": HotReload(解析一个C项目),
+        },
+        "解析整个Go项目": {
+            "Group": "编程",
+            "Color": "stop",
+            "AsButton": False,  # 加入下拉菜单中
+            "Info": "解析一个Go项目的所有源文件 | 输入参数为路径",
+            "Function": HotReload(解析一个Golang项目),
+        },
+        "解析整个Rust项目": {
+            "Group": "编程",
+            "Color": "stop",
+            "AsButton": False,  # 加入下拉菜单中
+            "Info": "解析一个Rust项目的所有源文件 | 输入参数为路径",
+            "Function": HotReload(解析一个Rust项目),
+        },
+        "解析整个Java项目": {
+            "Group": "编程",
+            "Color": "stop",
+            "AsButton": False,  # 加入下拉菜单中
+            "Info": "解析一个Java项目的所有源文件 | 输入参数为路径",
+            "Function": HotReload(解析一个Java项目),
+        },
+        "解析整个前端项目（js,ts,css等）": {
+            "Group": "编程",
+            "Color": "stop",
+            "AsButton": False,  # 加入下拉菜单中
+            "Info": "解析一个前端项目的所有源文件（js,ts,css等） | 输入参数为路径",
+            "Function": HotReload(解析一个前端项目),
+        },
+        "解析整个Lua项目": {
+            "Group": "编程",
+            "Color": "stop",
+            "AsButton": False,  # 加入下拉菜单中
+            "Info": "解析一个Lua项目的所有源文件 | 输入参数为路径",
+            "Function": HotReload(解析一个Lua项目),
+        },
+        "解析整个CSharp项目": {
+            "Group": "编程",
+            "Color": "stop",
+            "AsButton": False,  # 加入下拉菜单中
+            "Info": "解析一个CSharp项目的所有源文件 | 输入参数为路径",
+            "Function": HotReload(解析一个CSharp项目),
+        },
+        "解析Jupyter Notebook文件": {
+            "Group": "编程",
+            "Color": "stop",
+            "AsButton": False,
+            "Info": "解析Jupyter Notebook文件 | 输入参数为路径",
+            "Function": HotReload(解析ipynb文件),
+            "AdvancedArgs": True,  # 调用时，唤起高级参数输入区（默认False）
+            "ArgsReminder": "若输入0，则不解析notebook中的Markdown块",  # 高级参数输入区的显示提示
+        },
+        "读Tex论文写摘要": {
             "Group": "学术",
             "Color": "stop",
             "AsButton": False,
-            "AdvancedArgs": True,
-            "Info": "在输入区中输入论文ID，在高级参数区中输入问题",
-            "ArgsReminder": r"1、请在输入区中输入arxiv ID。 "
-                            r"2、请在下方高级参数区中输入你的问题，示例：“这篇文章的方法是什么，请用中文回答我” ",
-            "Function": HotReload(Arxiv论文对话),
+            "Info": "读取Tex论文并写摘要 | 输入参数为路径",
+            "Function": HotReload(读文章写摘要),
         },
         "翻译README或MD": {
             "Group": "编程",
@@ -245,7 +352,7 @@ def get_crazy_functions():
             "ArgsReminder": r"如果有必要, 请在此处给出自定义翻译命令, 解决部分词汇翻译不准确的问题。 "
                             r"例如当单词'agent'翻译不准确时, 请尝试把以下指令复制到高级参数区: "
                             r'If the term "agent" is used in this section, it should be translated to "智能体". ',
-            "Info": "Arixv论文精细翻译 | 输入参数arxiv论文的ID，比如1812.10695",
+            "Info": "ArXiv论文精细翻译 | 输入参数arxiv论文的ID，比如1812.10695",
             "Function": HotReload(Latex翻译中文并重新编译PDF),  # 当注册Class后，Function旧接口仅会在“虚空终端”中起作用
             "Class": Arxiv_Localize,    # 新一代插件需要注册Class
         },
@@ -327,36 +434,6 @@ def get_crazy_functions():
         logger.error(trimmed_format_exc())
         logger.error("Load function plugin failed")
 
-    # try:
-    #     from crazy_functions.联网的ChatGPT import 连接网络回答问题
-
-    #     function_plugins.update(
-    #         {
-    #             "连接网络回答问题（输入问题后点击该插件，需要访问谷歌）": {
-    #                 "Group": "对话",
-    #                 "Color": "stop",
-    #                 "AsButton": False,  # 加入下拉菜单中
-    #                 # "Info": "连接网络回答问题（需要访问谷歌）| 输入参数是一个问题",
-    #                 "Function": HotReload(连接网络回答问题),
-    #             }
-    #         }
-    #     )
-    #     from crazy_functions.联网的ChatGPT_bing版 import 连接bing搜索回答问题
-
-    #     function_plugins.update(
-    #         {
-    #             "连接网络回答问题（中文Bing版，输入问题后点击该插件）": {
-    #                 "Group": "对话",
-    #                 "Color": "stop",
-    #                 "AsButton": False,  # 加入下拉菜单中
-    #                 "Info": "连接网络回答问题（需要访问中文Bing）| 输入参数是一个问题",
-    #                 "Function": HotReload(连接bing搜索回答问题),
-    #             }
-    #         }
-    #     )
-    # except:
-    #     logger.error(trimmed_format_exc())
-    #     logger.error("Load function plugin failed")
 
     try:
         from crazy_functions.SourceCode_Analyse import 解析任意code项目
@@ -620,12 +697,6 @@ def get_crazy_functions():
         logger.error("Load function plugin failed")
 
 
-    
-
-
-
-
-
     # try:
     #     from crazy_functions.高级功能函数模板 import 测试图表渲染
     #     function_plugins.update({
@@ -640,19 +711,6 @@ def get_crazy_functions():
     #     logger.error(trimmed_format_exc())
     #     print('Load function plugin failed')
 
-    # try:
-    #     from crazy_functions.chatglm微调工具 import 微调数据集生成
-    #     function_plugins.update({
-    #         "黑盒模型学习: 微调数据集生成 (先上传数据集)": {
-    #             "Color": "stop",
-    #             "AsButton": False,
-    #             "AdvancedArgs": True,
-    #             "ArgsReminder": "针对数据集输入（如 绿帽子*深蓝色衬衫*黑色运动裤）给出指令，例如您可以将以下命令复制到下方: --llm_to_learn=azure-gpt-3.5 --prompt_prefix='根据下面的服装类型提示，想象一个穿着者，对这个人外貌、身处的环境、内心世界、过去经历进行描写。要求：100字以内，用第二人称。' --system_prompt=''",
-    #             "Function": HotReload(微调数据集生成)
-    #         }
-    #     })
-    # except:
-    #     print('Load function plugin failed')
 
     """
     设置默认值:
@@ -672,3 +730,26 @@ def get_crazy_functions():
             function_plugins[name]["Color"] = "secondary"
 
     return function_plugins
+
+
+
+
+def get_multiplex_button_functions():
+    """多路复用主提交按钮的功能映射
+    """
+    return {
+        "常规对话":
+            "",
+
+        "查互联网后回答":
+            "查互联网后回答",
+
+        "多模型对话": 
+            "询问多个GPT模型", # 映射到上面的 `询问多个GPT模型` 插件
+
+        "智能召回 RAG": 
+            "Rag智能召回", # 映射到上面的 `Rag智能召回` 插件
+
+        "多媒体查询": 
+            "多媒体智能体", # 映射到上面的 `多媒体智能体` 插件
+    }

crazy_functions/Arxiv_论文对话.py

@@ -1,573 +0,0 @@
-import asyncio
-import logging
-import os
-import threading
-import time
-from concurrent.futures import ThreadPoolExecutor
-from dataclasses import dataclass, field
-from pathlib import Path
-from threading import Lock as ThreadLock
-from typing import Generator
-from typing import List, Dict, Optional
-
-from crazy_functions.crazy_utils import input_clipping
-from crazy_functions.crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
-from crazy_functions.rag_fns.arxiv_fns.arxiv_splitter import ArxivSplitter, save_fragments_to_file, process_arxiv_sync
-from crazy_functions.rag_fns.arxiv_fns.section_fragment import SectionFragment as Fragment
-from crazy_functions.rag_fns.llama_index_worker import LlamaIndexRagWorker
-from toolbox import CatchException, update_ui, get_log_folder, update_ui_lastest_msg
-
-# 全局常量配置
-MAX_HISTORY_ROUND = 5  # 最大历史对话轮数
-MAX_CONTEXT_TOKEN_LIMIT = 4096  # 上下文最大token数
-REMEMBER_PREVIEW = 1000  # 记忆预览长度
-VECTOR_STORE_TYPE = "Simple"  # 向量存储类型：Simple或Milvus
-MAX_CONCURRENT_PAPERS = 20  # 最大并行处理论文数
-MAX_WORKERS = 3  # 最大工作线程数
-
-# 配置日志
-logging.basicConfig(
-    level=logging.INFO,
-    format='%(asctime)s - %(name)s - %(levelname)s - %(message)s'
-)
-logger = logging.getLogger(__name__)
-
-logger = logging.getLogger(__name__)
-
-
-@dataclass
-class ProcessingTask:
-    """论文处理任务数据类"""
-    arxiv_id: str
-    status: str = "pending"  # pending, processing, completed, failed
-    error: Optional[str] = None
-    fragments: List[Fragment] = None
-    start_time: float = field(default_factory=time.time)
-
-
-class ArxivRagWorker:
-    def __init__(self, user_name: str, llm_kwargs: Dict, arxiv_id: str = None):
-        """初始化ArxivRagWorker"""
-        self.user_name = user_name
-        self.llm_kwargs = llm_kwargs
-        self.arxiv_id = self._normalize_arxiv_id(arxiv_id) if arxiv_id else None
-        self.fragments = None
-
-
-        # 初始化基础目录
-        self.base_dir = Path(get_log_folder( plugin_name='arxiv_rag_cache'))
-        self._setup_directories()
-
-        # 初始化处理状态
-
-        # 线程安全的计数器和集合
-        self._processing_lock = ThreadLock()
-        self._processed_fragments = set()
-        self._processed_count = 0
-        # 优化的线程池配置
-        cpu_count = os.cpu_count() or 1
-        self.thread_pool = ThreadPoolExecutor(
-            max_workers=min(32, cpu_count * 4),
-            thread_name_prefix="arxiv_worker"
-        )
-
-        # 批处理配置
-        self._batch_size = min(20, cpu_count * 2)  # 动态设置批大小
-        self.max_concurrent_papers = MAX_CONCURRENT_PAPERS
-        self._semaphore = None
-        self._loop = None
-
-        # 初始化处理队列
-        self.processing_queue = {}
-
-        # 初始化工作组件
-        self._init_workers()
-
-    def _setup_directories(self):
-        """设置工作目录"""
-
-        if self.arxiv_id:
-            self.checkpoint_dir = self.base_dir / self.arxiv_id
-            self.vector_store_dir = self.checkpoint_dir / "vector_store"
-            self.fragment_store_dir = self.checkpoint_dir / "fragments"
-        else:
-            self.checkpoint_dir = self.base_dir
-            self.vector_store_dir = self.base_dir / "vector_store"
-            self.fragment_store_dir = self.base_dir / "fragments"
-
-        self.paper_path = self.checkpoint_dir / f"{self.arxiv_id}.processed"
-        self.loading = self.paper_path.exists()
-        # 创建必要的目录
-        for directory in [self.checkpoint_dir, self.vector_store_dir, self.fragment_store_dir]:
-            directory.mkdir(parents=True, exist_ok=True)
-            logger.info(f"Created directory: {directory}")
-
-    def _init_workers(self):
-        """初始化工作组件"""
-        try:
-            self.rag_worker = LlamaIndexRagWorker(
-                user_name=self.user_name,
-                llm_kwargs=self.llm_kwargs,
-                checkpoint_dir=str(self.vector_store_dir),
-                auto_load_checkpoint=True
-            )
-
-            self.arxiv_splitter = ArxivSplitter(
-                root_dir=str(self.checkpoint_dir / "arxiv_cache")
-            )
-        except Exception as e:
-            logger.error(f"Error initializing workers: {str(e)}")
-            raise
-
-    def _ensure_loop(self):
-        """确保存在事件循环"""
-        if threading.current_thread() is threading.main_thread():
-            if self._loop is None:
-                self._loop = asyncio.get_event_loop()
-        else:
-            try:
-                self._loop = asyncio.get_event_loop()
-            except RuntimeError:
-                self._loop = asyncio.new_event_loop()
-                asyncio.set_event_loop(self._loop)
-        return self._loop
-
-    @property
-    def semaphore(self):
-        """延迟创建semaphore"""
-        if self._semaphore is None:
-            self._semaphore = asyncio.Semaphore(self.max_concurrent_papers)
-        return self._semaphore
-
-    async def _process_fragments(self, fragments: List[Fragment]) -> None:
-        """优化的并行处理论文片段"""
-        if not fragments:
-            logger.warning("No fragments to process")
-            return
-
-        start_time = time.time()
-        total_fragments = len(fragments)
-
-        try:
-            # 1. 处理论文概述
-            overview = self._create_overview(fragments[0])
-            overview_success = self._safe_add_to_vector_store_sync(overview['text'])
-            if not overview_success:
-                raise RuntimeError("Failed to add overview to vector store")
-
-            # 2. 并行处理片段
-            successful_fragments = await self._parallel_process_fragments(fragments)
-
-            # 3. 保存处理结果
-            if successful_fragments > 0:
-                await self._save_results(fragments, overview['arxiv_id'], successful_fragments)
-
-        except Exception as e:
-            logger.error(f"Error in fragment processing: {str(e)}")
-            raise
-        finally:
-            self._log_processing_stats(start_time, total_fragments)
-
-    def _create_overview(self, first_fragment: Fragment) -> Dict:
-        """创建论文概述"""
-        return {
-            'arxiv_id': first_fragment.arxiv_id,
-            'text': (
-                f"Paper Title: {first_fragment.title}\n"
-                f"ArXiv ID: {first_fragment.arxiv_id}\n"
-                f"Abstract: {first_fragment.abstract}\n"
-                f"Table of contents:{first_fragment.catalogs}\n"
-                f"Type: OVERVIEW"
-            )
-        }
-
-    async def _parallel_process_fragments(self, fragments: List[Fragment]) -> int:
-        """并行处理所有片段"""
-        successful_count = 0
-        loop = self._ensure_loop()
-
-        for i in range(0, len(fragments), self._batch_size):
-            batch = fragments[i:i + self._batch_size]
-            batch_futures = []
-
-            for j, fragment in enumerate(batch):
-                if not self._is_fragment_processed(fragment, i + j):
-                    future = loop.run_in_executor(
-                        self.thread_pool,
-                        self._process_single_fragment_sync,
-                        fragment,
-                        i + j
-                    )
-                    batch_futures.append(future)
-
-            if batch_futures:
-                results = await asyncio.gather(*batch_futures, return_exceptions=True)
-                successful_count += sum(1 for r in results if isinstance(r, bool) and r)
-
-        return successful_count
-
-    def _is_fragment_processed(self, fragment: Fragment, index: int) -> bool:
-        """检查片段是否已处理"""
-        fragment_id = f"{fragment.arxiv_id}_{index}"
-        with self._processing_lock:
-            return fragment_id in self._processed_fragments
-
-    def _safe_add_to_vector_store_sync(self, text: str) -> bool:
-        """线程安全的向量存储添加"""
-        with self._processing_lock:
-            try:
-                self.rag_worker.add_text_to_vector_store(text)
-                return True
-            except Exception as e:
-                logger.error(f"Error adding to vector store: {str(e)}")
-                return False
-
-    def _process_single_fragment_sync(self, fragment: Fragment, index: int) -> bool:
-        """处理单个片段"""
-        fragment_id = f"{fragment.arxiv_id}_{index}"
-        try:
-            text = self._build_fragment_text(fragment)
-            if self._safe_add_to_vector_store_sync(text):
-                with self._processing_lock:
-                    self._processed_fragments.add(fragment_id)
-                    self._processed_count += 1
-                logger.info(f"Successfully processed fragment {index}")
-                return True
-            return False
-        except Exception as e:
-            logger.error(f"Error processing fragment {index}: {str(e)}")
-            return False
-
-    def _build_fragment_text(self, fragment: Fragment) -> str:
-        """构建片段文本"""
-        return "".join([
-            f"Paper Title: {fragment.title}\n",
-            f"Section: {fragment.current_section}\n",
-            f"Content: {fragment.content}\n",
-            f"Bibliography: {fragment.bibliography}\n",
-            "Type: FRAGMENT"
-        ])
-
-    async def _save_results(self, fragments: List[Fragment], arxiv_id: str, successful_count: int) -> None:
-        """保存处理结果"""
-        if successful_count > 0:
-            loop = self._ensure_loop()
-            await loop.run_in_executor(
-                self.thread_pool,
-                save_fragments_to_file,
-                fragments,
-                str(self.fragment_store_dir / f"{arxiv_id}_fragments.json")
-            )
-
-    def _log_processing_stats(self, start_time: float, total_fragments: int) -> None:
-        """记录处理统计信息"""
-        elapsed_time = time.time() - start_time
-        processing_rate = total_fragments / elapsed_time if elapsed_time > 0 else 0
-        logger.info(
-            f"Processed {self._processed_count}/{total_fragments} fragments "
-            f"in {elapsed_time:.2f}s (rate: {processing_rate:.2f} fragments/s)"
-        )
-
-    async def process_paper(self,  fragments: List[Fragment]) -> bool:
-        """处理论文主函数"""
-        try:
-
-            if self.paper_path.exists():
-                logger.info(f"Paper {self.arxiv_id} already processed")
-                return True
-
-            task = self._create_processing_task(self.arxiv_id)
-            try:
-                async with self.semaphore:
-                    await self._process_fragments(fragments)
-                    self._complete_task(task, fragments, self.paper_path)
-                    return True
-
-            except Exception as e:
-                self._fail_task(task, str(e))
-                raise
-
-        except Exception as e:
-            logger.error(f"Error processing paper {self.arxiv_id}: {str(e)}")
-            return False
-
-    def _create_processing_task(self, arxiv_id: str) -> ProcessingTask:
-        """创建处理任务"""
-        task = ProcessingTask(arxiv_id=arxiv_id)
-        with self._processing_lock:
-            self.processing_queue[arxiv_id] = task
-            task.status = "processing"
-        return task
-
-    def _complete_task(self, task: ProcessingTask, fragments: List[Fragment], paper_path: Path) -> None:
-        """完成任务处理"""
-        with self._processing_lock:
-            task.status = "completed"
-            task.fragments = fragments
-        paper_path.touch()
-        logger.info(f"Paper {task.arxiv_id} processed successfully with {self._processed_count} fragments")
-
-    def _fail_task(self, task: ProcessingTask, error: str) -> None:
-        """任务失败处理"""
-        with self._processing_lock:
-            task.status = "failed"
-            task.error = error
-
-    def _normalize_arxiv_id(self, input_str: str) -> str:
-        """规范化ArXiv ID"""
-        if not input_str:
-            return ""
-
-        input_str = input_str.strip().lower()
-        if 'arxiv.org/' in input_str:
-            if '/pdf/' in input_str:
-                arxiv_id = input_str.split('/pdf/')[-1]
-            else:
-                arxiv_id = input_str.split('/abs/')[-1]
-            return arxiv_id.split('v')[0].strip()
-        return input_str.split('v')[0].strip()
-
-    async def wait_for_paper(self, arxiv_id: str, timeout: float = 300.0) -> bool:
-        """等待论文处理完成"""
-        start_time = time.time()
-        try:
-            while True:
-                with self._processing_lock:
-                    task = self.processing_queue.get(arxiv_id)
-                if not task:
-                    return False
-
-                if task.status == "completed":
-                    return True
-                if task.status == "failed":
-                    return False
-
-                if time.time() - start_time > timeout:
-                    logger.error(f"Processing paper {arxiv_id} timed out")
-                    return False
-
-                await asyncio.sleep(0.1)
-        except Exception as e:
-            logger.error(f"Error waiting for paper {arxiv_id}: {str(e)}")
-            return False
-
-    def retrieve_and_generate(self, query: str) -> str:
-        """检索相关内容并生成提示词"""
-        try:
-            nodes = self.rag_worker.retrieve_from_store_with_query(query)
-            return self.rag_worker.build_prompt(query=query, nodes=nodes)
-        except Exception as e:
-            logger.error(f"Error in retrieve and generate: {str(e)}")
-            return ""
-
-    def remember_qa(self, question: str, answer: str) -> None:
-        """记忆问答对"""
-        try:
-            self.rag_worker.remember_qa(question, answer)
-        except Exception as e:
-            logger.error(f"Error remembering QA: {str(e)}")
-
-    async def auto_analyze_paper(self, chatbot: List, history: List, system_prompt: str) -> None:
-        """自动分析论文的关键问题"""
-        key_questions = [
-            "What is the main research question or problem addressed in this paper?",
-            "What methods or approaches did the authors use to investigate the problem?",
-            "What are the key findings or results presented in the paper?",
-            "How do the findings of this paper contribute to the broader field or topic of study?",
-            "What are the limitations of this study, and what future research directions do the authors suggest?"
-        ]
-
-        results = []
-        for question in key_questions:
-            try:
-                prompt = self.retrieve_and_generate(question)
-                if prompt:
-                    response = await request_gpt_model_in_new_thread_with_ui_alive(
-                        inputs=prompt,
-                        inputs_show_user=question,
-                        llm_kwargs=self.llm_kwargs,
-                        chatbot=chatbot,
-                        history=history,
-                        sys_prompt=system_prompt
-                    )
-                    results.append(f"Q: {question}\nA: {response}\n")
-                    self.remember_qa(question, response)
-            except Exception as e:
-                logger.error(f"Error in auto analysis: {str(e)}")
-
-        # 合并所有结果
-        summary = "\n\n".join(results)
-        chatbot[-1] = (chatbot[-1][0], f"论文已成功加载并完成初步分析：\n\n{summary}\n\n您现在可以继续提问更多细节。")
-
-@CatchException
-def Arxiv论文对话(txt: str, llm_kwargs: Dict, plugin_kwargs: Dict, chatbot: List,
-                  history: List, system_prompt: str, web_port: str) -> Generator:
-    """
-    Arxiv论文对话主函数
-    Args:
-        txt: arxiv ID/URL
-        llm_kwargs: LLM配置参数
-        plugin_kwargs: 插件配置参数，包含 advanced_arg 字段作为用户询问指令
-        chatbot: 对话历史
-        history: 聊天历史
-        system_prompt: 系统提示词
-        web_port: Web端口
-    """
-    # 初始化时，提示用户需要 arxiv ID/URL
-    from toolbox import promote_file_to_downloadzone
-    if len(history) == 0 and not txt.lower().strip().startswith(('https://arxiv.org', 'arxiv.org', '0', '1', '2')):
-        chatbot.append((txt, "请先提供Arxiv论文链接或ID。"))
-        yield from update_ui(chatbot=chatbot, history=history)
-        return
-
-    user_name = chatbot.get_user()
-    arxiv_worker = ArxivRagWorker(user_name, llm_kwargs, arxiv_id=txt)
-    arxiv_id = arxiv_worker.arxiv_id
-
-    # 处理新论文的情况
-    if txt.lower().strip().startswith(('https://arxiv.org', 'arxiv.org', '0', '1', '2')) and not arxiv_worker.loading:
-        chatbot.append((txt, "正在处理论文，请稍等..."))
-        yield from update_ui(chatbot=chatbot, history=history)
-        fragments, formatted_content, fragment_output_files = process_arxiv_sync(arxiv_worker.arxiv_splitter, arxiv_id)
-        for file in fragment_output_files:
-            promote_file_to_downloadzone(file, chatbot=chatbot)
-        chatbot.append(["论文文字内容已保存至下载区，接下来将进行论文编码，请耐心等待三分钟，论文的文字内容为：", formatted_content])
-        yield from update_ui(chatbot=chatbot, history=history)
-        try:
-            # 创建新的事件循环
-            loop = asyncio.new_event_loop()
-            asyncio.set_event_loop(loop)
-
-            try:
-                # 设置超时时间为5分钟
-                success = loop.run_until_complete(
-                    asyncio.wait_for(arxiv_worker.process_paper(fragments), timeout=300)
-                )
-                if success:
-                    success = loop.run_until_complete(
-                        asyncio.wait_for(arxiv_worker.wait_for_paper(arxiv_id), timeout=60)
-                    )
-                    if success:
-                        chatbot[-1] = (txt, "论文处理完成，您现在可以开始提问。")
-                    else:
-                        chatbot[-1] = (txt, "论文处理超时，请重试。")
-                else:
-                    chatbot[-1] = (txt, "论文处理失败，请检查论文ID是否正确或稍后重试。")
-            except asyncio.TimeoutError:
-                chatbot[-1] = (txt, "论文处理超时，请重试。")
-                success = False
-            finally:
-                loop.close()
-
-            if not success:
-                yield from update_ui(chatbot=chatbot, history=history)
-                return
-
-        except Exception as e:
-            logger.error(f"Error in main process: {str(e)}")
-            chatbot[-1] = (txt, f"处理过程中发生错误: {str(e)}")
-            yield from update_ui(chatbot=chatbot, history=history)
-            return
-
-        yield from update_ui(chatbot=chatbot, history=history)
-        return
-    # 处理用户询问的情况
-    # 获取用户询问指令
-    user_query = plugin_kwargs.get("advanced_arg",
-                                   "What is the main research question or problem addressed in this paper?")
-    if len(history)<2:
-        fragments, formatted_content, fragment_output_files = process_arxiv_sync(arxiv_worker.arxiv_splitter, arxiv_id)
-        for file in fragment_output_files:
-            promote_file_to_downloadzone(file, chatbot=chatbot)
-        chatbot.append(["论文文字内容已保存至下载区，论文的文字内容为：", formatted_content])
-        yield from update_ui(chatbot=chatbot, history=history)
-    if not user_query:
-        user_query = "What is the main research question or problem addressed in this paper?"
-        # chatbot.append((txt, "请提供您的问题。"))
-        # yield from update_ui(chatbot=chatbot, history=history)
-        # return
-
-    # 处理历史对话长度
-    if len(history) > MAX_HISTORY_ROUND * 2:
-        history = history[-(MAX_HISTORY_ROUND * 2):]
-
-    # 处理询问指令
-    query_clip, history, flags = input_clipping(
-        user_query,
-        history,
-        max_token_limit=MAX_CONTEXT_TOKEN_LIMIT,
-        return_clip_flags=True
-    )
-
-    if flags["original_input_len"] != flags["clipped_input_len"]:
-        yield from update_ui_lastest_msg('检测到长输入，正在处理...', chatbot, history, delay=0)
-        if len(user_query) > REMEMBER_PREVIEW:
-            HALF = REMEMBER_PREVIEW // 2
-            query_to_remember = user_query[
-                                :HALF] + f" ...\n...(省略{len(user_query) - REMEMBER_PREVIEW}字)...\n... " + user_query[
-                                                                                                             -HALF:]
-        else:
-            query_to_remember = query_clip
-    else:
-        query_to_remember = query_clip
-
-    chatbot.append((user_query, "正在思考中..."))
-    yield from update_ui(chatbot=chatbot, history=history)
-
-    # 生成提示词
-    prompt = arxiv_worker.retrieve_and_generate(query_clip)
-    if not prompt:
-        chatbot[-1] = (user_query, "抱歉，处理您的问题时出现错误，请重试。")
-        yield from update_ui(chatbot=chatbot, history=history)
-        return
-
-    # 获取回答
-    response = yield from request_gpt_model_in_new_thread_with_ui_alive(
-        inputs=prompt,
-        inputs_show_user=query_clip,
-        llm_kwargs=llm_kwargs,
-        chatbot=chatbot,
-        history=history,
-        sys_prompt=system_prompt
-    )
-
-    # 记忆问答对
-    # worker.remember_qa(query_to_remember, response)
-    history.extend([user_query, response])
-
-    yield from update_ui(chatbot=chatbot, history=history)
-
-
-if __name__ == "__main__":
-    # 测试代码
-    llm_kwargs = {
-        'api_key': os.getenv("one_api_key"),
-        'client_ip': '127.0.0.1',
-        'embed_model': 'text-embedding-3-small',
-        'llm_model': 'one-api-Qwen2.5-72B-Instruct',
-        'max_length': 4096,
-        'most_recent_uploaded': None,
-        'temperature': 1,
-        'top_p': 1
-    }
-    plugin_kwargs = {}
-    chatbot = []
-    history = []
-    system_prompt = "You are a helpful assistant."
-    web_port = "8080"
-
-    # 测试论文导入
-    arxiv_url = "https://arxiv.org/abs/2312.12345"
-    for response in Arxiv论文对话(
-            arxiv_url, llm_kwargs, plugin_kwargs,
-            chatbot, history, system_prompt, web_port
-    ):
-        print(response)
-
-    # 测试问答
-    question = "这篇论文的主要贡献是什么？"
-    for response in Arxiv论文对话(
-            question, llm_kwargs, plugin_kwargs,
-            chatbot, history, system_prompt, web_port
-    ):
-        print(response)

crazy_functions/Conversation_To_File.py

@@ -1,10 +1,11 @@
-from toolbox import CatchException, update_ui, promote_file_to_downloadzone, get_log_folder, get_user
-from crazy_functions.plugin_template.plugin_class_template import GptAcademicPluginTemplate, ArgProperty
 import re
+from toolbox import CatchException, update_ui, promote_file_to_downloadzone, get_log_folder, get_user, update_ui_latest_msg
+from crazy_functions.plugin_template.plugin_class_template import GptAcademicPluginTemplate, ArgProperty
+from loguru import logger
 
 f_prefix = 'GPT-Academic对话存档'
 
-def write_chat_to_file(chatbot, history=None, file_name=None):
+def write_chat_to_file_legacy(chatbot, history=None, file_name=None):
     """
     将对话记录history以Markdown格式写入文件中。如果没有指定文件名，则使用当前时间生成文件名。
     """
@@ -12,6 +13,9 @@ def write_chat_to_file(chatbot, history=None, file_name=None):
     import time
     from themes.theme import advanced_css
 
+    if (file_name is not None) and (file_name != "") and (not file_name.endswith('.html')): file_name += '.html'
+    else: file_name = None
+
     if file_name is None:
         file_name = f_prefix + time.strftime("%Y-%m-%d-%H-%M-%S", time.localtime()) + '.html'
     fp = os.path.join(get_log_folder(get_user(chatbot), plugin_name='chat_history'), file_name)
@@ -68,6 +72,147 @@ def write_chat_to_file(chatbot, history=None, file_name=None):
     promote_file_to_downloadzone(fp, rename_file=file_name, chatbot=chatbot)
     return '对话历史写入：' + fp
 
+def write_chat_to_file(chatbot, history=None, file_name=None):
+    """
+    将对话记录history以多种格式（HTML、Word、Markdown）写入文件中。如果没有指定文件名，则使用当前时间生成文件名。
+    
+    Args:
+        chatbot: 聊天机器人对象，包含对话内容
+        history: 对话历史记录
+        file_name: 指定的文件名，如果为None则使用时间戳
+        
+    Returns:
+        str: 提示信息，包含文件保存路径
+    """
+    import os
+    import time
+    import asyncio
+    import aiofiles
+    from toolbox import promote_file_to_downloadzone
+    from crazy_functions.doc_fns.conversation_doc.excel_doc import save_chat_tables
+    from crazy_functions.doc_fns.conversation_doc.html_doc import HtmlFormatter
+    from crazy_functions.doc_fns.conversation_doc.markdown_doc import MarkdownFormatter
+    from crazy_functions.doc_fns.conversation_doc.word_doc import WordFormatter
+    from crazy_functions.doc_fns.conversation_doc.txt_doc import TxtFormatter
+    from crazy_functions.doc_fns.conversation_doc.word2pdf import WordToPdfConverter
+
+    async def save_html():
+        try:
+            html_formatter = HtmlFormatter(chatbot, history)
+            html_content = html_formatter.create_document()
+            html_file = os.path.join(save_dir, base_name + '.html')
+            async with aiofiles.open(html_file, 'w', encoding='utf8') as f:
+                await f.write(html_content)
+            return html_file
+        except Exception as e:
+            print(f"保存HTML格式失败: {str(e)}")
+            return None
+
+    async def save_word():
+        try:
+            word_formatter = WordFormatter()
+            doc = word_formatter.create_document(history)
+            docx_file = os.path.join(save_dir, base_name + '.docx')
+            # 由于python-docx不支持异步，使用线程池执行
+            loop = asyncio.get_event_loop()
+            await loop.run_in_executor(None, doc.save, docx_file)
+            return docx_file
+        except Exception as e:
+            print(f"保存Word格式失败: {str(e)}")
+            return None
+    async def save_pdf(docx_file):
+        try:
+            if docx_file:
+                # 获取文件名和保存路径
+                pdf_file = os.path.join(save_dir, base_name + '.pdf')
+                
+                # 在线程池中执行转换
+                loop = asyncio.get_event_loop()
+                pdf_file = await loop.run_in_executor(
+                    None, 
+                    WordToPdfConverter.convert_to_pdf,
+                    docx_file
+                    # save_dir
+                )
+                
+                return pdf_file
+                
+        except Exception as e:
+            print(f"保存PDF格式失败: {str(e)}")
+            return None
+
+    async def save_markdown():
+        try:
+            md_formatter = MarkdownFormatter()
+            md_content = md_formatter.create_document(history)
+            md_file = os.path.join(save_dir, base_name + '.md')
+            async with aiofiles.open(md_file, 'w', encoding='utf8') as f:
+                await f.write(md_content)
+            return md_file
+        except Exception as e:
+            print(f"保存Markdown格式失败: {str(e)}")
+            return None
+
+    async def save_txt():
+        try:
+            txt_formatter = TxtFormatter()
+            txt_content = txt_formatter.create_document(history)
+            txt_file = os.path.join(save_dir, base_name + '.txt')
+            async with aiofiles.open(txt_file, 'w', encoding='utf8') as f:
+                await f.write(txt_content)
+            return txt_file
+        except Exception as e:
+            print(f"保存TXT格式失败: {str(e)}")
+            return None
+
+    async def main():
+        # 并发执行所有保存任务
+        html_task = asyncio.create_task(save_html())
+        word_task = asyncio.create_task(save_word())
+        md_task = asyncio.create_task(save_markdown())
+        txt_task = asyncio.create_task(save_txt())
+        
+        # 等待所有任务完成
+        html_file = await html_task
+        docx_file = await word_task
+        md_file = await md_task
+        txt_file = await txt_task
+        
+        # PDF转换需要等待word文件生成完成
+        pdf_file = await save_pdf(docx_file)
+        # 收集所有成功生成的文件
+        result_files = [f for f in [html_file, docx_file, md_file, txt_file, pdf_file] if f]
+        
+        # 保存Excel表格
+        excel_files = save_chat_tables(history, save_dir, base_name)
+        result_files.extend(excel_files)
+        
+        return result_files
+
+    # 生成时间戳
+    timestamp = time.strftime("%Y-%m-%d-%H-%M-%S", time.localtime())
+    
+    # 获取保存目录
+    save_dir = get_log_folder(get_user(chatbot), plugin_name='chat_history')
+    
+    # 处理文件名
+    base_name = file_name if file_name else f"聊天记录_{timestamp}"
+    
+    # 运行异步任务
+    result_files = asyncio.run(main())
+    
+    # 将生成的文件添加到下载区
+    for file in result_files:
+        promote_file_to_downloadzone(file, rename_file=os.path.basename(file), chatbot=chatbot)
+    
+    # 如果没有成功保存任何文件，返回错误信息
+    if not result_files:
+        return "保存对话记录失败，请检查错误日志"
+    
+    ext_list = [os.path.splitext(f)[1] for f in result_files]
+    # 返回成功信息和文件路径
+    return f"对话历史已保存至以下格式文件：" + "、".join(ext_list)
+
 def gen_file_preview(file_name):
     try:
         with open(file_name, 'r', encoding='utf8') as f:
@@ -119,12 +264,21 @@ def 对话历史存档(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_
     user_request    当前用户的请求信息（IP地址等）
     """
     file_name = plugin_kwargs.get("file_name", None)
-    if (file_name is not None) and (file_name != "") and (not file_name.endswith('.html')): file_name += '.html'
-    else: file_name = None
-
-    chatbot.append((None, f"[Local Message] {write_chat_to_file(chatbot, history, file_name)}，您可以调用下拉菜单中的“载入对话历史存档”还原当下的对话。"))
-    yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 由于请求gpt需要一段时间，我们先及时地做一次界面更新
 
+    chatbot.append((None, f"[Local Message] {write_chat_to_file_legacy(chatbot, history, file_name)}，您可以调用下拉菜单中的“载入对话历史存档”还原当下的对话。"))
+    try:
+        chatbot.append((None, f"[Local Message] 正在尝试生成pdf以及word格式的对话存档，请稍等..."))
+        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 由于请求需要一段时间，我们先及时地做一次界面更新
+        lastmsg = f"[Local Message] {write_chat_to_file(chatbot, history, file_name)}。" \
+              f"您可以调用下拉菜单中的“载入对话历史会话”还原当下的对话，请注意，目前只支持html格式载入历史。" \
+              f"当模型回答中存在表格，将提取表格内容存储为Excel的xlsx格式，如果你提供一些数据,然后输入指令要求模型帮你整理为表格" \
+              f"（如“请帮我将下面的数据整理为表格：”），再利用此插件就可以获取到Excel表格。"
+        yield from update_ui_latest_msg(lastmsg, chatbot, history) # 刷新界面 # 由于请求需要一段时间，我们先及时地做一次界面更新
+    except Exception as e:
+        logger.exception(f"已完成对话存档（pdf和word格式的对话存档生成未成功）。{str(e)}")
+        lastmsg = "已完成对话存档（pdf和word格式的对话存档生成未成功）。"
+        yield from update_ui_latest_msg(lastmsg, chatbot, history) # 刷新界面 # 由于请求需要一段时间，我们先及时地做一次界面更新
+    return
 
 class Conversation_To_File_Wrap(GptAcademicPluginTemplate):
     def __init__(self):
@@ -152,6 +306,8 @@ class Conversation_To_File_Wrap(GptAcademicPluginTemplate):
 
 
 
+
+
 def hide_cwd(str):
     import os
     current_path = os.getcwd()

crazy_functions/Internet_GPT.py

@@ -7,7 +7,7 @@ from bs4 import BeautifulSoup
 from functools import lru_cache
 from itertools import zip_longest
 from check_proxy import check_proxy
-from toolbox import CatchException, update_ui, get_conf
+from toolbox import CatchException, update_ui, get_conf, update_ui_latest_msg
 from crazy_functions.crazy_utils import request_gpt_model_in_new_thread_with_ui_alive, input_clipping
 from request_llms.bridge_all import model_info
 from request_llms.bridge_all import predict_no_ui_long_connection
@@ -49,7 +49,7 @@ def search_optimizer(
     mutable = ["", time.time(), ""]
     llm_kwargs["temperature"] = 0.8
     try:
-        querys_json = predict_no_ui_long_connection(
+        query_json = predict_no_ui_long_connection(
             inputs=query,
             llm_kwargs=llm_kwargs,
             history=[],
@@ -57,31 +57,31 @@ def search_optimizer(
             observe_window=mutable,
         )
     except Exception:
-        querys_json = "1234"
+        query_json = "null"
     #* 尝试解码优化后的搜索结果
-    querys_json = re.sub(r"```json|```", "", querys_json)
+    query_json = re.sub(r"```json|```", "", query_json)
     try:
-        querys = json.loads(querys_json)
+        queries = json.loads(query_json)
     except Exception:
         #* 如果解码失败,降低温度再试一次
         try:
             llm_kwargs["temperature"] = 0.4
-            querys_json = predict_no_ui_long_connection(
+            query_json = predict_no_ui_long_connection(
                 inputs=query,
                 llm_kwargs=llm_kwargs,
                 history=[],
                 sys_prompt=sys_prompt,
                 observe_window=mutable,
             )
-            querys_json = re.sub(r"```json|```", "", querys_json)
-            querys = json.loads(querys_json)
+            query_json = re.sub(r"```json|```", "", query_json)
+            queries = json.loads(query_json)
         except Exception:
             #* 如果再次失败，直接返回原始问题
-            querys = [query]
+            queries = [query]
     links = []
     success = 0
     Exceptions = ""
-    for q in querys:
+    for q in queries:
         try:
             link = searxng_request(q, proxies, categories, searxng_url, engines=engines)
             if len(link) > 0:
@@ -115,7 +115,8 @@ def get_auth_ip():
 
 def searxng_request(query, proxies, categories='general', searxng_url=None, engines=None):
     if searxng_url is None:
-        url = get_conf("SEARXNG_URL")
+        urls = get_conf("SEARXNG_URLS")
+        url = random.choice(urls)
     else:
         url = searxng_url
 
@@ -174,10 +175,17 @@ def scrape_text(url, proxies) -> str:
     Returns:
         str: The scraped text
     """
+    from loguru import logger
     headers = {
         'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/94.0.4606.61 Safari/537.36',
         'Content-Type': 'text/plain',
     }
+
+    # 首先采用Jina进行文本提取
+    if get_conf("JINA_API_KEY"):
+        try: return jina_scrape_text(url)
+        except: logger.debug("Jina API 请求失败，回到旧方法")
+
     try:
         response = requests.get(url, headers=headers, proxies=proxies, timeout=8)
         if response.encoding == "ISO-8859-1": response.encoding = response.apparent_encoding
@@ -193,6 +201,56 @@ def scrape_text(url, proxies) -> str:
     return text
 
 
+def jina_scrape_text(url) -> str:
+    "jina_39727421c8fa4e4fa9bd698e5211feaaDyGeVFESNrRaepWiLT0wmHYJSh-d"
+    headers = {
+        'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/94.0.4606.61 Safari/537.36',
+        'Content-Type': 'text/plain',
+        "X-Retain-Images": "none",
+        "Authorization": f'Bearer {get_conf("JINA_API_KEY")}'
+    }
+    response = requests.get("https://r.jina.ai/" + url, headers=headers, proxies=None, timeout=8)
+    if response.status_code != 200:
+        raise ValueError("Jina API 请求失败，开始尝试旧方法！" + response.text)
+    if response.encoding == "ISO-8859-1": response.encoding = response.apparent_encoding
+    result = response.text
+    result = result.replace("\\[", "[").replace("\\]", "]").replace("\\(", "(").replace("\\)", ")")
+    return response.text
+
+
+def internet_search_with_analysis_prompt(prompt, analysis_prompt, llm_kwargs, chatbot):
+    from toolbox import get_conf
+    proxies = get_conf('proxies')
+    categories = 'general'
+    searxng_url = None  # 使用默认的searxng_url
+    engines = None  # 使用默认的搜索引擎
+    yield from update_ui_latest_msg(lastmsg=f"检索中: {prompt} ...", chatbot=chatbot, history=[], delay=1)
+    urls = searxng_request(prompt, proxies, categories, searxng_url, engines=engines)
+    yield from update_ui_latest_msg(lastmsg=f"依次访问搜索到的网站 ...", chatbot=chatbot, history=[], delay=1)
+    if len(urls) == 0:
+        return None
+    max_search_result = 5   # 最多收纳多少个网页的结果
+    history = []
+    for index, url in enumerate(urls[:max_search_result]):
+        yield from update_ui_latest_msg(lastmsg=f"依次访问搜索到的网站: {url['link']} ...", chatbot=chatbot, history=[], delay=1)
+        res = scrape_text(url['link'], proxies)
+        prefix = f"第{index}份搜索结果 [源自{url['source'][0]}搜索] （{url['title'][:25]}）："
+        history.extend([prefix, res])
+    i_say = f"从以上搜索结果中抽取信息，然后回答问题：{prompt} {analysis_prompt}"
+    i_say, history = input_clipping( # 裁剪输入，从最长的条目开始裁剪，防止爆token
+        inputs=i_say,
+        history=history,
+        max_token_limit=8192
+    )
+    gpt_say = predict_no_ui_long_connection(
+        inputs=i_say,
+        llm_kwargs=llm_kwargs,
+        history=history,
+        sys_prompt="请从搜索结果中抽取信息，对最相关的两个搜索结果进行总结，然后回答问题。",
+        console_silence=False,
+    )
+    return gpt_say
+
 @CatchException
 def 连接网络回答问题(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
     optimizer_history = history[:-8]
@@ -213,23 +271,52 @@ def 连接网络回答问题(txt, llm_kwargs, plugin_kwargs, chatbot, history, s
         urls = search_optimizer(txt, proxies, optimizer_history, llm_kwargs, optimizer, categories, searxng_url, engines)
     history = []
     if len(urls) == 0:
-        chatbot.append((f"结论：{txt}",
-                        "[Local Message] 受到限制，无法从searxng获取信息！请尝试更换搜索引擎。"))
+        chatbot.append((f"结论：{txt}", "[Local Message] 受到限制，无法从searxng获取信息！请尝试更换搜索引擎。"))
         yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
         return
 
     # ------------- < 第2步：依次访问网页 > -------------
+    from concurrent.futures import ThreadPoolExecutor
+    from textwrap import dedent
     max_search_result = 5   # 最多收纳多少个网页的结果
     if optimizer == "开启(增强)":
         max_search_result = 8
-    chatbot.append(["联网检索中 ...", None])
-    for index, url in enumerate(urls[:max_search_result]):
-        res = scrape_text(url['link'], proxies)
-        prefix = f"第{index}份搜索结果 [源自{url['source'][0]}搜索] （{url['title'][:25]}）："
-        history.extend([prefix, res])
-        res_squeeze = res.replace('\n', '...')
-        chatbot[-1] = [prefix + "\n\n" + res_squeeze[:500] + "......", None]
-        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+    template = dedent("""
+        <details>
+        <summary>{TITLE}</summary>
+        <div class="search_result">{URL}</div>
+        <div class="search_result">{CONTENT}</div>
+        </details>
+    """)
+
+    buffer = ""
+
+    # 创建线程池
+    with ThreadPoolExecutor(max_workers=5) as executor:
+        # 提交任务到线程池
+        futures = []
+        for index, url in enumerate(urls[:max_search_result]):
+            future = executor.submit(scrape_text, url['link'], proxies)
+            futures.append((index, future, url))
+
+        # 处理完成的任务
+        for index, future, url in futures:
+            # 开始
+            prefix = f"正在加载 第{index+1}份搜索结果 [源自{url['source'][0]}搜索] （{url['title'][:25]}）："
+            string_structure = template.format(TITLE=prefix, URL=url['link'], CONTENT="正在加载，请稍后 ......")
+            yield from update_ui_latest_msg(lastmsg=(buffer + string_structure), chatbot=chatbot, history=history, delay=0.1)  # 刷新界面
+
+            # 获取结果
+            res = future.result()
+
+            # 显示结果
+            prefix = f"第{index+1}份搜索结果 [源自{url['source'][0]}搜索] （{url['title'][:25]}）："
+            string_structure = template.format(TITLE=prefix, URL=url['link'], CONTENT=res[:1000] + "......")
+            buffer += string_structure
+
+            # 更新历史
+            history.extend([prefix, res])
+            yield from update_ui_latest_msg(lastmsg=buffer, chatbot=chatbot, history=history, delay=0.1)  # 刷新界面
 
     # ------------- < 第3步：ChatGPT综合 > -------------
     if (optimizer != "开启(增强)"):

crazy_functions/Internet_GPT_Wrap.py

@@ -1,4 +1,4 @@
-
+import random
 from toolbox import get_conf
 from crazy_functions.Internet_GPT import 连接网络回答问题
 from crazy_functions.plugin_template.plugin_class_template import GptAcademicPluginTemplate, ArgProperty
@@ -20,6 +20,9 @@ class NetworkGPT_Wrap(GptAcademicPluginTemplate):
         第三个参数，名称`allow_cache`，参数`type`声明这是一个下拉菜单，下拉菜单上方显示`title`+`description`，下拉菜单的选项为`options`，`default_value`为下拉菜单默认值；
 
         """
+        urls = get_conf("SEARXNG_URLS")
+        url = random.choice(urls)
+
         gui_definition = {
             "main_input":
                 ArgProperty(title="输入问题", description="待通过互联网检索的问题，会自动读取输入框内容", default_value="", type="string").model_dump_json(), # 主输入，自动从输入框同步
@@ -30,16 +33,17 @@ class NetworkGPT_Wrap(GptAcademicPluginTemplate):
             "optimizer":
                 ArgProperty(title="搜索优化", options=["关闭", "开启", "开启(增强)"], default_value="关闭", description="是否使用搜索增强。注意这可能会消耗较多token", type="dropdown").model_dump_json(),
             "searxng_url":
-                ArgProperty(title="Searxng服务地址", description="输入Searxng的地址", default_value=get_conf("SEARXNG_URL"), type="string").model_dump_json(), # 主输入，自动从输入框同步
+                ArgProperty(title="Searxng服务地址", description="输入Searxng的地址", default_value=url, type="string").model_dump_json(), # 主输入，自动从输入框同步
 
         }
         return gui_definition
 
-    def execute(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
+    def execute(txt, llm_kwargs, plugin_kwargs:dict, chatbot, history, system_prompt, user_request):
         """
         执行插件
         """
-        if plugin_kwargs["categories"] == "网页": plugin_kwargs["categories"] = "general"
-        if plugin_kwargs["categories"] == "学术论文": plugin_kwargs["categories"] = "science"
+        if plugin_kwargs.get("categories", None) == "网页": plugin_kwargs["categories"] = "general"
+        elif plugin_kwargs.get("categories", None) == "学术论文": plugin_kwargs["categories"] = "science"
+        else: plugin_kwargs["categories"] = "general"
         yield from 连接网络回答问题(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request)
 

crazy_functions/Latex_Function.py

@@ -1,5 +1,5 @@
 from toolbox import update_ui, trimmed_format_exc, get_conf, get_log_folder, promote_file_to_downloadzone, check_repeat_upload, map_file_to_sha256
-from toolbox import CatchException, report_exception, update_ui_lastest_msg, zip_result, gen_time_str
+from toolbox import CatchException, report_exception, update_ui_latest_msg, zip_result, gen_time_str
 from functools import partial
 from loguru import logger
 
@@ -41,7 +41,7 @@ def switch_prompt(pfg, mode, more_requirement):
     return inputs_array, sys_prompt_array
 
 
-def desend_to_extracted_folder_if_exist(project_folder):
+def descend_to_extracted_folder_if_exist(project_folder):
     """
     Descend into the extracted folder if it exists, otherwise return the original folder.
 
@@ -130,7 +130,7 @@ def arxiv_download(chatbot, history, txt, allow_cache=True):
 
     if not txt.startswith('https://arxiv.org/abs/'):
         msg = f"解析arxiv网址失败, 期望格式例如: https://arxiv.org/abs/1707.06690。实际得到格式: {url_}。"
-        yield from update_ui_lastest_msg(msg, chatbot=chatbot, history=history)  # 刷新界面
+        yield from update_ui_latest_msg(msg, chatbot=chatbot, history=history)  # 刷新界面
         return msg, None
     # <-------------- set format ------------->
     arxiv_id = url_.split('/abs/')[-1]
@@ -156,16 +156,16 @@ def arxiv_download(chatbot, history, txt, allow_cache=True):
         return False
 
     if os.path.exists(dst) and allow_cache:
-        yield from update_ui_lastest_msg(f"调用缓存 {arxiv_id}", chatbot=chatbot, history=history)  # 刷新界面
+        yield from update_ui_latest_msg(f"调用缓存 {arxiv_id}", chatbot=chatbot, history=history)  # 刷新界面
         success = True
     else:
-        yield from update_ui_lastest_msg(f"开始下载 {arxiv_id}", chatbot=chatbot, history=history)  # 刷新界面
+        yield from update_ui_latest_msg(f"开始下载 {arxiv_id}", chatbot=chatbot, history=history)  # 刷新界面
         success = fix_url_and_download()
-        yield from update_ui_lastest_msg(f"下载完成 {arxiv_id}", chatbot=chatbot, history=history)  # 刷新界面
+        yield from update_ui_latest_msg(f"下载完成 {arxiv_id}", chatbot=chatbot, history=history)  # 刷新界面
 
 
     if not success:
-        yield from update_ui_lastest_msg(f"下载失败 {arxiv_id}", chatbot=chatbot, history=history)
+        yield from update_ui_latest_msg(f"下载失败 {arxiv_id}", chatbot=chatbot, history=history)
         raise tarfile.ReadError(f"论文下载失败 {arxiv_id}")
 
     # <-------------- extract file ------------->
@@ -288,7 +288,7 @@ def Latex英文纠错加PDF对比(txt, llm_kwargs, plugin_kwargs, chatbot, histo
         return
 
     # <-------------- if is a zip/tar file ------------->
-    project_folder = desend_to_extracted_folder_if_exist(project_folder)
+    project_folder = descend_to_extracted_folder_if_exist(project_folder)
 
     # <-------------- move latex project away from temp folder ------------->
     from shared_utils.fastapi_server import validate_path_safety
@@ -365,7 +365,7 @@ def Latex翻译中文并重新编译PDF(txt, llm_kwargs, plugin_kwargs, chatbot,
     try:
         txt, arxiv_id = yield from arxiv_download(chatbot, history, txt, allow_cache)
     except tarfile.ReadError as e:
-        yield from update_ui_lastest_msg(
+        yield from update_ui_latest_msg(
             "无法自动下载该论文的Latex源码，请前往arxiv打开此论文下载页面，点other Formats，然后download source手动下载latex源码包。接下来调用本地Latex翻译插件即可。",
             chatbot=chatbot, history=history)
         return
@@ -404,7 +404,7 @@ def Latex翻译中文并重新编译PDF(txt, llm_kwargs, plugin_kwargs, chatbot,
         return
 
     # <-------------- if is a zip/tar file ------------->
-    project_folder = desend_to_extracted_folder_if_exist(project_folder)
+    project_folder = descend_to_extracted_folder_if_exist(project_folder)
 
     # <-------------- move latex project away from temp folder ------------->
     from shared_utils.fastapi_server import validate_path_safety
@@ -518,7 +518,7 @@ def PDF翻译中文并重新编译PDF(txt, llm_kwargs, plugin_kwargs, chatbot, h
     # repeat, project_folder = check_repeat_upload(file_manifest[0], hash_tag)
 
     # if repeat:
-    #     yield from update_ui_lastest_msg(f"发现重复上传，请查收结果（压缩包）...", chatbot=chatbot, history=history)
+    #     yield from update_ui_latest_msg(f"发现重复上传，请查收结果（压缩包）...", chatbot=chatbot, history=history)
     #     try:
     #         translate_pdf = [f for f in glob.glob(f'{project_folder}/**/merge_translate_zh.pdf', recursive=True)][0]
     #         promote_file_to_downloadzone(translate_pdf, rename_file=None, chatbot=chatbot)
@@ -531,7 +531,7 @@ def PDF翻译中文并重新编译PDF(txt, llm_kwargs, plugin_kwargs, chatbot, h
     #         report_exception(chatbot, history, a=f"解析项目: {txt}", b=f"发现重复上传，但是无法找到相关文件")
     #         yield from update_ui(chatbot=chatbot, history=history)
     # else:
-    #     yield from update_ui_lastest_msg(f"未发现重复上传", chatbot=chatbot, history=history)
+    #     yield from update_ui_latest_msg(f"未发现重复上传", chatbot=chatbot, history=history)
 
     # <-------------- convert pdf into tex ------------->
     chatbot.append([f"解析项目: {txt}", "正在将PDF转换为tex项目，请耐心等待..."])
@@ -543,7 +543,7 @@ def PDF翻译中文并重新编译PDF(txt, llm_kwargs, plugin_kwargs, chatbot, h
         return False
 
     # <-------------- translate latex file into Chinese ------------->
-    yield from update_ui_lastest_msg("正在tex项目将翻译为中文...", chatbot=chatbot, history=history)
+    yield from update_ui_latest_msg("正在tex项目将翻译为中文...", chatbot=chatbot, history=history)
     file_manifest = [f for f in glob.glob(f'{project_folder}/**/*.tex', recursive=True)]
     if len(file_manifest) == 0:
         report_exception(chatbot, history, a=f"解析项目: {txt}", b=f"找不到任何.tex文件: {txt}")
@@ -551,7 +551,7 @@ def PDF翻译中文并重新编译PDF(txt, llm_kwargs, plugin_kwargs, chatbot, h
         return
 
     # <-------------- if is a zip/tar file ------------->
-    project_folder = desend_to_extracted_folder_if_exist(project_folder)
+    project_folder = descend_to_extracted_folder_if_exist(project_folder)
 
     # <-------------- move latex project away from temp folder ------------->
     from shared_utils.fastapi_server import validate_path_safety
@@ -559,7 +559,7 @@ def PDF翻译中文并重新编译PDF(txt, llm_kwargs, plugin_kwargs, chatbot, h
     project_folder = move_project(project_folder)
 
     # <-------------- set a hash tag for repeat-checking ------------->
-    with open(pj(project_folder, hash_tag + '.tag'), 'w') as f:
+    with open(pj(project_folder, hash_tag + '.tag'), 'w', encoding='utf8') as f:
         f.write(hash_tag)
         f.close()
 
@@ -571,7 +571,7 @@ def PDF翻译中文并重新编译PDF(txt, llm_kwargs, plugin_kwargs, chatbot, h
                                     switch_prompt=_switch_prompt_)
 
     # <-------------- compile PDF ------------->
-    yield from update_ui_lastest_msg("正在将翻译好的项目tex项目编译为PDF...", chatbot=chatbot, history=history)
+    yield from update_ui_latest_msg("正在将翻译好的项目tex项目编译为PDF...", chatbot=chatbot, history=history)
     success = yield from 编译Latex(chatbot, history, main_file_original='merge',
                                 main_file_modified='merge_translate_zh', mode='translate_zh',
                                 work_folder_original=project_folder, work_folder_modified=project_folder,

crazy_functions/PDF_Translate.py

@@ -1,5 +1,5 @@
 from toolbox import CatchException, check_packages, get_conf
-from toolbox import update_ui, update_ui_lastest_msg, disable_auto_promotion
+from toolbox import update_ui, update_ui_latest_msg, disable_auto_promotion
 from toolbox import trimmed_format_exc_markdown
 from crazy_functions.crazy_utils import get_files_from_everything
 from crazy_functions.pdf_fns.parse_pdf import get_avail_grobid_url
@@ -47,7 +47,7 @@ def 批量翻译PDF文档(txt, llm_kwargs, plugin_kwargs, chatbot, history, syst
                 yield from 解析PDF_基于DOC2X(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, DOC2X_API_KEY, user_request)
                 return
             except:
-                chatbot.append([None, f"DOC2X服务不可用，现在将执行效果稍差的旧版代码。{trimmed_format_exc_markdown()}"])
+                chatbot.append([None, f"DOC2X服务不可用，请检查报错详细。{trimmed_format_exc_markdown()}"])
                 yield from update_ui(chatbot=chatbot, history=history)
 
     if method == "GROBID":
@@ -57,9 +57,9 @@ def 批量翻译PDF文档(txt, llm_kwargs, plugin_kwargs, chatbot, history, syst
             yield from 解析PDF_基于GROBID(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, grobid_url)
             return
 
-    if method == "ClASSIC":
+    if method == "Classic":
         # ------- 第三种方法，早期代码，效果不理想 -------
-        yield from update_ui_lastest_msg("GROBID服务不可用，请检查config中的GROBID_URL。作为替代，现在将执行效果稍差的旧版代码。", chatbot, history, delay=3)
+        yield from update_ui_latest_msg("GROBID服务不可用，请检查config中的GROBID_URL。作为替代，现在将执行效果稍差的旧版代码。", chatbot, history, delay=3)
         yield from 解析PDF_简单拆解(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt)
         return
 
@@ -77,7 +77,7 @@ def 批量翻译PDF文档(txt, llm_kwargs, plugin_kwargs, chatbot, history, syst
         if grobid_url is not None:
             yield from 解析PDF_基于GROBID(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, grobid_url)
             return
-        yield from update_ui_lastest_msg("GROBID服务不可用，请检查config中的GROBID_URL。作为替代，现在将执行效果稍差的旧版代码。", chatbot, history, delay=3)
+        yield from update_ui_latest_msg("GROBID服务不可用，请检查config中的GROBID_URL。作为替代，现在将执行效果稍差的旧版代码。", chatbot, history, delay=3)
         yield from 解析PDF_简单拆解(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt)
         return
 

crazy_functions/PDF_Translate_Wrap.py

@@ -19,7 +19,7 @@ class PDF_Tran(GptAcademicPluginTemplate):
             "additional_prompt":
                 ArgProperty(title="额外提示词", description="例如：对专有名词、翻译语气等方面的要求", default_value="", type="string").model_dump_json(), # 高级参数输入区，自动同步
             "pdf_parse_method":
-                ArgProperty(title="PDF解析方法", options=["DOC2X", "GROBID", "ClASSIC"], description="无", default_value="GROBID", type="dropdown").model_dump_json(),
+                ArgProperty(title="PDF解析方法", options=["DOC2X", "GROBID", "Classic"], description="无", default_value="GROBID", type="dropdown").model_dump_json(),
         }
         return gui_definition
 

crazy_functions/Rag_Interface.py

@@ -4,7 +4,8 @@ from typing import List
 from shared_utils.fastapi_server import validate_path_safety
 
 from toolbox import report_exception
-from toolbox import CatchException, update_ui, get_conf, get_log_folder, update_ui_lastest_msg
+from toolbox import CatchException, update_ui, get_conf, get_log_folder, update_ui_latest_msg
+from shared_utils.fastapi_server import validate_path_safety
 from crazy_functions.crazy_utils import input_clipping
 from crazy_functions.crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
 
@@ -60,6 +61,7 @@ def Rag问答(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, u
     # 1. we retrieve rag worker from global context
     user_name = chatbot.get_user()
     checkpoint_dir = get_log_folder(user_name, plugin_name='experimental_rag')
+
     if user_name in RAG_WORKER_REGISTER:
         rag_worker = RAG_WORKER_REGISTER[user_name]
     else:
@@ -90,12 +92,9 @@ def Rag问答(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, u
         chatbot.append([txt, f'正在清空 ({current_context}) ...'])
         yield from update_ui(chatbot=chatbot, history=history)  # 刷新界面
         rag_worker.purge_vector_store()
-        yield from update_ui_lastest_msg('已清空', chatbot, history, delay=0)  # 刷新界面
+        yield from update_ui_latest_msg('已清空', chatbot, history, delay=0)  # 刷新界面
         return
 
-    else:
-        report_exception(chatbot, history, a=f"上传文件路径错误: {txt}", b="请检查并提供正确路径。")
-
     # 3. Normal Q&A processing
     chatbot.append([txt, f'正在召回知识 ({current_context}) ...'])
     yield from update_ui(chatbot=chatbot, history=history)  # 刷新界面
@@ -110,10 +109,10 @@ def Rag问答(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, u
 
     # 5. If input is clipped, add input to vector store before retrieve
     if input_is_clipped_flag:
-        yield from update_ui_lastest_msg('检测到长输入, 正在向量化 ...', chatbot, history, delay=0)  # 刷新界面
+        yield from update_ui_latest_msg('检测到长输入, 正在向量化 ...', chatbot, history, delay=0)  # 刷新界面
         # Save input to vector store
         rag_worker.add_text_to_vector_store(txt_origin)
-        yield from update_ui_lastest_msg('向量化完成 ...', chatbot, history, delay=0)  # 刷新界面
+        yield from update_ui_latest_msg('向量化完成 ...', chatbot, history, delay=0)  # 刷新界面
 
         if len(txt_origin) > REMEMBER_PREVIEW:
             HALF = REMEMBER_PREVIEW // 2
@@ -143,7 +142,7 @@ def Rag问答(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, u
     )
 
     # 8. Remember Q&A
-    yield from update_ui_lastest_msg(
+    yield from update_ui_latest_msg(
         model_say + '</br></br>' + f'对话记忆中, 请稍等 ({current_context}) ...',
         chatbot, history, delay=0.5
     )
@@ -151,4 +150,4 @@ def Rag问答(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, u
     history.extend([i_say, model_say])
 
     # 9. Final UI Update
-    yield from update_ui_lastest_msg(model_say, chatbot, history, delay=0, msg=tip)
+    yield from update_ui_latest_msg(model_say, chatbot, history, delay=0, msg=tip)

crazy_functions/Social_Helper.py

@@ -1,5 +1,5 @@
 import pickle, os, random
-from toolbox import CatchException, update_ui, get_conf, get_log_folder, update_ui_lastest_msg
+from toolbox import CatchException, update_ui, get_conf, get_log_folder, update_ui_latest_msg
 from crazy_functions.crazy_utils import input_clipping
 from crazy_functions.crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
 from request_llms.bridge_all import predict_no_ui_long_connection
@@ -9,7 +9,7 @@ from loguru import logger
 from typing import List
 
 
-SOCIAL_NETWOK_WORKER_REGISTER = {}
+SOCIAL_NETWORK_WORKER_REGISTER = {}
 
 class SocialNetwork():
     def __init__(self):
@@ -78,7 +78,7 @@ class SocialNetworkWorker(SaveAndLoad):
             for f in friend.friends_list: 
                 self.add_friend(f)
             msg = f"成功添加{len(friend.friends_list)}个联系人: {str(friend.friends_list)}"
-            yield from update_ui_lastest_msg(lastmsg=msg, chatbot=chatbot, history=history, delay=0)
+            yield from update_ui_latest_msg(lastmsg=msg, chatbot=chatbot, history=history, delay=0)
 
 
     def run(self, txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
@@ -104,12 +104,12 @@ class SocialNetworkWorker(SaveAndLoad):
         }
 
         try:
-            Explaination = '\n'.join([f'{k}: {v["explain_to_llm"]}' for k, v in self.tools_to_select.items()])
+            Explanation = '\n'.join([f'{k}: {v["explain_to_llm"]}' for k, v in self.tools_to_select.items()])
             class UserSociaIntention(BaseModel):
                 intention_type: str = Field(
                     description=
                         f"The type of user intention. You must choose from {self.tools_to_select.keys()}.\n\n" 
-                        f"Explaination:\n{Explaination}", 
+                        f"Explanation:\n{Explanation}", 
                     default="SocialAdvice"
                 )
             pydantic_cls_instance, err_msg = select_tool(
@@ -118,7 +118,7 @@ class SocialNetworkWorker(SaveAndLoad):
                 pydantic_cls=UserSociaIntention
             )
         except Exception as e:
-            yield from update_ui_lastest_msg(
+            yield from update_ui_latest_msg(
                 lastmsg=f"无法理解用户意图 {err_msg}", 
                 chatbot=chatbot, 
                 history=history, 
@@ -150,10 +150,10 @@ def I人助手(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt,
     # 1. we retrieve worker from global context
     user_name = chatbot.get_user()
     checkpoint_dir=get_log_folder(user_name, plugin_name='experimental_rag')
-    if user_name in SOCIAL_NETWOK_WORKER_REGISTER:
-        social_network_worker = SOCIAL_NETWOK_WORKER_REGISTER[user_name]
+    if user_name in SOCIAL_NETWORK_WORKER_REGISTER:
+        social_network_worker = SOCIAL_NETWORK_WORKER_REGISTER[user_name]
     else:
-        social_network_worker = SOCIAL_NETWOK_WORKER_REGISTER[user_name] = SocialNetworkWorker(
+        social_network_worker = SOCIAL_NETWORK_WORKER_REGISTER[user_name] = SocialNetworkWorker(
             user_name, 
             llm_kwargs, 
             checkpoint_dir=checkpoint_dir, 

crazy_functions/SourceCode_Comment.py

@@ -1,5 +1,5 @@
 import os, copy, time
-from toolbox import CatchException, report_exception, update_ui, zip_result, promote_file_to_downloadzone, update_ui_lastest_msg, get_conf, generate_file_link
+from toolbox import CatchException, report_exception, update_ui, zip_result, promote_file_to_downloadzone, update_ui_latest_msg, get_conf, generate_file_link
 from shared_utils.fastapi_server import validate_path_safety
 from crazy_functions.crazy_utils import input_clipping
 from crazy_functions.crazy_utils import request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency
@@ -117,7 +117,7 @@ def 注释源代码(file_manifest, project_folder, llm_kwargs, plugin_kwargs, ch
                 logger.error(f"文件: {fp} 的注释结果未能成功")
         file_links = generate_file_link(preview_html_list)
 
-        yield from update_ui_lastest_msg(
+        yield from update_ui_latest_msg(
             f"当前任务: <br/>{'<br/>'.join(tasks)}.<br/>" + 
             f"剩余源文件数量: {remain}.<br/>" + 
             f"已完成的文件: {sum(worker_done)}.<br/>" + 

crazy_functions/VideoResource_GPT.py

@@ -0,0 +1,204 @@
+import requests
+import random
+import time
+import re
+import json
+from bs4 import BeautifulSoup
+from functools import lru_cache
+from itertools import zip_longest
+from check_proxy import check_proxy
+from toolbox import CatchException, update_ui, get_conf, promote_file_to_downloadzone, update_ui_latest_msg, generate_file_link
+from crazy_functions.crazy_utils import request_gpt_model_in_new_thread_with_ui_alive, input_clipping
+from request_llms.bridge_all import model_info
+from request_llms.bridge_all import predict_no_ui_long_connection
+from crazy_functions.prompts.internet import SearchOptimizerPrompt, SearchAcademicOptimizerPrompt
+from crazy_functions.json_fns.pydantic_io import GptJsonIO, JsonStringError
+from textwrap import dedent
+from loguru import logger
+from pydantic import BaseModel, Field
+
+class Query(BaseModel):
+    search_keyword: str = Field(description="search query for video resource")
+
+
+class VideoResource(BaseModel):
+    thought: str = Field(description="analysis of the search results based on the user's query")
+    title: str = Field(description="title of the video")
+    author: str = Field(description="author/uploader of the video") 
+    bvid: str = Field(description="unique ID of the video")
+    another_failsafe_bvid: str = Field(description="provide another bvid, the other one is not working")
+
+
+def get_video_resource(search_keyword):
+    from crazy_functions.media_fns.get_media import search_videos
+
+    # Search for videos and return the first result
+    videos = search_videos(
+        search_keyword
+    )
+
+    # Return the first video if results exist, otherwise return None
+    return videos
+
+def download_video(bvid, user_name, chatbot, history):
+    # from experimental_mods.get_bilibili_resource import download_bilibili
+    from crazy_functions.media_fns.get_media import download_video
+    # pause a while
+    tic_time = 8
+    for i in range(tic_time):
+        yield from update_ui_latest_msg(
+            lastmsg=f"即将下载音频。等待{tic_time-i}秒后自动继续, 点击“停止”键取消此操作。", 
+            chatbot=chatbot, history=[], delay=1)
+
+    # download audio
+    chatbot.append((None, "下载音频, 请稍等...")); yield from update_ui(chatbot=chatbot, history=history)
+    downloaded_files = yield from download_video(bvid, only_audio=True, user_name=user_name, chatbot=chatbot, history=history)
+
+    if len(downloaded_files) == 0:
+        # failed to download audio
+        return []
+
+    # preview
+    preview_list = [promote_file_to_downloadzone(fp) for fp in downloaded_files]
+    file_links = generate_file_link(preview_list)
+    yield from update_ui_latest_msg(f"已完成的文件: <br/>" + file_links, chatbot=chatbot, history=history, delay=0)
+    chatbot.append((None, f"即将下载视频。"))
+
+    # pause a while
+    tic_time = 16
+    for i in range(tic_time):
+        yield from update_ui_latest_msg(
+            lastmsg=f"即将下载视频。等待{tic_time-i}秒后自动继续, 点击“停止”键取消此操作。", 
+            chatbot=chatbot, history=[], delay=1)
+
+    # download video
+    chatbot.append((None, "下载视频, 请稍等...")); yield from update_ui(chatbot=chatbot, history=history)
+    downloaded_files_part2 = yield from download_video(bvid, only_audio=False, user_name=user_name, chatbot=chatbot, history=history)
+
+    # preview
+    preview_list = [promote_file_to_downloadzone(fp) for fp in downloaded_files_part2]
+    file_links = generate_file_link(preview_list)
+    yield from update_ui_latest_msg(f"已完成的文件: <br/>" + file_links, chatbot=chatbot, history=history, delay=0)
+
+    # return
+    return downloaded_files + downloaded_files_part2
+
+
+class Strategy(BaseModel):
+    thought: str = Field(description="analysis of the user's wish, for example, can you recall the name of the resource?")
+    which_methods: str = Field(description="Which method to use to find the necessary information? choose from 'method_1' and 'method_2'.")
+    method_1_search_keywords: str = Field(description="Generate keywords to search the internet if you choose method 1, otherwise empty.")
+    method_2_generate_keywords: str = Field(description="Generate keywords for video download engine if you choose method 2, otherwise empty.")
+
+
+@CatchException
+def 多媒体任务(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
+    user_wish: str = txt
+    # query demos: 
+    #   - "我想找一首歌，里面有句歌词是“turn your face towards the sun”"
+    #   - "一首歌，第一句是红豆生南国"
+    #   - "一首音乐，中国航天任务专用的那首"
+    #   - "戴森球计划在熔岩星球的音乐"
+    #   - "hanser的百变什么精"
+    #   - "打大圣残躯时的bgm"
+    #   - "渊下宫战斗音乐"
+
+    # 搜索
+    chatbot.append((txt, "检索中, 请稍等..."))
+    yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+    if "跳过联网搜索" not in user_wish:
+        # 结构化生成
+        internet_search_keyword = user_wish
+
+        yield from update_ui_latest_msg(lastmsg=f"发起互联网检索: {internet_search_keyword} ...", chatbot=chatbot, history=[], delay=1)
+        from crazy_functions.Internet_GPT import internet_search_with_analysis_prompt
+        result = yield from internet_search_with_analysis_prompt(
+            prompt=internet_search_keyword,
+            analysis_prompt="请根据搜索结果分析，获取用户需要找的资源的名称、作者、出处等信息。",
+            llm_kwargs=llm_kwargs,
+            chatbot=chatbot
+        )
+
+        yield from update_ui_latest_msg(lastmsg=f"互联网检索结论: {result} \n\n 正在生成进一步检索方案 ...", chatbot=chatbot, history=[], delay=1)
+        rf_req = dedent(f"""
+        The user wish to get the following resource:
+            {user_wish}
+        Meanwhile, you can access another expert's opinion on the user's wish:
+            {result}
+        Generate search keywords (less than 5 keywords) for video download engine accordingly.
+        """)
+    else:
+        user_wish = user_wish.replace("跳过联网搜索", "").strip()
+        rf_req = dedent(f"""
+        The user wish to get the following resource:
+            {user_wish}
+        Generate research keywords (less than 5 keywords) accordingly.
+        """)
+    gpt_json_io = GptJsonIO(Query)
+    inputs = rf_req + gpt_json_io.format_instructions
+    run_gpt_fn = lambda inputs, sys_prompt: predict_no_ui_long_connection(inputs=inputs, llm_kwargs=llm_kwargs, history=[], sys_prompt=sys_prompt, observe_window=[])
+    analyze_res = run_gpt_fn(inputs, "")
+    logger.info(analyze_res)
+    query: Query = gpt_json_io.generate_output_auto_repair(analyze_res, run_gpt_fn)
+    video_engine_keywords = query.search_keyword
+    # 关键词展示
+    chatbot.append((None, f"检索关键词已确认: {video_engine_keywords}。筛选中, 请稍等..."))
+    yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+
+    # 获取候选资源
+    candidate_dictionary: dict =  get_video_resource(video_engine_keywords)
+    candidate_dictionary_as_str = json.dumps(candidate_dictionary, ensure_ascii=False, indent=4)
+
+    # 展示候选资源
+    candidate_display = "\n".join([f"{i+1}. {it['title']}" for i, it in enumerate(candidate_dictionary)])
+    chatbot.append((None, f"候选:\n\n{candidate_display}"))
+    yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+
+    # 结构化生成
+    rf_req_2 = dedent(f"""
+    The user wish to get the following resource:
+        {user_wish}
+
+    Select the most relevant and suitable video resource from the following search results:
+        {candidate_dictionary_as_str}
+
+    Note:
+        1. The first several search video results are more likely to satisfy the user's wish.
+        2. The time duration of the video should be less than 10 minutes.
+        3. You should analyze the search results first, before giving your answer.
+        4. Use Chinese if possible.
+        5. Beside the primary video selection, give a backup video resource `bvid`.
+    """)
+    gpt_json_io = GptJsonIO(VideoResource)
+    inputs = rf_req_2 + gpt_json_io.format_instructions
+    run_gpt_fn = lambda inputs, sys_prompt: predict_no_ui_long_connection(inputs=inputs, llm_kwargs=llm_kwargs, history=[], sys_prompt=sys_prompt, observe_window=[])
+    analyze_res = run_gpt_fn(inputs, "")
+    logger.info(analyze_res)
+    video_resource: VideoResource = gpt_json_io.generate_output_auto_repair(analyze_res, run_gpt_fn)
+
+    # Display
+    chatbot.append(
+        (None, 
+            f"分析：{video_resource.thought}" "<br/>"
+            f"选择: `{video_resource.title}`。" "<br/>" 
+            f"作者：{video_resource.author}"
+        )
+    )
+    chatbot.append((None, f"下载中, 请稍等..."))
+    yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+
+    if video_resource and video_resource.bvid:
+        logger.info(video_resource)
+        downloaded = yield from download_video(video_resource.bvid, chatbot.get_user(), chatbot, history)
+        if not downloaded:
+            chatbot.append((None, f"下载失败, 尝试备选 ..."))
+            yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+            downloaded = yield from download_video(video_resource.another_failsafe_bvid, chatbot.get_user(), chatbot, history)
+
+
+
+
+        
+@CatchException
+def debug(bvid, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
+    yield from download_video(bvid, chatbot.get_user(), chatbot, history)

crazy_functions/agent_fns/auto_agent.py

@@ -1,5 +1,5 @@
 from toolbox import CatchException, update_ui, gen_time_str, trimmed_format_exc, ProxyNetworkActivate
-from toolbox import report_exception, get_log_folder, update_ui_lastest_msg, Singleton
+from toolbox import report_exception, get_log_folder, update_ui_latest_msg, Singleton
 from crazy_functions.agent_fns.pipe import PluginMultiprocessManager, PipeCom
 from crazy_functions.agent_fns.general import AutoGenGeneral
 

crazy_functions/agent_fns/echo_agent.py

@@ -8,7 +8,7 @@ class EchoDemo(PluginMultiprocessManager):
         while True:
             msg = self.child_conn.recv() # PipeCom
             if msg.cmd == "user_input":
-                # wait futher user input
+                # wait father user input
                 self.child_conn.send(PipeCom("show", msg.content))
                 wait_success = self.subprocess_worker_wait_user_feedback(wait_msg="我准备好处理下一个问题了.")
                 if not wait_success:

crazy_functions/agent_fns/general.py

@@ -27,7 +27,7 @@ def gpt_academic_generate_oai_reply(
         llm_kwargs=llm_config,
         history=history,
         sys_prompt=self._oai_system_message[0]['content'],
-        console_slience=True
+        console_silence=True
     )
     assumed_done = reply.endswith('\nTERMINATE')
     return True, reply

crazy_functions/agent_fns/python_comment_agent.py

@@ -10,7 +10,7 @@ from crazy_functions.crazy_utils import request_gpt_model_in_new_thread_with_ui_
 # TODO: 解决缩进问题
 
 find_function_end_prompt = '''
-Below is a page of code that you need to read. This page may not yet complete, you job is to split this page to sperate functions, class functions etc.
+Below is a page of code that you need to read. This page may not yet complete, you job is to split this page to separate functions, class functions etc.
 - Provide the line number where the first visible function ends.
 - Provide the line number where the next visible function begins.
 - If there are no other functions in this page, you should simply return the line number of the last line.
@@ -59,7 +59,7 @@ OUTPUT:
 
 
 
-revise_funtion_prompt = '''
+revise_function_prompt = '''
 You need to read the following code, and revise the source code ({FILE_BASENAME}) according to following instructions:
 1. You should analyze the purpose of the functions (if there are any).
 2. You need to add docstring for the provided functions (if there are any).
@@ -117,7 +117,7 @@ def zip_result(folder):
 '''
 
 
-revise_funtion_prompt_chinese = '''
+revise_function_prompt_chinese = '''
 您需要阅读以下代码，并根据以下说明修订源代码({FILE_BASENAME}):
 1. 如果源代码中包含函数的话, 你应该分析给定函数实现了什么功能
 2. 如果源代码中包含函数的话, 你需要为函数添加docstring, docstring必须使用中文
@@ -188,9 +188,9 @@ class PythonCodeComment():
         self.language = language
         self.observe_window_update = observe_window_update
         if self.language == "chinese":
-            self.core_prompt = revise_funtion_prompt_chinese
+            self.core_prompt = revise_function_prompt_chinese
         else:
-            self.core_prompt = revise_funtion_prompt
+            self.core_prompt = revise_function_prompt
         self.path = None
         self.file_basename = None
         self.file_brief = ""
@@ -222,7 +222,7 @@ class PythonCodeComment():
             history=[],
             sys_prompt="",
             observe_window=[],
-            console_slience=True
+            console_silence=True
         )
 
         def extract_number(text):
@@ -316,7 +316,7 @@ class PythonCodeComment():
     def tag_code(self, fn, hint):
         code = fn
         _, n_indent = self.dedent(code)
-        indent_reminder = "" if n_indent == 0 else "(Reminder: as you can see, this piece of code has indent made up with {n_indent} whitespace, please preseve them in the OUTPUT.)"
+        indent_reminder = "" if n_indent == 0 else "(Reminder: as you can see, this piece of code has indent made up with {n_indent} whitespace, please preserve them in the OUTPUT.)"
         brief_reminder = "" if self.file_brief == "" else f"({self.file_basename} abstract: {self.file_brief})"
         hint_reminder = "" if hint is None else f"(Reminder: do not ignore or modify code such as `{hint}`, provide complete code in the OUTPUT.)"
         self.llm_kwargs['temperature'] = 0
@@ -333,7 +333,7 @@ class PythonCodeComment():
             history=[],
             sys_prompt="",
             observe_window=[],
-            console_slience=True
+            console_silence=True
         )
 
         def get_code_block(reply):
@@ -400,7 +400,7 @@ class PythonCodeComment():
         return revised
 
     def begin_comment_source_code(self, chatbot=None, history=None):
-        # from toolbox import update_ui_lastest_msg
+        # from toolbox import update_ui_latest_msg
         assert self.path is not None
         assert '.py' in self.path   # must be python source code
         # write_target = self.path + '.revised.py'
@@ -409,10 +409,10 @@ class PythonCodeComment():
         # with open(self.path + '.revised.py', 'w+', encoding='utf8') as f:
         while True:
             try:
-                # yield from update_ui_lastest_msg(f"({self.file_basename}) 正在读取下一段代码片段:\n", chatbot=chatbot, history=history, delay=0)
+                # yield from update_ui_latest_msg(f"({self.file_basename}) 正在读取下一段代码片段:\n", chatbot=chatbot, history=history, delay=0)
                 next_batch, line_no_start, line_no_end = self.get_next_batch()
                 self.observe_window_update(f"正在处理{self.file_basename} - {line_no_start}/{len(self.full_context)}\n")
-                # yield from update_ui_lastest_msg(f"({self.file_basename}) 处理代码片段:\n\n{next_batch}", chatbot=chatbot, history=history, delay=0)
+                # yield from update_ui_latest_msg(f"({self.file_basename}) 处理代码片段:\n\n{next_batch}", chatbot=chatbot, history=history, delay=0)
                 
                 hint = None
                 MAX_ATTEMPT = 2

crazy_functions/chatglm微调工具.py

@@ -1,141 +0,0 @@
-from toolbox import CatchException, update_ui, promote_file_to_downloadzone
-from crazy_functions.crazy_utils import request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency
-import datetime, json
-
-def fetch_items(list_of_items, batch_size):
-    for i in range(0, len(list_of_items), batch_size):
-        yield list_of_items[i:i + batch_size]
-
-def string_to_options(arguments):
-    import argparse
-    import shlex
-
-    # Create an argparse.ArgumentParser instance
-    parser = argparse.ArgumentParser()
-
-    # Add command-line arguments
-    parser.add_argument("--llm_to_learn", type=str, help="LLM model to learn", default="gpt-3.5-turbo")
-    parser.add_argument("--prompt_prefix", type=str, help="Prompt prefix", default='')
-    parser.add_argument("--system_prompt", type=str, help="System prompt", default='')
-    parser.add_argument("--batch", type=int, help="System prompt", default=50)
-    parser.add_argument("--pre_seq_len", type=int, help="pre_seq_len", default=50)
-    parser.add_argument("--learning_rate", type=float, help="learning_rate", default=2e-2)
-    parser.add_argument("--num_gpus", type=int, help="num_gpus", default=1)
-    parser.add_argument("--json_dataset", type=str, help="json_dataset", default="")
-    parser.add_argument("--ptuning_directory", type=str, help="ptuning_directory", default="")
-
-
-
-    # Parse the arguments
-    args = parser.parse_args(shlex.split(arguments))
-
-    return args
-
-@CatchException
-def 微调数据集生成(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
-    """
-    txt             输入栏用户输入的文本，例如需要翻译的一段话，再例如一个包含了待处理文件的路径
-    llm_kwargs      gpt模型参数，如温度和top_p等，一般原样传递下去就行
-    plugin_kwargs   插件模型的参数
-    chatbot         聊天显示框的句柄，用于显示给用户
-    history         聊天历史，前情提要
-    system_prompt   给gpt的静默提醒
-    user_request    当前用户的请求信息（IP地址等）
-    """
-    history = []    # 清空历史，以免输入溢出
-    chatbot.append(("这是什么功能？", "[Local Message] 微调数据集生成"))
-    if ("advanced_arg" in plugin_kwargs) and (plugin_kwargs["advanced_arg"] == ""): plugin_kwargs.pop("advanced_arg")
-    args = plugin_kwargs.get("advanced_arg", None)
-    if args is None:
-        chatbot.append(("没给定指令", "退出"))
-        yield from update_ui(chatbot=chatbot, history=history); return
-    else:
-        arguments = string_to_options(arguments=args)
-
-    dat = []
-    with open(txt, 'r', encoding='utf8') as f:
-        for line in f.readlines():
-            json_dat = json.loads(line)
-            dat.append(json_dat["content"])
-
-    llm_kwargs['llm_model'] = arguments.llm_to_learn
-    for batch in fetch_items(dat, arguments.batch):
-        res = yield from request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
-            inputs_array=[f"{arguments.prompt_prefix}\n\n{b}" for b in (batch)],
-            inputs_show_user_array=[f"Show Nothing" for _ in (batch)],
-            llm_kwargs=llm_kwargs,
-            chatbot=chatbot,
-            history_array=[[] for _ in (batch)],
-            sys_prompt_array=[arguments.system_prompt for _ in (batch)],
-            max_workers=10  # OpenAI所允许的最大并行过载
-        )
-
-        with open(txt+'.generated.json', 'a+', encoding='utf8') as f:
-            for b, r in zip(batch, res[1::2]):
-                f.write(json.dumps({"content":b, "summary":r}, ensure_ascii=False)+'\n')
-
-    promote_file_to_downloadzone(txt+'.generated.json', rename_file='generated.json', chatbot=chatbot)
-    return
-
-
-
-@CatchException
-def 启动微调(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
-    """
-    txt             输入栏用户输入的文本，例如需要翻译的一段话，再例如一个包含了待处理文件的路径
-    llm_kwargs      gpt模型参数，如温度和top_p等，一般原样传递下去就行
-    plugin_kwargs   插件模型的参数
-    chatbot         聊天显示框的句柄，用于显示给用户
-    history         聊天历史，前情提要
-    system_prompt   给gpt的静默提醒
-    user_request    当前用户的请求信息（IP地址等）
-    """
-    import subprocess
-    history = []    # 清空历史，以免输入溢出
-    chatbot.append(("这是什么功能？", "[Local Message] 微调数据集生成"))
-    if ("advanced_arg" in plugin_kwargs) and (plugin_kwargs["advanced_arg"] == ""): plugin_kwargs.pop("advanced_arg")
-    args = plugin_kwargs.get("advanced_arg", None)
-    if args is None:
-        chatbot.append(("没给定指令", "退出"))
-        yield from update_ui(chatbot=chatbot, history=history); return
-    else:
-        arguments = string_to_options(arguments=args)
-
-
-
-    pre_seq_len = arguments.pre_seq_len             # 128
-    learning_rate = arguments.learning_rate                               # 2e-2
-    num_gpus = arguments.num_gpus                   # 1
-    json_dataset = arguments.json_dataset                 # 't_code.json'
-    ptuning_directory = arguments.ptuning_directory       # '/home/hmp/ChatGLM2-6B/ptuning'
-
-    command = f"torchrun --standalone --nnodes=1 --nproc-per-node={num_gpus} main.py \
-        --do_train \
-        --train_file AdvertiseGen/{json_dataset} \
-        --validation_file AdvertiseGen/{json_dataset} \
-        --preprocessing_num_workers 20 \
-        --prompt_column content \
-        --response_column summary \
-        --overwrite_cache \
-        --model_name_or_path THUDM/chatglm2-6b \
-        --output_dir output/clothgen-chatglm2-6b-pt-{pre_seq_len}-{learning_rate} \
-        --overwrite_output_dir \
-        --max_source_length 256 \
-        --max_target_length 256 \
-        --per_device_train_batch_size 1 \
-        --per_device_eval_batch_size 1 \
-        --gradient_accumulation_steps 16 \
-        --predict_with_generate \
-        --max_steps 100 \
-        --logging_steps 10 \
-        --save_steps 20 \
-        --learning_rate {learning_rate} \
-        --pre_seq_len {pre_seq_len} \
-        --quantization_bit 4"
-
-    process = subprocess.Popen(command, shell=True, cwd=ptuning_directory)
-    try:
-        process.communicate(timeout=3600*24)
-    except subprocess.TimeoutExpired:
-        process.kill()
-    return

crazy_functions/crazy_utils.py

@@ -1,7 +1,7 @@
 import os
 import threading
 from loguru import logger
-from shared_utils.char_visual_effect import scolling_visual_effect
+from shared_utils.char_visual_effect import scrolling_visual_effect
 from toolbox import update_ui, get_conf, trimmed_format_exc, get_max_token, Singleton
 
 def input_clipping(inputs, history, max_token_limit, return_clip_flags=False):
@@ -169,6 +169,7 @@ def can_multi_process(llm) -> bool:
     def default_condition(llm) -> bool:
         # legacy condition
         if llm.startswith('gpt-'): return True
+        if llm.startswith('chatgpt-'): return True
         if llm.startswith('api2d-'): return True
         if llm.startswith('azure-'): return True
         if llm.startswith('spark'): return True
@@ -255,7 +256,7 @@ def request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
                 # 【第一种情况】：顺利完成
                 gpt_say = predict_no_ui_long_connection(
                     inputs=inputs, llm_kwargs=llm_kwargs, history=history,
-                    sys_prompt=sys_prompt, observe_window=mutable[index], console_slience=True
+                    sys_prompt=sys_prompt, observe_window=mutable[index], console_silence=True
                 )
                 mutable[index][2] = "已成功"
                 return gpt_say
@@ -325,7 +326,7 @@ def request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
             mutable[thread_index][1] = time.time()
         # 在前端打印些好玩的东西
         for thread_index, _ in enumerate(worker_done):
-            print_something_really_funny = f"[ ...`{scolling_visual_effect(mutable[thread_index][0], scroller_max_len)}`... ]"
+            print_something_really_funny = f"[ ...`{scrolling_visual_effect(mutable[thread_index][0], scroller_max_len)}`... ]"
             observe_win.append(print_something_really_funny)
         # 在前端打印些好玩的东西
         stat_str = ''.join([f'`{mutable[thread_index][2]}`: {obs}\n\n'
@@ -388,11 +389,11 @@ def read_and_clean_pdf_text(fp):
         """
         提取文本块主字体
         """
-        fsize_statiscs = {}
+        fsize_statistics = {}
         for wtf in l['spans']:
-            if wtf['size'] not in fsize_statiscs: fsize_statiscs[wtf['size']] = 0
-            fsize_statiscs[wtf['size']] += len(wtf['text'])
-        return max(fsize_statiscs, key=fsize_statiscs.get)
+            if wtf['size'] not in fsize_statistics: fsize_statistics[wtf['size']] = 0
+            fsize_statistics[wtf['size']] += len(wtf['text'])
+        return max(fsize_statistics, key=fsize_statistics.get)
 
     def ffsize_same(a,b):
         """
@@ -432,11 +433,11 @@ def read_and_clean_pdf_text(fp):
 
         ############################## <第 2 步，获取正文主字体> ##################################
         try:
-            fsize_statiscs = {}
+            fsize_statistics = {}
             for span in meta_span:
-                if span[1] not in fsize_statiscs: fsize_statiscs[span[1]] = 0
-                fsize_statiscs[span[1]] += span[2]
-            main_fsize = max(fsize_statiscs, key=fsize_statiscs.get)
+                if span[1] not in fsize_statistics: fsize_statistics[span[1]] = 0
+                fsize_statistics[span[1]] += span[2]
+            main_fsize = max(fsize_statistics, key=fsize_statistics.get)
             if REMOVE_FOOT_NOTE:
                 give_up_fize_threshold = main_fsize * REMOVE_FOOT_FFSIZE_PERCENT
         except:
@@ -609,9 +610,9 @@ class nougat_interface():
 
 
     def NOUGAT_parse_pdf(self, fp, chatbot, history):
-        from toolbox import update_ui_lastest_msg
+        from toolbox import update_ui_latest_msg
 
-        yield from update_ui_lastest_msg("正在解析论文, 请稍候。进度：正在排队, 等待线程锁...",
+        yield from update_ui_latest_msg("正在解析论文, 请稍候。进度：正在排队, 等待线程锁...",
                                          chatbot=chatbot, history=history, delay=0)
         self.threadLock.acquire()
         import glob, threading, os
@@ -619,7 +620,7 @@ class nougat_interface():
         dst = os.path.join(get_log_folder(plugin_name='nougat'), gen_time_str())
         os.makedirs(dst)
 
-        yield from update_ui_lastest_msg("正在解析论文, 请稍候。进度：正在加载NOUGAT... （提示：首次运行需要花费较长时间下载NOUGAT参数）",
+        yield from update_ui_latest_msg("正在解析论文, 请稍候。进度：正在加载NOUGAT... （提示：首次运行需要花费较长时间下载NOUGAT参数）",
                                          chatbot=chatbot, history=history, delay=0)
         command = ['nougat', '--out', os.path.abspath(dst), os.path.abspath(fp)]
         self.nougat_with_timeout(command, cwd=os.getcwd(), timeout=3600)

crazy_functions/doc_fns/AI_review_doc.py

@@ -0,0 +1,812 @@
+import os
+import time
+from abc import ABC, abstractmethod
+from datetime import datetime
+from docx import Document
+from docx.enum.style import WD_STYLE_TYPE
+from docx.enum.text import WD_PARAGRAPH_ALIGNMENT, WD_LINE_SPACING
+from docx.oxml.ns import qn
+from docx.shared import  Inches, Cm
+from docx.shared import Pt, RGBColor, Inches
+from typing import Dict, List, Tuple
+import markdown
+from crazy_functions.doc_fns.conversation_doc.word_doc import convert_markdown_to_word
+
+
+
+class DocumentFormatter(ABC):
+    """文档格式化基类，定义文档格式化的基本接口"""
+
+    def __init__(self, final_summary: str, file_summaries_map: Dict, failed_files: List[Tuple]):
+        self.final_summary = final_summary
+        self.file_summaries_map = file_summaries_map
+        self.failed_files = failed_files
+
+    @abstractmethod
+    def format_failed_files(self) -> str:
+        """格式化失败文件列表"""
+        pass
+
+    @abstractmethod
+    def format_file_summaries(self) -> str:
+        """格式化文件总结内容"""
+        pass
+
+    @abstractmethod
+    def create_document(self) -> str:
+        """创建完整文档"""
+        pass
+
+
+class WordFormatter(DocumentFormatter):
+    """Word格式文档生成器 - 符合中国政府公文格式规范(GB/T 9704-2012)，并进行了优化"""
+
+    def __init__(self, *args, **kwargs):
+        super().__init__(*args, **kwargs)
+        self.doc = Document()
+        self._setup_document()
+        self._create_styles()
+        # 初始化三级标题编号系统
+        self.numbers = {
+            1: 0,  # 一级标题编号
+            2: 0,  # 二级标题编号
+            3: 0  # 三级标题编号
+        }
+
+    def _setup_document(self):
+        """设置文档基本格式，包括页面设置和页眉"""
+        sections = self.doc.sections
+        for section in sections:
+            # 设置页面大小为A4
+            section.page_width = Cm(21)
+            section.page_height = Cm(29.7)
+            # 设置页边距
+            section.top_margin = Cm(3.7)  # 上边距37mm
+            section.bottom_margin = Cm(3.5)  # 下边距35mm
+            section.left_margin = Cm(2.8)  # 左边距28mm
+            section.right_margin = Cm(2.6)  # 右边距26mm
+            # 设置页眉页脚距离
+            section.header_distance = Cm(2.0)
+            section.footer_distance = Cm(2.0)
+
+            # 添加页眉
+            header = section.header
+            header_para = header.paragraphs[0]
+            header_para.alignment = WD_PARAGRAPH_ALIGNMENT.RIGHT
+            header_run = header_para.add_run("该文档由GPT-academic生成")
+            header_run.font.name = '仿宋'
+            header_run._element.rPr.rFonts.set(qn('w:eastAsia'), '仿宋')
+            header_run.font.size = Pt(9)
+
+    def _create_styles(self):
+        """创建文档样式"""
+        # 创建正文样式
+        style = self.doc.styles.add_style('Normal_Custom', WD_STYLE_TYPE.PARAGRAPH)
+        style.font.name = '仿宋'
+        style._element.rPr.rFonts.set(qn('w:eastAsia'), '仿宋')
+        style.font.size = Pt(14)
+        style.paragraph_format.line_spacing_rule = WD_LINE_SPACING.ONE_POINT_FIVE
+        style.paragraph_format.space_after = Pt(0)
+        style.paragraph_format.first_line_indent = Pt(28)
+
+        # 创建各级标题样式
+        self._create_heading_style('Title_Custom', '方正小标宋简体', 32, WD_PARAGRAPH_ALIGNMENT.CENTER)
+        self._create_heading_style('Heading1_Custom', '黑体', 22, WD_PARAGRAPH_ALIGNMENT.LEFT)
+        self._create_heading_style('Heading2_Custom', '黑体', 18, WD_PARAGRAPH_ALIGNMENT.LEFT)
+        self._create_heading_style('Heading3_Custom', '黑体', 16, WD_PARAGRAPH_ALIGNMENT.LEFT)
+
+    def _create_heading_style(self, style_name: str, font_name: str, font_size: int, alignment):
+        """创建标题样式"""
+        style = self.doc.styles.add_style(style_name, WD_STYLE_TYPE.PARAGRAPH)
+        style.font.name = font_name
+        style._element.rPr.rFonts.set(qn('w:eastAsia'), font_name)
+        style.font.size = Pt(font_size)
+        style.font.bold = True
+        style.paragraph_format.alignment = alignment
+        style.paragraph_format.space_before = Pt(12)
+        style.paragraph_format.space_after = Pt(12)
+        style.paragraph_format.line_spacing_rule = WD_LINE_SPACING.ONE_POINT_FIVE
+        return style
+
+    def _get_heading_number(self, level: int) -> str:
+        """
+        生成标题编号
+
+        Args:
+            level: 标题级别 (0-3)
+
+        Returns:
+            str: 格式化的标题编号
+        """
+        if level == 0:  # 主标题不需要编号
+            return ""
+
+        self.numbers[level] += 1  # 增加当前级别的编号
+
+        # 重置下级标题编号
+        for i in range(level + 1, 4):
+            self.numbers[i] = 0
+
+        # 根据级别返回不同格式的编号
+        if level == 1:
+            return f"{self.numbers[1]}. "
+        elif level == 2:
+            return f"{self.numbers[1]}.{self.numbers[2]} "
+        elif level == 3:
+            return f"{self.numbers[1]}.{self.numbers[2]}.{self.numbers[3]} "
+        return ""
+
+    def _add_heading(self, text: str, level: int):
+        """
+        添加带编号的标题
+
+        Args:
+            text: 标题文本
+            level: 标题级别 (0-3)
+        """
+        style_map = {
+            0: 'Title_Custom',
+            1: 'Heading1_Custom',
+            2: 'Heading2_Custom',
+            3: 'Heading3_Custom'
+        }
+
+        number = self._get_heading_number(level)
+        paragraph = self.doc.add_paragraph(style=style_map[level])
+
+        if number:
+            number_run = paragraph.add_run(number)
+            font_size = 22 if level == 1 else (18 if level == 2 else 16)
+            self._get_run_style(number_run, '黑体', font_size, True)
+
+        text_run = paragraph.add_run(text)
+        font_size = 32 if level == 0 else (22 if level == 1 else (18 if level == 2 else 16))
+        self._get_run_style(text_run, '黑体', font_size, True)
+
+        # 主标题添加日期
+        if level == 0:
+            date_paragraph = self.doc.add_paragraph()
+            date_paragraph.alignment = WD_PARAGRAPH_ALIGNMENT.CENTER
+            date_run = date_paragraph.add_run(datetime.now().strftime('%Y年%m月%d日'))
+            self._get_run_style(date_run, '仿宋', 16, False)
+
+        return paragraph
+
+    def _get_run_style(self, run, font_name: str, font_size: int, bold: bool = False):
+        """设置文本运行对象的样式"""
+        run.font.name = font_name
+        run._element.rPr.rFonts.set(qn('w:eastAsia'), font_name)
+        run.font.size = Pt(font_size)
+        run.font.bold = bold
+
+    def format_failed_files(self) -> str:
+        """格式化失败文件列表"""
+        result = []
+        if not self.failed_files:
+            return "\n".join(result)
+
+        result.append("处理失败文件:")
+        for fp, reason in self.failed_files:
+            result.append(f"• {os.path.basename(fp)}: {reason}")
+
+        self._add_heading("处理失败文件", 1)
+        for fp, reason in self.failed_files:
+            self._add_content(f"• {os.path.basename(fp)}: {reason}", indent=False)
+        self.doc.add_paragraph()
+
+        return "\n".join(result)
+
+    def _add_content(self, text: str, indent: bool = True):
+        """添加正文内容，使用convert_markdown_to_word处理文本"""
+        # 使用convert_markdown_to_word处理markdown文本
+        processed_text = convert_markdown_to_word(text)
+        paragraph = self.doc.add_paragraph(processed_text, style='Normal_Custom')
+        if not indent:
+            paragraph.paragraph_format.first_line_indent = Pt(0)
+        return paragraph
+
+    def format_file_summaries(self) -> str:
+        """
+        格式化文件总结内容，确保正确的标题层级并处理markdown文本
+        """
+        result = []
+        # 首先对文件路径进行分组整理
+        file_groups = {}
+        for path in sorted(self.file_summaries_map.keys()):
+            dir_path = os.path.dirname(path)
+            if dir_path not in file_groups:
+                file_groups[dir_path] = []
+            file_groups[dir_path].append(path)
+
+        # 处理没有目录的文件
+        root_files = file_groups.get("", [])
+        if root_files:
+            for path in sorted(root_files):
+                file_name = os.path.basename(path)
+                result.append(f"\n📄 {file_name}")
+                result.append(self.file_summaries_map[path])
+                # 无目录的文件作为二级标题
+                self._add_heading(f"📄 {file_name}", 2)
+                # 使用convert_markdown_to_word处理文件内容
+                self._add_content(convert_markdown_to_word(self.file_summaries_map[path]))
+                self.doc.add_paragraph()
+
+        # 处理有目录的文件
+        for dir_path in sorted(file_groups.keys()):
+            if dir_path == "":  # 跳过已处理的根目录文件
+                continue
+
+            # 添加目录作为二级标题
+            result.append(f"\n📁 {dir_path}")
+            self._add_heading(f"📁 {dir_path}", 2)
+
+            # 该目录下的所有文件作为三级标题
+            for path in sorted(file_groups[dir_path]):
+                file_name = os.path.basename(path)
+                result.append(f"\n📄 {file_name}")
+                result.append(self.file_summaries_map[path])
+
+                # 添加文件名作为三级标题
+                self._add_heading(f"📄 {file_name}", 3)
+                # 使用convert_markdown_to_word处理文件内容
+                self._add_content(convert_markdown_to_word(self.file_summaries_map[path]))
+                self.doc.add_paragraph()
+
+        return "\n".join(result)
+
+
+    def create_document(self):
+        """创建完整Word文档并返回文档对象"""
+        # 重置所有编号
+        for level in self.numbers:
+            self.numbers[level] = 0
+
+        # 添加主标题
+        self._add_heading("文档总结报告", 0)
+        self.doc.add_paragraph()
+
+        # 添加总体摘要，使用convert_markdown_to_word处理
+        self._add_heading("总体摘要", 1)
+        self._add_content(convert_markdown_to_word(self.final_summary))
+        self.doc.add_paragraph()
+
+        # 添加失败文件列表（如果有）
+        if self.failed_files:
+            self.format_failed_files()
+
+        # 添加文件详细总结
+        self._add_heading("各文件详细总结", 1)
+        self.format_file_summaries()
+
+        return self.doc
+
+    def save_as_pdf(self, word_path, pdf_path=None):
+        """将生成的Word文档转换为PDF
+        
+        参数:
+            word_path: Word文档的路径
+            pdf_path: 可选，PDF文件的输出路径。如果未指定，将使用与Word文档相同的名称和位置
+            
+        返回:
+            生成的PDF文件路径，如果转换失败则返回None
+        """
+        from crazy_functions.doc_fns.conversation_doc.word2pdf import WordToPdfConverter
+        try:
+            pdf_path = WordToPdfConverter.convert_to_pdf(word_path, pdf_path)
+            return pdf_path
+        except Exception as e:
+            print(f"PDF转换失败: {str(e)}")
+            return None
+
+
+class MarkdownFormatter(DocumentFormatter):
+    """Markdown格式文档生成器"""
+
+    def format_failed_files(self) -> str:
+        if not self.failed_files:
+            return ""
+
+        formatted_text = ["\n## ⚠️ 处理失败的文件"]
+        for fp, reason in self.failed_files:
+            formatted_text.append(f"- {os.path.basename(fp)}: {reason}")
+        formatted_text.append("\n---")
+        return "\n".join(formatted_text)
+
+    def format_file_summaries(self) -> str:
+        formatted_text = []
+        sorted_paths = sorted(self.file_summaries_map.keys())
+        current_dir = ""
+
+        for path in sorted_paths:
+            dir_path = os.path.dirname(path)
+            if dir_path != current_dir:
+                if dir_path:
+                    formatted_text.append(f"\n## 📁 {dir_path}")
+                current_dir = dir_path
+
+            file_name = os.path.basename(path)
+            formatted_text.append(f"\n### 📄 {file_name}")
+            formatted_text.append(self.file_summaries_map[path])
+            formatted_text.append("\n---")
+
+        return "\n".join(formatted_text)
+
+    def create_document(self) -> str:
+        document = [
+            "# 📑 文档总结报告",
+            "\n## 总体摘要",
+            self.final_summary
+        ]
+
+        if self.failed_files:
+            document.append(self.format_failed_files())
+
+        document.extend([
+            "\n# 📚 各文件详细总结",
+            self.format_file_summaries()
+        ])
+
+        return "\n".join(document)
+
+
+
+class HtmlFormatter(DocumentFormatter):
+    """HTML格式文档生成器 - 优化版"""
+
+    def __init__(self, *args, **kwargs):
+        super().__init__(*args, **kwargs)
+        self.md = markdown.Markdown(extensions=['extra','codehilite', 'tables','nl2br'])
+        self.css_styles = """
+        @keyframes fadeIn {
+            from { opacity: 0; transform: translateY(20px); }
+            to { opacity: 1; transform: translateY(0); }
+        }
+
+        @keyframes slideIn {
+            from { transform: translateX(-20px); opacity: 0; }
+            to { transform: translateX(0); opacity: 1; }
+        }
+
+        @keyframes pulse {
+            0% { transform: scale(1); }
+            50% { transform: scale(1.05); }
+            100% { transform: scale(1); }
+        }
+
+        :root {
+            /* Enhanced color palette */
+            --primary-color: #2563eb;
+            --primary-light: #eff6ff;
+            --secondary-color: #1e293b;
+            --background-color: #f8fafc;
+            --text-color: #334155;
+            --text-light: #64748b;
+            --border-color: #e2e8f0;
+            --error-color: #ef4444;
+            --error-light: #fef2f2;
+            --success-color: #22c55e;
+            --warning-color: #f59e0b;
+            --card-shadow: 0 4px 6px -1px rgb(0 0 0 / 0.1), 0 2px 4px -2px rgb(0 0 0 / 0.1);
+            --hover-shadow: 0 20px 25px -5px rgb(0 0 0 / 0.1), 0 8px 10px -6px rgb(0 0 0 / 0.1);
+            
+            /* Typography */
+            --heading-font: "Plus Jakarta Sans", system-ui, sans-serif;
+            --body-font: "Inter", system-ui, sans-serif;
+        }
+
+        body {
+            font-family: var(--body-font);
+            line-height: 1.8;
+            max-width: 1200px;
+            margin: 0 auto;
+            padding: 2rem;
+            color: var(--text-color);
+            background-color: var(--background-color);
+            font-size: 16px;
+            -webkit-font-smoothing: antialiased;
+        }
+
+        .container {
+            background: white;
+            padding: 3rem;
+            border-radius: 24px;
+            box-shadow: var(--card-shadow);
+            transition: all 0.4s cubic-bezier(0.4, 0, 0.2, 1);
+            animation: fadeIn 0.6s ease-out;
+            border: 1px solid var(--border-color);
+        }
+
+        .container:hover {
+            box-shadow: var(--hover-shadow);
+            transform: translateY(-2px);
+        }
+
+        h1, h2, h3 {
+            font-family: var(--heading-font);
+            font-weight: 600;
+        }
+
+        h1 {
+            color: var(--primary-color);
+            font-size: 2.8em;
+            text-align: center;
+            margin: 2rem 0 3rem;
+            padding-bottom: 1.5rem;
+            border-bottom: 3px solid var(--primary-color);
+            letter-spacing: -0.03em;
+            position: relative;
+            display: flex;
+            align-items: center;
+            justify-content: center;
+            gap: 1rem;
+        }
+
+        h1::after {
+            content: '';
+            position: absolute;
+            bottom: -3px;
+            left: 50%;
+            transform: translateX(-50%);
+            width: 120px;
+            height: 3px;
+            background: linear-gradient(90deg, var(--primary-color), var(--primary-light));
+            border-radius: 3px;
+            transition: width 0.3s ease;
+        }
+
+        h1:hover::after {
+            width: 180px;
+        }
+
+        h2 {
+            color: var(--secondary-color);
+            font-size: 1.9em;
+            margin: 2.5rem 0 1.5rem;
+            padding-left: 1.2rem;
+            border-left: 4px solid var(--primary-color);
+            letter-spacing: -0.02em;
+            display: flex;
+            align-items: center;
+            gap: 1rem;
+            transition: all 0.3s ease;
+        }
+
+        h2:hover {
+            color: var(--primary-color);
+            transform: translateX(5px);
+        }
+
+        h3 {
+            color: var(--text-color);
+            font-size: 1.5em;
+            margin: 2rem 0 1rem;
+            padding-bottom: 0.8rem;
+            border-bottom: 2px solid var(--border-color);
+            transition: all 0.3s ease;
+            display: flex;
+            align-items: center;
+            gap: 0.8rem;
+        }
+
+        h3:hover {
+            color: var(--primary-color);
+            border-bottom-color: var(--primary-color);
+        }
+
+        .summary {
+            background: var(--primary-light);
+            padding: 2.5rem;
+            border-radius: 16px;
+            margin: 2.5rem 0;
+            box-shadow: 0 4px 6px -1px rgba(37, 99, 235, 0.1);
+            position: relative;
+            overflow: hidden;
+            transition: transform 0.3s ease, box-shadow 0.3s ease;
+            animation: slideIn 0.5s ease-out;
+        }
+
+        .summary:hover {
+            transform: translateY(-3px);
+            box-shadow: 0 8px 12px -2px rgba(37, 99, 235, 0.15);
+        }
+
+        .summary::before {
+            content: '';
+            position: absolute;
+            top: 0;
+            left: 0;
+            width: 4px;
+            height: 100%;
+            background: linear-gradient(to bottom, var(--primary-color), rgba(37, 99, 235, 0.6));
+        }
+
+        .summary p {
+            margin: 1.2rem 0;
+            line-height: 1.9;
+            color: var(--text-color);
+            transition: color 0.3s ease;
+        }
+
+        .summary:hover p {
+            color: var(--secondary-color);
+        }
+
+        .details {
+            margin-top: 3.5rem;
+            padding-top: 2.5rem;
+            border-top: 2px dashed var(--border-color);
+            animation: fadeIn 0.8s ease-out;
+        }
+
+        .failed-files {
+            background: var(--error-light);
+            padding: 2rem;
+            border-radius: 16px;
+            margin: 3rem 0;
+            border-left: 4px solid var(--error-color);
+            position: relative;
+            transition: all 0.3s ease;
+            animation: slideIn 0.5s ease-out;
+        }
+
+        .failed-files:hover {
+            transform: translateX(5px);
+            box-shadow: 0 8px 15px -3px rgba(239, 68, 68, 0.1);
+        }
+
+        .failed-files h2 {
+            color: var(--error-color);
+            border-left: none;
+            padding-left: 0;
+        }
+
+        .failed-files ul {
+            margin: 1.8rem 0;
+            padding-left: 1.2rem;
+            list-style-type: none;
+        }
+
+        .failed-files li {
+            margin: 1.2rem 0;
+            padding: 1.2rem 1.8rem;
+            background: rgba(239, 68, 68, 0.08);
+            border-radius: 12px;
+            transition: all 0.3s cubic-bezier(0.4, 0, 0.2, 1);
+        }
+
+        .failed-files li:hover {
+            transform: translateX(8px);
+            background: rgba(239, 68, 68, 0.12);
+        }
+
+        .directory-section {
+            margin: 3.5rem 0;
+            padding: 2rem;
+            background: var(--background-color);
+            border-radius: 16px;
+            position: relative;
+            transition: all 0.3s ease;
+            animation: fadeIn 0.6s ease-out;
+        }
+
+        .directory-section:hover {
+            background: white;
+            box-shadow: var(--card-shadow);
+        }
+
+        .file-summary {
+            background: white;
+            padding: 2rem;
+            margin: 1.8rem 0;
+            border-radius: 16px;
+            box-shadow: var(--card-shadow);
+            border-left: 4px solid var(--border-color);
+            transition: all 0.4s cubic-bezier(0.4, 0, 0.2, 1);
+            position: relative;
+            overflow: hidden;
+        }
+
+        .file-summary:hover {
+            border-left-color: var(--primary-color);
+            transform: translateX(8px) translateY(-2px);
+            box-shadow: var(--hover-shadow);
+        }
+
+        .file-summary {
+            background: white;
+            padding: 2rem;
+            margin: 1.8rem 0;
+            border-radius: 16px;
+            box-shadow: var(--card-shadow);
+            border-left: 4px solid var(--border-color);
+            transition: all 0.4s cubic-bezier(0.4, 0, 0.2, 1);
+            position: relative;
+        }
+
+        .file-summary:hover {
+            border-left-color: var(--primary-color);
+            transform: translateX(8px) translateY(-2px);
+            box-shadow: var(--hover-shadow);
+        }
+
+        .icon {
+            display: inline-flex;
+            align-items: center;
+            justify-content: center;
+            width: 32px;
+            height: 32px;
+            border-radius: 8px;
+            background: var(--primary-light);
+            color: var(--primary-color);
+            font-size: 1.2em;
+            transition: all 0.3s ease;
+        }
+
+        .file-summary:hover .icon,
+        .directory-section:hover .icon {
+            transform: scale(1.1);
+            background: var(--primary-color);
+            color: white;
+        }
+
+        /* Smooth scrolling */
+        html {
+            scroll-behavior: smooth;
+        }
+
+        /* Selection style */
+        ::selection {
+            background: var(--primary-light);
+            color: var(--primary-color);
+        }
+
+        /* Print styles */
+        @media print {
+            body {
+                background: white;
+            }
+            .container {
+                box-shadow: none;
+                padding: 0;
+            }
+            .file-summary, .failed-files {
+                break-inside: avoid;
+                box-shadow: none;
+            }
+            .icon {
+                display: none;
+            }
+        }
+
+        /* Responsive design */
+        @media (max-width: 768px) {
+            body {
+                padding: 1rem;
+                font-size: 15px;
+            }
+            
+            .container {
+                padding: 1.5rem;
+            }
+
+            h1 {
+                font-size: 2.2em;
+                margin: 1.5rem 0 2rem;
+            }
+
+            h2 {
+                font-size: 1.7em;
+            }
+
+            h3 {
+                font-size: 1.4em;
+            }
+
+            .summary, .failed-files, .directory-section {
+                padding: 1.5rem;
+            }
+
+            .file-summary {
+                padding: 1.2rem;
+            }
+
+            .icon {
+                width: 28px;
+                height: 28px;
+            }
+        }
+
+        /* Dark mode support */
+        @media (prefers-color-scheme: dark) {
+            :root {
+                --primary-light: rgba(37, 99, 235, 0.15);
+                --background-color: #0f172a;
+                --text-color: #e2e8f0;
+                --text-light: #94a3b8;
+                --border-color: #1e293b;
+                --error-light: rgba(239, 68, 68, 0.15);
+            }
+
+            .container, .file-summary {
+                background: #1e293b;
+            }
+
+            .directory-section {
+                background: #0f172a;
+            }
+
+            .directory-section:hover {
+                background: #1e293b;
+            }
+        }
+        """
+
+    def format_failed_files(self) -> str:
+        if not self.failed_files:
+            return ""
+
+        failed_files_html = ['<div class="failed-files">']
+        failed_files_html.append('<h2><span class="icon">⚠️</span> 处理失败的文件</h2>')
+        failed_files_html.append("<ul>")
+        for fp, reason in self.failed_files:
+            failed_files_html.append(
+                f'<li><strong>📄 {os.path.basename(fp)}</strong><br><span style="color: var(--text-light)">{reason}</span></li>'
+            )
+        failed_files_html.append("</ul></div>")
+        return "\n".join(failed_files_html)
+
+    def format_file_summaries(self) -> str:
+        formatted_html = []
+        sorted_paths = sorted(self.file_summaries_map.keys())
+        current_dir = ""
+
+        for path in sorted_paths:
+            dir_path = os.path.dirname(path)
+            if dir_path != current_dir:
+                if dir_path:
+                    formatted_html.append('<div class="directory-section">')
+                    formatted_html.append(f'<h2><span class="icon">📁</span> {dir_path}</h2>')
+                    formatted_html.append('</div>')
+                current_dir = dir_path
+
+            file_name = os.path.basename(path)
+            formatted_html.append('<div class="file-summary">')
+            formatted_html.append(f'<h3><span class="icon">📄</span> {file_name}</h3>')
+            formatted_html.append(self.md.convert(self.file_summaries_map[path]))
+            formatted_html.append('</div>')
+
+        return "\n".join(formatted_html)
+
+    def create_document(self) -> str:
+        """生成HTML文档
+        Returns:
+            str: 完整的HTML文档字符串
+        """
+        return f"""
+        <!DOCTYPE html>
+        <html lang="zh-CN">
+        <head>
+            <meta charset="utf-8">
+            <meta name="viewport" content="width=device-width, initial-scale=1">
+            <title>文档总结报告</title>
+            <link href="https://cdnjs.cloudflare.com/ajax/libs/inter/3.19.3/inter.css" rel="stylesheet">
+            <link href="https://fonts.googleapis.com/css2?family=Plus+Jakarta+Sans:wght@400;600&display=swap" rel="stylesheet">
+            <style>{self.css_styles}</style>
+        </head>
+        <body>
+            <div class="container">
+                <h1><span class="icon">📑</span> 文档总结报告</h1>
+                <div class="summary">
+                    <h2><span class="icon">📋</span> 总体摘要</h2>
+                    <p>{self.md.convert(self.final_summary)}</p>
+                </div>
+                {self.format_failed_files()}
+                <div class="details">
+                    <h2><span class="icon">📚</span> 各文件详细总结</h2>
+                    {self.format_file_summaries()}
+                </div>
+            </div>
+
+        </body>
+        </html>
+        """

crazy_functions/doc_fns/batch_file_query_doc.py

@@ -9,6 +9,9 @@ from docx.oxml.ns import qn
 from docx.shared import  Inches, Cm
 from docx.shared import Pt, RGBColor, Inches
 from typing import Dict, List, Tuple
+import markdown
+from crazy_functions.doc_fns.conversation_doc.word_doc import  convert_markdown_to_word
+
 
 
 class DocumentFormatter(ABC):
@@ -194,26 +197,17 @@ class WordFormatter(DocumentFormatter):
         return "\n".join(result)
 
     def _add_content(self, text: str, indent: bool = True):
-        """添加正文内容"""
-        paragraph = self.doc.add_paragraph(text, style='Normal_Custom')
+        """添加正文内容，使用convert_markdown_to_word处理文本"""
+        # 使用convert_markdown_to_word处理markdown文本
+        processed_text = convert_markdown_to_word(text)
+        paragraph = self.doc.add_paragraph(processed_text, style='Normal_Custom')
         if not indent:
             paragraph.paragraph_format.first_line_indent = Pt(0)
         return paragraph
 
     def format_file_summaries(self) -> str:
         """
-        格式化文件总结内容，确保正确的标题层级
-
-        返回:
-            str: 格式化后的文件总结字符串
-
-        标题层级规则:
-        1. 一级标题为"各文件详细总结"
-        2. 如果文件有目录路径:
-           - 目录路径作为二级标题 (2.1, 2.2 等)
-           - 该目录下所有文件作为三级标题 (2.1.1, 2.1.2 等)
-        3. 如果文件没有目录路径:
-           - 文件直接作为二级标题 (2.1, 2.2 等)
+        格式化文件总结内容，确保正确的标题层级并处理markdown文本
         """
         result = []
         # 首先对文件路径进行分组整理
@@ -233,7 +227,8 @@ class WordFormatter(DocumentFormatter):
                 result.append(self.file_summaries_map[path])
                 # 无目录的文件作为二级标题
                 self._add_heading(f"📄 {file_name}", 2)
-                self._add_content(self.file_summaries_map[path])
+                # 使用convert_markdown_to_word处理文件内容
+                self._add_content(convert_markdown_to_word(self.file_summaries_map[path]))
                 self.doc.add_paragraph()
 
         # 处理有目录的文件
@@ -253,7 +248,8 @@ class WordFormatter(DocumentFormatter):
 
                 # 添加文件名作为三级标题
                 self._add_heading(f"📄 {file_name}", 3)
-                self._add_content(self.file_summaries_map[path])
+                # 使用convert_markdown_to_word处理文件内容
+                self._add_content(convert_markdown_to_word(self.file_summaries_map[path]))
                 self.doc.add_paragraph()
 
         return "\n".join(result)
@@ -269,9 +265,9 @@ class WordFormatter(DocumentFormatter):
         self._add_heading("文档总结报告", 0)
         self.doc.add_paragraph()
 
-        # 添加总体摘要
+        # 添加总体摘要，使用convert_markdown_to_word处理
         self._add_heading("总体摘要", 1)
-        self._add_content(self.final_summary)
+        self._add_content(convert_markdown_to_word(self.final_summary))
         self.doc.add_paragraph()
 
         # 添加失败文件列表（如果有）
@@ -284,6 +280,24 @@ class WordFormatter(DocumentFormatter):
 
         return self.doc
 
+    def save_as_pdf(self, word_path, pdf_path=None):
+        """将生成的Word文档转换为PDF
+        
+        参数:
+            word_path: Word文档的路径
+            pdf_path: 可选，PDF文件的输出路径。如果未指定，将使用与Word文档相同的名称和位置
+            
+        返回:
+            生成的PDF文件路径，如果转换失败则返回None
+        """
+        from crazy_functions.doc_fns.conversation_doc.word2pdf import WordToPdfConverter
+        try:
+            pdf_path = WordToPdfConverter.convert_to_pdf(word_path, pdf_path)
+            return pdf_path
+        except Exception as e:
+            print(f"PDF转换失败: {str(e)}")
+            return None
+
 
 class MarkdownFormatter(DocumentFormatter):
     """Markdown格式文档生成器"""
@@ -335,61 +349,395 @@ class MarkdownFormatter(DocumentFormatter):
         return "\n".join(document)
 
 
+
 class HtmlFormatter(DocumentFormatter):
-    """HTML格式文档生成器"""
+    """HTML格式文档生成器 - 优化版"""
 
     def __init__(self, *args, **kwargs):
         super().__init__(*args, **kwargs)
+        self.md = markdown.Markdown(extensions=['extra','codehilite', 'tables','nl2br'])
         self.css_styles = """
+        @keyframes fadeIn {
+            from { opacity: 0; transform: translateY(20px); }
+            to { opacity: 1; transform: translateY(0); }
+        }
+
+        @keyframes slideIn {
+            from { transform: translateX(-20px); opacity: 0; }
+            to { transform: translateX(0); opacity: 1; }
+        }
+
+        @keyframes pulse {
+            0% { transform: scale(1); }
+            50% { transform: scale(1.05); }
+            100% { transform: scale(1); }
+        }
+
+        :root {
+            /* Enhanced color palette */
+            --primary-color: #2563eb;
+            --primary-light: #eff6ff;
+            --secondary-color: #1e293b;
+            --background-color: #f8fafc;
+            --text-color: #334155;
+            --text-light: #64748b;
+            --border-color: #e2e8f0;
+            --error-color: #ef4444;
+            --error-light: #fef2f2;
+            --success-color: #22c55e;
+            --warning-color: #f59e0b;
+            --card-shadow: 0 4px 6px -1px rgb(0 0 0 / 0.1), 0 2px 4px -2px rgb(0 0 0 / 0.1);
+            --hover-shadow: 0 20px 25px -5px rgb(0 0 0 / 0.1), 0 8px 10px -6px rgb(0 0 0 / 0.1);
+            
+            /* Typography */
+            --heading-font: "Plus Jakarta Sans", system-ui, sans-serif;
+            --body-font: "Inter", system-ui, sans-serif;
+        }
+
         body {
-            font-family: "Microsoft YaHei", Arial, sans-serif;
-            line-height: 1.6;
-            max-width: 1000px;
+            font-family: var(--body-font);
+            line-height: 1.8;
+            max-width: 1200px;
             margin: 0 auto;
-            padding: 20px;
-            color: #333;
+            padding: 2rem;
+            color: var(--text-color);
+            background-color: var(--background-color);
+            font-size: 16px;
+            -webkit-font-smoothing: antialiased;
         }
+
+        .container {
+            background: white;
+            padding: 3rem;
+            border-radius: 24px;
+            box-shadow: var(--card-shadow);
+            transition: all 0.4s cubic-bezier(0.4, 0, 0.2, 1);
+            animation: fadeIn 0.6s ease-out;
+            border: 1px solid var(--border-color);
+        }
+
+        .container:hover {
+            box-shadow: var(--hover-shadow);
+            transform: translateY(-2px);
+        }
+
+        h1, h2, h3 {
+            font-family: var(--heading-font);
+            font-weight: 600;
+        }
+
         h1 {
-            color: #2c3e50;
-            border-bottom: 2px solid #eee;
-            padding-bottom: 10px;
-            font-size: 24px;
+            color: var(--primary-color);
+            font-size: 2.8em;
             text-align: center;
+            margin: 2rem 0 3rem;
+            padding-bottom: 1.5rem;
+            border-bottom: 3px solid var(--primary-color);
+            letter-spacing: -0.03em;
+            position: relative;
+            display: flex;
+            align-items: center;
+            justify-content: center;
+            gap: 1rem;
         }
+
+        h1::after {
+            content: '';
+            position: absolute;
+            bottom: -3px;
+            left: 50%;
+            transform: translateX(-50%);
+            width: 120px;
+            height: 3px;
+            background: linear-gradient(90deg, var(--primary-color), var(--primary-light));
+            border-radius: 3px;
+            transition: width 0.3s ease;
+        }
+
+        h1:hover::after {
+            width: 180px;
+        }
+
         h2 {
-            color: #34495e;
-            margin-top: 30px;
-            font-size: 20px;
-            border-left: 4px solid #3498db;
-            padding-left: 10px;
+            color: var(--secondary-color);
+            font-size: 1.9em;
+            margin: 2.5rem 0 1.5rem;
+            padding-left: 1.2rem;
+            border-left: 4px solid var(--primary-color);
+            letter-spacing: -0.02em;
+            display: flex;
+            align-items: center;
+            gap: 1rem;
+            transition: all 0.3s ease;
         }
+
+        h2:hover {
+            color: var(--primary-color);
+            transform: translateX(5px);
+        }
+
         h3 {
-            color: #2c3e50;
-            font-size: 18px;
-            margin-top: 20px;
+            color: var(--text-color);
+            font-size: 1.5em;
+            margin: 2rem 0 1rem;
+            padding-bottom: 0.8rem;
+            border-bottom: 2px solid var(--border-color);
+            transition: all 0.3s ease;
+            display: flex;
+            align-items: center;
+            gap: 0.8rem;
         }
+
+        h3:hover {
+            color: var(--primary-color);
+            border-bottom-color: var(--primary-color);
+        }
+
         .summary {
-            background-color: #f8f9fa;
-            padding: 20px;
-            border-radius: 5px;
-            margin: 20px 0;
-            box-shadow: 0 2px 4px rgba(0,0,0,0.1);
+            background: var(--primary-light);
+            padding: 2.5rem;
+            border-radius: 16px;
+            margin: 2.5rem 0;
+            box-shadow: 0 4px 6px -1px rgba(37, 99, 235, 0.1);
+            position: relative;
+            overflow: hidden;
+            transition: transform 0.3s ease, box-shadow 0.3s ease;
+            animation: slideIn 0.5s ease-out;
         }
+
+        .summary:hover {
+            transform: translateY(-3px);
+            box-shadow: 0 8px 12px -2px rgba(37, 99, 235, 0.15);
+        }
+
+        .summary::before {
+            content: '';
+            position: absolute;
+            top: 0;
+            left: 0;
+            width: 4px;
+            height: 100%;
+            background: linear-gradient(to bottom, var(--primary-color), rgba(37, 99, 235, 0.6));
+        }
+
+        .summary p {
+            margin: 1.2rem 0;
+            line-height: 1.9;
+            color: var(--text-color);
+            transition: color 0.3s ease;
+        }
+
+        .summary:hover p {
+            color: var(--secondary-color);
+        }
+
         .details {
-            margin-top: 40px;
+            margin-top: 3.5rem;
+            padding-top: 2.5rem;
+            border-top: 2px dashed var(--border-color);
+            animation: fadeIn 0.8s ease-out;
         }
+
         .failed-files {
-            background-color: #fff3f3;
-            padding: 15px;
-            border-left: 4px solid #e74c3c;
-            margin: 20px 0;
+            background: var(--error-light);
+            padding: 2rem;
+            border-radius: 16px;
+            margin: 3rem 0;
+            border-left: 4px solid var(--error-color);
+            position: relative;
+            transition: all 0.3s ease;
+            animation: slideIn 0.5s ease-out;
         }
+
+        .failed-files:hover {
+            transform: translateX(5px);
+            box-shadow: 0 8px 15px -3px rgba(239, 68, 68, 0.1);
+        }
+
+        .failed-files h2 {
+            color: var(--error-color);
+            border-left: none;
+            padding-left: 0;
+        }
+
+        .failed-files ul {
+            margin: 1.8rem 0;
+            padding-left: 1.2rem;
+            list-style-type: none;
+        }
+
+        .failed-files li {
+            margin: 1.2rem 0;
+            padding: 1.2rem 1.8rem;
+            background: rgba(239, 68, 68, 0.08);
+            border-radius: 12px;
+            transition: all 0.3s cubic-bezier(0.4, 0, 0.2, 1);
+        }
+
+        .failed-files li:hover {
+            transform: translateX(8px);
+            background: rgba(239, 68, 68, 0.12);
+        }
+
+        .directory-section {
+            margin: 3.5rem 0;
+            padding: 2rem;
+            background: var(--background-color);
+            border-radius: 16px;
+            position: relative;
+            transition: all 0.3s ease;
+            animation: fadeIn 0.6s ease-out;
+        }
+
+        .directory-section:hover {
+            background: white;
+            box-shadow: var(--card-shadow);
+        }
+
         .file-summary {
-            background-color: #fff;
-            padding: 15px;
-            margin: 15px 0;
-            border-radius: 4px;
-            box-shadow: 0 1px 3px rgba(0,0,0,0.1);
+            background: white;
+            padding: 2rem;
+            margin: 1.8rem 0;
+            border-radius: 16px;
+            box-shadow: var(--card-shadow);
+            border-left: 4px solid var(--border-color);
+            transition: all 0.4s cubic-bezier(0.4, 0, 0.2, 1);
+            position: relative;
+            overflow: hidden;
+        }
+
+        .file-summary:hover {
+            border-left-color: var(--primary-color);
+            transform: translateX(8px) translateY(-2px);
+            box-shadow: var(--hover-shadow);
+        }
+
+        .file-summary {
+            background: white;
+            padding: 2rem;
+            margin: 1.8rem 0;
+            border-radius: 16px;
+            box-shadow: var(--card-shadow);
+            border-left: 4px solid var(--border-color);
+            transition: all 0.4s cubic-bezier(0.4, 0, 0.2, 1);
+            position: relative;
+        }
+
+        .file-summary:hover {
+            border-left-color: var(--primary-color);
+            transform: translateX(8px) translateY(-2px);
+            box-shadow: var(--hover-shadow);
+        }
+
+        .icon {
+            display: inline-flex;
+            align-items: center;
+            justify-content: center;
+            width: 32px;
+            height: 32px;
+            border-radius: 8px;
+            background: var(--primary-light);
+            color: var(--primary-color);
+            font-size: 1.2em;
+            transition: all 0.3s ease;
+        }
+
+        .file-summary:hover .icon,
+        .directory-section:hover .icon {
+            transform: scale(1.1);
+            background: var(--primary-color);
+            color: white;
+        }
+
+        /* Smooth scrolling */
+        html {
+            scroll-behavior: smooth;
+        }
+
+        /* Selection style */
+        ::selection {
+            background: var(--primary-light);
+            color: var(--primary-color);
+        }
+
+        /* Print styles */
+        @media print {
+            body {
+                background: white;
+            }
+            .container {
+                box-shadow: none;
+                padding: 0;
+            }
+            .file-summary, .failed-files {
+                break-inside: avoid;
+                box-shadow: none;
+            }
+            .icon {
+                display: none;
+            }
+        }
+
+        /* Responsive design */
+        @media (max-width: 768px) {
+            body {
+                padding: 1rem;
+                font-size: 15px;
+            }
+            
+            .container {
+                padding: 1.5rem;
+            }
+
+            h1 {
+                font-size: 2.2em;
+                margin: 1.5rem 0 2rem;
+            }
+
+            h2 {
+                font-size: 1.7em;
+            }
+
+            h3 {
+                font-size: 1.4em;
+            }
+
+            .summary, .failed-files, .directory-section {
+                padding: 1.5rem;
+            }
+
+            .file-summary {
+                padding: 1.2rem;
+            }
+
+            .icon {
+                width: 28px;
+                height: 28px;
+            }
+        }
+
+        /* Dark mode support */
+        @media (prefers-color-scheme: dark) {
+            :root {
+                --primary-light: rgba(37, 99, 235, 0.15);
+                --background-color: #0f172a;
+                --text-color: #e2e8f0;
+                --text-light: #94a3b8;
+                --border-color: #1e293b;
+                --error-light: rgba(239, 68, 68, 0.15);
+            }
+
+            .container, .file-summary {
+                background: #1e293b;
+            }
+
+            .directory-section {
+                background: #0f172a;
+            }
+
+            .directory-section:hover {
+                background: #1e293b;
+            }
         }
         """
 
@@ -398,10 +746,12 @@ class HtmlFormatter(DocumentFormatter):
             return ""
 
         failed_files_html = ['<div class="failed-files">']
-        failed_files_html.append("<h2>⚠️ 处理失败的文件</h2>")
+        failed_files_html.append('<h2><span class="icon">⚠️</span> 处理失败的文件</h2>')
         failed_files_html.append("<ul>")
         for fp, reason in self.failed_files:
-            failed_files_html.append(f"<li><strong>{os.path.basename(fp)}:</strong> {reason}</li>")
+            failed_files_html.append(
+                f'<li><strong>📄 {os.path.basename(fp)}</strong><br><span style="color: var(--text-light)">{reason}</span></li>'
+            )
         failed_files_html.append("</ul></div>")
         return "\n".join(failed_files_html)
 
@@ -414,37 +764,49 @@ class HtmlFormatter(DocumentFormatter):
             dir_path = os.path.dirname(path)
             if dir_path != current_dir:
                 if dir_path:
-                    formatted_html.append(f'<h2>📁 {dir_path}</h2>')
+                    formatted_html.append('<div class="directory-section">')
+                    formatted_html.append(f'<h2><span class="icon">📁</span> {dir_path}</h2>')
+                    formatted_html.append('</div>')
                 current_dir = dir_path
 
             file_name = os.path.basename(path)
             formatted_html.append('<div class="file-summary">')
-            formatted_html.append(f'<h3>📄 {file_name}</h3>')
-            formatted_html.append(f'<p>{self.file_summaries_map[path]}</p>')
+            formatted_html.append(f'<h3><span class="icon">📄</span> {file_name}</h3>')
+            formatted_html.append(self.md.convert(self.file_summaries_map[path]))
             formatted_html.append('</div>')
 
         return "\n".join(formatted_html)
 
     def create_document(self) -> str:
+        """生成HTML文档
+        Returns:
+            str: 完整的HTML文档字符串
+        """
         return f"""
         <!DOCTYPE html>
-        <html>
+        <html lang="zh-CN">
         <head>
-            <meta charset='utf-8'>
+            <meta charset="utf-8">
+            <meta name="viewport" content="width=device-width, initial-scale=1">
             <title>文档总结报告</title>
+            <link href="https://cdnjs.cloudflare.com/ajax/libs/inter/3.19.3/inter.css" rel="stylesheet">
+            <link href="https://fonts.googleapis.com/css2?family=Plus+Jakarta+Sans:wght@400;600&display=swap" rel="stylesheet">
             <style>{self.css_styles}</style>
         </head>
         <body>
-            <h1>📑 文档总结报告</h1>
-            <h2>总体摘要</h2>
-            <div class="summary">{self.final_summary}</div>
-            {self.format_failed_files()}
-            <div class="details">
-                <h2>📚 各文件详细总结</h2>
-                {self.format_file_summaries()}
+            <div class="container">
+                <h1><span class="icon">📑</span> 文档总结报告</h1>
+                <div class="summary">
+                    <h2><span class="icon">📋</span> 总体摘要</h2>
+                    <p>{self.md.convert(self.final_summary)}</p>
+                </div>
+                {self.format_failed_files()}
+                <div class="details">
+                    <h2><span class="icon">📚</span> 各文件详细总结</h2>
+                    {self.format_file_summaries()}
+                </div>
             </div>
+
         </body>
         </html>
-        """
-
-
+        """

crazy_functions/doc_fns/content_folder.py

@@ -1,10 +1,10 @@
 from abc import ABC, abstractmethod
 from typing import Any, Dict, Optional, Type, TypeVar, Generic, Union
+
 from dataclasses import dataclass
 from enum import Enum, auto
 import logging
 from datetime import datetime
-from crazy_functions.rag_fns.arxiv_fns.section_fragment import SectionFragment
 
 # 设置日志
 logger = logging.getLogger(__name__)
@@ -235,153 +235,3 @@ class ContentFoldingManager:
 
         return formatter.format(content, metadata, options)
 
-
-@dataclass
-class PaperMetadata(BaseMetadata):
-    """论文元数据"""
-    title: str
-    authors: str
-    abstract: str
-    catalogs: str
-    arxiv_id: str = ""
-
-    def validate(self) -> bool:
-        """验证论文元数据的有效性"""
-        try:
-            if not self._validate_non_empty_str(self.title):
-                return False
-            if not self._validate_non_empty_str(self.authors):
-                return False
-            if not self._validate_non_empty_str(self.abstract):
-                return False
-            if not self._validate_non_empty_str(self.catalogs):
-                return False
-            return True
-        except Exception as e:
-            logger.error(f"Paper metadata validation error: {str(e)}")
-            return False
-
-
-class PaperContentFormatter(ContentFormatter[PaperMetadata]):
-    """论文内容格式化器"""
-
-    def format(self,
-               fragments: list[SectionFragment],
-               metadata: PaperMetadata,
-               options: Optional[FoldingOptions] = None) -> str:
-        """格式化论文内容
-
-        Args:
-            fragments: 论文片段列表
-            metadata: 论文元数据
-            options: 折叠选项
-
-        Returns:
-            str: 格式化后的论文内容
-        """
-        if not metadata.validate():
-            raise MetadataError("Invalid paper metadata")
-
-        try:
-            options = options or FoldingOptions()
-
-            # 1. 生成标题部分（不折叠）
-            result = [f"# {metadata.title}\n"]
-
-            # 2. 生成作者信息（折叠）
-            result.append(self._create_folded_section(
-                "Authors",
-                metadata.authors,
-                options
-            ))
-
-            # 3. 生成摘要（折叠）
-            result.append(self._create_folded_section(
-                "Abstract",
-                metadata.abstract,
-                options
-            ))
-
-            # 4. 生成目录树（折叠）
-            result.append(self._create_folded_section(
-                "Table of Contents",
-                f"```\n{metadata.catalogs}\n```",
-                options
-            ))
-
-            # 5. 按章节组织并生成内容
-            sections = self._organize_sections(fragments)
-            for section, section_fragments in sections.items():
-                # 拼接该章节的所有内容
-                section_content = "\n\n".join(
-                    fragment.content for fragment in section_fragments
-                )
-
-                result.append(self._create_folded_section(
-                    section,
-                    section_content,
-                    options
-                ))
-
-            # 6. 生成参考文献（折叠）
-            # 收集所有非空的参考文献
-            all_refs = "\n".join(filter(None,
-                                        (fragment.bibliography for fragment in fragments)
-                                        ))
-            if all_refs:
-                result.append(self._create_folded_section(
-                    "Bibliography",
-                    f"```bibtex\n{all_refs}\n```",
-                    options
-                ))
-
-            return "\n\n".join(result)
-
-        except Exception as e:
-            logger.error(f"Error formatting paper content: {str(e)}")
-            raise FormattingError(f"Failed to format paper content: {str(e)}")
-
-    def _create_folded_section(self,
-                               title: str,
-                               content: str,
-                               options: FoldingOptions) -> str:
-        """创建折叠区块
-
-        Args:
-            title: 区块标题
-            content: 区块内容
-            options: 折叠选项
-
-        Returns:
-            str: 格式化后的折叠区块
-        """
-        css_class = f' class="{options.custom_css}"' if options.custom_css else ''
-
-        result = (
-            f'<details{css_class}><summary>{title}</summary>\n\n'
-            f'{content}\n\n'
-            f'</details>'
-        )
-
-        return self._add_indent(result, options.indent_level)
-
-    def _organize_sections(self,
-                           fragments: list[SectionFragment]
-                           ) -> Dict[str, list[SectionFragment]]:
-        """将片段按章节分组
-
-        Args:
-            fragments: 论文片段列表
-
-        Returns:
-            Dict[str, list[SectionFragment]]: 按章节分组的片段字典
-        """
-        sections: Dict[str, list[SectionFragment]] = {}
-
-        for fragment in fragments:
-            section = fragment.current_section or "Uncategorized"
-            if section not in sections:
-                sections[section] = []
-            sections[section].append(fragment)
-
-        return sections

crazy_functions/doc_fns/conversation_doc/excel_doc.py

@@ -0,0 +1,211 @@
+import re
+import os
+import pandas as pd
+from datetime import datetime
+from openpyxl import Workbook
+
+
+class ExcelTableFormatter:
+    """聊天记录中Markdown表格转Excel生成器"""
+
+    def __init__(self):
+        """初始化Excel文档对象"""
+        self.workbook = Workbook()
+        self._table_count = 0
+        self._current_sheet = None
+
+    def _normalize_table_row(self, row):
+        """标准化表格行，处理不同的分隔符情况"""
+        row = row.strip()
+        if row.startswith('|'):
+            row = row[1:]
+        if row.endswith('|'):
+            row = row[:-1]
+        return [cell.strip() for cell in row.split('|')]
+
+    def _is_separator_row(self, row):
+        """检查是否是分隔行（由 - 或 : 组成）"""
+        clean_row = re.sub(r'[\s|]', '', row)
+        return bool(re.match(r'^[-:]+$', clean_row))
+
+    def _extract_tables_from_text(self, text):
+        """从文本中提取所有表格内容"""
+        if not isinstance(text, str):
+            return []
+
+        tables = []
+        current_table = []
+        is_in_table = False
+
+        for line in text.split('\n'):
+            line = line.strip()
+            if not line:
+                if is_in_table and current_table:
+                    if len(current_table) >= 2:
+                        tables.append(current_table)
+                    current_table = []
+                    is_in_table = False
+                continue
+
+            if '|' in line:
+                if not is_in_table:
+                    is_in_table = True
+                current_table.append(line)
+            else:
+                if is_in_table and current_table:
+                    if len(current_table) >= 2:
+                        tables.append(current_table)
+                    current_table = []
+                    is_in_table = False
+
+        if is_in_table and current_table and len(current_table) >= 2:
+            tables.append(current_table)
+
+        return tables
+
+    def _parse_table(self, table_lines):
+        """解析表格内容为结构化数据"""
+        try:
+            headers = self._normalize_table_row(table_lines[0])
+
+            separator_index = next(
+                (i for i, line in enumerate(table_lines) if self._is_separator_row(line)),
+                1
+            )
+
+            data_rows = []
+            for line in table_lines[separator_index + 1:]:
+                cells = self._normalize_table_row(line)
+                # 确保单元格数量与表头一致
+                while len(cells) < len(headers):
+                    cells.append('')
+                cells = cells[:len(headers)]
+                data_rows.append(cells)
+
+            if headers and data_rows:
+                return {
+                    'headers': headers,
+                    'data': data_rows
+                }
+        except Exception as e:
+            print(f"解析表格时发生错误: {str(e)}")
+
+        return None
+
+    def _create_sheet(self, question_num, table_num):
+        """创建新的工作表"""
+        sheet_name = f'Q{question_num}_T{table_num}'
+        if len(sheet_name) > 31:
+            sheet_name = f'Table{self._table_count}'
+
+        if sheet_name in self.workbook.sheetnames:
+            sheet_name = f'{sheet_name}_{datetime.now().strftime("%H%M%S")}'
+
+        return self.workbook.create_sheet(title=sheet_name)
+
+    def create_document(self, history):
+        """
+        处理聊天历史中的所有表格并创建Excel文档
+
+        Args:
+            history: 聊天历史列表
+
+        Returns:
+            Workbook: 处理完成的Excel工作簿对象，如果没有表格则返回None
+        """
+        has_tables = False
+
+        # 删除默认创建的工作表
+        default_sheet = self.workbook['Sheet']
+        self.workbook.remove(default_sheet)
+
+        # 遍历所有回答
+        for i in range(1, len(history), 2):
+            answer = history[i]
+            tables = self._extract_tables_from_text(answer)
+
+            for table_lines in tables:
+                parsed_table = self._parse_table(table_lines)
+                if parsed_table:
+                    self._table_count += 1
+                    sheet = self._create_sheet(i // 2 + 1, self._table_count)
+
+                    # 写入表头
+                    for col, header in enumerate(parsed_table['headers'], 1):
+                        sheet.cell(row=1, column=col, value=header)
+
+                    # 写入数据
+                    for row_idx, row_data in enumerate(parsed_table['data'], 2):
+                        for col_idx, value in enumerate(row_data, 1):
+                            sheet.cell(row=row_idx, column=col_idx, value=value)
+
+                    has_tables = True
+
+        return self.workbook if has_tables else None
+
+
+def save_chat_tables(history, save_dir, base_name):
+    """
+    保存聊天历史中的表格到Excel文件
+
+    Args:
+        history: 聊天历史列表
+        save_dir: 保存目录
+        base_name: 基础文件名
+
+    Returns:
+        list: 保存的文件路径列表
+    """
+    result_files = []
+
+    try:
+        # 创建Excel格式
+        excel_formatter = ExcelTableFormatter()
+        workbook = excel_formatter.create_document(history)
+
+        if workbook is not None:
+            # 确保保存目录存在
+            os.makedirs(save_dir, exist_ok=True)
+
+            # 生成Excel文件路径
+            excel_file = os.path.join(save_dir, base_name + '.xlsx')
+
+            # 保存Excel文件
+            workbook.save(excel_file)
+            result_files.append(excel_file)
+            print(f"已保存表格到Excel文件: {excel_file}")
+    except Exception as e:
+        print(f"保存Excel格式失败: {str(e)}")
+
+    return result_files
+
+
+# 使用示例
+if __name__ == "__main__":
+    # 示例聊天历史
+    history = [
+        "问题1",
+        """这是第一个表格：
+        | A | B | C |
+        |---|---|---|
+        | 1 | 2 | 3 |""",
+
+        "问题2",
+        "这是没有表格的回答",
+
+        "问题3",
+        """回答包含多个表格：
+        | Name | Age |
+        |------|-----|
+        | Tom  | 20  |
+
+        第二个表格：
+        | X | Y |
+        |---|---|
+        | 1 | 2 |"""
+    ]
+
+    # 保存表格
+    save_dir = "output"
+    base_name = "chat_tables"
+    saved_files = save_chat_tables(history, save_dir, base_name)

crazy_functions/doc_fns/conversation_doc/html_doc.py

@@ -0,0 +1,190 @@
+
+
+class HtmlFormatter:
+    """聊天记录HTML格式生成器"""
+    
+    def __init__(self, chatbot, history):
+        self.chatbot = chatbot
+        self.history = history
+        self.css_styles = """
+        :root {
+            --primary-color: #2563eb;
+            --primary-light: #eff6ff;
+            --secondary-color: #1e293b;
+            --background-color: #f8fafc;
+            --text-color: #334155;
+            --border-color: #e2e8f0;
+            --card-shadow: 0 4px 6px -1px rgb(0 0 0 / 0.1), 0 2px 4px -2px rgb(0 0 0 / 0.1);
+        }
+
+        body {
+            font-family: system-ui, -apple-system, BlinkMacSystemFont, 'Segoe UI', Roboto, sans-serif;
+            line-height: 1.8;
+            margin: 0;
+            padding: 2rem;
+            color: var(--text-color);
+            background-color: var(--background-color);
+        }
+
+        .container {
+            max-width: 1200px;
+            margin: 0 auto;
+            background: white;
+            padding: 2rem;
+            border-radius: 16px;
+            box-shadow: var(--card-shadow);
+        }
+        ::selection {
+            background: var(--primary-light);
+            color: var(--primary-color);
+        }
+        @keyframes fadeIn {
+            from { opacity: 0; transform: translateY(20px); }
+            to { opacity: 1; transform: translateY(0); }
+        }
+        
+        @keyframes slideIn {
+            from { transform: translateX(-20px); opacity: 0; }
+            to { transform: translateX(0); opacity: 1; }
+        }
+        
+        .container {
+            animation: fadeIn 0.6s ease-out;
+        }
+        
+        .QaBox {
+            animation: slideIn 0.5s ease-out;
+            transition: all 0.3s ease;
+        }
+        
+        .QaBox:hover {
+            transform: translateX(5px);
+        }
+        .Question, .Answer, .historyBox {
+            transition: all 0.3s ease;
+        }
+        .chat-title {
+            color: var(--primary-color);
+            font-size: 2em;
+            text-align: center;
+            margin: 1rem 0 2rem;
+            padding-bottom: 1rem;
+            border-bottom: 2px solid var(--primary-color);
+        }
+
+        .chat-body {
+            display: flex;
+            flex-direction: column;
+            gap: 1.5rem;
+            margin: 2rem 0;
+        }
+
+        .QaBox {
+            background: white;
+            padding: 1.5rem;
+            border-radius: 8px;
+            border-left: 4px solid var(--primary-color);
+            box-shadow: 0 2px 4px rgba(0, 0, 0, 0.1);
+            margin-bottom: 1.5rem;
+        }
+
+        .Question {
+            color: var(--secondary-color);
+            font-weight: 500;
+            margin-bottom: 1rem;
+        }
+
+        .Answer {
+            color: var(--text-color);
+            background: var(--primary-light);
+            padding: 1rem;
+            border-radius: 6px;
+        }
+
+        .history-section {
+            margin-top: 3rem;
+            padding-top: 2rem;
+            border-top: 2px solid var(--border-color);
+        }
+
+        .history-title {
+            color: var(--secondary-color);
+            font-size: 1.5em;
+            margin-bottom: 1.5rem;
+            text-align: center;
+        }
+
+        .historyBox {
+            background: white;
+            padding: 1rem;
+            margin: 0.5rem 0;
+            border-radius: 6px;
+            border: 1px solid var(--border-color);
+        }
+
+        @media (prefers-color-scheme: dark) {
+            :root {
+                --background-color: #0f172a;
+                --text-color: #e2e8f0;
+                --border-color: #1e293b;
+            }
+            
+            .container, .QaBox {
+                background: #1e293b;
+            }
+        }
+        """
+
+    def format_chat_content(self) -> str:
+        """格式化聊天内容"""
+        chat_content = []
+        for q, a in self.chatbot:
+            question = str(q) if q is not None else ""
+            answer = str(a) if a is not None else ""
+            chat_content.append(f'''
+            <div class="QaBox">
+                <div class="Question">{question}</div>
+                <div class="Answer">{answer}</div>
+            </div>
+            ''')
+        return "\n".join(chat_content)
+
+    def format_history_content(self) -> str:
+        """格式化历史记录内容"""
+        if not self.history:
+            return ""
+            
+        history_content = []
+        for entry in self.history:
+            history_content.append(f'''
+            <div class="historyBox">
+                <div class="entry">{entry}</div>
+            </div>
+            ''')
+        return "\n".join(history_content)
+
+    def create_document(self) -> str:
+        """生成完整的HTML文档
+        
+        Returns:
+            str: 完整的HTML文档字符串
+        """
+        return f"""
+        <!DOCTYPE html>
+        <html lang="zh-CN">
+        <head>
+            <meta charset="utf-8">
+            <meta name="viewport" content="width=device-width, initial-scale=1">
+            <title>对话存档</title>
+            <style>{self.css_styles}</style>
+        </head>
+        <body>
+            <div class="container">
+                <h1 class="chat-title">对话存档</h1>
+                <div class="chat-body">
+                    {self.format_chat_content()}
+                </div>
+            </div>
+        </body>
+        </html>
+        """

crazy_functions/doc_fns/conversation_doc/markdown_doc.py

@@ -0,0 +1,39 @@
+
+class MarkdownFormatter:
+    """Markdown格式文档生成器 - 用于生成对话记录的markdown文档"""
+
+    def __init__(self):
+        self.content = []
+
+    def _add_content(self, text: str):
+        """添加正文内容"""
+        if text:
+            self.content.append(f"\n{text}\n")
+
+    def create_document(self, history: list) -> str:
+        """
+        创建完整的Markdown文档
+        Args:
+            history: 历史记录列表，偶数位置为问题，奇数位置为答案
+        Returns:
+            str: 生成的Markdown文本
+        """
+        self.content = []
+        
+        # 处理问答对
+        for i in range(0, len(history), 2):
+            question = history[i]
+            answer = history[i + 1]
+            
+            # 添加问题
+            self.content.append(f"\n### 问题 {i//2 + 1}")
+            self._add_content(question)
+            
+            # 添加回答
+            self.content.append(f"\n### 回答 {i//2 + 1}")
+            self._add_content(answer)
+            
+            # 添加分隔线
+            self.content.append("\n---\n")
+
+        return "\n".join(self.content)

crazy_functions/doc_fns/conversation_doc/pdf_doc.py

@@ -0,0 +1,172 @@
+from datetime import datetime
+import os
+import re
+from reportlab.pdfbase import pdfmetrics
+from reportlab.pdfbase.ttfonts import TTFont
+
+def convert_markdown_to_pdf(markdown_text):
+    """将Markdown文本转换为PDF格式的纯文本"""
+    if not markdown_text:
+        return ""
+
+    # 标准化换行符
+    markdown_text = markdown_text.replace('\r\n', '\n').replace('\r', '\n')
+
+    # 处理标题、粗体、斜体
+    markdown_text = re.sub(r'^#\s+(.+)$', r'\1', markdown_text, flags=re.MULTILINE)
+    markdown_text = re.sub(r'\*\*(.+?)\*\*', r'\1', markdown_text)
+    markdown_text = re.sub(r'\*(.+?)\*', r'\1', markdown_text)
+
+    # 处理列表
+    markdown_text = re.sub(r'^\s*[-*+]\s+(.+?)(?=\n|$)', r'• \1', markdown_text, flags=re.MULTILINE)
+    markdown_text = re.sub(r'^\s*\d+\.\s+(.+?)(?=\n|$)', r'\1', markdown_text, flags=re.MULTILINE)
+
+    # 处理链接
+    markdown_text = re.sub(r'\[([^\]]+)\]\(([^)]+)\)', r'\1', markdown_text)
+
+    # 处理段落
+    markdown_text = re.sub(r'\n{2,}', '\n', markdown_text)
+    markdown_text = re.sub(r'(?<!\n)(?<!^)(?<!•\s)(?<!\d\.\s)\n(?![\s•\d])', '\n\n', markdown_text, flags=re.MULTILINE)
+
+    # 清理空白
+    markdown_text = re.sub(r' +', ' ', markdown_text)
+    markdown_text = re.sub(r'(?m)^\s+|\s+$', '', markdown_text)
+
+    return markdown_text.strip()
+
+class PDFFormatter:
+    """聊天记录PDF文档生成器 - 使用 Noto Sans CJK 字体"""
+
+    def __init__(self):
+        self._init_reportlab()
+        self._register_fonts()
+        self.styles = self._get_reportlab_lib()['getSampleStyleSheet']()
+        self._create_styles()
+
+    def _init_reportlab(self):
+        """初始化 ReportLab 相关组件"""
+        from reportlab.lib.pagesizes import A4
+        from reportlab.lib.styles import getSampleStyleSheet, ParagraphStyle
+        from reportlab.lib.units import cm
+        from reportlab.platypus import SimpleDocTemplate, Paragraph, Spacer
+        
+        self._lib = {
+            'A4': A4,
+            'getSampleStyleSheet': getSampleStyleSheet,
+            'ParagraphStyle': ParagraphStyle,
+            'cm': cm
+        }
+        
+        self._platypus = {
+            'SimpleDocTemplate': SimpleDocTemplate,
+            'Paragraph': Paragraph,
+            'Spacer': Spacer
+        }
+
+    def _get_reportlab_lib(self):
+        return self._lib
+
+    def _get_reportlab_platypus(self):
+        return self._platypus
+
+    def _register_fonts(self):
+        """注册 Noto Sans CJK 字体"""
+        possible_font_paths = [
+            '/usr/share/fonts/opentype/noto/NotoSansCJK-Regular.ttc',
+            '/usr/share/fonts/noto-cjk/NotoSansCJK-Regular.ttc',
+            '/usr/share/fonts/noto/NotoSansCJK-Regular.ttc'
+        ]
+
+        font_registered = False
+        for path in possible_font_paths:
+            if os.path.exists(path):
+                try:
+                    pdfmetrics.registerFont(TTFont('NotoSansCJK', path))
+                    font_registered = True
+                    break
+                except:
+                    continue
+
+        if not font_registered:
+            print("Warning: Could not find Noto Sans CJK font. Using fallback font.")
+            self.font_name = 'Helvetica'
+        else:
+            self.font_name = 'NotoSansCJK'
+
+    def _create_styles(self):
+        """创建文档样式"""
+        ParagraphStyle = self._lib['ParagraphStyle']
+
+        # 标题样式
+        self.styles.add(ParagraphStyle(
+            name='Title_Custom',
+            fontName=self.font_name,
+            fontSize=24,
+            leading=38,
+            alignment=1,
+            spaceAfter=32
+        ))
+
+        # 日期样式
+        self.styles.add(ParagraphStyle(
+            name='Date_Style',
+            fontName=self.font_name,
+            fontSize=16,
+            leading=20,
+            alignment=1,
+            spaceAfter=20
+        ))
+
+        # 问题样式
+        self.styles.add(ParagraphStyle(
+            name='Question_Style',
+            fontName=self.font_name,
+            fontSize=12,
+            leading=18,
+            leftIndent=28,
+            spaceAfter=6
+        ))
+
+        # 回答样式
+        self.styles.add(ParagraphStyle(
+            name='Answer_Style',
+            fontName=self.font_name,
+            fontSize=12,
+            leading=18,
+            leftIndent=28,
+            spaceAfter=12
+        ))
+
+    def create_document(self, history, output_path):
+        """生成PDF文档"""
+        # 创建PDF文档
+        doc = self._platypus['SimpleDocTemplate'](
+            output_path,
+            pagesize=self._lib['A4'],
+            rightMargin=2.6 * self._lib['cm'],
+            leftMargin=2.8 * self._lib['cm'],
+            topMargin=3.7 * self._lib['cm'],
+            bottomMargin=3.5 * self._lib['cm']
+        )
+
+        # 构建内容
+        story = []
+        Paragraph = self._platypus['Paragraph']
+
+        # 添加对话内容
+        for i in range(0, len(history), 2):
+            question = history[i]
+            answer = convert_markdown_to_pdf(history[i + 1]) if i + 1 < len(history) else ""
+
+            if question:
+                q_text = f'问题 {i // 2 + 1}：{str(question)}'
+                story.append(Paragraph(q_text, self.styles['Question_Style']))
+
+            if answer:
+                a_text = f'回答 {i // 2 + 1}：{str(answer)}'
+                story.append(Paragraph(a_text, self.styles['Answer_Style']))
+
+        # 构建PDF
+        doc.build(story)
+
+        return doc

crazy_functions/doc_fns/conversation_doc/txt_doc.py

@@ -0,0 +1,79 @@
+
+import re
+
+
+def convert_markdown_to_txt(markdown_text):
+    """Convert markdown text to plain text while preserving formatting"""
+    # Standardize line endings
+    markdown_text = markdown_text.replace('\r\n', '\n').replace('\r', '\n')
+
+    # 1. Handle headers but keep their formatting instead of removing them
+    markdown_text = re.sub(r'^#\s+(.+)$', r'# \1', markdown_text, flags=re.MULTILINE)
+    markdown_text = re.sub(r'^##\s+(.+)$', r'## \1', markdown_text, flags=re.MULTILINE)
+    markdown_text = re.sub(r'^###\s+(.+)$', r'### \1', markdown_text, flags=re.MULTILINE)
+
+    # 2. Handle bold and italic - simply remove markers
+    markdown_text = re.sub(r'\*\*(.+?)\*\*', r'\1', markdown_text)
+    markdown_text = re.sub(r'\*(.+?)\*', r'\1', markdown_text)
+
+    # 3. Handle lists but preserve formatting
+    markdown_text = re.sub(r'^\s*[-*+]\s+(.+?)(?=\n|$)', r'• \1', markdown_text, flags=re.MULTILINE)
+
+    # 4. Handle links - keep only the text
+    markdown_text = re.sub(r'\[([^\]]+)\]\(([^)]+)\)', r'\1 (\2)', markdown_text)
+
+    # 5. Handle HTML links - convert to user-friendly format
+    markdown_text = re.sub(r'<a href=[\'"]([^\'"]+)[\'"](?:\s+target=[\'"][^\'"]+[\'"])?>([^<]+)</a>', r'\2 (\1)',
+                           markdown_text)
+
+    # 6. Preserve paragraph breaks
+    markdown_text = re.sub(r'\n{3,}', '\n\n', markdown_text)  # normalize multiple newlines to double newlines
+
+    # 7. Clean up extra spaces but maintain indentation
+    markdown_text = re.sub(r' +', ' ', markdown_text)
+
+    return markdown_text.strip()
+
+
+class TxtFormatter:
+    """Chat history TXT document generator"""
+
+    def __init__(self):
+        self.content = []
+        self._setup_document()
+
+    def _setup_document(self):
+        """Initialize document with header"""
+        self.content.append("=" * 50)
+        self.content.append("GPT-Academic对话记录".center(48))
+        self.content.append("=" * 50)
+
+    def _format_header(self):
+        """Create document header with current date"""
+        from datetime import datetime
+        date_str = datetime.now().strftime('%Y年%m月%d日')
+        return [
+            date_str.center(48),
+            "\n"  # Add blank line after date
+        ]
+
+    def create_document(self, history):
+        """Generate document from chat history"""
+        # Add header with date
+        self.content.extend(self._format_header())
+
+        # Add conversation content
+        for i in range(0, len(history), 2):
+            question = history[i]
+            answer = convert_markdown_to_txt(history[i + 1]) if i + 1 < len(history) else ""
+
+            if question:
+                self.content.append(f"问题 {i // 2 + 1}：{str(question)}")
+                self.content.append("")  # Add blank line
+
+            if answer:
+                self.content.append(f"回答 {i // 2 + 1}：{str(answer)}")
+                self.content.append("")  # Add blank line
+
+        # Join all content with newlines
+        return "\n".join(self.content)

crazy_functions/doc_fns/conversation_doc/word2pdf.py

@@ -0,0 +1,155 @@
+from docx2pdf import convert
+import os
+import platform
+import subprocess
+from typing import Union
+from pathlib import Path
+from datetime import datetime
+
+class WordToPdfConverter:
+    """Word文档转PDF转换器"""
+    
+    @staticmethod
+    def convert_to_pdf(word_path: Union[str, Path], pdf_path: Union[str, Path] = None) -> str:
+        """
+        将Word文档转换为PDF
+        
+        参数:
+            word_path: Word文档的路径
+            pdf_path: 可选，PDF文件的输出路径。如果未指定，将使用与Word文档相同的名称和位置
+            
+        返回:
+            生成的PDF文件路径
+        
+        异常:
+            如果转换失败，将抛出相应异常
+        """
+        try:
+            # 确保输入路径是Path对象
+            word_path = Path(word_path)
+            
+            # 如果未指定pdf_path，则使用与word文档相同的名称
+            if pdf_path is None:
+                pdf_path = word_path.with_suffix('.pdf')
+            else:
+                pdf_path = Path(pdf_path)
+            
+            # 检查操作系统
+            if platform.system() == 'Linux':
+                # Linux系统需要安装libreoffice
+                which_result = subprocess.run(['which', 'libreoffice'], capture_output=True, text=True)
+                if which_result.returncode != 0:
+                    raise RuntimeError("请先安装LibreOffice: sudo apt-get install libreoffice")
+                
+                print(f"开始转换Word文档: {word_path} 到 PDF")
+                
+                # 使用subprocess代替os.system
+                result = subprocess.run(
+                    ['libreoffice', '--headless', '--convert-to', 'pdf:writer_pdf_Export', 
+                     str(word_path), '--outdir', str(pdf_path.parent)],
+                    capture_output=True, text=True
+                )
+                
+                if result.returncode != 0:
+                    error_msg = result.stderr or "未知错误"
+                    print(f"LibreOffice转换失败，错误信息: {error_msg}")
+                    raise RuntimeError(f"LibreOffice转换失败: {error_msg}")
+                
+                print(f"LibreOffice转换输出: {result.stdout}")
+                
+                # 如果输出路径与默认生成的不同，则重命名
+                default_pdf = word_path.with_suffix('.pdf')
+                if default_pdf != pdf_path and default_pdf.exists():
+                    os.rename(default_pdf, pdf_path)
+                    print(f"已将PDF从 {default_pdf} 重命名为 {pdf_path}")
+                
+                # 验证PDF是否成功生成
+                if not pdf_path.exists() or pdf_path.stat().st_size == 0:
+                    raise RuntimeError("PDF生成失败或文件为空")
+                
+                print(f"PDF转换成功，文件大小: {pdf_path.stat().st_size} 字节")
+            else:
+                # Windows和MacOS使用docx2pdf
+                print(f"使用docx2pdf转换 {word_path} 到 {pdf_path}")
+                convert(word_path, pdf_path)
+                
+                # 验证PDF是否成功生成
+                if not pdf_path.exists() or pdf_path.stat().st_size == 0:
+                    raise RuntimeError("PDF生成失败或文件为空")
+                    
+                print(f"PDF转换成功，文件大小: {pdf_path.stat().st_size} 字节")
+            
+            return str(pdf_path)
+            
+        except Exception as e:
+            print(f"PDF转换异常: {str(e)}")
+            raise Exception(f"转换PDF失败: {str(e)}")
+
+    @staticmethod
+    def batch_convert(word_dir: Union[str, Path], pdf_dir: Union[str, Path] = None) -> list:
+        """
+        批量转换目录下的所有Word文档
+        
+        参数:
+            word_dir: 包含Word文档的目录路径
+            pdf_dir: 可选，PDF文件的输出目录。如果未指定，将使用与Word文档相同的目录
+            
+        返回:
+            生成的PDF文件路径列表
+        """
+        word_dir = Path(word_dir)
+        if pdf_dir:
+            pdf_dir = Path(pdf_dir)
+            pdf_dir.mkdir(parents=True, exist_ok=True)
+            
+        converted_files = []
+        
+        for word_file in word_dir.glob("*.docx"):
+            try:
+                if pdf_dir:
+                    pdf_path = pdf_dir / word_file.with_suffix('.pdf').name
+                else:
+                    pdf_path = word_file.with_suffix('.pdf')
+                    
+                pdf_file = WordToPdfConverter.convert_to_pdf(word_file, pdf_path)
+                converted_files.append(pdf_file)
+                
+            except Exception as e:
+                print(f"转换 {word_file} 失败: {str(e)}")
+                
+        return converted_files
+
+    @staticmethod
+    def convert_doc_to_pdf(doc, output_dir: Union[str, Path] = None) -> str:
+        """
+        将docx对象直接转换为PDF
+        
+        参数:
+            doc: python-docx的Document对象
+            output_dir: 可选，输出目录。如果未指定，将使用当前目录
+            
+        返回:
+            生成的PDF文件路径
+        """
+        try:
+            # 设置临时文件路径和输出路径
+            output_dir = Path(output_dir) if output_dir else Path.cwd()
+            output_dir.mkdir(parents=True, exist_ok=True)
+            
+            # 生成临时word文件
+            temp_docx = output_dir / f"temp_{datetime.now().strftime('%Y%m%d_%H%M%S')}.docx"
+            doc.save(temp_docx)
+            
+            # 转换为PDF
+            pdf_path = temp_docx.with_suffix('.pdf')
+            WordToPdfConverter.convert_to_pdf(temp_docx, pdf_path)
+            
+            # 删除临时word文件
+            temp_docx.unlink()
+            
+            return str(pdf_path)
+            
+        except Exception as e:
+            if temp_docx.exists():
+                temp_docx.unlink()
+            raise Exception(f"转换PDF失败: {str(e)}") 

crazy_functions/doc_fns/conversation_doc/word_doc.py

@@ -0,0 +1,177 @@
+import re
+from docx import Document
+from docx.shared import Cm, Pt
+from docx.enum.text import WD_PARAGRAPH_ALIGNMENT, WD_LINE_SPACING
+from docx.enum.style import WD_STYLE_TYPE
+from docx.oxml.ns import qn
+from datetime import datetime
+
+
+def convert_markdown_to_word(markdown_text):
+    # 0. 首先标准化所有换行符为\n
+    markdown_text = markdown_text.replace('\r\n', '\n').replace('\r', '\n')
+
+    # 1. 处理标题 - 支持更多级别的标题，使用更精确的正则
+    # 保留标题标记，以便后续处理时还能识别出标题级别
+    markdown_text = re.sub(r'^(#{1,6})\s+(.+?)(?:\s+#+)?$', r'\1 \2', markdown_text, flags=re.MULTILINE)
+
+    # 2. 处理粗体、斜体和加粗斜体
+    markdown_text = re.sub(r'\*\*\*(.+?)\*\*\*', r'\1', markdown_text)  # 加粗斜体
+    markdown_text = re.sub(r'\*\*(.+?)\*\*', r'\1', markdown_text)  # 加粗
+    markdown_text = re.sub(r'\*(.+?)\*', r'\1', markdown_text)  # 斜体
+    markdown_text = re.sub(r'_(.+?)_', r'\1', markdown_text)  # 下划线斜体
+    markdown_text = re.sub(r'__(.+?)__', r'\1', markdown_text)  # 下划线加粗
+
+    # 3. 处理代码块 - 不移除，而是简化格式
+    # 多行代码块
+    markdown_text = re.sub(r'```(?:\w+)?\n([\s\S]*?)```', r'[代码块]\n\1[/代码块]', markdown_text)
+    # 单行代码
+    markdown_text = re.sub(r'`([^`]+)`', r'[代码]\1[/代码]', markdown_text)
+
+    # 4. 处理列表 - 保留列表结构
+    # 匹配无序列表
+    markdown_text = re.sub(r'^(\s*)[-*+]\s+(.+?)$', r'\1• \2', markdown_text, flags=re.MULTILINE)
+
+    # 5. 处理Markdown链接
+    markdown_text = re.sub(r'\[([^\]]+)\]\(([^)]+?)\s*(?:"[^"]*")?\)', r'\1 (\2)', markdown_text)
+
+    # 6. 处理HTML链接
+    markdown_text = re.sub(r'<a href=[\'"]([^\'"]+)[\'"](?:\s+target=[\'"][^\'"]+[\'"])?>([^<]+)</a>', r'\2 (\1)',
+                           markdown_text)
+
+    # 7. 处理图片
+    markdown_text = re.sub(r'!\[([^\]]*)\]\([^)]+\)', r'[图片：\1]', markdown_text)
+
+    return markdown_text
+
+
+class WordFormatter:
+    """聊天记录Word文档生成器 - 符合中国政府公文格式规范(GB/T 9704-2012)"""
+
+    def __init__(self):
+        self.doc = Document()
+        self._setup_document()
+        self._create_styles()
+
+    def _setup_document(self):
+        """设置文档基本格式，包括页面设置和页眉"""
+        sections = self.doc.sections
+        for section in sections:
+            # 设置页面大小为A4
+            section.page_width = Cm(21)
+            section.page_height = Cm(29.7)
+            # 设置页边距
+            section.top_margin = Cm(3.7)  # 上边距37mm
+            section.bottom_margin = Cm(3.5)  # 下边距35mm
+            section.left_margin = Cm(2.8)  # 左边距28mm
+            section.right_margin = Cm(2.6)  # 右边距26mm
+            # 设置页眉页脚距离
+            section.header_distance = Cm(2.0)
+            section.footer_distance = Cm(2.0)
+
+            # 添加页眉
+            header = section.header
+            header_para = header.paragraphs[0]
+            header_para.alignment = WD_PARAGRAPH_ALIGNMENT.RIGHT
+            header_run = header_para.add_run("GPT-Academic对话记录")
+            header_run.font.name = '仿宋'
+            header_run._element.rPr.rFonts.set(qn('w:eastAsia'), '仿宋')
+            header_run.font.size = Pt(9)
+
+    def _create_styles(self):
+        """创建文档样式"""
+        # 创建正文样式
+        style = self.doc.styles.add_style('Normal_Custom', WD_STYLE_TYPE.PARAGRAPH)
+        style.font.name = '仿宋'
+        style._element.rPr.rFonts.set(qn('w:eastAsia'), '仿宋')
+        style.font.size = Pt(12)  # 调整为12磅
+        style.paragraph_format.line_spacing_rule = WD_LINE_SPACING.ONE_POINT_FIVE
+        style.paragraph_format.space_after = Pt(0)
+
+        # 创建问题样式
+        question_style = self.doc.styles.add_style('Question_Style', WD_STYLE_TYPE.PARAGRAPH)
+        question_style.font.name = '黑体'
+        question_style._element.rPr.rFonts.set(qn('w:eastAsia'), '黑体')
+        question_style.font.size = Pt(14)  # 调整为14磅
+        question_style.font.bold = True
+        question_style.paragraph_format.space_before = Pt(12)  # 减小段前距
+        question_style.paragraph_format.space_after = Pt(6)
+        question_style.paragraph_format.line_spacing_rule = WD_LINE_SPACING.ONE_POINT_FIVE
+        question_style.paragraph_format.left_indent = Pt(0)  # 移除左缩进
+
+        # 创建回答样式
+        answer_style = self.doc.styles.add_style('Answer_Style', WD_STYLE_TYPE.PARAGRAPH)
+        answer_style.font.name = '仿宋'
+        answer_style._element.rPr.rFonts.set(qn('w:eastAsia'), '仿宋')
+        answer_style.font.size = Pt(12)  # 调整为12磅
+        answer_style.paragraph_format.space_before = Pt(6)
+        answer_style.paragraph_format.space_after = Pt(12)
+        answer_style.paragraph_format.line_spacing_rule = WD_LINE_SPACING.ONE_POINT_FIVE
+        answer_style.paragraph_format.left_indent = Pt(0)  # 移除左缩进
+
+        # 创建标题样式
+        title_style = self.doc.styles.add_style('Title_Custom', WD_STYLE_TYPE.PARAGRAPH)
+        title_style.font.name = '黑体'  # 改用黑体
+        title_style._element.rPr.rFonts.set(qn('w:eastAsia'), '黑体')
+        title_style.font.size = Pt(22)  # 调整为22磅
+        title_style.font.bold = True
+        title_style.paragraph_format.alignment = WD_PARAGRAPH_ALIGNMENT.CENTER
+        title_style.paragraph_format.space_before = Pt(0)
+        title_style.paragraph_format.space_after = Pt(24)
+        title_style.paragraph_format.line_spacing_rule = WD_LINE_SPACING.ONE_POINT_FIVE
+
+        # 添加参考文献样式
+        ref_style = self.doc.styles.add_style('Reference_Style', WD_STYLE_TYPE.PARAGRAPH)
+        ref_style.font.name = '宋体'
+        ref_style._element.rPr.rFonts.set(qn('w:eastAsia'), '宋体')
+        ref_style.font.size = Pt(10.5)  # 参考文献使用小号字体
+        ref_style.paragraph_format.space_before = Pt(3)
+        ref_style.paragraph_format.space_after = Pt(3)
+        ref_style.paragraph_format.line_spacing_rule = WD_LINE_SPACING.SINGLE
+        ref_style.paragraph_format.left_indent = Pt(21)
+        ref_style.paragraph_format.first_line_indent = Pt(-21)
+
+        # 添加参考文献标题样式
+        ref_title_style = self.doc.styles.add_style('Reference_Title_Style', WD_STYLE_TYPE.PARAGRAPH)
+        ref_title_style.font.name = '黑体'
+        ref_title_style._element.rPr.rFonts.set(qn('w:eastAsia'), '黑体')
+        ref_title_style.font.size = Pt(16)
+        ref_title_style.font.bold = True
+        ref_title_style.paragraph_format.space_before = Pt(24)
+        ref_title_style.paragraph_format.space_after = Pt(12)
+        ref_title_style.paragraph_format.line_spacing_rule = WD_LINE_SPACING.ONE_POINT_FIVE
+
+    def create_document(self,  history):
+        """写入聊天历史"""
+        # 添加标题
+        title_para = self.doc.add_paragraph(style='Title_Custom')
+        title_run = title_para.add_run('GPT-Academic 对话记录')
+
+        # 添加日期
+        date_para = self.doc.add_paragraph()
+        date_para.alignment = WD_PARAGRAPH_ALIGNMENT.CENTER
+        date_run = date_para.add_run(datetime.now().strftime('%Y年%m月%d日'))
+        date_run.font.name = '仿宋'
+        date_run._element.rPr.rFonts.set(qn('w:eastAsia'), '仿宋')
+        date_run.font.size = Pt(16)
+
+        self.doc.add_paragraph()  # 添加空行
+
+        # 添加对话内容
+        for i in range(0, len(history), 2):
+            question = history[i]
+            answer = convert_markdown_to_word(history[i + 1])
+
+            if question:
+                q_para = self.doc.add_paragraph(style='Question_Style')
+                q_para.add_run(f'问题 {i//2 + 1}：').bold = True
+                q_para.add_run(str(question))
+
+            if answer:
+                a_para = self.doc.add_paragraph(style='Answer_Style')
+                a_para.add_run(f'回答 {i//2 + 1}：').bold = True
+                a_para.add_run(str(answer))
+
+
+        return self.doc
+

crazy_functions/doc_fns/read_fns/docx_reader.py

@@ -0,0 +1,6 @@
+import nltk
+nltk.data.path.append('~/nltk_data')
+nltk.download('averaged_perceptron_tagger', download_dir='~/nltk_data',
+             )
+nltk.download('punkt', download_dir='~/nltk_data',
+               )

crazy_functions/doc_fns/read_fns/excel_reader.py

@@ -0,0 +1,286 @@
+from __future__ import annotations
+
+import pandas as pd
+import numpy as np
+from pathlib import Path
+from typing import Optional, List, Set, Dict, Union, Iterator, Tuple
+from dataclasses import dataclass, field
+import logging
+from concurrent.futures import ThreadPoolExecutor, as_completed
+import chardet
+from functools import lru_cache
+import os
+
+
+@dataclass
+class ExtractorConfig:
+    """提取器配置类"""
+    encoding: str = 'auto'
+    na_filter: bool = True
+    skip_blank_lines: bool = True
+    chunk_size: int = 10000
+    max_workers: int = 4
+    preserve_format: bool = True
+    read_all_sheets: bool = True  # 新增：是否读取所有工作表
+    text_cleanup: Dict[str, bool] = field(default_factory=lambda: {
+        'remove_extra_spaces': True,
+        'normalize_whitespace': False,
+        'remove_special_chars': False,
+        'lowercase': False
+    })
+
+
+class ExcelTextExtractor:
+    """增强的Excel格式文件文本内容提取器"""
+
+    SUPPORTED_EXTENSIONS: Set[str] = {
+        '.xlsx', '.xls', '.csv', '.tsv', '.xlsm', '.xltx', '.xltm', '.ods'
+    }
+
+    def __init__(self, config: Optional[ExtractorConfig] = None):
+        self.config = config or ExtractorConfig()
+        self._setup_logging()
+        self._detect_encoding = lru_cache(maxsize=128)(self._detect_encoding)
+
+    def _setup_logging(self) -> None:
+        """配置日志记录器"""
+        logging.basicConfig(
+            level=logging.INFO,
+            format='%(asctime)s - %(name)s - %(levelname)s - %(message)s'
+        )
+        self.logger = logging.getLogger(__name__)
+        fh = logging.FileHandler('excel_extractor.log')
+        fh.setLevel(logging.ERROR)
+        self.logger.addHandler(fh)
+
+    def _detect_encoding(self, file_path: Path) -> str:
+        if self.config.encoding != 'auto':
+            return self.config.encoding
+
+        try:
+            with open(file_path, 'rb') as f:
+                raw_data = f.read(10000)
+                result = chardet.detect(raw_data)
+                return result['encoding'] or 'utf-8'
+        except Exception as e:
+            self.logger.warning(f"Encoding detection failed: {e}. Using utf-8")
+            return 'utf-8'
+
+    def _validate_file(self, file_path: Union[str, Path]) -> Path:
+        path = Path(file_path).resolve()
+
+        if not path.exists():
+            raise ValueError(f"File not found: {path}")
+
+        if not path.is_file():
+            raise ValueError(f"Not a file: {path}")
+
+        if not os.access(path, os.R_OK):
+            raise PermissionError(f"No read permission: {path}")
+
+        if path.suffix.lower() not in self.SUPPORTED_EXTENSIONS:
+            raise ValueError(
+                f"Unsupported format: {path.suffix}. "
+                f"Supported: {', '.join(sorted(self.SUPPORTED_EXTENSIONS))}"
+            )
+
+        return path
+
+    def _format_value(self, value: Any) -> str:
+        if pd.isna(value) or value is None:
+            return ''
+        if isinstance(value, (int, float)):
+            return str(value)
+        return str(value).strip()
+
+    def _process_chunk(self, chunk: pd.DataFrame, columns: Optional[List[str]] = None, sheet_name: str = '') -> str:
+        """处理数据块，新增sheet_name参数"""
+        try:
+            if columns:
+                chunk = chunk[columns]
+
+            if self.config.preserve_format:
+                formatted_chunk = chunk.applymap(self._format_value)
+                rows = []
+
+                # 添加工作表名称作为标题
+                if sheet_name:
+                    rows.append(f"[Sheet: {sheet_name}]")
+
+                # 添加表头
+                headers = [str(col) for col in formatted_chunk.columns]
+                rows.append('\t'.join(headers))
+
+                # 添加数据行
+                for _, row in formatted_chunk.iterrows():
+                    rows.append('\t'.join(row.values))
+
+                return '\n'.join(rows)
+            else:
+                flat_values = (
+                    chunk.astype(str)
+                    .replace({'nan': '', 'None': '', 'NaN': ''})
+                    .values.flatten()
+                )
+                return ' '.join(v for v in flat_values if v)
+
+        except Exception as e:
+            self.logger.error(f"Error processing chunk: {e}")
+            raise
+
+    def _read_file(self, file_path: Path) -> Union[pd.DataFrame, Iterator[pd.DataFrame], Dict[str, pd.DataFrame]]:
+        """读取文件，支持多工作表"""
+        try:
+            encoding = self._detect_encoding(file_path)
+
+            if file_path.suffix.lower() in {'.csv', '.tsv'}:
+                sep = '\t' if file_path.suffix.lower() == '.tsv' else ','
+
+                # 对大文件使用分块读取
+                if file_path.stat().st_size > self.config.chunk_size * 1024:
+                    return pd.read_csv(
+                        file_path,
+                        encoding=encoding,
+                        na_filter=self.config.na_filter,
+                        skip_blank_lines=self.config.skip_blank_lines,
+                        sep=sep,
+                        chunksize=self.config.chunk_size,
+                        on_bad_lines='warn'
+                    )
+                else:
+                    return pd.read_csv(
+                        file_path,
+                        encoding=encoding,
+                        na_filter=self.config.na_filter,
+                        skip_blank_lines=self.config.skip_blank_lines,
+                        sep=sep
+                    )
+            else:
+                # Excel文件处理，支持多工作表
+                if self.config.read_all_sheets:
+                    # 读取所有工作表
+                    return pd.read_excel(
+                        file_path,
+                        na_filter=self.config.na_filter,
+                        keep_default_na=self.config.na_filter,
+                        engine='openpyxl',
+                        sheet_name=None  # None表示读取所有工作表
+                    )
+                else:
+                    # 只读取第一个工作表
+                    return pd.read_excel(
+                        file_path,
+                        na_filter=self.config.na_filter,
+                        keep_default_na=self.config.na_filter,
+                        engine='openpyxl',
+                        sheet_name=0  # 读取第一个工作表
+                    )
+
+        except Exception as e:
+            self.logger.error(f"Error reading file {file_path}: {e}")
+            raise
+
+    def extract_text(
+            self,
+            file_path: Union[str, Path],
+            columns: Optional[List[str]] = None,
+            separator: str = '\n'
+    ) -> str:
+        """提取文本，支持多工作表"""
+        try:
+            path = self._validate_file(file_path)
+            self.logger.info(f"Processing: {path}")
+
+            reader = self._read_file(path)
+            texts = []
+
+            # 处理Excel多工作表
+            if isinstance(reader, dict):
+                for sheet_name, df in reader.items():
+                    sheet_text = self._process_chunk(df, columns, sheet_name)
+                    if sheet_text:
+                        texts.append(sheet_text)
+                return separator.join(texts)
+
+            # 处理单个DataFrame
+            elif isinstance(reader, pd.DataFrame):
+                return self._process_chunk(reader, columns)
+
+            # 处理DataFrame迭代器
+            else:
+                with ThreadPoolExecutor(max_workers=self.config.max_workers) as executor:
+                    futures = {
+                        executor.submit(self._process_chunk, chunk, columns): i
+                        for i, chunk in enumerate(reader)
+                    }
+
+                    chunk_texts = []
+                    for future in as_completed(futures):
+                        try:
+                            text = future.result()
+                            if text:
+                                chunk_texts.append((futures[future], text))
+                        except Exception as e:
+                            self.logger.error(f"Error in chunk {futures[future]}: {e}")
+
+                    # 按块的顺序排序
+                    chunk_texts.sort(key=lambda x: x[0])
+                    texts = [text for _, text in chunk_texts]
+
+                # 合并文本，保留格式
+                if texts and self.config.preserve_format:
+                    result = texts[0]  # 第一块包含表头
+                    if len(texts) > 1:
+                        # 跳过后续块的表头行
+                        for text in texts[1:]:
+                            result += '\n' + '\n'.join(text.split('\n')[1:])
+                    return result
+                else:
+                    return separator.join(texts)
+
+        except Exception as e:
+            self.logger.error(f"Extraction failed: {e}")
+            raise
+
+    @staticmethod
+    def get_supported_formats() -> List[str]:
+        """获取支持的文件格式列表"""
+        return sorted(ExcelTextExtractor.SUPPORTED_EXTENSIONS)
+
+
+def main():
+    """主函数：演示用法"""
+    config = ExtractorConfig(
+        encoding='auto',
+        preserve_format=True,
+        read_all_sheets=True,  # 启用多工作表读取
+        text_cleanup={
+            'remove_extra_spaces': True,
+            'normalize_whitespace': False,
+            'remove_special_chars': False,
+            'lowercase': False
+        }
+    )
+
+    extractor = ExcelTextExtractor(config)
+
+    try:
+        sample_file = 'example.xlsx'
+        if Path(sample_file).exists():
+            text = extractor.extract_text(
+                sample_file,
+                columns=['title', 'content']
+            )
+            print("提取的文本:")
+            print(text)
+        else:
+            print(f"示例文件 {sample_file} 不存在")
+
+        print("\n支持的格式:", extractor.get_supported_formats())
+
+    except Exception as e:
+        print(f"错误: {e}")
+
+
+if __name__ == "__main__":
+    main()

crazy_functions/doc_fns/read_fns/markitdown/markdown_reader.py

@@ -0,0 +1,359 @@
+from __future__ import annotations
+
+from pathlib import Path
+from typing import Optional, Set, Dict, Union, List
+from dataclasses import dataclass, field
+import logging
+import os
+import re
+import subprocess
+import tempfile
+import shutil
+
+@dataclass
+class MarkdownConverterConfig:
+    """PDF 到 Markdown 转换器配置类
+
+    Attributes:
+        extract_images: 是否提取图片
+        extract_tables: 是否尝试保留表格结构
+        extract_code_blocks: 是否识别代码块
+        extract_math: 是否转换数学公式
+        output_dir: 输出目录路径
+        image_dir: 图片保存目录路径
+        paragraph_separator: 段落之间的分隔符
+        text_cleanup: 文本清理选项字典
+        docintel_endpoint: Document Intelligence端点URL (可选)
+        enable_plugins: 是否启用插件
+        llm_client: LLM客户端对象 (例如OpenAI client)
+        llm_model: 要使用的LLM模型名称
+    """
+    extract_images: bool = True
+    extract_tables: bool = True
+    extract_code_blocks: bool = True
+    extract_math: bool = True
+    output_dir: str = ""
+    image_dir: str = "images"
+    paragraph_separator: str = '\n\n'
+    text_cleanup: Dict[str, bool] = field(default_factory=lambda: {
+        'remove_extra_spaces': True,
+        'normalize_whitespace': True,
+        'remove_special_chars': False,
+        'lowercase': False
+    })
+    docintel_endpoint: str = ""
+    enable_plugins: bool = False
+    llm_client: Optional[object] = None
+    llm_model: str = ""
+
+
+class MarkdownConverter:
+    """PDF 到 Markdown 转换器
+
+    使用 markitdown 库实现 PDF 到 Markdown 的转换，支持多种配置选项。
+    """
+
+    SUPPORTED_EXTENSIONS: Set[str] = {
+        '.pdf',
+    }
+
+    def __init__(self, config: Optional[MarkdownConverterConfig] = None):
+        """初始化转换器
+
+        Args:
+            config: 转换器配置对象，如果为None则使用默认配置
+        """
+        self.config = config or MarkdownConverterConfig()
+        self._setup_logging()
+        
+        # 检查是否安装了 markitdown
+        self._check_markitdown_installation()
+
+    def _setup_logging(self) -> None:
+        """配置日志记录器"""
+        logging.basicConfig(
+            level=logging.INFO,
+            format='%(asctime)s - %(name)s - %(levelname)s - %(message)s'
+        )
+        self.logger = logging.getLogger(__name__)
+
+        # 添加文件处理器
+        fh = logging.FileHandler('markdown_converter.log')
+        fh.setLevel(logging.ERROR)
+        self.logger.addHandler(fh)
+    
+    def _check_markitdown_installation(self) -> None:
+        """检查是否安装了 markitdown"""
+        try:
+            # 尝试导入 markitdown 库
+            from markitdown import MarkItDown
+            self.logger.info("markitdown 库已安装")
+        except ImportError:
+            self.logger.warning("markitdown 库未安装，尝试安装...")
+            try:
+                subprocess.check_call(["pip", "install", "markitdown"])
+                self.logger.info("markitdown 库安装成功")
+                from markitdown import MarkItDown
+            except (subprocess.SubprocessError, ImportError):
+                self.logger.error("无法安装 markitdown 库，请手动安装")
+                self.markitdown_available = False
+                return
+        
+        self.markitdown_available = True
+
+    def _validate_file(self, file_path: Union[str, Path], max_size_mb: int = 100) -> Path:
+        """验证文件
+
+        Args:
+            file_path: 文件路径
+            max_size_mb: 允许的最大文件大小(MB)
+
+        Returns:
+            Path: 验证后的Path对象
+
+        Raises:
+            ValueError: 文件不存在、格式不支持或大小超限
+            PermissionError: 没有读取权限
+        """
+        path = Path(file_path).resolve()
+
+        if not path.exists():
+            raise ValueError(f"文件不存在: {path}")
+
+        if not path.is_file():
+            raise ValueError(f"不是一个文件: {path}")
+
+        if not os.access(path, os.R_OK):
+            raise PermissionError(f"没有读取权限: {path}")
+
+        file_size_mb = path.stat().st_size / (1024 * 1024)
+        if file_size_mb > max_size_mb:
+            raise ValueError(
+                f"文件大小 ({file_size_mb:.1f}MB) 超过限制 {max_size_mb}MB"
+            )
+
+        if path.suffix.lower() not in self.SUPPORTED_EXTENSIONS:
+            raise ValueError(
+                f"不支持的格式: {path.suffix}. "
+                f"支持的格式: {', '.join(sorted(self.SUPPORTED_EXTENSIONS))}"
+            )
+
+        return path
+
+    def _cleanup_text(self, text: str) -> str:
+        """清理文本
+
+        Args:
+            text: 原始文本
+
+        Returns:
+            str: 清理后的文本
+        """
+        if self.config.text_cleanup['remove_extra_spaces']:
+            text = ' '.join(text.split())
+
+        if self.config.text_cleanup['normalize_whitespace']:
+            text = text.replace('\t', ' ').replace('\r', '\n')
+
+        if self.config.text_cleanup['lowercase']:
+            text = text.lower()
+
+        return text.strip()
+
+    @staticmethod
+    def get_supported_formats() -> List[str]:
+        """获取支持的文件格式列表"""
+        return sorted(MarkdownConverter.SUPPORTED_EXTENSIONS)
+
+    def convert_to_markdown(
+            self,
+            file_path: Union[str, Path],
+            output_path: Optional[Union[str, Path]] = None
+    ) -> str:
+        """将 PDF 转换为 Markdown
+
+        Args:
+            file_path: PDF 文件路径
+            output_path: 输出 Markdown 文件路径，如果为 None 则返回内容而不保存
+
+        Returns:
+            str: 转换后的 Markdown 内容
+
+        Raises:
+            Exception: 转换过程中的错误
+        """
+        try:
+            path = self._validate_file(file_path)
+            self.logger.info(f"处理: {path}")
+
+            if not self.markitdown_available:
+                raise ImportError("markitdown 库未安装，无法进行转换")
+
+            # 导入 markitdown 库
+            from markitdown import MarkItDown
+
+            # 准备输出目录
+            if output_path:
+                output_path = Path(output_path)
+                output_dir = output_path.parent
+                output_dir.mkdir(parents=True, exist_ok=True)
+            else:
+                # 创建临时目录作为输出目录
+                temp_dir = tempfile.mkdtemp()
+                output_dir = Path(temp_dir)
+                output_path = output_dir / f"{path.stem}.md"
+
+            # 图片目录
+            image_dir = output_dir / self.config.image_dir
+            image_dir.mkdir(parents=True, exist_ok=True)
+
+            # 创建 MarkItDown 实例并进行转换
+            if self.config.docintel_endpoint:
+                md = MarkItDown(docintel_endpoint=self.config.docintel_endpoint)
+            elif self.config.llm_client and self.config.llm_model:
+                md = MarkItDown(
+                    enable_plugins=self.config.enable_plugins,
+                    llm_client=self.config.llm_client,
+                    llm_model=self.config.llm_model
+                )
+            else:
+                md = MarkItDown(enable_plugins=self.config.enable_plugins)
+            
+            # 执行转换
+            result = md.convert(str(path))
+            markdown_content = result.text_content
+            
+            # 清理文本
+            markdown_content = self._cleanup_text(markdown_content)
+            
+            # 如果需要保存到文件
+            if output_path:
+                with open(output_path, 'w', encoding='utf-8') as f:
+                    f.write(markdown_content)
+                self.logger.info(f"转换成功，输出到: {output_path}")
+            
+            return markdown_content
+
+        except Exception as e:
+            self.logger.error(f"转换失败: {e}")
+            raise
+        finally:
+            # 如果使用了临时目录且没有指定输出路径，则清理临时目录
+            if 'temp_dir' in locals() and not output_path:
+                shutil.rmtree(temp_dir, ignore_errors=True)
+
+    def convert_to_markdown_and_save(
+            self,
+            file_path: Union[str, Path],
+            output_path: Union[str, Path]
+    ) -> Path:
+        """将 PDF 转换为 Markdown 并保存到指定路径
+
+        Args:
+            file_path: PDF 文件路径
+            output_path: 输出 Markdown 文件路径
+
+        Returns:
+            Path: 输出文件的 Path 对象
+
+        Raises:
+            Exception: 转换过程中的错误
+        """
+        self.convert_to_markdown(file_path, output_path)
+        return Path(output_path)
+    
+    def batch_convert(
+            self, 
+            file_paths: List[Union[str, Path]], 
+            output_dir: Union[str, Path]
+    ) -> List[Path]:
+        """批量转换多个 PDF 文件为 Markdown
+
+        Args:
+            file_paths: PDF 文件路径列表
+            output_dir: 输出目录路径
+
+        Returns:
+            List[Path]: 输出文件路径列表
+
+        Raises:
+            Exception: 转换过程中的错误
+        """
+        output_dir = Path(output_dir)
+        output_dir.mkdir(parents=True, exist_ok=True)
+        
+        output_paths = []
+        for file_path in file_paths:
+            path = Path(file_path)
+            output_path = output_dir / f"{path.stem}.md"
+            
+            try:
+                self.convert_to_markdown(file_path, output_path)
+                output_paths.append(output_path)
+                self.logger.info(f"成功转换: {path} -> {output_path}")
+            except Exception as e:
+                self.logger.error(f"转换失败 {path}: {e}")
+        
+        return output_paths
+
+
+def main():
+    """主函数：演示用法"""
+    # 配置
+    config = MarkdownConverterConfig(
+        extract_images=True,
+        extract_tables=True,
+        extract_code_blocks=True,
+        extract_math=True,
+        enable_plugins=False,
+        text_cleanup={
+            'remove_extra_spaces': True,
+            'normalize_whitespace': True,
+            'remove_special_chars': False,
+            'lowercase': False
+        }
+    )
+
+    # 创建转换器
+    converter = MarkdownConverter(config)
+
+    # 使用示例
+    try:
+        # 替换为实际的文件路径
+        sample_file = './crazy_functions/doc_fns/read_fns/paper/2501.12599v1.pdf'
+        if Path(sample_file).exists():
+            # 转换为 Markdown 并打印内容
+            markdown_content = converter.convert_to_markdown(sample_file)
+            print("转换后的 Markdown 内容:")
+            print(markdown_content[:500] + "...")  # 只打印前500个字符
+            
+            # 转换并保存到文件
+            output_file = f"./output_{Path(sample_file).stem}.md"
+            output_path = converter.convert_to_markdown_and_save(sample_file, output_file)
+            print(f"\n已保存到: {output_path}")
+            
+            # 使用LLM增强的示例 (需要添加相应的导入和配置)
+            # try:
+            #     from openai import OpenAI
+            #     client = OpenAI()
+            #     llm_config = MarkdownConverterConfig(
+            #         llm_client=client,
+            #         llm_model="gpt-4o"
+            #     )
+            #     llm_converter = MarkdownConverter(llm_config)
+            #     llm_result = llm_converter.convert_to_markdown("example.jpg")
+            #     print("LLM增强的结果:")
+            #     print(llm_result[:500] + "...")
+            # except ImportError:
+            #     print("未安装OpenAI库，跳过LLM示例")
+        else:
+            print(f"示例文件 {sample_file} 不存在")
+
+        print("\n支持的格式:", converter.get_supported_formats())
+
+    except Exception as e:
+        print(f"错误: {e}")
+
+
+if __name__ == "__main__":
+    main() 

crazy_functions/doc_fns/read_fns/unstructured_all/paper_metadata_extractor.py

@@ -0,0 +1,493 @@
+from __future__ import annotations
+
+from pathlib import Path
+from typing import Optional, Set, Dict, Union, List
+from dataclasses import dataclass, field
+import logging
+import os
+import re
+
+from unstructured.partition.auto import partition
+from unstructured.documents.elements import (
+    Text, Title, NarrativeText, ListItem, Table,
+    Footer, Header, PageBreak, Image, Address
+)
+
+
+@dataclass
+class PaperMetadata:
+    """论文元数据类"""
+    title: str = ""
+    authors: List[str] = field(default_factory=list)
+    affiliations: List[str] = field(default_factory=list)
+    journal: str = ""
+    volume: str = ""
+    issue: str = ""
+    year: str = ""
+    doi: str = ""
+    date: str = ""
+    publisher: str = ""
+    conference: str = ""
+    abstract: str = ""
+    keywords: List[str] = field(default_factory=list)
+
+
+@dataclass
+class ExtractorConfig:
+    """元数据提取器配置类"""
+    paragraph_separator: str = '\n\n'
+    text_cleanup: Dict[str, bool] = field(default_factory=lambda: {
+        'remove_extra_spaces': True,
+        'normalize_whitespace': True,
+        'remove_special_chars': False,
+        'lowercase': False
+    })
+
+
+class PaperMetadataExtractor:
+    """论文元数据提取器
+    
+    使用unstructured库从多种文档格式中提取论文的标题、作者、摘要等元数据信息。
+    """
+
+    SUPPORTED_EXTENSIONS: Set[str] = {
+        '.pdf', '.docx', '.doc', '.txt', '.ppt', '.pptx',
+        '.xlsx', '.xls', '.md', '.org', '.odt', '.rst',
+        '.rtf', '.epub', '.html', '.xml', '.json'
+    }
+
+    # 定义论文各部分的关键词模式
+    SECTION_PATTERNS = {
+        'abstract': r'\b(摘要|abstract|summary|概要|résumé|zusammenfassung|аннотация)\b',
+        'keywords': r'\b(关键词|keywords|key\s+words|关键字|mots[- ]clés|schlüsselwörter|ключевые слова)\b',
+    }
+
+    def __init__(self, config: Optional[ExtractorConfig] = None):
+        """初始化提取器
+        
+        Args:
+            config: 提取器配置对象，如果为None则使用默认配置
+        """
+        self.config = config or ExtractorConfig()
+        self._setup_logging()
+
+    def _setup_logging(self) -> None:
+        """配置日志记录器"""
+        logging.basicConfig(
+            level=logging.INFO,
+            format='%(asctime)s - %(name)s - %(levelname)s - %(message)s'
+        )
+        self.logger = logging.getLogger(__name__)
+
+        # 添加文件处理器
+        fh = logging.FileHandler('paper_metadata_extractor.log')
+        fh.setLevel(logging.ERROR)
+        self.logger.addHandler(fh)
+
+    def _validate_file(self, file_path: Union[str, Path], max_size_mb: int = 100) -> Path:
+        """验证文件
+        
+        Args:
+            file_path: 文件路径
+            max_size_mb: 允许的最大文件大小(MB)
+            
+        Returns:
+            Path: 验证后的Path对象
+            
+        Raises:
+            ValueError: 文件不存在、格式不支持或大小超限
+            PermissionError: 没有读取权限
+        """
+        path = Path(file_path).resolve()
+
+        if not path.exists():
+            raise ValueError(f"文件不存在: {path}")
+
+        if not path.is_file():
+            raise ValueError(f"不是文件: {path}")
+
+        if not os.access(path, os.R_OK):
+            raise PermissionError(f"没有读取权限: {path}")
+
+        file_size_mb = path.stat().st_size / (1024 * 1024)
+        if file_size_mb > max_size_mb:
+            raise ValueError(
+                f"文件大小 ({file_size_mb:.1f}MB) 超过限制 {max_size_mb}MB"
+            )
+
+        if path.suffix.lower() not in self.SUPPORTED_EXTENSIONS:
+            raise ValueError(
+                f"不支持的文件格式: {path.suffix}. "
+                f"支持的格式: {', '.join(sorted(self.SUPPORTED_EXTENSIONS))}"
+            )
+
+        return path
+
+    def _cleanup_text(self, text: str) -> str:
+        """清理文本
+        
+        Args:
+            text: 原始文本
+            
+        Returns:
+            str: 清理后的文本
+        """
+        if self.config.text_cleanup['remove_extra_spaces']:
+            text = ' '.join(text.split())
+
+        if self.config.text_cleanup['normalize_whitespace']:
+            text = text.replace('\t', ' ').replace('\r', '\n')
+
+        if self.config.text_cleanup['lowercase']:
+            text = text.lower()
+
+        return text.strip()
+
+    @staticmethod
+    def get_supported_formats() -> List[str]:
+        """获取支持的文件格式列表"""
+        return sorted(PaperMetadataExtractor.SUPPORTED_EXTENSIONS)
+
+    def extract_metadata(self, file_path: Union[str, Path], strategy: str = "fast") -> PaperMetadata:
+        """提取论文元数据
+        
+        Args:
+            file_path: 文件路径
+            strategy: 提取策略 ("fast" 或 "accurate")
+            
+        Returns:
+            PaperMetadata: 提取的论文元数据
+            
+        Raises:
+            Exception: 提取过程中的错误
+        """
+        try:
+            path = self._validate_file(file_path)
+            self.logger.info(f"正在处理: {path}")
+
+            # 使用unstructured库分解文档
+            elements = partition(
+                str(path),
+                strategy=strategy,
+                include_metadata=True,
+                nlp=False,
+            )
+
+            # 提取元数据
+            metadata = PaperMetadata()
+            
+            # 提取标题和作者
+            self._extract_title_and_authors(elements, metadata)
+            
+            # 提取摘要和关键词
+            self._extract_abstract_and_keywords(elements, metadata)
+            
+            # 提取其他元数据
+            self._extract_additional_metadata(elements, metadata)
+            
+            return metadata
+
+        except Exception as e:
+            self.logger.error(f"元数据提取失败: {e}")
+            raise
+
+    def _extract_title_and_authors(self, elements, metadata: PaperMetadata) -> None:
+        """从文档中提取标题和作者信息 - 改进版"""
+        # 收集所有潜在的标题候选
+        title_candidates = []
+        all_text = []
+        raw_text = []
+        
+        # 首先收集文档前30个元素的文本，用于辅助判断
+        for i, element in enumerate(elements[:30]):
+            if isinstance(element, (Text, Title, NarrativeText)):
+                text = str(element).strip()
+                if text:
+                    all_text.append(text)
+                    raw_text.append(text)
+        
+        # 打印出原始文本，用于调试
+        print("原始文本前10行:")
+        for i, text in enumerate(raw_text[:10]):
+            print(f"{i}: {text}")
+        
+        # 1. 尝试查找连续的标题片段并合并它们
+        i = 0
+        while i < len(all_text) - 1:
+            current = all_text[i]
+            next_text = all_text[i + 1]
+            
+            # 检查是否存在标题分割情况：一行以冒号结尾，下一行像是标题的延续
+            if current.endswith(':') and len(current) < 50 and len(next_text) > 5 and next_text[0].isupper():
+                # 合并这两行文本
+                combined_title = f"{current} {next_text}"
+                # 查找合并前的文本并替换
+                all_text[i] = combined_title
+                all_text.pop(i + 1)
+                # 给合并后的标题很高的分数
+                title_candidates.append((combined_title, 15, i))
+            else:
+                i += 1
+        
+        # 2. 首先尝试从标题元素中查找
+        for i, element in enumerate(elements[:15]):  # 只检查前15个元素
+            if isinstance(element, Title):
+                title_text = str(element).strip()
+                # 排除常见的非标题内容
+                if title_text.lower() not in ['abstract', '摘要', 'introduction', '引言']:
+                    # 计算标题分数（越高越可能是真正的标题）
+                    score = self._evaluate_title_candidate(title_text, i, element)
+                    title_candidates.append((title_text, score, i))
+        
+        # 3. 特别处理常见的论文标题格式
+        for i, text in enumerate(all_text[:15]):
+            # 特别检查"KIMI K1.5:"类型的前缀标题
+            if re.match(r'^[A-Z][A-Z0-9\s\.]+(\s+K\d+(\.\d+)?)?:', text):
+                score = 12  # 给予很高的分数
+                title_candidates.append((text, score, i))
+                
+                # 如果下一行也是全大写，很可能是标题的延续
+                if i+1 < len(all_text) and all_text[i+1].isupper() and len(all_text[i+1]) > 10:
+                    combined_title = f"{text} {all_text[i+1]}"
+                    title_candidates.append((combined_title, 15, i))  # 给合并标题更高分数
+            
+            # 匹配全大写的标题行
+            elif text.isupper() and len(text) > 10 and len(text) < 100:
+                score = 10 - i * 0.5  # 越靠前越可能是标题
+                title_candidates.append((text, score, i))
+        
+        # 对标题候选按分数排序并选取最佳候选
+        if title_candidates:
+            title_candidates.sort(key=lambda x: x[1], reverse=True)
+            metadata.title = title_candidates[0][0]
+            title_position = title_candidates[0][2]
+            print(f"所有标题候选: {title_candidates[:3]}")
+        else:
+            # 如果没有找到合适的标题，使用一个备选策略
+            for text in all_text[:10]:
+                if text.isupper() and len(text) > 10 and len(text) < 200:  # 大写且适当长度的文本
+                    metadata.title = text
+                    break
+            title_position = 0
+        
+        # 提取作者信息 - 改进后的作者提取逻辑
+        author_candidates = []
+        
+        # 1. 特别处理"TECHNICAL REPORT OF"之后的行，通常是作者或团队
+        for i, text in enumerate(all_text):
+            if "TECHNICAL REPORT" in text.upper() and i+1 < len(all_text):
+                team_text = all_text[i+1].strip()
+                if re.search(r'\b(team|group|lab)\b', team_text, re.IGNORECASE):
+                    author_candidates.append((team_text, 15))
+        
+        # 2. 查找包含Team的文本
+        for text in all_text[:20]:
+            if "Team" in text and len(text) < 30:
+                # 这很可能是团队名
+                author_candidates.append((text, 12))
+        
+        # 添加作者到元数据
+        if author_candidates:
+            # 按分数排序
+            author_candidates.sort(key=lambda x: x[1], reverse=True)
+            
+            # 去重
+            seen_authors = set()
+            for author, _ in author_candidates:
+                if author.lower() not in seen_authors and not author.isdigit():
+                    seen_authors.add(author.lower())
+                    metadata.authors.append(author)
+        
+        # 如果没有找到作者，尝试查找隶属机构信息中的团队名称
+        if not metadata.authors:
+            for text in all_text[:20]:
+                if re.search(r'\b(team|group|lab|laboratory|研究组|团队)\b', text, re.IGNORECASE):
+                    if len(text) < 50:  # 避免太长的文本
+                        metadata.authors.append(text.strip())
+                        break
+        
+        # 提取隶属机构信息
+        for i, element in enumerate(elements[:30]):
+            element_text = str(element).strip()
+            if re.search(r'(university|institute|department|school|laboratory|college|center|centre|\d{5,}|^[a-zA-Z]+@|学院|大学|研究所|研究院)', element_text, re.IGNORECASE):
+                # 可能是隶属机构
+                if element_text not in metadata.affiliations and len(element_text) > 10:
+                    metadata.affiliations.append(element_text)
+
+    def _evaluate_title_candidate(self, text, position, element):
+        """评估标题候选项的可能性分数"""
+        score = 0
+        
+        # 位置因素：越靠前越可能是标题
+        score += max(0, 10 - position) * 0.5
+        
+        # 长度因素：标题通常不会太短也不会太长
+        if 10 <= len(text) <= 150:
+            score += 3
+        elif len(text) < 10:
+            score -= 2
+        elif len(text) > 150:
+            score -= 3
+        
+        # 格式因素
+        if text.isupper():  # 全大写可能是标题
+            score += 2
+        if re.match(r'^[A-Z]', text):  # 首字母大写
+            score += 1
+        if ':' in text:  # 标题常包含冒号
+            score += 1.5
+        
+        # 内容因素
+        if re.search(r'\b(scaling|learning|model|approach|method|system|framework|analysis)\b', text.lower()):
+            score += 2  # 包含常见的学术论文关键词
+            
+        # 避免误判
+        if re.match(r'^\d+$', text):  # 纯数字
+            score -= 10
+        if re.search(r'^(http|www|doi)', text.lower()):  # URL或DOI
+            score -= 5
+        if len(text.split()) <= 2 and len(text) < 15:  # 太短的短语
+            score -= 3
+            
+        # 元数据因素(如果有)
+        if hasattr(element, 'metadata') and element.metadata:
+            # 修复：正确处理ElementMetadata对象
+            try:
+                # 尝试通过getattr安全地获取属性
+                font_size = getattr(element.metadata, 'font_size', None)
+                if font_size is not None and font_size > 14:  # 假设标准字体大小是12
+                    score += 3
+                    
+                font_weight = getattr(element.metadata, 'font_weight', None)
+                if font_weight == 'bold':
+                    score += 2  # 粗体加分
+            except (AttributeError, TypeError):
+                # 如果metadata的访问方式不正确，尝试其他可能的访问方式
+                try:
+                    metadata_dict = element.metadata.__dict__ if hasattr(element.metadata, '__dict__') else {}
+                    if 'font_size' in metadata_dict and metadata_dict['font_size'] > 14:
+                        score += 3
+                    if 'font_weight' in metadata_dict and metadata_dict['font_weight'] == 'bold':
+                        score += 2
+                except Exception:
+                    # 如果所有尝试都失败，忽略元数据处理
+                    pass
+        
+        return score
+
+    def _extract_abstract_and_keywords(self, elements, metadata: PaperMetadata) -> None:
+        """从文档中提取摘要和关键词"""
+        abstract_found = False
+        keywords_found = False
+        abstract_text = []
+        
+        for i, element in enumerate(elements):
+            element_text = str(element).strip().lower()
+            
+            # 寻找摘要部分
+            if not abstract_found and (
+                isinstance(element, Title) and 
+                re.search(self.SECTION_PATTERNS['abstract'], element_text, re.IGNORECASE)
+            ):
+                abstract_found = True
+                continue
+            
+            # 如果找到摘要部分，收集内容直到遇到关键词部分或新章节
+            if abstract_found and not keywords_found:
+                # 检查是否遇到关键词部分或新章节
+                if (
+                    isinstance(element, Title) or 
+                    re.search(self.SECTION_PATTERNS['keywords'], element_text, re.IGNORECASE) or
+                    re.match(r'\b(introduction|引言|method|方法)\b', element_text, re.IGNORECASE)
+                ):
+                    keywords_found = re.search(self.SECTION_PATTERNS['keywords'], element_text, re.IGNORECASE)
+                    abstract_found = False  # 停止收集摘要
+                else:
+                    # 收集摘要文本
+                    if isinstance(element, (Text, NarrativeText)) and element_text:
+                        abstract_text.append(element_text)
+            
+            # 如果找到关键词部分，提取关键词
+            if keywords_found and not abstract_found and not metadata.keywords:
+                if isinstance(element, (Text, NarrativeText)):
+                    # 清除可能的"关键词:"/"Keywords:"前缀
+                    cleaned_text = re.sub(r'^\s*(关键词|keywords|key\s+words)\s*[：:]\s*', '', element_text, flags=re.IGNORECASE)
+                    
+                    # 尝试按不同分隔符分割
+                    for separator in [';', '；', ',', '，']:
+                        if separator in cleaned_text:
+                            metadata.keywords = [k.strip() for k in cleaned_text.split(separator) if k.strip()]
+                            break
+                    
+                    # 如果未能分割，将整个文本作为一个关键词
+                    if not metadata.keywords and cleaned_text:
+                        metadata.keywords = [cleaned_text]
+                    
+                    keywords_found = False  # 已提取关键词，停止处理
+        
+        # 设置摘要文本
+        if abstract_text:
+            metadata.abstract = self.config.paragraph_separator.join(abstract_text)
+
+    def _extract_additional_metadata(self, elements, metadata: PaperMetadata) -> None:
+        """提取其他元数据信息"""
+        for element in elements[:30]:  # 只检查文档前部分
+            element_text = str(element).strip()
+            
+            # 尝试匹配DOI
+            doi_match = re.search(r'(doi|DOI):\s*(10\.\d{4,}\/[a-zA-Z0-9.-]+)', element_text)
+            if doi_match and not metadata.doi:
+                metadata.doi = doi_match.group(2)
+            
+            # 尝试匹配日期
+            date_match = re.search(r'(published|received|accepted|submitted):\s*(\d{1,2}\s+[a-zA-Z]+\s+\d{4}|\d{4}[-/]\d{1,2}[-/]\d{1,2})', element_text, re.IGNORECASE)
+            if date_match and not metadata.date:
+                metadata.date = date_match.group(2)
+                
+            # 尝试匹配年份
+            year_match = re.search(r'\b(19|20)\d{2}\b', element_text)
+            if year_match and not metadata.year:
+                metadata.year = year_match.group(0)
+                
+            # 尝试匹配期刊/会议名称
+            journal_match = re.search(r'(journal|conference):\s*([^,;.]+)', element_text, re.IGNORECASE)
+            if journal_match:
+                if "journal" in journal_match.group(1).lower() and not metadata.journal:
+                    metadata.journal = journal_match.group(2).strip()
+                elif not metadata.conference:
+                    metadata.conference = journal_match.group(2).strip()
+
+
+def main():
+    """主函数：演示用法"""
+    # 创建提取器
+    extractor = PaperMetadataExtractor()
+
+    # 使用示例
+    try:
+        # 替换为实际的文件路径
+        sample_file = '/Users/boyin.liu/Documents/示例文档/论文/3.pdf'
+        if Path(sample_file).exists():
+            metadata = extractor.extract_metadata(sample_file)
+            print("提取的元数据:")
+            print(f"标题: {metadata.title}")
+            print(f"作者: {', '.join(metadata.authors)}")
+            print(f"机构: {', '.join(metadata.affiliations)}")
+            print(f"摘要: {metadata.abstract[:200]}...")
+            print(f"关键词: {', '.join(metadata.keywords)}")
+            print(f"DOI: {metadata.doi}")
+            print(f"日期: {metadata.date}")
+            print(f"年份: {metadata.year}")
+            print(f"期刊: {metadata.journal}")
+            print(f"会议: {metadata.conference}")
+        else:
+            print(f"示例文件 {sample_file} 不存在")
+
+        print("\n支持的格式:", extractor.get_supported_formats())
+
+    except Exception as e:
+        print(f"错误: {e}")
+
+
+if __name__ == "__main__":
+    main() 

crazy_functions/doc_fns/read_fns/unstructured_all/unstructured_md.py

@@ -0,0 +1,86 @@
+from pathlib import Path
+from crazy_functions.doc_fns.read_fns.unstructured_all.paper_structure_extractor import PaperStructureExtractor
+
+def extract_and_save_as_markdown(paper_path, output_path=None):
+    """
+    提取论文结构并保存为Markdown格式
+    
+    参数:
+        paper_path: 论文文件路径
+        output_path: 输出的Markdown文件路径，如果不指定，将使用与输入相同的文件名但扩展名为.md
+    
+    返回:
+        保存的Markdown文件路径
+    """
+    # 创建提取器
+    extractor = PaperStructureExtractor()
+    
+    # 解析文件路径
+    paper_path = Path(paper_path)
+    
+    # 如果未指定输出路径，使用相同文件名但扩展名为.md
+    if output_path is None:
+        output_path = paper_path.with_suffix('.md')
+    else:
+        output_path = Path(output_path)
+    
+    # 确保输出目录存在
+    output_path.parent.mkdir(parents=True, exist_ok=True)
+    
+    print(f"正在处理论文: {paper_path}")
+    
+    try:
+        # 提取论文结构
+        paper = extractor.extract_paper_structure(paper_path)
+        
+        # 生成Markdown内容
+        markdown_content = extractor.generate_markdown(paper)
+        
+        # 保存到文件
+        with open(output_path, 'w', encoding='utf-8') as f:
+            f.write(markdown_content)
+        
+        print(f"已成功保存Markdown文件: {output_path}")
+        
+        # 打印摘要信息
+        print("\n论文摘要信息:")
+        print(f"标题: {paper.metadata.title}")
+        print(f"作者: {', '.join(paper.metadata.authors)}")
+        print(f"关键词: {', '.join(paper.keywords)}")
+        print(f"章节数: {len(paper.sections)}")
+        print(f"图表数: {len(paper.figures)}")
+        print(f"表格数: {len(paper.tables)}")
+        print(f"公式数: {len(paper.formulas)}")
+        print(f"参考文献数: {len(paper.references)}")
+        
+        return output_path
+    
+    except Exception as e:
+        print(f"处理论文时出错: {e}")
+        import traceback
+        traceback.print_exc()
+        return None
+
+# 使用示例
+if __name__ == "__main__":
+    # 替换为实际的论文文件路径
+    sample_paper = "crazy_functions/doc_fns/read_fns/paper/2501.12599v1.pdf"
+    
+    # 可以指定输出路径，也可以使用默认路径
+    # output_file = "/path/to/output/paper_structure.md"
+    # extract_and_save_as_markdown(sample_paper, output_file)
+    
+    # 使用默认输出路径（与输入文件同名但扩展名为.md）
+    extract_and_save_as_markdown(sample_paper)
+    
+    # # 批量处理多个论文的示例
+    # paper_dir = Path("/path/to/papers/folder")
+    # output_dir = Path("/path/to/output/folder")
+    #
+    # # 确保输出目录存在
+    # output_dir.mkdir(parents=True, exist_ok=True)
+    #
+    # # 处理目录中的所有PDF文件
+    # for paper_file in paper_dir.glob("*.pdf"):
+    #     output_file = output_dir / f"{paper_file.stem}.md"
+    #     extract_and_save_as_markdown(paper_file, output_file)

crazy_functions/doc_fns/read_fns/unstructured_all/unstructured_reader.py

@@ -0,0 +1,275 @@
+from __future__ import annotations
+
+from pathlib import Path
+from typing import Optional, Set, Dict, Union, List
+from dataclasses import dataclass, field
+import logging
+import os
+
+from unstructured.partition.auto import partition
+from unstructured.documents.elements import (
+    Text, Title, NarrativeText, ListItem, Table,
+    Footer, Header, PageBreak, Image, Address
+)
+
+
+@dataclass
+class TextExtractorConfig:
+    """通用文档提取器配置类
+
+    Attributes:
+        extract_headers_footers: 是否提取页眉页脚
+        extract_tables: 是否提取表格内容
+        extract_lists: 是否提取列表内容
+        extract_titles: 是否提取标题
+        paragraph_separator: 段落之间的分隔符
+        text_cleanup: 文本清理选项字典
+    """
+    extract_headers_footers: bool = False
+    extract_tables: bool = True
+    extract_lists: bool = True
+    extract_titles: bool = True
+    paragraph_separator: str = '\n\n'
+    text_cleanup: Dict[str, bool] = field(default_factory=lambda: {
+        'remove_extra_spaces': True,
+        'normalize_whitespace': True,
+        'remove_special_chars': False,
+        'lowercase': False
+    })
+
+
+class UnstructuredTextExtractor:
+    """通用文档文本内容提取器
+
+    使用 unstructured 库支持多种文档格式的文本提取，提供统一的接口和配置选项。
+    """
+
+    SUPPORTED_EXTENSIONS: Set[str] = {
+        # 文档格式
+        '.pdf', '.docx', '.doc', '.txt',
+        # 演示文稿
+        '.ppt', '.pptx',
+        # 电子表格
+        '.xlsx', '.xls', '.csv',
+        # 图片
+        '.png', '.jpg', '.jpeg', '.tiff',
+        # 邮件
+        '.eml', '.msg', '.p7s',
+        # Markdown
+        ".md",
+        # Org Mode
+        ".org",
+        # Open Office
+        ".odt",
+        # reStructured Text
+        ".rst",
+        # Rich Text
+        ".rtf",
+        # TSV
+        ".tsv",
+        # EPUB
+        '.epub',
+        # 其他格式
+        '.html', '.xml',  '.json',
+    }
+
+    def __init__(self, config: Optional[TextExtractorConfig] = None):
+        """初始化提取器
+
+        Args:
+            config: 提取器配置对象，如果为None则使用默认配置
+        """
+        self.config = config or TextExtractorConfig()
+        self._setup_logging()
+
+    def _setup_logging(self) -> None:
+        """配置日志记录器"""
+        logging.basicConfig(
+            level=logging.INFO,
+            format='%(asctime)s - %(name)s - %(levelname)s - %(message)s'
+        )
+        self.logger = logging.getLogger(__name__)
+
+        # 添加文件处理器
+        fh = logging.FileHandler('text_extractor.log')
+        fh.setLevel(logging.ERROR)
+        self.logger.addHandler(fh)
+
+    def _validate_file(self, file_path: Union[str, Path], max_size_mb: int = 100) -> Path:
+        """验证文件
+
+        Args:
+            file_path: 文件路径
+            max_size_mb: 允许的最大文件大小(MB)
+
+        Returns:
+            Path: 验证后的Path对象
+
+        Raises:
+            ValueError: 文件不存在、格式不支持或大小超限
+            PermissionError: 没有读取权限
+        """
+        path = Path(file_path).resolve()
+
+        if not path.exists():
+            raise ValueError(f"File not found: {path}")
+
+        if not path.is_file():
+            raise ValueError(f"Not a file: {path}")
+
+        if not os.access(path, os.R_OK):
+            raise PermissionError(f"No read permission: {path}")
+
+        file_size_mb = path.stat().st_size / (1024 * 1024)
+        if file_size_mb > max_size_mb:
+            raise ValueError(
+                f"File size ({file_size_mb:.1f}MB) exceeds limit of {max_size_mb}MB"
+            )
+
+        if path.suffix.lower() not in self.SUPPORTED_EXTENSIONS:
+            raise ValueError(
+                f"Unsupported format: {path.suffix}. "
+                f"Supported: {', '.join(sorted(self.SUPPORTED_EXTENSIONS))}"
+            )
+
+        return path
+
+    def _cleanup_text(self, text: str) -> str:
+        """清理文本
+
+        Args:
+            text: 原始文本
+
+        Returns:
+            str: 清理后的文本
+        """
+        if self.config.text_cleanup['remove_extra_spaces']:
+            text = ' '.join(text.split())
+
+        if self.config.text_cleanup['normalize_whitespace']:
+            text = text.replace('\t', ' ').replace('\r', '\n')
+
+        if self.config.text_cleanup['lowercase']:
+            text = text.lower()
+
+        return text.strip()
+
+    def _should_extract_element(self, element) -> bool:
+        """判断是否应该提取某个元素
+
+        Args:
+            element: 文档元素
+
+        Returns:
+            bool: 是否应该提取
+        """
+        if isinstance(element, (Text, NarrativeText)):
+            return True
+
+        if isinstance(element, Title) and self.config.extract_titles:
+            return True
+
+        if isinstance(element, ListItem) and self.config.extract_lists:
+            return True
+
+        if isinstance(element, Table) and self.config.extract_tables:
+            return True
+
+        if isinstance(element, (Header, Footer)) and self.config.extract_headers_footers:
+            return True
+
+        return False
+
+    @staticmethod
+    def get_supported_formats() -> List[str]:
+        """获取支持的文件格式列表"""
+        return sorted(UnstructuredTextExtractor.SUPPORTED_EXTENSIONS)
+
+    def extract_text(
+            self,
+            file_path: Union[str, Path],
+            strategy: str = "fast"
+    ) -> str:
+        """提取文本
+
+        Args:
+            file_path: 文件路径
+            strategy: 提取策略 ("fast" 或 "accurate")
+
+        Returns:
+            str: 提取的文本内容
+
+        Raises:
+            Exception: 提取过程中的错误
+        """
+        try:
+            path = self._validate_file(file_path)
+            self.logger.info(f"Processing: {path}")
+
+            # 修改这里：添加 nlp=False 参数来禁用 NLTK
+            elements = partition(
+                str(path),
+                strategy=strategy,
+                include_metadata=True,
+                nlp=True,
+            )
+
+            # 其余代码保持不变
+            text_parts = []
+            for element in elements:
+                if self._should_extract_element(element):
+                    text = str(element)
+                    cleaned_text = self._cleanup_text(text)
+                    if cleaned_text:
+                        if isinstance(element, (Header, Footer)):
+                            prefix = "[Header] " if isinstance(element, Header) else "[Footer] "
+                            text_parts.append(f"{prefix}{cleaned_text}")
+                        else:
+                            text_parts.append(cleaned_text)
+
+            return self.config.paragraph_separator.join(text_parts)
+
+        except Exception as e:
+            self.logger.error(f"Extraction failed: {e}")
+            raise
+
+
+
+def main():
+    """主函数：演示用法"""
+    # 配置
+    config = TextExtractorConfig(
+        extract_headers_footers=True,
+        extract_tables=True,
+        extract_lists=True,
+        extract_titles=True,
+        text_cleanup={
+            'remove_extra_spaces': True,
+            'normalize_whitespace': True,
+            'remove_special_chars': False,
+            'lowercase': False
+        }
+    )
+
+    # 创建提取器
+    extractor = UnstructuredTextExtractor(config)
+
+    # 使用示例
+    try:
+        # 替换为实际的文件路径
+        sample_file = './crazy_functions/doc_fns/read_fns/paper/2501.12599v1.pdf'
+        if Path(sample_file).exists() or True:
+            text = extractor.extract_text(sample_file)
+            print("提取的文本:")
+            print(text)
+        else:
+            print(f"示例文件 {sample_file} 不存在")
+
+        print("\n支持的格式:", extractor.get_supported_formats())
+
+    except Exception as e:
+        print(f"错误: {e}")
+
+
+if __name__ == "__main__":
+    main()

crazy_functions/doc_fns/read_fns/web_reader.py

@@ -0,0 +1,219 @@
+from __future__ import annotations
+
+from dataclasses import dataclass, field
+from typing import Dict, Optional, Union
+from urllib.parse import urlparse
+import logging
+import trafilatura
+import requests
+from pathlib import Path
+
+
+@dataclass
+class WebExtractorConfig:
+    """网页内容提取器配置类
+
+    Attributes:
+        extract_comments: 是否提取评论
+        extract_tables: 是否提取表格
+        extract_links: 是否保留链接信息
+        paragraph_separator: 段落分隔符
+        timeout: 网络请求超时时间(秒)
+        max_retries: 最大重试次数
+        user_agent: 自定义User-Agent
+        text_cleanup: 文本清理选项
+    """
+    extract_comments: bool = False
+    extract_tables: bool = True
+    extract_links: bool = False
+    paragraph_separator: str = '\n\n'
+    timeout: int = 10
+    max_retries: int = 3
+    user_agent: str = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36'
+    text_cleanup: Dict[str, bool] = field(default_factory=lambda: {
+        'remove_extra_spaces': True,
+        'normalize_whitespace': True,
+        'remove_special_chars': False,
+        'lowercase': False
+    })
+
+
+class WebTextExtractor:
+    """网页文本内容提取器
+    
+    使用trafilatura库提取网页中的主要文本内容，去除广告、导航等无关内容。
+    """
+
+    def __init__(self, config: Optional[WebExtractorConfig] = None):
+        """初始化提取器
+
+        Args:
+            config: 提取器配置对象，如果为None则使用默认配置
+        """
+        self.config = config or WebExtractorConfig()
+        self._setup_logging()
+
+    def _setup_logging(self) -> None:
+        """配置日志记录器"""
+        logging.basicConfig(
+            level=logging.INFO,
+            format='%(asctime)s - %(name)s - %(levelname)s - %(message)s'
+        )
+        self.logger = logging.getLogger(__name__)
+
+        # 添加文件处理器
+        fh = logging.FileHandler('web_extractor.log')
+        fh.setLevel(logging.ERROR)
+        self.logger.addHandler(fh)
+
+    def _validate_url(self, url: str) -> bool:
+        """验证URL格式是否有效
+
+        Args:
+            url: 网页URL
+
+        Returns:
+            bool: URL是否有效
+        """
+        try:
+            result = urlparse(url)
+            return all([result.scheme, result.netloc])
+        except Exception:
+            return False
+
+    def _download_webpage(self, url: str) -> Optional[str]:
+        """下载网页内容
+
+        Args:
+            url: 网页URL
+
+        Returns:
+            Optional[str]: 网页HTML内容，失败返回None
+
+        Raises:
+            Exception: 下载失败时抛出异常
+        """
+        headers = {'User-Agent': self.config.user_agent}
+        
+        for attempt in range(self.config.max_retries):
+            try:
+                response = requests.get(
+                    url, 
+                    headers=headers,
+                    timeout=self.config.timeout
+                )
+                response.raise_for_status()
+                return response.text
+            except requests.RequestException as e:
+                self.logger.warning(f"Attempt {attempt + 1} failed: {e}")
+                if attempt == self.config.max_retries - 1:
+                    raise Exception(f"Failed to download webpage after {self.config.max_retries} attempts: {e}")
+        return None
+
+    def _cleanup_text(self, text: str) -> str:
+        """清理文本
+
+        Args:
+            text: 原始文本
+
+        Returns:
+            str: 清理后的文本
+        """
+        if not text:
+            return ""
+
+        if self.config.text_cleanup['remove_extra_spaces']:
+            text = ' '.join(text.split())
+
+        if self.config.text_cleanup['normalize_whitespace']:
+            text = text.replace('\t', ' ').replace('\r', '\n')
+
+        if self.config.text_cleanup['lowercase']:
+            text = text.lower()
+
+        return text.strip()
+
+    def extract_text(self, url: str) -> str:
+        """提取网页文本内容
+
+        Args:
+            url: 网页URL
+
+        Returns:
+            str: 提取的文本内容
+
+        Raises:
+            ValueError: URL无效时抛出
+            Exception: 提取失败时抛出
+        """
+        try:
+            if not self._validate_url(url):
+                raise ValueError(f"Invalid URL: {url}")
+
+            self.logger.info(f"Processing URL: {url}")
+            
+            # 下载网页
+            html_content = self._download_webpage(url)
+            if not html_content:
+                raise Exception("Failed to download webpage")
+
+            # 配置trafilatura提取选项
+            extract_config = {
+                'include_comments': self.config.extract_comments,
+                'include_tables': self.config.extract_tables,
+                'include_links': self.config.extract_links,
+                'no_fallback': False,  # 允许使用后备提取器
+            }
+
+            # 提取文本
+            extracted_text = trafilatura.extract(
+                html_content,
+                **extract_config
+            )
+
+            if not extracted_text:
+                raise Exception("No content could be extracted")
+
+            # 清理文本
+            cleaned_text = self._cleanup_text(extracted_text)
+            
+            return cleaned_text
+
+        except Exception as e:
+            self.logger.error(f"Extraction failed: {e}")
+            raise
+
+
+def main():
+    """主函数：演示用法"""
+    # 配置
+    config = WebExtractorConfig(
+        extract_comments=False,
+        extract_tables=True,
+        extract_links=False,
+        timeout=10,
+        text_cleanup={
+            'remove_extra_spaces': True,
+            'normalize_whitespace': True,
+            'remove_special_chars': False,
+            'lowercase': False
+        }
+    )
+
+    # 创建提取器
+    extractor = WebTextExtractor(config)
+
+    # 使用示例
+    try:
+        # 替换为实际的URL
+        sample_url = 'https://arxiv.org/abs/2412.00036'
+        text = extractor.extract_text(sample_url)
+        print("提取的文本:")
+        print(text)
+
+    except Exception as e:
+        print(f"错误: {e}")
+
+
+if __name__ == "__main__":
+    main()

crazy_functions/doc_fns/tex_html_formatter.py

@@ -1,354 +0,0 @@
-from pathlib import Path
-from typing import List, Dict
-from dataclasses import dataclass
-from datetime import datetime
-import os
-import re
-
-
-@dataclass
-class SectionFragment:
-    """Arxiv论文片段数据类"""
-    title: str
-    authors: str
-    abstract: str
-    catalogs: str
-    arxiv_id: str = ""
-    current_section: str = "Introduction"
-    content: str = ''
-    bibliography: str = ''
-
-
-class PaperHtmlFormatter:
-    """HTML格式论文文档生成器"""
-
-    def __init__(self, fragments: List[SectionFragment], output_dir: Path):
-        self.fragments = fragments
-        self.output_dir = output_dir
-        self.css_styles = """
-        :root {
-            --primary-color: #1a73e8;
-            --secondary-color: #34495e;
-            --background-color: #f8f9fa;
-            --text-color: #2c3e50;
-            --border-color: #e0e0e0;
-            --code-bg-color: #f6f8fa;
-        }
-
-        body {
-            font-family: "Source Serif Pro", "Times New Roman", serif;
-            line-height: 1.8;
-            max-width: 1000px;
-            margin: 0 auto;
-            padding: 2rem;
-            color: var(--text-color);
-            background-color: var(--background-color);
-            font-size: 16px;
-        }
-
-        .container {
-            background: white;
-            padding: 2rem;
-            border-radius: 8px;
-            box-shadow: 0 2px 12px rgba(0,0,0,0.1);
-        }
-
-        h1 {
-            color: var(--primary-color);
-            font-size: 2.2em;
-            text-align: center;
-            margin: 1.5rem 0;
-            padding-bottom: 1rem;
-            border-bottom: 3px solid var(--primary-color);
-        }
-
-        h2 {
-            color: var(--secondary-color);
-            font-size: 1.8em;
-            margin-top: 2rem;
-            padding-left: 1rem;
-            border-left: 4px solid var(--primary-color);
-        }
-
-        h3 {
-            color: var(--text-color);
-            font-size: 1.5em;
-            margin-top: 1.5rem;
-            border-bottom: 2px solid var(--border-color);
-            padding-bottom: 0.5rem;
-        }
-
-        .authors {
-            text-align: center;
-            color: var(--secondary-color);
-            font-size: 1.1em;
-            margin: 1rem 0 2rem;
-        }
-
-        .abstract-container {
-            background: var(--background-color);
-            padding: 1.5rem;
-            border-radius: 6px;
-            margin: 2rem 0;
-        }
-
-        .abstract-title {
-            font-weight: bold;
-            color: var(--primary-color);
-            margin-bottom: 1rem;
-        }
-
-        .abstract-content {
-            font-style: italic;
-            line-height: 1.7;
-        }
-
-        .toc {
-            background: white;
-            padding: 1.5rem;
-            border-radius: 6px;
-            margin: 2rem 0;
-            box-shadow: 0 2px 8px rgba(0,0,0,0.05);
-        }
-
-        .toc-title {
-            color: var(--primary-color);
-            font-size: 1.4em;
-            margin-bottom: 1rem;
-        }
-
-        .section-content {
-            background: white;
-            padding: 1.5rem;
-            border-radius: 6px;
-            margin: 1.5rem 0;
-            box-shadow: 0 1px 3px rgba(0,0,0,0.05);
-        }
-
-        .fragment {
-            margin: 2rem 0;
-            padding-left: 1rem;
-            border-left: 3px solid var(--border-color);
-        }
-
-        .fragment:hover {
-            border-left-color: var(--primary-color);
-        }
-
-        .bibliography {
-            background: var(--code-bg-color);
-            padding: 1rem;
-            border-radius: 4px;
-            font-family: "Source Code Pro", monospace;
-            font-size: 0.9em;
-            white-space: pre-wrap;
-            margin-top: 1rem;
-        }
-
-        pre {
-            background: var(--code-bg-color);
-            padding: 1rem;
-            border-radius: 4px;
-            overflow-x: auto;
-            font-family: "Source Code Pro", monospace;
-        }
-
-        .paper-info {
-            background: white;
-            padding: 2rem;
-            border-radius: 8px;
-            margin: 2rem 0;
-            box-shadow: 0 2px 8px rgba(0,0,0,0.1);
-        }
-
-        .arxiv-id {
-            text-align: center;
-            color: #666;
-            font-size: 0.9em;
-            margin: 1rem 0;
-        }
-
-        .section-title {
-            display: flex;
-            align-items: center;
-            gap: 0.5rem;
-            color: var(--secondary-color);
-        }
-
-        .section-icon {
-            color: var(--primary-color);
-        }
-
-        @media print {
-            body {
-                background: white;
-            }
-            .container {
-                box-shadow: none;
-            }
-        }
-        """
-
-    def _sanitize_html(self, text: str) -> str:
-        """清理HTML特殊字符"""
-        if not text:
-            return ""
-
-        replacements = {
-            "&": "&",
-            "<": "&lt;",
-            ">": "&gt;",
-            '"': "&quot;",
-            "'": "&#39;"
-        }
-
-        for old, new in replacements.items():
-            text = text.replace(old, new)
-        return text
-
-    def _create_section_id(self, section: str) -> str:
-        """创建section的ID"""
-        section = section.strip() or "uncategorized"
-        # 移除特殊字符,转换为小写并用连字符替换空格
-        section_id = re.sub(r'[^\w\s-]', '', section.lower())
-        return section_id.replace(' ', '-')
-
-    def format_paper_info(self) -> str:
-        """格式化论文基本信息"""
-        if not self.fragments:
-            return ""
-
-        first_fragment = self.fragments[0]
-        paper_info = ['<div class="paper-info">']
-
-        # 添加标题
-        if first_fragment.title:
-            paper_info.append(f'<h1>{self._sanitize_html(first_fragment.title)}</h1>')
-
-        # 添加arXiv ID
-        if first_fragment.arxiv_id:
-            paper_info.append(f'<div class="arxiv-id">arXiv: {self._sanitize_html(first_fragment.arxiv_id)}</div>')
-
-        # 添加作者
-        if first_fragment.authors:
-            paper_info.append(f'<div class="authors">{self._sanitize_html(first_fragment.authors)}</div>')
-
-        # 添加摘要
-        if first_fragment.abstract:
-            paper_info.append('<div class="abstract-container">')
-            paper_info.append('<div class="abstract-title">Abstract</div>')
-            paper_info.append(f'<div class="abstract-content">{self._sanitize_html(first_fragment.abstract)}</div>')
-            paper_info.append('</div>')
-
-        # 添加目录结构
-        if first_fragment.catalogs:
-            paper_info.append('<h2>Document Structure</h2>')
-            paper_info.append('<pre>')
-            paper_info.append(self._sanitize_html(first_fragment.catalogs))
-            paper_info.append('</pre>')
-
-        paper_info.append('</div>')
-        return '\n'.join(paper_info)
-
-    def format_table_of_contents(self, sections: Dict[str, List[SectionFragment]]) -> str:
-        """生成目录"""
-        toc = ['<div class="toc">']
-        toc.append('<div class="toc-title">Table of Contents</div>')
-        toc.append('<nav>')
-
-        for section in sections:
-            section_id = self._create_section_id(section)
-            clean_section = section.strip() or "Uncategorized"
-            toc.append(f'<div><a href="#{section_id}">{self._sanitize_html(clean_section)} '
-                       f'</a></div>')
-
-        toc.append('</nav>')
-        toc.append('</div>')
-        return '\n'.join(toc)
-
-    def format_sections(self) -> str:
-        """格式化论文各部分内容"""
-        sections = {}
-        for fragment in self.fragments:
-            section = fragment.current_section or "Uncategorized"
-            if section not in sections:
-                sections[section] = []
-            sections[section].append(fragment)
-
-        formatted_html = ['<div class="content">']
-        formatted_html.append(self.format_table_of_contents(sections))
-
-        # 生成各部分内容
-        for section, fragments in sections.items():
-            section_id = self._create_section_id(section)
-            formatted_html.append(f'<h2 id="{section_id}">')
-            formatted_html.append(f'<span class="section-title">')
-            formatted_html.append(f'<span class="section-icon">§</span>')
-            formatted_html.append(f'{self._sanitize_html(section)}')
-            formatted_html.append('</span>')
-            formatted_html.append('</h2>')
-
-            formatted_html.append('<div class="section-content">')
-
-            for i, fragment in enumerate(fragments, 1):
-                formatted_html.append('<div class="fragment">')
-
-                # 添加内容
-                if fragment.content:
-                    formatted_html.append(
-                        f'<div class="fragment-content">{self._sanitize_html(fragment.content)}</div>'
-                    )
-
-                # 添加参考文献
-                if fragment.bibliography:
-                    formatted_html.append('<div class="bibliography">')
-                    formatted_html.append(f'{self._sanitize_html(fragment.bibliography)}')
-                    formatted_html.append('</div>')
-
-                formatted_html.append('</div>')
-
-            formatted_html.append('</div>')
-
-        formatted_html.append('</div>')
-        return '\n'.join(formatted_html)
-
-    def save_html(self) -> Path:
-        """保存HTML文档"""
-        try:
-            timestamp = datetime.now().strftime("%Y%m%d_%H%M%S")
-            filename = f"paper_content_{timestamp}.html"
-            file_path = self.output_dir / filename
-
-            html_content = f"""
-            <!DOCTYPE html>
-            <html lang="en">
-            <head>
-                <meta charset="utf-8">
-                <meta name="viewport" content="width=device-width, initial-scale=1">
-                <title>{self._sanitize_html(self.fragments[0].title if self.fragments else 'Paper Content')}</title>
-                <style>
-                {self.css_styles}
-                </style>
-            </head>
-            <body>
-                <div class="container">
-                    {self.format_paper_info()}
-                    {self.format_sections()}
-                </div>
-            </body>
-            </html>
-            """
-
-            with open(file_path, "w", encoding="utf-8") as f:
-                f.write(html_content)
-
-            print(f"HTML document saved to: {file_path}")
-            return file_path
-
-        except Exception as e:
-            print(f"Error saving HTML document: {str(e)}")
-            raise
-
-# 使用示例：
-# formatter = PaperHtmlFormatter(fragments, output_dir)
-# output_path = formatter.save_html()

crazy_functions/game_fns/game_ascii_art.py

@@ -1,4 +1,4 @@
-from toolbox import CatchException, update_ui, update_ui_lastest_msg
+from toolbox import CatchException, update_ui, update_ui_latest_msg
 from crazy_functions.multi_stage.multi_stage_utils import GptAcademicGameBaseState
 from crazy_functions.crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
 from request_llms.bridge_all import predict_no_ui_long_connection
@@ -13,7 +13,7 @@ class MiniGame_ASCII_Art(GptAcademicGameBaseState):
         else:
             if prompt.strip() == 'exit':
                 self.delete_game = True
-                yield from update_ui_lastest_msg(lastmsg=f"谜底是{self.obj}，游戏结束。", chatbot=chatbot, history=history, delay=0.)
+                yield from update_ui_latest_msg(lastmsg=f"谜底是{self.obj}，游戏结束。", chatbot=chatbot, history=history, delay=0.)
                 return
             chatbot.append([prompt, ""])
         yield from update_ui(chatbot=chatbot, history=history)
@@ -31,12 +31,12 @@ class MiniGame_ASCII_Art(GptAcademicGameBaseState):
             self.cur_task = 'identify user guess'
             res = get_code_block(raw_res)
             history += ['', f'the answer is {self.obj}', inputs, res]
-            yield from update_ui_lastest_msg(lastmsg=res, chatbot=chatbot, history=history, delay=0.)
+            yield from update_ui_latest_msg(lastmsg=res, chatbot=chatbot, history=history, delay=0.)
 
         elif self.cur_task == 'identify user guess':
             if is_same_thing(self.obj, prompt, self.llm_kwargs):
                 self.delete_game = True
-                yield from update_ui_lastest_msg(lastmsg="你猜对了！", chatbot=chatbot, history=history, delay=0.)
+                yield from update_ui_latest_msg(lastmsg="你猜对了！", chatbot=chatbot, history=history, delay=0.)
             else:
                 self.cur_task = 'identify user guess'
-                yield from update_ui_lastest_msg(lastmsg="猜错了，再试试，输入“exit”获取答案。", chatbot=chatbot, history=history, delay=0.)
+                yield from update_ui_latest_msg(lastmsg="猜错了，再试试，输入“exit”获取答案。", chatbot=chatbot, history=history, delay=0.)

crazy_functions/game_fns/game_interactive_story.py

@@ -63,7 +63,7 @@ prompts_terminate = """小说的前文回顾：
 """
 
 
-from toolbox import CatchException, update_ui, update_ui_lastest_msg
+from toolbox import CatchException, update_ui, update_ui_latest_msg
 from crazy_functions.multi_stage.multi_stage_utils import GptAcademicGameBaseState
 from crazy_functions.crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
 from request_llms.bridge_all import predict_no_ui_long_connection
@@ -112,7 +112,7 @@ class MiniGame_ResumeStory(GptAcademicGameBaseState):
             if prompt.strip() == 'exit' or prompt.strip() == '结束剧情':
                 # should we terminate game here?
                 self.delete_game = True
-                yield from update_ui_lastest_msg(lastmsg=f"游戏结束。", chatbot=chatbot, history=history, delay=0.)
+                yield from update_ui_latest_msg(lastmsg=f"游戏结束。", chatbot=chatbot, history=history, delay=0.)
                 return
             if '剧情收尾' in prompt:
                 self.cur_task = 'story_terminate'
@@ -137,8 +137,8 @@ class MiniGame_ResumeStory(GptAcademicGameBaseState):
             )
             self.story.append(story_paragraph)
             # # 配图
-            yield from update_ui_lastest_msg(lastmsg=story_paragraph + '<br/>正在生成插图中 ...', chatbot=chatbot, history=history, delay=0.)
-            yield from update_ui_lastest_msg(lastmsg=story_paragraph + '<br/>'+ self.generate_story_image(story_paragraph), chatbot=chatbot, history=history, delay=0.)
+            yield from update_ui_latest_msg(lastmsg=story_paragraph + '<br/>正在生成插图中 ...', chatbot=chatbot, history=history, delay=0.)
+            yield from update_ui_latest_msg(lastmsg=story_paragraph + '<br/>'+ self.generate_story_image(story_paragraph), chatbot=chatbot, history=history, delay=0.)
 
             # # 构建后续剧情引导
             previously_on_story = ""
@@ -171,8 +171,8 @@ class MiniGame_ResumeStory(GptAcademicGameBaseState):
             )
             self.story.append(story_paragraph)
             # # 配图
-            yield from update_ui_lastest_msg(lastmsg=story_paragraph + '<br/>正在生成插图中 ...', chatbot=chatbot, history=history, delay=0.)
-            yield from update_ui_lastest_msg(lastmsg=story_paragraph + '<br/>'+ self.generate_story_image(story_paragraph), chatbot=chatbot, history=history, delay=0.)
+            yield from update_ui_latest_msg(lastmsg=story_paragraph + '<br/>正在生成插图中 ...', chatbot=chatbot, history=history, delay=0.)
+            yield from update_ui_latest_msg(lastmsg=story_paragraph + '<br/>'+ self.generate_story_image(story_paragraph), chatbot=chatbot, history=history, delay=0.)
 
             # # 构建后续剧情引导
             previously_on_story = ""
@@ -204,8 +204,8 @@ class MiniGame_ResumeStory(GptAcademicGameBaseState):
                 chatbot, history_, self.sys_prompt_
             )
             # # 配图
-            yield from update_ui_lastest_msg(lastmsg=story_paragraph + '<br/>正在生成插图中 ...', chatbot=chatbot, history=history, delay=0.)
-            yield from update_ui_lastest_msg(lastmsg=story_paragraph + '<br/>'+ self.generate_story_image(story_paragraph), chatbot=chatbot, history=history, delay=0.)
+            yield from update_ui_latest_msg(lastmsg=story_paragraph + '<br/>正在生成插图中 ...', chatbot=chatbot, history=history, delay=0.)
+            yield from update_ui_latest_msg(lastmsg=story_paragraph + '<br/>'+ self.generate_story_image(story_paragraph), chatbot=chatbot, history=history, delay=0.)
 
             # terminate game
             self.delete_game = True

crazy_functions/gen_fns/gen_fns_shared.py

@@ -2,7 +2,7 @@ import time
 import importlib
 from toolbox import trimmed_format_exc, gen_time_str, get_log_folder
 from toolbox import CatchException, update_ui, gen_time_str, trimmed_format_exc, is_the_upload_folder
-from toolbox import promote_file_to_downloadzone, get_log_folder, update_ui_lastest_msg
+from toolbox import promote_file_to_downloadzone, get_log_folder, update_ui_latest_msg
 import multiprocessing
 
 def get_class_name(class_string):

crazy_functions/json_fns/pydantic_io.py

@@ -102,10 +102,10 @@ class GptJsonIO():
                 logging.info(f'Repairing json：{response}')
                 repair_prompt = self.generate_repair_prompt(broken_json = response, error=repr(e))
                 result = self.generate_output(gpt_gen_fn(repair_prompt, self.format_instructions))
-                logging.info('Repaire json success.')
+                logging.info('Repair json success.')
             except Exception as e:
                 # 没辙了，放弃治疗
-                logging.info('Repaire json fail.')
+                logging.info('Repair json fail.')
                 raise JsonStringError('Cannot repair json.', str(e))
         return result
 

crazy_functions/latex_fns/latex_actions.py

@@ -3,7 +3,7 @@ import re
 import shutil
 import numpy as np
 from loguru import logger
-from toolbox import update_ui, update_ui_lastest_msg, get_log_folder, gen_time_str
+from toolbox import update_ui, update_ui_latest_msg, get_log_folder, gen_time_str
 from toolbox import get_conf, promote_file_to_downloadzone
 from crazy_functions.latex_fns.latex_toolbox import PRESERVE, TRANSFORM
 from crazy_functions.latex_fns.latex_toolbox import set_forbidden_text, set_forbidden_text_begin_end, set_forbidden_text_careful_brace
@@ -20,7 +20,7 @@ def split_subprocess(txt, project_folder, return_dict, opts):
     """
     break down latex file to a linked list,
     each node use a preserve flag to indicate whether it should
-    be proccessed by GPT.
+    be processed by GPT.
     """
     text = txt
     mask = np.zeros(len(txt), dtype=np.uint8) + TRANSFORM
@@ -85,14 +85,14 @@ class LatexPaperSplit():
     """
     break down latex file to a linked list,
     each node use a preserve flag to indicate whether it should
-    be proccessed by GPT.
+    be processed by GPT.
     """
     def __init__(self) -> None:
         self.nodes = None
         self.msg = "*{\\scriptsize\\textbf{警告：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，" + \
             "版权归原文作者所有。翻译内容可靠性无保障，请仔细鉴别并以原文为准。" + \
             "项目Github地址 \\url{https://github.com/binary-husky/gpt_academic/}。"
-        # 请您不要删除或修改这行警告，除非您是论文的原作者（如果您是论文原作者，欢迎加REAME中的QQ联系开发者）
+        # 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README中的QQ联系开发者）
         self.msg_declare = "为了防止大语言模型的意外谬误产生扩散影响，禁止移除或修改此警告。}}\\\\"
         self.title = "unknown"
         self.abstract = "unknown"
@@ -151,7 +151,7 @@ class LatexPaperSplit():
         """
         break down latex file to a linked list,
         each node use a preserve flag to indicate whether it should
-        be proccessed by GPT.
+        be processed by GPT.
         P.S. use multiprocessing to avoid timeout error
         """
         import multiprocessing
@@ -300,7 +300,8 @@ def Latex精细分解与转化(file_manifest, project_folder, llm_kwargs, plugin
     write_html(pfg.sp_file_contents, pfg.sp_file_result, chatbot=chatbot, project_folder=project_folder)
 
     #  <-------- 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']}。"
+    model_name = llm_kwargs['llm_model'].replace('_', '\\_')  # 替换LLM模型名称中的下划线为转义字符
+    msg = f"当前大语言模型: {model_name}，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'))
 
@@ -350,7 +351,42 @@ def 编译Latex(chatbot, history, main_file_original, main_file_modified, work_f
     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
-    yield from update_ui_lastest_msg('编译已经开始...', chatbot, history)   # 刷新Gradio前端界面
+    yield from update_ui_latest_msg('编译已经开始...', chatbot, history)   # 刷新Gradio前端界面
+    # 检查是否需要使用xelatex
+    def check_if_need_xelatex(tex_path):
+        try:
+            with open(tex_path, 'r', encoding='utf-8', errors='replace') as f:
+                content = f.read(5000)
+                # 检查是否有使用xelatex的宏包
+                need_xelatex = any(
+                    pkg in content 
+                    for pkg in ['fontspec', 'xeCJK', 'xetex', 'unicode-math', 'xltxtra', 'xunicode']
+                )
+                if need_xelatex:
+                    logger.info(f"检测到宏包需要xelatex编译, 切换至xelatex编译")
+                else:
+                    logger.info(f"未检测到宏包需要xelatex编译, 使用pdflatex编译")
+                return need_xelatex
+        except Exception:
+            return False
+
+    # 根据编译器类型返回编译命令
+    def get_compile_command(compiler, filename):
+        compile_command = f'{compiler} -interaction=batchmode -file-line-error {filename}.tex'
+        logger.info('Latex 编译指令: ' + compile_command)
+        return compile_command
+
+    # 确定使用的编译器
+    compiler = 'pdflatex'
+    if check_if_need_xelatex(pj(work_folder_modified, f'{main_file_modified}.tex')):
+        logger.info("检测到宏包需要xelatex编译，切换至xelatex编译")
+        # Check if xelatex is installed
+        try:
+            import subprocess
+            subprocess.run(['xelatex', '--version'], capture_output=True, check=True)
+            compiler = 'xelatex'
+        except (subprocess.CalledProcessError, FileNotFoundError):
+            raise RuntimeError("检测到需要使用xelatex编译，但系统中未安装xelatex。请先安装texlive或其他提供xelatex的LaTeX发行版。")
 
     while True:
         import os
@@ -360,36 +396,36 @@ def 编译Latex(chatbot, history, main_file_original, main_file_modified, work_f
             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
-        ok = compile_latex_with_timeout(f'pdflatex -interaction=batchmode -file-line-error {main_file_original}.tex', work_folder_original)
+        yield from update_ui_latest_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
+        ok = compile_latex_with_timeout(get_compile_command(compiler, main_file_original), work_folder_original)
 
-        yield from update_ui_lastest_msg(f'尝试第 {n_fix}/{max_try} 次编译, 编译转化后的PDF ...', chatbot, history)   # 刷新Gradio前端界面
-        ok = compile_latex_with_timeout(f'pdflatex -interaction=batchmode -file-line-error {main_file_modified}.tex', work_folder_modified)
+        yield from update_ui_latest_msg(f'尝试第 {n_fix}/{max_try} 次编译, 编译转化后的PDF ...', chatbot, history)   # 刷新Gradio前端界面
+        ok = compile_latex_with_timeout(get_compile_command(compiler, main_file_modified), work_folder_modified)
 
         if ok and os.path.exists(pj(work_folder_modified, f'{main_file_modified}.pdf')):
             # 只有第二步成功，才能继续下面的步骤
-            yield from update_ui_lastest_msg(f'尝试第 {n_fix}/{max_try} 次编译, 编译BibTex ...', chatbot, history)    # 刷新Gradio前端界面
+            yield from update_ui_latest_msg(f'尝试第 {n_fix}/{max_try} 次编译, 编译BibTex ...', chatbot, history)    # 刷新Gradio前端界面
             if not os.path.exists(pj(work_folder_original, f'{main_file_original}.bbl')):
                 ok = compile_latex_with_timeout(f'bibtex  {main_file_original}.aux', work_folder_original)
             if not os.path.exists(pj(work_folder_modified, f'{main_file_modified}.bbl')):
                 ok = compile_latex_with_timeout(f'bibtex  {main_file_modified}.aux', work_folder_modified)
 
-            yield from update_ui_lastest_msg(f'尝试第 {n_fix}/{max_try} 次编译, 编译文献交叉引用 ...', chatbot, history)  # 刷新Gradio前端界面
-            ok = compile_latex_with_timeout(f'pdflatex -interaction=batchmode -file-line-error {main_file_original}.tex', work_folder_original)
-            ok = compile_latex_with_timeout(f'pdflatex -interaction=batchmode -file-line-error {main_file_modified}.tex', work_folder_modified)
-            ok = compile_latex_with_timeout(f'pdflatex -interaction=batchmode -file-line-error {main_file_original}.tex', work_folder_original)
-            ok = compile_latex_with_timeout(f'pdflatex -interaction=batchmode -file-line-error {main_file_modified}.tex', work_folder_modified)
+            yield from update_ui_latest_msg(f'尝试第 {n_fix}/{max_try} 次编译, 编译文献交叉引用 ...', chatbot, history)  # 刷新Gradio前端界面
+            ok = compile_latex_with_timeout(get_compile_command(compiler, main_file_original), work_folder_original)
+            ok = compile_latex_with_timeout(get_compile_command(compiler, main_file_modified), work_folder_modified)
+            ok = compile_latex_with_timeout(get_compile_command(compiler, main_file_original), work_folder_original)
+            ok = compile_latex_with_timeout(get_compile_command(compiler, main_file_modified), work_folder_modified)
 
             if mode!='translate_zh':
-                yield from update_ui_lastest_msg(f'尝试第 {n_fix}/{max_try} 次编译, 使用latexdiff生成论文转化前后对比 ...', chatbot, history) # 刷新Gradio前端界面
+                yield from update_ui_latest_msg(f'尝试第 {n_fix}/{max_try} 次编译, 使用latexdiff生成论文转化前后对比 ...', chatbot, history) # 刷新Gradio前端界面
                 logger.info(    f'latexdiff --encoding=utf8 --append-safecmd=subfile {work_folder_original}/{main_file_original}.tex  {work_folder_modified}/{main_file_modified}.tex --flatten > {work_folder}/merge_diff.tex')
                 ok = compile_latex_with_timeout(f'latexdiff --encoding=utf8 --append-safecmd=subfile {work_folder_original}/{main_file_original}.tex  {work_folder_modified}/{main_file_modified}.tex --flatten > {work_folder}/merge_diff.tex', os.getcwd())
 
-                yield from update_ui_lastest_msg(f'尝试第 {n_fix}/{max_try} 次编译, 正在编译对比PDF ...', chatbot, history)   # 刷新Gradio前端界面
-                ok = compile_latex_with_timeout(f'pdflatex  -interaction=batchmode -file-line-error merge_diff.tex', work_folder)
+                yield from update_ui_latest_msg(f'尝试第 {n_fix}/{max_try} 次编译, 正在编译对比PDF ...', chatbot, history)   # 刷新Gradio前端界面
+                ok = compile_latex_with_timeout(get_compile_command(compiler, 'merge_diff'), work_folder)
                 ok = compile_latex_with_timeout(f'bibtex    merge_diff.aux', work_folder)
-                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)
+                ok = compile_latex_with_timeout(get_compile_command(compiler, 'merge_diff'), work_folder)
+                ok = compile_latex_with_timeout(get_compile_command(compiler, 'merge_diff'), work_folder)
 
         # <---------- 检查结果 ----------->
         results_ = ""
@@ -399,13 +435,13 @@ def 编译Latex(chatbot, history, main_file_original, main_file_modified, work_f
         results_ += f"原始PDF编译是否成功: {original_pdf_success};"
         results_ += f"转化PDF编译是否成功: {modified_pdf_success};"
         results_ += f"对比PDF编译是否成功: {diff_pdf_success};"
-        yield from update_ui_lastest_msg(f'第{n_fix}编译结束:<br/>{results_}...', chatbot, history) # 刷新Gradio前端界面
+        yield from update_ui_latest_msg(f'第{n_fix}编译结束:<br/>{results_}...', chatbot, history) # 刷新Gradio前端界面
 
         if diff_pdf_success:
             result_pdf = pj(work_folder_modified, f'merge_diff.pdf')    # get pdf path
             promote_file_to_downloadzone(result_pdf, rename_file=None, chatbot=chatbot)  # promote file to web UI
         if modified_pdf_success:
-            yield from update_ui_lastest_msg(f'转化PDF编译已经成功, 正在尝试生成对比PDF, 请稍候 ...', chatbot, history)    # 刷新Gradio前端界面
+            yield from update_ui_latest_msg(f'转化PDF编译已经成功, 正在尝试生成对比PDF, 请稍候 ...', 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')):
@@ -436,7 +472,7 @@ def 编译Latex(chatbot, history, main_file_original, main_file_modified, work_f
                 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
+            yield from update_ui_latest_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
 
     return False # 失败啦

crazy_functions/latex_fns/latex_toolbox.py

@@ -168,7 +168,7 @@ def set_forbidden_text(text, mask, pattern, flags=0):
 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.
+    count the number of the braces so as to catch complete text area.
     e.g.
     \begin{abstract} blablablablablabla. \end{abstract}
     """
@@ -188,7 +188,7 @@ def reverse_forbidden_text(text, mask, pattern, flags=0, forbid_wrapper=True):
 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.
+    count the number of the braces so as to catch complete text area.
     e.g.
     \caption{blablablablabla\texbf{blablabla}blablabla.}
     """
@@ -214,7 +214,7 @@ def reverse_forbidden_text_careful_brace(
 ):
     """
     Move area out of preserve area (make text editable for GPT)
-    count the number of the braces so as to catch compelete text area.
+    count the number of the braces so as to catch complete text area.
     e.g.
     \caption{blablablablabla\texbf{blablabla}blablabla.}
     """
@@ -287,23 +287,23 @@ 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 = []
+    candidates = []
     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)
+            candidates.append(texf)
         else:
             continue
 
-    if len(canidates) == 0:
+    if len(candidates) == 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 = []
+    elif len(candidates) == 1:
+        return candidates[0]
+    else:  # if len(candidates) >= 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
+        candidates_score = []
         # 给出一些判定模板文档的词作为扣分项
         unexpected_words = [
             "\\LaTeX",
@@ -316,19 +316,19 @@ def find_main_tex_file(file_manifest, mode):
             "reviewers",
         ]
         expected_words = ["\\input", "\\ref", "\\cite"]
-        for texf in canidates:
-            canidates_score.append(0)
+        for texf in candidates:
+            candidates_score.append(0)
             with open(texf, "r", encoding="utf8", errors="ignore") as f:
                 file_content = f.read()
                 file_content = rm_comments(file_content)
             for uw in unexpected_words:
                 if uw in file_content:
-                    canidates_score[-1] -= 1
+                    candidates_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]
+                    candidates_score[-1] += 1
+        select = np.argmax(candidates_score)  # 取评分最高者返回
+        return candidates[select]
 
 
 def rm_comments(main_file):
@@ -374,7 +374,7 @@ def find_tex_file_ignore_case(fp):
 
 def merge_tex_files_(project_foler, main_file, mode):
     """
-    Merge Tex project recrusively
+    Merge Tex project recursively
     """
     main_file = rm_comments(main_file)
     for s in reversed([q for q in re.finditer(r"\\input\{(.*?)\}", main_file, re.M)]):
@@ -429,7 +429,7 @@ def find_title_and_abs(main_file):
 
 def merge_tex_files(project_foler, main_file, mode):
     """
-    Merge Tex project recrusively
+    Merge Tex project recursively
     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
     """

crazy_functions/media_fns/get_media.py

@@ -0,0 +1,43 @@
+from toolbox import update_ui, get_conf, promote_file_to_downloadzone, update_ui_latest_msg, generate_file_link
+from shared_utils.docker_as_service_api import stream_daas
+from shared_utils.docker_as_service_api import DockerServiceApiComModel
+import random
+
+def download_video(video_id, only_audio, user_name, chatbot, history):
+    from toolbox import get_log_folder
+    chatbot.append([None, "Processing..."])
+    yield from update_ui(chatbot, history)
+    client_command = f'{video_id} --audio-only' if only_audio else video_id
+    server_urls = get_conf('DAAS_SERVER_URLS')
+    server_url = random.choice(server_urls)
+    docker_service_api_com_model = DockerServiceApiComModel(client_command=client_command)
+    save_file_dir = get_log_folder(user_name, plugin_name='media_downloader')
+    for output_manifest in stream_daas(docker_service_api_com_model, server_url, save_file_dir):
+        status_buf = ""
+        status_buf += "DaaS message: \n\n"
+        status_buf += output_manifest['server_message'].replace('\n', '<br/>')
+        status_buf += "\n\n"
+        status_buf += "DaaS standard error: \n\n"
+        status_buf += output_manifest['server_std_err'].replace('\n', '<br/>')
+        status_buf += "\n\n"
+        status_buf += "DaaS standard output: \n\n"
+        status_buf += output_manifest['server_std_out'].replace('\n', '<br/>')
+        status_buf += "\n\n"
+        status_buf += "DaaS file attach: \n\n"
+        status_buf += str(output_manifest['server_file_attach'])
+        yield from update_ui_latest_msg(status_buf, chatbot, history)
+
+    return output_manifest['server_file_attach']
+
+
+def search_videos(keywords):
+    from toolbox import get_log_folder
+    client_command = keywords
+    server_urls = get_conf('DAAS_SERVER_URLS')
+    server_url = random.choice(server_urls)
+    server_url = server_url.replace('stream', 'search')
+    docker_service_api_com_model = DockerServiceApiComModel(client_command=client_command)
+    save_file_dir = get_log_folder("default_user", plugin_name='media_downloader')
+    for output_manifest in stream_daas(docker_service_api_com_model, server_url, save_file_dir):
+        return output_manifest['server_message']
+

crazy_functions/multi_stage/multi_stage_utils.py

@@ -1,6 +1,6 @@
 from pydantic import BaseModel, Field
 from typing import List
-from toolbox import update_ui_lastest_msg, disable_auto_promotion
+from toolbox import update_ui_latest_msg, disable_auto_promotion
 from toolbox import CatchException, update_ui, get_conf, select_api_key, get_log_folder
 from request_llms.bridge_all import predict_no_ui_long_connection
 from crazy_functions.json_fns.pydantic_io import GptJsonIO, JsonStringError

crazy_functions/pdf_fns/parse_pdf.py

@@ -113,7 +113,7 @@ def translate_pdf(article_dict, llm_kwargs, chatbot, fp, generated_conclusion_fi
             return [txt]
         else:
             # raw_token_num > TOKEN_LIMIT_PER_FRAGMENT
-            # find a smooth token limit to achieve even seperation
+            # find a smooth token limit to achieve even separation
             count = int(math.ceil(raw_token_num / TOKEN_LIMIT_PER_FRAGMENT))
             token_limit_smooth = raw_token_num // count + count
             return breakdown_text_to_satisfy_token_limit(txt, limit=token_limit_smooth, llm_model=llm_kwargs['llm_model'])

crazy_functions/pdf_fns/parse_pdf_grobid.py

@@ -1,6 +1,6 @@
 import os
 from toolbox import CatchException, report_exception, get_log_folder, gen_time_str, check_packages
-from toolbox import update_ui, promote_file_to_downloadzone, update_ui_lastest_msg, disable_auto_promotion
+from toolbox import update_ui, promote_file_to_downloadzone, update_ui_latest_msg, disable_auto_promotion
 from toolbox import write_history_to_file, promote_file_to_downloadzone, get_conf, extract_archive
 from crazy_functions.pdf_fns.parse_pdf import parse_pdf, translate_pdf
 

crazy_functions/pdf_fns/parse_pdf_via_doc2x.py

@@ -6,75 +6,128 @@ from crazy_functions.crazy_utils import get_files_from_everything
 from shared_utils.colorful import *
 from loguru import logger
 import os
+import requests
 import time
 
-def refresh_key(doc2x_api_key):
-    import requests, json
-    url = "https://api.doc2x.noedgeai.com/api/token/refresh"
-    res = requests.post(
-        url,
-        headers={"Authorization": "Bearer " + doc2x_api_key}
-    )
-    res_json = []
-    if res.status_code == 200:
-        decoded = res.content.decode("utf-8")
-        res_json = json.loads(decoded)
-        doc2x_api_key = res_json['data']['token']
-    else:
-        raise RuntimeError(format("[ERROR] status code: %d, body: %s" % (res.status_code, res.text)))
-    return doc2x_api_key
 
+def retry_request(max_retries=3, delay=3):
+    """
+    Decorator for retrying HTTP requests
+    Args:
+        max_retries: Maximum number of retry attempts
+        delay: Delay between retries in seconds
+    """
+
+    def decorator(func):
+        def wrapper(*args, **kwargs):
+            for attempt in range(max_retries):
+                try:
+                    return func(*args, **kwargs)
+                except Exception as e:
+                    if attempt < max_retries - 1:
+                        logger.error(
+                            f"Request failed, retrying... ({attempt + 1}/{max_retries}) Error: {e}"
+                        )
+                        time.sleep(delay)
+                        continue
+                    raise e
+            return None
+
+        return wrapper
+
+    return decorator
+
+
+@retry_request()
+def make_request(method, url, **kwargs):
+    """
+    Make HTTP request with retry mechanism
+    """
+    return requests.request(method, url, **kwargs)
+
+
+def doc2x_api_response_status(response, uid=""):
+    """
+    Check the status of Doc2x API response
+    Args:
+        response_data: Response object from Doc2x API
+    """
+    response_json = response.json()
+    response_data = response_json.get("data", {})
+    code = response_json.get("code", "Unknown")
+    meg = response_data.get("message", response_json)
+    trace_id = response.headers.get("trace-id", "Failed to get trace-id")
+    if response.status_code != 200:
+        raise RuntimeError(
+            f"Doc2x return an error:\nTrace ID: {trace_id} {uid}\n{response.status_code} - {response_json}"
+        )
+    if code in ["parse_page_limit_exceeded", "parse_concurrency_limit"]:
+        raise RuntimeError(
+            f"Reached the limit of Doc2x:\nTrace ID: {trace_id} {uid}\n{code} - {meg}"
+        )
+    if code not in ["ok", "success"]:
+        raise RuntimeError(
+            f"Doc2x return an error:\nTrace ID: {trace_id} {uid}\n{code} - {meg}"
+        )
+    return response_data
 
 
 def 解析PDF_DOC2X_转Latex(pdf_file_path):
-    zip_file_path, unzipped_folder = 解析PDF_DOC2X(pdf_file_path, format='tex')
+    zip_file_path, unzipped_folder = 解析PDF_DOC2X(pdf_file_path, format="tex")
     return unzipped_folder
 
 
-def 解析PDF_DOC2X(pdf_file_path, format='tex'):
+def 解析PDF_DOC2X(pdf_file_path, format="tex"):
     """
-        format: 'tex', 'md', 'docx'
+    format: 'tex', 'md', 'docx'
     """
-    import requests, json, os
-    DOC2X_API_KEY = get_conf('DOC2X_API_KEY')
+
+    DOC2X_API_KEY = get_conf("DOC2X_API_KEY")
     latex_dir = get_log_folder(plugin_name="pdf_ocr_latex")
     markdown_dir = get_log_folder(plugin_name="pdf_ocr")
     doc2x_api_key = DOC2X_API_KEY
 
+    # < ------ 第1步：预上传获取URL，然后上传文件 ------ >
+    logger.info("Doc2x 上传文件：预上传获取URL")
+    res = make_request(
+        "POST",
+        "https://v2.doc2x.noedgeai.com/api/v2/parse/preupload",
+        headers={"Authorization": "Bearer " + doc2x_api_key},
+        timeout=15,
+    )
+    res_data = doc2x_api_response_status(res)
+    upload_url = res_data["url"]
+    uuid = res_data["uid"]
 
-    # < ------ 第1步：上传 ------ >
-    logger.info("Doc2x 第1步：上传")
-    with open(pdf_file_path, 'rb') as file:
-        res = requests.post(
-            "https://v2.doc2x.noedgeai.com/api/v2/parse/pdf",
-            headers={"Authorization": "Bearer " + doc2x_api_key},
-            data=file
-        )
-    # res_json = []
-    if res.status_code == 200:
-        res_json = res.json()
-    else:
-        raise RuntimeError(f"Doc2x return an error: {res.json()}")
-    uuid = res_json['data']['uid']
+    logger.info("Doc2x 上传文件：上传文件")
+    with open(pdf_file_path, "rb") as file:
+        res = make_request("PUT", upload_url, data=file, timeout=60)
+    res.raise_for_status()
 
     # < ------ 第2步：轮询等待 ------ >
-    logger.info("Doc2x 第2步：轮询等待")
-    params = {'uid': uuid}
-    while True:
-        res = requests.get(
-            'https://v2.doc2x.noedgeai.com/api/v2/parse/status',
+    logger.info("Doc2x 处理文件中：轮询等待")
+    params = {"uid": uuid}
+    max_attempts = 60
+    attempt = 0
+    while attempt < max_attempts:
+        res = make_request(
+            "GET",
+            "https://v2.doc2x.noedgeai.com/api/v2/parse/status",
             headers={"Authorization": "Bearer " + doc2x_api_key},
-            params=params
+            params=params,
+            timeout=15,
         )
-        res_json = res.json()
-        if res_json['data']['status'] == "success":
+        res_data = doc2x_api_response_status(res)
+        if res_data["status"] == "success":
             break
-        elif res_json['data']['status'] == "processing":
-            time.sleep(3)
-            logger.info(f"Doc2x is processing at {res_json['data']['progress']}%")
-        elif res_json['data']['status'] == "failed":
-            raise RuntimeError(f"Doc2x return an error: {res_json}")
-
+        elif res_data["status"] == "processing":
+            time.sleep(5)
+            logger.info(f"Doc2x is processing at {res_data['progress']}%")
+            attempt += 1
+        else:
+            raise RuntimeError(f"Doc2x return an error: {res_data}")
+    if attempt >= max_attempts:
+        raise RuntimeError("Doc2x processing timeout after maximum attempts")
 
     # < ------ 第3步：提交转化 ------ >
     logger.info("Doc2x 第3步：提交转化")
@@ -84,42 +137,44 @@ def 解析PDF_DOC2X(pdf_file_path, format='tex'):
         "formula_mode": "dollar",
         "filename": "output"
     }
-    res = requests.post(
-        'https://v2.doc2x.noedgeai.com/api/v2/convert/parse',
+    res = make_request(
+        "POST",
+        "https://v2.doc2x.noedgeai.com/api/v2/convert/parse",
         headers={"Authorization": "Bearer " + doc2x_api_key},
-        json=data
+        json=data,
+        timeout=15,
     )
-    if res.status_code == 200:
-        res_json = res.json()
-    else:
-        raise RuntimeError(f"Doc2x return an error: {res.json()}")
-
+    doc2x_api_response_status(res, uid=f"uid: {uuid}")
 
     # < ------ 第4步：等待结果 ------ >
     logger.info("Doc2x 第4步：等待结果")
-    params = {'uid': uuid}
-    while True:
-        res = requests.get(
-            'https://v2.doc2x.noedgeai.com/api/v2/convert/parse/result',
+    params = {"uid": uuid}
+    max_attempts = 36
+    attempt = 0
+    while attempt < max_attempts:
+        res = make_request(
+            "GET",
+            "https://v2.doc2x.noedgeai.com/api/v2/convert/parse/result",
             headers={"Authorization": "Bearer " + doc2x_api_key},
-            params=params
+            params=params,
+            timeout=15,
         )
-        res_json = res.json()
-        if res_json['data']['status'] == "success":
+        res_data = doc2x_api_response_status(res, uid=f"uid: {uuid}")
+        if res_data["status"] == "success":
             break
-        elif res_json['data']['status'] == "processing":
+        elif res_data["status"] == "processing":
             time.sleep(3)
-            logger.info(f"Doc2x still processing")
-        elif res_json['data']['status'] == "failed":
-            raise RuntimeError(f"Doc2x return an error: {res_json}")
-
+            logger.info("Doc2x still processing to convert file")
+            attempt += 1
+    if attempt >= max_attempts:
+        raise RuntimeError("Doc2x conversion timeout after maximum attempts")
 
     # < ------ 第5步：最后的处理 ------ >
-    logger.info("Doc2x 第5步：最后的处理")
+    logger.info("Doc2x 第5步：下载转换后的文件")
 
-    if format=='tex':
+    if format == "tex":
         target_path = latex_dir
-    if format=='md':
+    if format == "md":
         target_path = markdown_dir
     os.makedirs(target_path, exist_ok=True)
 
@@ -127,17 +182,18 @@ def 解析PDF_DOC2X(pdf_file_path, format='tex'):
     # < ------ 下载 ------ >
     for attempt in range(max_attempt):
         try:
-            result_url = res_json['data']['url']
-            res = requests.get(result_url)
-            zip_path = os.path.join(target_path, gen_time_str() + '.zip')
+            result_url = res_data["url"]
+            res = make_request("GET", result_url, timeout=60)
+            zip_path = os.path.join(target_path, gen_time_str() + ".zip")
             unzip_path = os.path.join(target_path, gen_time_str())
             if res.status_code == 200:
-                with open(zip_path, "wb") as f: f.write(res.content)
+                with open(zip_path, "wb") as f:
+                    f.write(res.content)
             else:
                 raise RuntimeError(f"Doc2x return an error: {res.json()}")
         except Exception as e:
             if attempt < max_attempt - 1:
-                logger.error(f"Failed to download latex file, retrying... {e}")
+                logger.error(f"Failed to download uid = {uuid} file, retrying... {e}")
                 time.sleep(3)
                 continue
             else:
@@ -145,22 +201,31 @@ def 解析PDF_DOC2X(pdf_file_path, format='tex'):
 
     # < ------ 解压 ------ >
     import zipfile
-    with zipfile.ZipFile(zip_path, 'r') as zip_ref:
+    with zipfile.ZipFile(zip_path, "r") as zip_ref:
         zip_ref.extractall(unzip_path)
     return zip_path, unzip_path
 
 
-def 解析PDF_DOC2X_单文件(fp, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, DOC2X_API_KEY, user_request):
-
+def 解析PDF_DOC2X_单文件(
+    fp,
+    project_folder,
+    llm_kwargs,
+    plugin_kwargs,
+    chatbot,
+    history,
+    system_prompt,
+    DOC2X_API_KEY,
+    user_request,
+):
     def pdf2markdown(filepath):
         chatbot.append((None, f"Doc2x 解析中"))
-        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+        yield from update_ui(chatbot=chatbot, history=history)  # 刷新界面
 
-        md_zip_path, unzipped_folder = 解析PDF_DOC2X(filepath, format='md')
+        md_zip_path, unzipped_folder = 解析PDF_DOC2X(filepath, format="md")
 
         promote_file_to_downloadzone(md_zip_path, chatbot=chatbot)
         chatbot.append((None, f"完成解析 {md_zip_path} ..."))
-        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+        yield from update_ui(chatbot=chatbot, history=history)  # 刷新界面
         return md_zip_path
 
     def deliver_to_markdown_plugin(md_zip_path, user_request):
@@ -174,77 +239,97 @@ def 解析PDF_DOC2X_单文件(fp, project_folder, llm_kwargs, plugin_kwargs, cha
         os.makedirs(target_path_base, exist_ok=True)
         shutil.copyfile(md_zip_path, this_file_path)
         ex_folder = this_file_path + ".extract"
-        extract_archive(
-            file_path=this_file_path, dest_dir=ex_folder
-        )
+        extract_archive(file_path=this_file_path, dest_dir=ex_folder)
 
         # edit markdown files
-        success, file_manifest, project_folder = get_files_from_everything(ex_folder, type='.md')
+        success, file_manifest, project_folder = get_files_from_everything(
+            ex_folder, type=".md"
+        )
         for generated_fp in file_manifest:
             # 修正一些公式问题
-            with open(generated_fp, 'r', encoding='utf8') as f:
+            with open(generated_fp, "r", encoding="utf8") as f:
                 content = f.read()
             # 将公式中的\[ \]替换成$$
-            content = content.replace(r'\[', r'$$').replace(r'\]', r'$$')
+            content = content.replace(r"\[", r"$$").replace(r"\]", r"$$")
             # 将公式中的\( \)替换成$
-            content = content.replace(r'\(', r'$').replace(r'\)', r'$')
-            content = content.replace('```markdown', '\n').replace('```', '\n')
-            with open(generated_fp, 'w', encoding='utf8') as f:
+            content = content.replace(r"\(", r"$").replace(r"\)", r"$")
+            content = content.replace("```markdown", "\n").replace("```", "\n")
+            with open(generated_fp, "w", encoding="utf8") as f:
                 f.write(content)
             promote_file_to_downloadzone(generated_fp, chatbot=chatbot)
-            yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+            yield from update_ui(chatbot=chatbot, history=history)  # 刷新界面
 
             # 生成在线预览html
-            file_name = '在线预览翻译（原文）' + gen_time_str() + '.html'
+            file_name = "在线预览翻译（原文）" + gen_time_str() + ".html"
             preview_fp = os.path.join(ex_folder, file_name)
-            from shared_utils.advanced_markdown_format import markdown_convertion_for_file
+            from shared_utils.advanced_markdown_format import (
+                markdown_convertion_for_file,
+            )
+
             with open(generated_fp, "r", encoding="utf-8") as f:
                 md = f.read()
             #     # Markdown中使用不标准的表格，需要在表格前加上一个emoji，以便公式渲染
             #     md = re.sub(r'^<table>', r'.<table>', md, flags=re.MULTILINE)
             html = markdown_convertion_for_file(md)
-            with open(preview_fp, "w", encoding="utf-8") as f: f.write(html)
+            with open(preview_fp, "w", encoding="utf-8") as f:
+                f.write(html)
             chatbot.append([None, f"生成在线预览：{generate_file_link([preview_fp])}"])
             promote_file_to_downloadzone(preview_fp, chatbot=chatbot)
 
-
-
         chatbot.append((None, f"调用Markdown插件 {ex_folder} ..."))
-        plugin_kwargs['markdown_expected_output_dir'] = ex_folder
+        plugin_kwargs["markdown_expected_output_dir"] = ex_folder
 
-        translated_f_name = 'translated_markdown.md'
-        generated_fp = plugin_kwargs['markdown_expected_output_path'] = os.path.join(ex_folder, translated_f_name)
-        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
-        yield from Markdown英译中(ex_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request)
+        translated_f_name = "translated_markdown.md"
+        generated_fp = plugin_kwargs["markdown_expected_output_path"] = os.path.join(
+            ex_folder, translated_f_name
+        )
+        yield from update_ui(chatbot=chatbot, history=history)  # 刷新界面
+        yield from Markdown英译中(
+            ex_folder,
+            llm_kwargs,
+            plugin_kwargs,
+            chatbot,
+            history,
+            system_prompt,
+            user_request,
+        )
         if os.path.exists(generated_fp):
             # 修正一些公式问题
-            with open(generated_fp, 'r', encoding='utf8') as f: content = f.read()
-            content = content.replace('```markdown', '\n').replace('```', '\n')
+            with open(generated_fp, "r", encoding="utf8") as f:
+                content = f.read()
+            content = content.replace("```markdown", "\n").replace("```", "\n")
             # Markdown中使用不标准的表格，需要在表格前加上一个emoji，以便公式渲染
             # content = re.sub(r'^<table>', r'.<table>', content, flags=re.MULTILINE)
-            with open(generated_fp, 'w', encoding='utf8') as f: f.write(content)
+            with open(generated_fp, "w", encoding="utf8") as f:
+                f.write(content)
             # 生成在线预览html
-            file_name = '在线预览翻译' + gen_time_str() + '.html'
+            file_name = "在线预览翻译" + gen_time_str() + ".html"
             preview_fp = os.path.join(ex_folder, file_name)
-            from shared_utils.advanced_markdown_format import markdown_convertion_for_file
+            from shared_utils.advanced_markdown_format import (
+                markdown_convertion_for_file,
+            )
+
             with open(generated_fp, "r", encoding="utf-8") as f:
                 md = f.read()
             html = markdown_convertion_for_file(md)
-            with open(preview_fp, "w", encoding="utf-8") as f: f.write(html)
+            with open(preview_fp, "w", encoding="utf-8") as f:
+                f.write(html)
             promote_file_to_downloadzone(preview_fp, chatbot=chatbot)
             # 生成包含图片的压缩包
             dest_folder = get_log_folder(chatbot.get_user())
-            zip_name = '翻译后的带图文档.zip'
-            zip_folder(source_folder=ex_folder, dest_folder=dest_folder, zip_name=zip_name)
+            zip_name = "翻译后的带图文档.zip"
+            zip_folder(
+                source_folder=ex_folder, dest_folder=dest_folder, zip_name=zip_name
+            )
             zip_fp = os.path.join(dest_folder, zip_name)
             promote_file_to_downloadzone(zip_fp, chatbot=chatbot)
-            yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+            yield from update_ui(chatbot=chatbot, history=history)  # 刷新界面
+
     md_zip_path = yield from pdf2markdown(fp)
     yield from deliver_to_markdown_plugin(md_zip_path, user_request)
 
+
 def 解析PDF_基于DOC2X(file_manifest, *args):
     for index, fp in enumerate(file_manifest):
         yield from 解析PDF_DOC2X_单文件(fp, *args)
     return
-
-

crazy_functions/pdf_fns/parse_word.py

@@ -14,17 +14,17 @@ def extract_text_from_files(txt, chatbot, history):
         final_result(list):文本内容
         page_one(list):第一页内容/摘要
         file_manifest(list):文件路径
-        excption(string):需要用户手动处理的信息,如没出错则保持为空
+        exception(string):需要用户手动处理的信息,如没出错则保持为空
     """
 
     final_result = []
     page_one = []
     file_manifest = []
-    excption = ""
+    exception = ""
 
     if txt == "":
         final_result.append(txt)
-        return False, final_result, page_one, file_manifest, excption   #如输入区内容不是文件则直接返回输入区内容
+        return False, final_result, page_one, file_manifest, exception   #如输入区内容不是文件则直接返回输入区内容
 
     #查找输入区内容中的文件
     file_pdf,pdf_manifest,folder_pdf = get_files_from_everything(txt, '.pdf')
@@ -33,20 +33,20 @@ def extract_text_from_files(txt, chatbot, history):
     file_doc,doc_manifest,folder_doc = get_files_from_everything(txt, '.doc')
 
     if file_doc:
-        excption = "word"
-        return False, final_result, page_one, file_manifest, excption
+        exception = "word"
+        return False, final_result, page_one, file_manifest, exception
 
     file_num = len(pdf_manifest) + len(md_manifest) + len(word_manifest)
     if file_num == 0:
         final_result.append(txt)
-        return False, final_result, page_one, file_manifest, excption   #如输入区内容不是文件则直接返回输入区内容
+        return False, final_result, page_one, file_manifest, exception   #如输入区内容不是文件则直接返回输入区内容
 
     if file_pdf:
         try:    # 尝试导入依赖，如果缺少依赖，则给出安装建议
             import fitz
         except:
-            excption = "pdf"
-            return False, final_result, page_one, file_manifest, excption
+            exception = "pdf"
+            return False, final_result, page_one, file_manifest, exception
         for index, fp in enumerate(pdf_manifest):
             file_content, pdf_one = read_and_clean_pdf_text(fp) # （尝试）按照章节切割PDF
             file_content = file_content.encode('utf-8', 'ignore').decode()   # avoid reading non-utf8 chars
@@ -72,8 +72,8 @@ def extract_text_from_files(txt, chatbot, history):
         try:    # 尝试导入依赖，如果缺少依赖，则给出安装建议
             from docx import Document
         except:
-            excption = "word_pip"
-            return False, final_result, page_one, file_manifest, excption
+            exception = "word_pip"
+            return False, final_result, page_one, file_manifest, exception
         for index, fp in enumerate(word_manifest):
             doc = Document(fp)
             file_content = '\n'.join([p.text for p in doc.paragraphs])
@@ -82,4 +82,4 @@ def extract_text_from_files(txt, chatbot, history):
             final_result.append(file_content)
             file_manifest.append(os.path.relpath(fp, folder_word))
 
-    return True, final_result, page_one, file_manifest, excption
+    return True, final_result, page_one, file_manifest, exception

crazy_functions/rag_fns/arxiv_fns/arxiv_downloader.py

@@ -1,115 +0,0 @@
-import logging
-import tarfile
-from pathlib import Path
-from typing import Optional, Dict
-
-import requests
-
-
-class ArxivDownloader:
-    """用于下载arXiv论文源码的下载器"""
-
-    def __init__(self, root_dir: str = "./papers", proxies: Optional[Dict[str, str]] = None):
-        """
-        初始化下载器
-        
-        Args:
-            root_dir: 保存下载文件的根目录
-            proxies: 代理服务器设置，例如 {"http": "http://proxy:port", "https": "https://proxy:port"}
-        """
-        self.root_dir = Path(root_dir)
-        self.root_dir.mkdir(exist_ok=True)
-        self.proxies = proxies
-
-        # 配置日志
-        logging.basicConfig(
-            level=logging.INFO,
-            format='%(asctime)s - %(levelname)s - %(message)s'
-        )
-
-    def _download_and_extract(self, arxiv_id: str) -> str:
-        """
-        下载并解压arxiv论文源码
-        
-        Args:
-            arxiv_id: arXiv论文ID，例如"2103.00020"
-            
-        Returns:
-            str: 解压后的文件目录路径
-            
-        Raises:
-            RuntimeError: 当下载失败时抛出
-        """
-        paper_dir = self.root_dir / arxiv_id
-        tar_path = paper_dir / f"{arxiv_id}.tar.gz"
-
-        # 检查缓存
-        if paper_dir.exists() and any(paper_dir.iterdir()):
-            logging.info(f"Using cached version for {arxiv_id}")
-            return str(paper_dir)
-
-        paper_dir.mkdir(exist_ok=True)
-
-        urls = [
-            f"https://arxiv.org/src/{arxiv_id}",
-            f"https://arxiv.org/e-print/{arxiv_id}"
-        ]
-
-        for url in urls:
-            try:
-                logging.info(f"Downloading from {url}")
-                response = requests.get(url, proxies=self.proxies)
-                if response.status_code == 200:
-                    tar_path.write_bytes(response.content)
-                    with tarfile.open(tar_path, 'r:gz') as tar:
-                        tar.extractall(path=paper_dir)
-                    return str(paper_dir)
-            except Exception as e:
-                logging.warning(f"Download failed for {url}: {e}")
-                continue
-
-        raise RuntimeError(f"Failed to download paper {arxiv_id}")
-
-    def download_paper(self, arxiv_id: str) -> str:
-        """
-        下载指定的arXiv论文
-        
-        Args:
-            arxiv_id: arXiv论文ID
-            
-        Returns:
-            str: 论文文件所在的目录路径
-        """
-        return self._download_and_extract(arxiv_id)
-
-
-def main():
-    """测试下载功能"""
-    # 配置代理（如果需要）
-    proxies = {
-        "http": "http://your-proxy:port",
-        "https": "https://your-proxy:port"
-    }
-
-    # 创建下载器实例（如果不需要代理，可以不传入proxies参数）
-    downloader = ArxivDownloader(root_dir="./downloaded_papers", proxies=None)
-
-    # 测试下载一篇论文（这里使用一个示例ID）
-    try:
-        paper_id = "2103.00020"  # 这是一个示例ID
-        paper_dir = downloader.download_paper(paper_id)
-        print(f"Successfully downloaded paper to: {paper_dir}")
-
-        # 检查下载的文件
-        paper_path = Path(paper_dir)
-        if paper_path.exists():
-            print("Downloaded files:")
-            for file in paper_path.rglob("*"):
-                if file.is_file():
-                    print(f"- {file.relative_to(paper_path)}")
-    except Exception as e:
-        print(f"Error downloading paper: {e}")
-
-
-if __name__ == "__main__":
-    main()

crazy_functions/rag_fns/arxiv_fns/arxiv_splitter.py

@@ -1,836 +0,0 @@
-import asyncio
-import logging
-import re
-import tarfile
-import time
-from copy import deepcopy
-from pathlib import Path
-from typing import List, Optional, Dict, Set
-
-import aiohttp
-
-from crazy_functions.rag_fns.arxiv_fns.author_extractor import LatexAuthorExtractor
-from crazy_functions.rag_fns.arxiv_fns.essay_structure import EssayStructureParser, DocumentStructure, read_tex_file
-from crazy_functions.rag_fns.arxiv_fns.section_extractor import Section
-from crazy_functions.rag_fns.arxiv_fns.section_fragment import SectionFragment
-from crazy_functions.rag_fns.arxiv_fns.tex_utils import TexUtils
-from crazy_functions.doc_fns.content_folder import PaperContentFormatter, PaperMetadata
-
-
-def save_fragments_to_file(fragments: List[SectionFragment], output_dir: Path ) -> Path:
-    """
-    Save all fragments to a single structured markdown file.
-
-    Args:
-        fragments: List of SectionFragment objects
-        output_dir: Output directory path
-
-    Returns:
-        Path: Path to the generated markdown file
-    """
-    from datetime import datetime
-    from pathlib import Path
-
-    # Create output directory
-    timestamp = datetime.now().strftime("%Y%m%d_%H%M%S")
-    output_path = Path(output_dir)
-    output_path.mkdir(parents=True, exist_ok=True)
-
-    # Generate filename
-    filename = f"paper_latex_content_{timestamp}.md"
-    file_path = output_path/ filename
-
-    # Group fragments by section
-    sections = {}
-    for fragment in fragments:
-        section = fragment.current_section or "Uncategorized"
-        if section not in sections:
-            sections[section] = []
-        sections[section].append(fragment)
-
-    with open(file_path, "w", encoding="utf-8") as f:
-        # Write document header
-        f.write("# Document Fragments Analysis\n\n")
-        f.write("## Overview\n")
-        f.write(f"- Total Fragments: {len(fragments)}\n")
-        f.write(f"- Generated Time: {datetime.now().strftime('%Y-%m-%d %H:%M:%S')}\n")
-
-        # Add paper information if available
-        if fragments and (fragments[0].title or fragments[0].abstract):
-            f.write("\n## Paper Information\n")
-            if fragments[0].title:
-                f.write(f"### Title\n{fragments[0].title}\n")
-            if fragments[0].authors:
-                f.write(f"\n### Authors\n{fragments[0].authors}\n")
-            if fragments[0].abstract:
-                f.write(f"\n### Abstract\n{fragments[0].abstract}\n")
-
-        # Write section tree if available
-        if fragments and fragments[0].catalogs:
-            f.write("\n## Section Tree\n")
-            f.write("```\n")  # 添加代码块开始标记
-            f.write(fragments[0].catalogs)
-            f.write("\n```")  # 添加代码块结束标记
-
-        # Generate table of contents
-        f.write("\n## Table of Contents\n")
-        for section in sections:
-            clean_section = section.strip() or "Uncategorized"
-            fragment_count = len(sections[section])
-            f.write(f"- [{clean_section}](#{clean_section.lower().replace(' ', '-')}) "
-                    f"({fragment_count} fragments)\n")
-
-        # Write content sections
-        f.write("\n## Content\n")
-        for section, section_fragments in sections.items():
-            clean_section = section.strip() or "Uncategorized"
-            f.write(f"\n### {clean_section}\n")
-
-            # Write each fragment
-            for i, fragment in enumerate(section_fragments, 1):
-                f.write(f"\n#### Fragment {i}\n")
-
-                # Metadata
-                f.write("**Metadata:**\n")
-                metadata = [
-                    f"- Section: {fragment.current_section}",
-                    f"- Length: {len(fragment.content)} chars",
-                    f"- ArXiv ID: {fragment.arxiv_id}" if fragment.arxiv_id else None
-                ]
-                f.write("\n".join(filter(None, metadata)) + "\n")
-
-                # Content
-                f.write("\n**Content:**\n")
-                f.write("\n")
-                f.write(fragment.content)
-                f.write("\n")
-
-                # Bibliography if exists
-                if fragment.bibliography:
-                    f.write("\n**Bibliography:**\n")
-                    f.write("```bibtex\n")
-                    f.write(fragment.bibliography)
-                    f.write("\n```\n")
-
-                # Add separator
-                if i < len(section_fragments):
-                    f.write("\n---\n")
-
-        # Add statistics
-        f.write("\n## Statistics\n")
-
-        # Length distribution
-        lengths = [len(f.content) for f in fragments]
-        f.write("\n### Length Distribution\n")
-        f.write(f"- Minimum: {min(lengths)} chars\n")
-        f.write(f"- Maximum: {max(lengths)} chars\n")
-        f.write(f"- Average: {sum(lengths) / len(lengths):.1f} chars\n")
-
-        # Section distribution
-        f.write("\n### Section Distribution\n")
-        for section, section_fragments in sections.items():
-            percentage = (len(section_fragments) / len(fragments)) * 100
-            f.write(f"- {section}: {len(section_fragments)} ({percentage:.1f}%)\n")
-
-    print(f"Fragments saved to: {file_path}")
-    return file_path
-
-
-# 定义各种引用命令的模式
-CITATION_PATTERNS = [
-    # 基本的 \cite{} 格式
-    r'\\cite(?:\*)?(?:\[[^\]]*\])?{([^}]+)}',
-    # natbib 格式
-    r'\\citep(?:\*)?(?:\[[^\]]*\])?{([^}]+)}',
-    r'\\citet(?:\*)?(?:\[[^\]]*\])?{([^}]+)}',
-    r'\\citeauthor(?:\*)?(?:\[[^\]]*\])?{([^}]+)}',
-    r'\\citeyear(?:\*)?(?:\[[^\]]*\])?{([^}]+)}',
-    r'\\citealt(?:\*)?(?:\[[^\]]*\])?{([^}]+)}',
-    r'\\citealp(?:\*)?(?:\[[^\]]*\])?{([^}]+)}',
-    # biblatex 格式
-    r'\\textcite(?:\*)?(?:\[[^\]]*\])?{([^}]+)}',
-    r'\\parencite(?:\*)?(?:\[[^\]]*\])?{([^}]+)}',
-    r'\\autocite(?:\*)?(?:\[[^\]]*\])?{([^}]+)}',
-    # 自定义 [cite:...] 格式
-    r'\[cite:([^\]]+)\]',
-]
-
-# 编译所有模式
-COMPILED_PATTERNS = [re.compile(pattern) for pattern in CITATION_PATTERNS]
-
-
-class ArxivSplitter:
-    """Arxiv论文智能分割器"""
-
-    def __init__(self,
-                 root_dir: str = "gpt_log/arxiv_cache",
-                 proxies: Optional[Dict[str, str]] = None,
-                 cache_ttl: int = 7 * 24 * 60 * 60):
-        """
-        初始化分割器
-
-        Args:
-            char_range: 字符数范围(最小值, 最大值)
-            root_dir: 缓存根目录
-            proxies: 代理设置
-            cache_ttl: 缓存过期时间(秒)
-        """
-        self.root_dir = Path(root_dir)
-        self.root_dir.mkdir(parents=True, exist_ok=True)
-        self.proxies = proxies or {}
-        self.cache_ttl = cache_ttl
-
-        # 动态计算最优线程数
-        import multiprocessing
-        cpu_count = multiprocessing.cpu_count()
-        # 根据CPU核心数动态设置，但设置上限防止过度并发
-        self.document_structure = DocumentStructure()
-        self.document_parser = EssayStructureParser()
-
-        self.max_workers = min(32, cpu_count * 2)
-
-        # 初始化TeX处理器
-        self.tex_processor = TexUtils()
-
-        # 配置日志
-        self._setup_logging()
-
-    def _setup_logging(self):
-        """配置日志"""
-        logging.basicConfig(
-            level=logging.INFO,
-            format='%(asctime)s - %(levelname)s - %(message)s'
-        )
-        self.logger = logging.getLogger(__name__)
-
-    def _normalize_arxiv_id(self, input_str: str) -> str:
-        """规范化ArXiv ID"""
-        if 'arxiv.org/' in input_str.lower():
-            # 处理URL格式
-            if '/pdf/' in input_str:
-                arxiv_id = input_str.split('/pdf/')[-1]
-            else:
-                arxiv_id = input_str.split('/abs/')[-1]
-            # 移除版本号和其他后缀
-            return arxiv_id.split('v')[0].strip()
-        return input_str.split('v')[0].strip()
-
-    def _check_cache(self, paper_dir: Path) -> bool:
-        """
-        检查缓存是否有效，包括文件完整性检查
-
-        Args:
-            paper_dir: 论文目录路径
-
-        Returns:
-            bool: 如果缓存有效返回True，否则返回False
-        """
-        if not paper_dir.exists():
-            return False
-
-        # 检查目录中是否存在必要文件
-        has_tex_files = False
-        has_main_tex = False
-
-        for file_path in paper_dir.rglob("*"):
-            if file_path.suffix == '.tex':
-                has_tex_files = True
-                content = self.tex_processor.read_file(str(file_path))
-                if content and r'\documentclass' in content:
-                    has_main_tex = True
-                    break
-
-        if not (has_tex_files and has_main_tex):
-            return False
-
-        # 检查缓存时间
-        cache_time = paper_dir.stat().st_mtime
-        if (time.time() - cache_time) < self.cache_ttl:
-            self.logger.info(f"Using valid cache for {paper_dir.name}")
-            return True
-
-        return False
-
-    async def download_paper(self, arxiv_id: str, paper_dir: Path) -> bool:
-        """
-        异步下载论文，包含重试机制和临时文件处理
-
-        Args:
-            arxiv_id: ArXiv论文ID
-            paper_dir: 目标目录路径
-
-        Returns:
-            bool: 下载成功返回True，否则返回False
-        """
-        from crazy_functions.rag_fns.arxiv_fns.arxiv_downloader import ArxivDownloader
-        temp_tar_path = paper_dir / f"{arxiv_id}_temp.tar.gz"
-        final_tar_path = paper_dir / f"{arxiv_id}.tar.gz"
-
-        # 确保目录存在
-        paper_dir.mkdir(parents=True, exist_ok=True)
-
-        # 尝试使用 ArxivDownloader 下载
-        try:
-            downloader = ArxivDownloader(root_dir=str(paper_dir), proxies=self.proxies)
-            downloaded_dir = downloader.download_paper(arxiv_id)
-            if downloaded_dir:
-                self.logger.info(f"Successfully downloaded using ArxivDownloader to {downloaded_dir}")
-                return True
-        except Exception as e:
-            self.logger.warning(f"ArxivDownloader failed: {str(e)}. Falling back to direct download.")
-
-        # 如果 ArxivDownloader 失败，使用原有的下载方式作为备选
-        urls = [
-            f"https://arxiv.org/src/{arxiv_id}",
-            f"https://arxiv.org/e-print/{arxiv_id}"
-        ]
-
-        max_retries = 3
-        retry_delay = 1  # 初始重试延迟（秒）
-
-        for url in urls:
-            for attempt in range(max_retries):
-                try:
-                    self.logger.info(f"Downloading from {url} (attempt {attempt + 1}/{max_retries})")
-                    async with aiohttp.ClientSession() as session:
-                        async with session.get(url, proxy=self.proxies.get('http')) as response:
-                            if response.status == 200:
-                                content = await response.read()
-
-                                # 写入临时文件
-                                temp_tar_path.write_bytes(content)
-
-                                try:
-                                    # 验证tar文件完整性并解压
-                                    loop = asyncio.get_event_loop()
-                                    await loop.run_in_executor(None, self._process_tar_file, temp_tar_path, paper_dir)
-
-                                    # 下载成功后移动临时文件到最终位置
-                                    temp_tar_path.rename(final_tar_path)
-                                    return True
-
-                                except Exception as e:
-                                    self.logger.warning(f"Invalid tar file: {str(e)}")
-                                    if temp_tar_path.exists():
-                                        temp_tar_path.unlink()
-
-                except Exception as e:
-                    self.logger.warning(f"Download attempt {attempt + 1} failed from {url}: {str(e)}")
-                    await asyncio.sleep(retry_delay * (attempt + 1))  # 指数退避
-                    continue
-
-        return False
-
-    def _process_tar_file(self, tar_path: Path, extract_path: Path):
-        """处理tar文件的同步操作"""
-        with tarfile.open(tar_path, 'r:gz') as tar:
-            tar.testall()  # 验证文件完整性
-            tar.extractall(path=extract_path)  # 解压文件
-
-    def process_references(self, doc_structure: DocumentStructure, ref_bib: str) -> DocumentStructure:
-        """
-        Process citations in document structure and add referenced literature for each section
-
-        Args:
-            doc_structure: DocumentStructure object
-            ref_bib: String containing references separated by newlines
-
-        Returns:
-            Updated DocumentStructure object
-        """
-        try:
-            # Create a copy to avoid modifying the original
-            doc = deepcopy(doc_structure)
-
-            # Parse references into a mapping
-            ref_map = self._parse_references(ref_bib)
-            if not ref_map:
-                self.logger.warning("No valid references found in ref_bib")
-                return doc
-
-            # Process all sections recursively
-            self._process_section_references(doc.toc, ref_map)
-
-            return doc
-
-        except Exception as e:
-            self.logger.error(f"Error processing references: {str(e)}")
-            return doc_structure  # Return original if processing fails
-
-    def _process_section_references(self, sections: List[Section], ref_map: Dict[str, str]) -> None:
-        """
-        Recursively process sections to add references
-
-        Args:
-            sections: List of Section objects
-            ref_map: Mapping of citation keys to full references
-        """
-        for section in sections:
-            if section.content:
-                # Find citations in current section
-                cited_refs = self.find_citations(section.content)
-
-                if cited_refs:
-                    # Get full references for citations
-                    full_refs = []
-                    for ref_key in cited_refs:
-                        ref_text = ref_map.get(ref_key)
-                        if ref_text:
-                            full_refs.append(ref_text)
-                        else:
-                            self.logger.warning(f"Reference not found for citation key: {ref_key}")
-
-                    # Add references to section content
-                    if full_refs:
-                        section.bibliography = "\n\n".join(full_refs)
-
-            # Process subsections recursively
-            if section.subsections:
-                self._process_section_references(section.subsections, ref_map)
-
-    def _parse_references(self, ref_bib: str) -> Dict[str, str]:
-        """
-        Parse reference string into a mapping of citation keys to full references
-
-        Args:
-            ref_bib: Reference string with references separated by newlines
-
-        Returns:
-            Dict mapping citation keys to full reference text
-        """
-        ref_map = {}
-        current_ref = []
-        current_key = None
-
-        try:
-            for line in ref_bib.split('\n'):
-                line = line.strip()
-                if not line:
-                    continue
-
-                # New reference entry
-                if line.startswith('@'):
-                    # Save previous reference if exists
-                    if current_key and current_ref:
-                        ref_map[current_key] = '\n'.join(current_ref)
-                        current_ref = []
-
-                    # Extract key from new reference
-                    key_match = re.search(r'{(.*?),', line)
-                    if key_match:
-                        current_key = key_match.group(1)
-                        current_ref.append(line)
-                else:
-                    if current_ref is not None:
-                        current_ref.append(line)
-
-            # Save last reference
-            if current_key and current_ref:
-                ref_map[current_key] = '\n'.join(current_ref)
-
-        except Exception as e:
-            self.logger.error(f"Error parsing references: {str(e)}")
-
-        return ref_map
-
-    # 编译一次正则表达式以提高效率
-
-    @staticmethod
-    def _clean_citation_key(key: str) -> str:
-        """Clean individual citation key."""
-        return key.strip().strip(',').strip()
-
-    def _extract_keys_from_group(self, keys_str: str) -> Set[str]:
-        """Extract and clean individual citation keys from a group."""
-        try:
-            # 分割多个引用键（支持逗号和分号分隔）
-            separators = '[,;]'
-            keys = re.split(separators, keys_str)
-            # 清理并过滤空键
-            return {self._clean_citation_key(k) for k in keys if self._clean_citation_key(k)}
-        except Exception as e:
-            self.logger.warning(f"Error processing citation group '{keys_str}': {e}")
-            return set()
-
-    def find_citations(self, content: str) -> Set[str]:
-        """
-        Find citation keys in text content in various formats.
-
-        Args:
-            content: Text content to search for citations
-
-        Returns:
-            Set of unique citation keys
-
-        Examples:
-            Supported formats include:
-            - \cite{key1,key2}
-            - \cite[p. 1]{key}
-            - \citep{key}
-            - \citet{key}
-            - [cite:key1, key2]
-            - And many other variants
-        """
-        citations = set()
-
-        if not content:
-            return citations
-
-        try:
-            # 对每个编译好的模式进行搜索
-            for pattern in COMPILED_PATTERNS:
-                matches = pattern.finditer(content)
-                for match in matches:
-                    # 获取捕获组中的引用键
-                    keys_str = match.group(1)
-                    if keys_str:
-                        # 提取并添加所有引用键
-                        new_keys = self._extract_keys_from_group(keys_str)
-                        citations.update(new_keys)
-
-        except Exception as e:
-            self.logger.error(f"Error finding citations: {str(e)}")
-
-        # 移除明显无效的键
-        citations = {key for key in citations
-                     if key and not key.startswith(('\\', '{', '}', '[', ']'))}
-
-        return citations
-
-    def get_citation_contexts(self, content: str, context_chars: int = 100) -> dict:
-        """
-        Find citations and their surrounding context.
-
-        Args:
-            content: Text content to search for citations
-            context_chars: Number of characters of context to include before/after
-
-        Returns:
-            Dict mapping citation keys to lists of context strings
-        """
-        contexts = {}
-
-        if not content:
-            return contexts
-
-        try:
-            for pattern in COMPILED_PATTERNS:
-                matches = pattern.finditer(content)
-                for match in matches:
-                    # 获取匹配的位置
-                    start = max(0, match.start() - context_chars)
-                    end = min(len(content), match.end() + context_chars)
-
-                    # 获取上下文
-                    context = content[start:end]
-
-                    # 获取并处理引用键
-                    keys_str = match.group(1)
-                    keys = self._extract_keys_from_group(keys_str)
-
-                    # 为每个键添加上下文
-                    for key in keys:
-                        if key not in contexts:
-                            contexts[key] = []
-                        contexts[key].append(context)
-
-        except Exception as e:
-            self.logger.error(f"Error finding citation contexts: {str(e)}")
-
-        return contexts
-
-    async def process(self, arxiv_id_or_url: str) -> List[SectionFragment]:
-        """
-        Process ArXiv paper and convert to list of SectionFragments.
-        Each fragment represents the smallest section unit.
-
-        Args:
-            arxiv_id_or_url: ArXiv paper ID or URL
-
-        Returns:
-            List[SectionFragment]: List of processed paper fragments
-        """
-        try:
-            arxiv_id = self._normalize_arxiv_id(arxiv_id_or_url)
-            paper_dir = self.root_dir / arxiv_id
-
-            # Check if paper directory exists, if not, try to download
-            if not paper_dir.exists():
-                self.logger.info(f"Downloading paper {arxiv_id}")
-                await self.download_paper(arxiv_id, paper_dir)
-
-            # Find main TeX file
-            main_tex = self.tex_processor.find_main_tex_file(str(paper_dir))
-            if not main_tex:
-                raise RuntimeError(f"No main TeX file found in {paper_dir}")
-
-            # 读取主 TeX 文件内容
-            main_tex_content = read_tex_file(main_tex)
-
-            # Get all related TeX files and references
-            tex_files = self.tex_processor.resolve_includes(main_tex)
-            ref_bib = self.tex_processor.resolve_references(main_tex, paper_dir)
-
-            if not tex_files:
-                raise RuntimeError(f"No valid TeX files found for {arxiv_id}")
-
-            # Reset document structure for new processing
-            self.document_structure = DocumentStructure()
-
-            # 提取作者信息
-            author_extractor = LatexAuthorExtractor()
-            authors = author_extractor.extract_authors(main_tex_content)
-            self.document_structure.authors = authors  # 保存到文档结构中
-
-            # Process each TeX file
-            for file_path in tex_files:
-                self.logger.info(f"Processing TeX file: {file_path}")
-                tex_content = read_tex_file(file_path)
-                if tex_content:
-                    additional_doc = self.document_parser.parse(tex_content)
-                    self.document_structure = self.document_structure.merge(additional_doc)
-
-            # Process references if available
-            if ref_bib:
-                self.document_structure = self.process_references(self.document_structure, ref_bib)
-                self.logger.info("Successfully processed references")
-            else:
-                self.logger.info("No references found to process")
-
-            # Generate table of contents once
-            section_tree = self.document_structure.generate_toc_tree()
-
-            # Convert DocumentStructure to SectionFragments
-            fragments = self._convert_to_fragments(
-                doc_structure=self.document_structure,
-                arxiv_id=arxiv_id,
-                section_tree=section_tree
-            )
-
-            return fragments
-
-        except Exception as e:
-            self.logger.error(f"Failed to process {arxiv_id_or_url}: {str(e)}")
-            raise
-
-    def _convert_to_fragments(self,
-                              doc_structure: DocumentStructure,
-                              arxiv_id: str,
-                              section_tree: str) -> List[SectionFragment]:
-        """
-        Convert DocumentStructure to list of SectionFragments.
-        Creates a fragment for each leaf section in the document hierarchy.
-
-        Args:
-            doc_structure: Source DocumentStructure
-            arxiv_id: ArXiv paper ID
-            section_tree: Pre-generated table of contents tree
-
-        Returns:
-            List[SectionFragment]: List of paper fragments
-        """
-        fragments = []
-
-        # Create a base template for all fragments to avoid repetitive assignments
-        base_fragment_template = {
-            'title': doc_structure.title,
-            'authors': doc_structure.authors,
-            'abstract': doc_structure.abstract,
-            'catalogs': section_tree,
-            'arxiv_id': arxiv_id
-        }
-
-        def get_leaf_sections(section: Section, path: List[str] = None) -> None:
-            """
-            Recursively find all leaf sections and create fragments.
-            A leaf section is one that has content but no subsections, or has neither.
-
-            Args:
-                section: Current section being processed
-                path: List of section titles forming the path to current section
-            """
-            if path is None:
-                path = []
-
-            current_path = path + [section.title]
-
-            if not section.subsections:
-                # This is a leaf section, create a fragment if it has content
-                if section.content or section.bibliography:
-                    fragment = SectionFragment(
-                        **base_fragment_template,
-                        current_section="/".join(current_path),
-                        content=self._clean_content(section.content),
-                        bibliography=section.bibliography
-                    )
-                    if self._validate_fragment(fragment):
-                        fragments.append(fragment)
-            else:
-                # Process each subsection
-                for subsection in section.subsections:
-                    get_leaf_sections(subsection, current_path)
-
-        # Process all top-level sections
-        for section in doc_structure.toc:
-            get_leaf_sections(section)
-
-        # Add a fragment for the abstract if it exists
-        if doc_structure.abstract:
-            abstract_fragment = SectionFragment(
-                **base_fragment_template,
-                current_section="Abstract",
-                content=self._clean_content(doc_structure.abstract)
-            )
-            if self._validate_fragment(abstract_fragment):
-                fragments.insert(0, abstract_fragment)
-
-        self.logger.info(f"Created {len(fragments)} fragments")
-        return fragments
-
-    def _validate_fragment(self, fragment: SectionFragment) -> bool:
-        """
-        Validate if the fragment has all required fields with meaningful content.
-
-        Args:
-            fragment: SectionFragment to validate
-
-        Returns:
-            bool: True if fragment is valid, False otherwise
-        """
-        try:
-            return all([
-                fragment.title.strip(),
-                fragment.catalogs.strip(),
-                fragment.current_section.strip(),
-                fragment.content.strip() or fragment.bibliography.strip()
-            ])
-        except AttributeError:
-            return False
-
-    def _clean_content(self, content: str) -> str:
-        """
-        Clean and normalize content text.
-
-        Args:
-            content: Raw content text
-
-        Returns:
-            str: Cleaned content text
-        """
-        if not content:
-            return ""
-
-        # Remove excessive whitespace
-        content = re.sub(r'\s+', ' ', content)
-
-        # Remove remaining LaTeX artifacts
-        content = re.sub(r'\\item\s*', '• ', content)  # Convert \item to bullet points
-        content = re.sub(r'\\[a-zA-Z]+\{([^}]*)\}', r'\1', content)  # Remove simple LaTeX commands
-
-        # Clean special characters
-        content = content.replace('\\\\', '\n')  # Convert LaTeX newlines to actual newlines
-        content = re.sub(r'\s*\n\s*', '\n', content)  # Clean up newlines
-
-        return content.strip()
-
-
-def process_arxiv_sync(splitter: ArxivSplitter, arxiv_id: str) -> tuple[List[SectionFragment], str, List[Path]]:
-    """
-    同步处理 ArXiv 文档并返回分割后的片段
-
-    Args:
-        splitter: ArxivSplitter 实例
-        arxiv_id: ArXiv 文档ID
-
-    Returns:
-        list: 分割后的文档片段列表
-    """
-    try:
-        from crazy_functions.doc_fns.tex_html_formatter import PaperHtmlFormatter
-        # 创建一个异步函数来执行异步操作
-        async def _process():
-            return await splitter.process(arxiv_id)
-
-        # 使用 asyncio.run() 运行异步函数
-        output_files=[]
-        fragments = asyncio.run(_process())
-        file_save_path = splitter.root_dir / "arxiv_fragments"
-        # 保存片段到文件
-        try:
-            md_output_dir = save_fragments_to_file(
-                fragments,
-                output_dir = file_save_path
-            )
-            output_files.append(md_output_dir)
-        except:
-            pass
-        # 创建论文格式化器
-        formatter = PaperContentFormatter()
-
-        # 准备元数据
-        # 创建格式化选项
-
-        metadata = PaperMetadata(
-            title=fragments[0].title,
-            authors=fragments[0].authors,
-            abstract=fragments[0].abstract,
-            catalogs=fragments[0].catalogs,
-            arxiv_id=fragments[0].arxiv_id
-        )
-
-        # 格式化内容
-        formatted_content = formatter.format(fragments, metadata)
-
-        try:
-            html_formatter = PaperHtmlFormatter(fragments, file_save_path)
-            html_output_dir = html_formatter.save_html()
-            output_files.append(html_output_dir)
-        except:
-            pass
-        return fragments, formatted_content, output_files
-
-    except Exception as e:
-        print(f"✗ Processing failed for {arxiv_id}: {str(e)}")
-        raise
-def test_arxiv_splitter():
-    """测试ArXiv分割器的功能"""
-
-    # 测试配置
-    test_cases = [
-        {
-            "arxiv_id": "2411.03663",
-            "expected_title": "Large Language Models and Simple Scripts",
-            "min_fragments": 10,
-        },
-        # {
-        #     "arxiv_id": "1805.10988",
-        #     "expected_title": "RAG vs Fine-tuning",
-        #     "min_fragments": 15,
-        # }
-    ]
-
-    # 创建分割器实例
-    splitter = ArxivSplitter(
-        root_dir="private_upload/default_user"
-    )
-
-    for case in test_cases:
-        print(f"\nTesting paper: {case['arxiv_id']}")
-        try:
-            # fragments = await splitter.process(case['arxiv_id'])
-            fragments, formatted_content, output_dir = process_arxiv_sync(splitter, case['arxiv_id'])
-            # 保存fragments
-            for fragment in fragments:
-                # 长度检查
-                print((fragment.content))
-                print(len(fragment.content))
-            # 类型检查
-            print(output_dir)
-
-        except Exception as e:
-            print(f"✗ Test failed for {case['arxiv_id']}: {str(e)}")
-            raise
-
-
-if __name__ == "__main__":
-    test_arxiv_splitter()

crazy_functions/rag_fns/arxiv_fns/author_extractor.py

@@ -1,177 +0,0 @@
-import re
-from typing import Optional
-
-
-class LatexAuthorExtractor:
-    def __init__(self):
-        # Patterns for matching author blocks with balanced braces
-        self.author_block_patterns = [
-            # Standard LaTeX patterns with optional arguments
-            r'\\author(?:\s*\[[^\]]*\])?\s*\{((?:[^{}]|{(?:[^{}]|{[^{}]*})*})*)\}',
-            r'\\(?:title)?author[s]?\s*\{((?:[^{}]|{(?:[^{}]|{[^{}]*})*})*)\}',
-            r'\\name[s]?\s*\{((?:[^{}]|{(?:[^{}]|{[^{}]*})*})*)\}',
-            r'\\Author[s]?\s*\{((?:[^{}]|{(?:[^{}]|{[^{}]*})*})*)\}',
-            r'\\AUTHOR[S]?\s*\{((?:[^{}]|{(?:[^{}]|{[^{}]*})*})*)\}',
-            # Conference and journal specific patterns
-            r'\\addauthor\s*\{((?:[^{}]|{(?:[^{}]|{[^{}]*})*})*)\}',
-            r'\\IEEEauthor\s*\{((?:[^{}]|{(?:[^{}]|{[^{}]*})*})*)\}',
-            r'\\speaker\s*\{((?:[^{}]|{(?:[^{}]|{[^{}]*})*})*)\}',
-            r'\\authorrunning\s*\{((?:[^{}]|{(?:[^{}]|{[^{}]*})*})*)\}',
-            # Academic publisher specific patterns
-            r'\\alignauthor\s*\{((?:[^{}]|{(?:[^{}]|{[^{}]*})*})*)\}',
-            r'\\spauthor\s*\{((?:[^{}]|{(?:[^{}]|{[^{}]*})*})*)\}',
-            r'\\authors\s*\{((?:[^{}]|{(?:[^{}]|{[^{}]*})*})*)\}',
-        ]
-
-        # Cleaning patterns for LaTeX commands and formatting
-        self.cleaning_patterns = [
-            # Text formatting commands - preserve content
-            (r'\\textbf\{([^}]+)\}', r'\1'),
-            (r'\\textit\{([^}]+)\}', r'\1'),
-            (r'\\emph\{([^}]+)\}', r'\1'),
-            (r'\\texttt\{([^}]+)\}', r'\1'),
-            (r'\\textrm\{([^}]+)\}', r'\1'),
-            (r'\\text\{([^}]+)\}', r'\1'),
-
-            # Affiliation and footnote markers
-            (r'\$\^{[^}]+}\$', ''),
-            (r'\^{[^}]+}', ''),
-            (r'\\thanks\{[^}]+\}', ''),
-            (r'\\footnote\{[^}]+\}', ''),
-
-            # Email and contact formatting
-            (r'\\email\{([^}]+)\}', r'\1'),
-            (r'\\href\{[^}]+\}\{([^}]+)\}', r'\1'),
-
-            # Institution formatting
-            (r'\\inst\{[^}]+\}', ''),
-            (r'\\affil\{[^}]+\}', ''),
-
-            # Special characters and symbols
-            (r'\\&', '&'),
-            (r'\\\\\s*', ' '),
-            (r'\\,', ' '),
-            (r'\\;', ' '),
-            (r'\\quad', ' '),
-            (r'\\qquad', ' '),
-
-            # Math mode content
-            (r'\$[^$]+\$', ''),
-
-            # Common symbols
-            (r'\\dagger', '†'),
-            (r'\\ddagger', '‡'),
-            (r'\\ast', '*'),
-            (r'\\star', '★'),
-
-            # Remove remaining LaTeX commands
-            (r'\\[a-zA-Z]+', ''),
-
-            # Clean up remaining special characters
-            (r'[\\{}]', '')
-        ]
-
-    def extract_author_block(self, text: str) -> Optional[str]:
-        """
-        Extract the complete author block from LaTeX text.
-
-        Args:
-            text (str): Input LaTeX text
-
-        Returns:
-            Optional[str]: Extracted author block or None if not found
-        """
-        try:
-            if not text:
-                return None
-
-            for pattern in self.author_block_patterns:
-                match = re.search(pattern, text, re.DOTALL | re.MULTILINE)
-                if match:
-                    return match.group(1).strip()
-            return None
-
-        except (AttributeError, IndexError) as e:
-            print(f"Error extracting author block: {e}")
-            return None
-
-    def clean_tex_commands(self, text: str) -> str:
-        """
-        Remove LaTeX commands and formatting from text while preserving content.
-
-        Args:
-            text (str): Text containing LaTeX commands
-
-        Returns:
-            str: Cleaned text with commands removed
-        """
-        if not text:
-            return ""
-
-        cleaned_text = text
-
-        # Apply cleaning patterns
-        for pattern, replacement in self.cleaning_patterns:
-            cleaned_text = re.sub(pattern, replacement, cleaned_text)
-
-        # Clean up whitespace
-        cleaned_text = re.sub(r'\s+', ' ', cleaned_text)
-        cleaned_text = cleaned_text.strip()
-
-        return cleaned_text
-
-    def extract_authors(self, text: str) -> Optional[str]:
-        """
-        Extract and clean author information from LaTeX text.
-
-        Args:
-            text (str): Input LaTeX text
-
-        Returns:
-            Optional[str]: Cleaned author information or None if extraction fails
-        """
-        try:
-            if not text:
-                return None
-
-            # Extract author block
-            author_block = self.extract_author_block(text)
-            if not author_block:
-                return None
-
-            # Clean LaTeX commands
-            cleaned_authors = self.clean_tex_commands(author_block)
-            return cleaned_authors or None
-
-        except Exception as e:
-            print(f"Error processing text: {e}")
-            return None
-
-
-def test_author_extractor():
-    """Test the LatexAuthorExtractor with sample inputs."""
-    test_cases = [
-        # Basic test case
-        (r"\author{John Doe}", "John Doe"),
-
-        # Test with multiple authors
-        (r"\author{Alice Smith \and Bob Jones}", "Alice Smith and Bob Jones"),
-
-        # Test with affiliations
-        (r"\author[1]{John Smith}\affil[1]{University}", "John Smith"),
-
-    ]
-
-    extractor = LatexAuthorExtractor()
-
-    for i, (input_tex, expected) in enumerate(test_cases, 1):
-        result = extractor.extract_authors(input_tex)
-    print(f"\nTest case {i}:")
-    print(f"Input: {input_tex[:50]}...")
-    print(f"Expected: {expected[:50]}...")
-    print(f"Got: {result[:50]}...")
-    print(f"Pass: {bool(result and result.strip() == expected.strip())}")
-
-
-if __name__ == "__main__":
-    test_author_extractor()

crazy_functions/rag_fns/arxiv_fns/essay_structure.py

@@ -1,290 +0,0 @@
-"""
-LaTeX Document Parser
-
-This module provides functionality for parsing and extracting structured information from LaTeX documents,
-including metadata, document structure, and content. It uses modular design and clean architecture principles.
-"""
-
-import logging
-import re
-from abc import ABC, abstractmethod
-from copy import deepcopy
-from dataclasses import dataclass, field
-from typing import List, Dict
-
-from crazy_functions.rag_fns.arxiv_fns.latex_cleaner import clean_latex_commands
-from crazy_functions.rag_fns.arxiv_fns.section_extractor import Section, EnhancedSectionExtractor
-
-# Configure logging
-logging.basicConfig(level=logging.INFO)
-logger = logging.getLogger(__name__)
-
-
-def read_tex_file(file_path):
-    encodings = ['utf-8', 'latin1', 'gbk', 'gb2312', 'ascii']
-    for encoding in encodings:
-        try:
-            with open(file_path, 'r', encoding=encoding) as f:
-                return f.read()
-        except UnicodeDecodeError:
-            continue
-
-
-@dataclass
-class DocumentStructure:
-    title: str = ''
-    authors: str = ''
-    abstract: str = ''
-    toc: List[Section] = field(default_factory=list)
-    metadata: Dict[str, str] = field(default_factory=dict)
-
-    def merge(self, other: 'DocumentStructure', strategy: str = 'smart') -> 'DocumentStructure':
-        """
-        Merge this document structure with another one.
-
-        Args:
-            other: Another DocumentStructure to merge with
-            strategy: Merge strategy - 'smart' (default) or 'append'
-                     'smart' - Intelligently merge sections with same titles
-                     'append' - Simply append sections from other document
-        """
-        merged = deepcopy(self)
-
-        # Merge title if needed
-        if not merged.title and other.title:
-            merged.title = other.title
-
-        # Merge abstract
-        merged.abstract = self._merge_abstract(merged.abstract, other.abstract)
-
-        # Merge metadata
-        merged.metadata.update(other.metadata)
-
-        if strategy == 'append':
-            merged.toc.extend(deepcopy(other.toc))
-        else:  # smart merge
-            # Create sections lookup for efficient merging
-            sections_map = {s.title: s for s in merged.toc}
-
-            for other_section in other.toc:
-                if other_section.title in sections_map:
-                    # Merge existing section
-                    idx = next(i for i, s in enumerate(merged.toc)
-                               if s.title == other_section.title)
-                    merged.toc[idx] = merged.toc[idx].merge(other_section)
-                else:
-                    # Add new section
-                    merged.toc.append(deepcopy(other_section))
-
-        return merged
-
-    @staticmethod
-    def _merge_abstract(abstract1: str, abstract2: str) -> str:
-        """Merge abstracts intelligently."""
-        if not abstract1:
-            return abstract2
-        if not abstract2:
-            return abstract1
-        # Combine non-empty abstracts with a separator
-        return f"{abstract1}\n\n{abstract2}"
-
-    def generate_toc_tree(self, indent_char: str = "  ", abstract_preview_length: int = 0) -> str:
-        """
-        Generate a tree-like string representation of the table of contents including abstract.
-
-        Args:
-            indent_char: Character(s) used for indentation. Default is two spaces.
-            abstract_preview_length: Maximum length of abstract preview. Default is 200 characters.
-
-        Returns:
-            str: A formatted string showing the hierarchical document structure with abstract
-        """
-
-        def _format_section(section: Section, level: int = 0) -> str:
-            # Create the current section line with proper indentation
-            current_line = f"{indent_char * level}{'•' if level > 0 else '○'} {section.title}\n"
-
-            # Recursively process subsections
-            subsections = ""
-            if section.subsections:
-                subsections = "".join(_format_section(subsec, level + 1)
-                                      for subsec in section.subsections)
-
-            return current_line + subsections
-
-        result = []
-
-        # Add document title if it exists
-        if self.title:
-            result.append(f"《{self.title}》\n")
-
-        # Add abstract if it exists
-        if self.abstract:
-            result.append("\n□ Abstract:")
-            # Format abstract content with word wrap
-            abstract_preview = self.abstract[:abstract_preview_length]
-            if len(self.abstract) > abstract_preview_length:
-                abstract_preview += "..."
-
-            # Split abstract into lines and indent them
-            wrapped_lines = []
-            current_line = ""
-            for word in abstract_preview.split():
-                if len(current_line) + len(word) + 1 <= 80:  # 80 characters per line
-                    current_line = (current_line + " " + word).strip()
-                else:
-                    wrapped_lines.append(current_line)
-                    current_line = word
-            if current_line:
-                wrapped_lines.append(current_line)
-
-            # Add formatted abstract lines
-            for line in wrapped_lines:
-                result.append(f"\n{indent_char}{line}")
-            result.append("\n")  # Add extra newline after abstract
-
-        # Add table of contents header if there are sections
-        if self.toc:
-            result.append("\n◈ Table of Contents:\n")
-
-            # Add all top-level sections and their subsections
-            result.extend(_format_section(section, 0) for section in self.toc)
-
-        return "".join(result)
-
-
-class BaseExtractor(ABC):
-    """Base class for LaTeX content extractors."""
-
-    @abstractmethod
-    def extract(self, content: str) -> str:
-        """Extract specific content from LaTeX document."""
-        pass
-
-
-class TitleExtractor(BaseExtractor):
-    """Extracts title from LaTeX document."""
-
-    PATTERNS = [
-        r'\\title{(.+?)}',
-        r'\\title\[.*?\]{(.+?)}',
-        r'\\Title{(.+?)}',
-        r'\\TITLE{(.+?)}',
-        r'\\begin{document}\s*\\section[*]?{(.+?)}',
-        r'\\maketitle\s*\\section[*]?{(.+?)}',
-        r'\\chapter[*]?{(.+?)}'
-    ]
-
-    def extract(self, content: str) -> str:
-        """Extract title using defined patterns."""
-        for pattern in self.PATTERNS:
-            matches = list(re.finditer(pattern, content, re.IGNORECASE | re.DOTALL))
-            for match in matches:
-                title = match.group(1).strip()
-                if title:
-                    return clean_latex_commands(title)
-        return ''
-
-
-class AbstractExtractor(BaseExtractor):
-    """Extracts abstract from LaTeX document."""
-
-    PATTERNS = [
-        r'\\begin{abstract}(.*?)\\end{abstract}',
-        r'\\abstract{(.*?)}',
-        r'\\ABSTRACT{(.*?)}',
-        r'\\Abstract{(.*?)}',
-        r'\\begin{Abstract}(.*?)\\end{Abstract}',
-        r'\\section[*]?{(?:Abstract|ABSTRACT)}\s*(.*?)(?:\\section|\Z)',
-        r'\\chapter[*]?{(?:Abstract|ABSTRACT)}\s*(.*?)(?:\\chapter|\Z)'
-    ]
-
-    def extract(self, content: str) -> str:
-        """Extract abstract using defined patterns."""
-        for pattern in self.PATTERNS:
-            matches = list(re.finditer(pattern, content, re.IGNORECASE | re.DOTALL))
-            for match in matches:
-                abstract = match.group(1).strip()
-                if abstract:
-                    return clean_latex_commands(abstract)
-        return ''
-
-
-class EssayStructureParser:
-    """Main class for parsing LaTeX documents."""
-
-    def __init__(self):
-        self.title_extractor = TitleExtractor()
-        self.abstract_extractor = AbstractExtractor()
-        self.section_extractor = EnhancedSectionExtractor()  # Using the enhanced extractor
-
-    def parse(self, content: str) -> DocumentStructure:
-        """Parse LaTeX document and extract structured information."""
-        try:
-            content = self._preprocess_content(content)
-
-            return DocumentStructure(
-                title=self.title_extractor.extract(content),
-                abstract=self.abstract_extractor.extract(content),
-                toc=self.section_extractor.extract(content)
-            )
-        except Exception as e:
-            logger.error(f"Error parsing LaTeX document: {str(e)}")
-            raise
-
-    def _preprocess_content(self, content: str) -> str:
-        """Preprocess LaTeX content for parsing."""
-        # Remove comments
-        content = re.sub(r'(?<!\\)%.*$', '', content, flags=re.MULTILINE)
-        return content
-
-
-def pretty_print_structure(doc: DocumentStructure, max_content_length: int = 100):
-    """Print document structure in a readable format."""
-    print(f"Title: {doc.title}\n")
-    print(f"Abstract: {doc.abstract}\n")
-    print("Table of Contents:")
-
-    def print_section(section: Section, indent: int = 0):
-        print("  " * indent + f"- {section.title}")
-        if section.content:
-            preview = section.content[:max_content_length]
-            if len(section.content) > max_content_length:
-                preview += "..."
-            print("  " * (indent + 1) + f"Content: {preview}")
-        for subsection in section.subsections:
-            print_section(subsection, indent + 1)
-
-    for section in doc.toc:
-        print_section(section)
-
-
-# Example usage:
-if __name__ == "__main__":
-
-    # Test with a file
-    file_path = 'test_cache/2411.03663/neurips_2024.tex'
-    main_tex = read_tex_file(file_path)
-
-    # Parse main file
-    parser = EssayStructureParser()
-    main_doc = parser.parse(main_tex)
-
-    # Merge other documents
-    file_path_list = [
-        "test_cache/2411.03663/1_intro.tex",
-        "test_cache/2411.03663/0_abstract.tex",
-        "test_cache/2411.03663/2_pre.tex",
-        "test_cache/2411.03663/3_method.tex",
-        "test_cache/2411.03663/4_experiment.tex",
-        "test_cache/2411.03663/5_related_work.tex",
-        "test_cache/2411.03663/6_conclu.tex",
-        "test_cache/2411.03663/reference.bib"
-    ]
-    for file_path in file_path_list:
-        tex_content = read_tex_file(file_path)
-        additional_doc = parser.parse(tex_content)
-        main_doc = main_doc.merge(additional_doc)
-
-    tree = main_doc.generate_toc_tree()
-    pretty_print_structure(main_doc)

crazy_functions/rag_fns/arxiv_fns/latex_cleaner.py

@@ -1,329 +0,0 @@
-import logging
-import re
-from dataclasses import dataclass, field
-from enum import Enum
-from functools import lru_cache
-from typing import Set, Dict, Pattern, Optional, List, Tuple
-
-
-class EnvType(Enum):
-    """Environment classification types."""
-    PRESERVE = "preserve"  # Preserve complete environment including commands
-    REMOVE = "remove"  # Remove environment completely
-    EXTRACT = "extract"  # Extract and clean content
-
-
-@dataclass
-class LatexConfig:
-    """Configuration for LaTeX processing."""
-    preserve_envs: Set[str] = field(default_factory=lambda: {
-        # Math environments - preserve complete content
-        'equation', 'equation*', 'align', 'align*', 'displaymath',
-        'math', 'eqnarray', 'eqnarray*', 'gather', 'gather*',
-        'multline', 'multline*', 'flalign', 'flalign*',
-        'alignat', 'alignat*', 'cases', 'split', 'aligned',
-        # Tables and figures - preserve structure and content
-        'table', 'table*', 'tabular', 'tabularx', 'array', 'matrix',
-        'figure', 'figure*', 'subfigure', 'wrapfigure',
-        'minipage', 'tabbing', 'verbatim', 'longtable',
-        'sidewaystable', 'sidewaysfigure', 'floatrow',
-        # Arrays and matrices
-        'pmatrix', 'bmatrix', 'Bmatrix', 'vmatrix', 'Vmatrix',
-        'smallmatrix', 'array', 'matrix*', 'pmatrix*', 'bmatrix*',
-        # Algorithms and code
-        'algorithm', 'algorithmic', 'lstlisting', 'verbatim',
-        'minted', 'listing', 'algorithmic*', 'algorithm2e',
-        # Theorems and proofs
-        'theorem', 'proof', 'definition', 'lemma', 'corollary',
-        'proposition', 'example', 'remark', 'note', 'claim',
-        'axiom', 'property', 'assumption', 'conjecture', 'observation',
-        # Bibliography
-        'thebibliography', 'bibliography', 'references'
-    })
-
-    # 引用类命令的特殊处理配置
-    citation_commands: Set[str] = field(default_factory=lambda: {
-        # Basic citations
-        'cite', 'citep', 'citet', 'citeyear', 'citeauthor',
-        'citeyearpar', 'citetext', 'citenum',
-        # Natbib citations
-        'citefullauthor', 'citealp', 'citealt', 'citename',
-        'citepalias', 'citetalias', 'citetext',
-        # Cross-references
-        'ref', 'eqref', 'pageref', 'autoref', 'nameref', 'cref',
-        'Cref', 'vref', 'Vref', 'fref', 'pref',
-        # Hyperref
-        'hyperref', 'href', 'url',
-        # Labels
-        'label', 'tag'
-    })
-
-    preserve_commands: Set[str] = field(default_factory=lambda: {
-        # Text formatting
-        'emph', 'textbf', 'textit', 'underline', 'texttt', 'footnote',
-        'section', 'subsection', 'subsubsection', 'paragraph', 'part',
-        'chapter', 'title', 'author', 'date', 'thanks',
-        # Math operators and symbols
-        'frac', 'sum', 'int', 'prod', 'lim', 'sup', 'inf',
-        'partial', 'nabla', 'implies', 'iff', 'therefore',
-        'exists', 'forall', 'in', 'subset', 'subseteq',
-        # Greek letters and math symbols
-        'alpha', 'beta', 'gamma', 'delta', 'epsilon', 'zeta',
-        'eta', 'theta', 'iota', 'kappa', 'lambda', 'mu',
-        'nu', 'xi', 'pi', 'rho', 'sigma', 'tau',
-        'upsilon', 'phi', 'chi', 'psi', 'omega',
-        'Gamma', 'Delta', 'Theta', 'Lambda', 'Xi', 'Pi',
-        'Sigma', 'Upsilon', 'Phi', 'Psi', 'Omega',
-        # Math commands
-        'left', 'right', 'big', 'Big', 'bigg', 'Bigg',
-        'mathbf', 'mathit', 'mathsf', 'mathtt', 'mathbb',
-        'mathcal', 'mathfrak', 'mathscr', 'mathrm', 'mathop',
-        'operatorname', 'overline', 'underline', 'overbrace',
-        'underbrace', 'overset', 'underset', 'stackrel',
-        # Spacing and alignment
-        'quad', 'qquad', 'hspace', 'vspace', 'medskip',
-        'bigskip', 'smallskip', 'hfill', 'vfill', 'centering',
-        'raggedright', 'raggedleft'
-    })
-
-    remove_commands: Set[str] = field(default_factory=lambda: {
-        # Document setup
-        'documentclass', 'usepackage', 'input', 'include', 'includeonly',
-        'bibliographystyle', 'frontmatter', 'mainmatter',
-        'newtheorem', 'theoremstyle', 'proofname',
-        'newcommand', 'renewcommand', 'providecommand', 'DeclareMathOperator',
-        'newenvironment',
-        # Layout and spacing
-        'pagestyle', 'thispagestyle', 'newpage', 'clearpage',
-        'pagebreak', 'linebreak', 'newline', 'setlength',
-        'setcounter', 'addtocounter', 'makeatletter',
-        'makeatother', 'pagenumbering'
-    })
-
-    latex_chars: Dict[str, str] = field(default_factory=lambda: {
-        '~': ' ', '\\&': '&', '\\%': '%', '\\_': '_', '\\$': '$',
-        '\\#': '#', '\\{': '{', '\\}': '}', '``': '"', "''": '"',
-        '\\textbackslash': '\\', '\\ldots': '...', '\\dots': '...',
-        '\\textasciitilde': '~', '\\textasciicircum': '^'
-    })
-
-    # 保留原始格式的特殊命令模式
-    special_command_patterns: List[Tuple[str, str]] = field(default_factory=lambda: [
-        (r'\\cite\*?(?:\[[^\]]*\])?{([^}]+)}', r'\\cite{\1}'),
-        (r'\\ref\*?{([^}]+)}', r'\\ref{\1}'),
-        (r'\\label{([^}]+)}', r'\\label{\1}'),
-        (r'\\eqref{([^}]+)}', r'\\eqref{\1}'),
-        (r'\\autoref{([^}]+)}', r'\\autoref{\1}'),
-        (r'\\url{([^}]+)}', r'\\url{\1}'),
-        (r'\\href{([^}]+)}{([^}]+)}', r'\\href{\1}{\2}')
-    ])
-
-
-class LatexCleaner:
-    """Enhanced LaTeX text cleaner that preserves mathematical content and citations."""
-
-    def __init__(self, config: Optional[LatexConfig] = None):
-        self.config = config or LatexConfig()
-        self.logger = logging.getLogger(__name__)
-        # 初始化正则表达式缓存
-        self._regex_cache = {}
-
-    @lru_cache(maxsize=128)
-    def _get_env_pattern(self, env_name: str) -> Pattern:
-        """Get cached regex pattern for environment matching."""
-        return re.compile(fr'\\begin{{{env_name}}}(.*?)\\end{{{env_name}}}', re.DOTALL)
-
-    def _get_env_type(self, env_name: str) -> EnvType:
-        """Determine environment processing type."""
-        if env_name.rstrip('*') in {name.rstrip('*') for name in self.config.preserve_envs}:
-            return EnvType.PRESERVE
-        elif env_name in {'comment'}:
-            return EnvType.REMOVE
-        return EnvType.EXTRACT
-
-    def _preserve_special_commands(self, text: str) -> str:
-        """Preserve special commands like citations and references with their complete structure."""
-        for pattern, replacement in self.config.special_command_patterns:
-            if pattern not in self._regex_cache:
-                self._regex_cache[pattern] = re.compile(pattern)
-
-            def replace_func(match):
-                # 保持原始命令格式
-                return match.group(0)
-
-            text = self._regex_cache[pattern].sub(replace_func, text)
-        return text
-
-    def _process_environment(self, match: re.Match) -> str:
-        """Process LaTeX environments while preserving complete content for special environments."""
-        try:
-            env_name = match.group(1)
-            content = match.group(2)
-            env_type = self._get_env_type(env_name)
-
-            if env_type == EnvType.PRESERVE:
-                # 完整保留环境内容
-                complete_env = match.group(0)
-                return f"\n[BEGIN_{env_name}]\n{complete_env}\n[END_{env_name}]\n"
-            elif env_type == EnvType.REMOVE:
-                return ' '
-            else:
-                # 处理嵌套环境
-                return self._clean_nested_environments(content)
-        except Exception as e:
-            self.logger.error(f"Error processing environment {match.group(1) if match else 'unknown'}: {e}")
-            return match.group(0)
-
-    def _preserve_inline_math(self, text: str) -> str:
-        """Preserve complete inline math content."""
-
-        def preserve_math(match):
-            return f" {match.group(0)} "
-
-        patterns = [
-            (r'\$[^$]+\$', preserve_math),
-            (r'\\[\(\[].*?\\[\)\]]', preserve_math),
-            (r'\\begin{math}.*?\\end{math}', preserve_math)
-        ]
-
-        for pattern, handler in patterns:
-            if pattern not in self._regex_cache:
-                self._regex_cache[pattern] = re.compile(pattern, re.DOTALL)
-            text = self._regex_cache[pattern].sub(handler, text)
-
-        return text
-
-    def _clean_nested_environments(self, text: str) -> str:
-        """Process nested environments recursively."""
-        pattern = r'\\begin{(\w+)}(.*?)\\end{\1}'
-        if pattern not in self._regex_cache:
-            self._regex_cache[pattern] = re.compile(pattern, re.DOTALL)
-
-        return self._regex_cache[pattern].sub(self._process_environment, text)
-
-    def _clean_commands(self, text: str) -> str:
-        """Clean LaTeX commands while preserving important content."""
-        # 首先处理特殊命令
-        text = self._preserve_special_commands(text)
-
-        # 保留内联数学
-        text = self._preserve_inline_math(text)
-
-        # 移除指定的命令
-        for cmd in self.config.remove_commands:
-            if cmd not in self._regex_cache:
-                self._regex_cache[cmd] = re.compile(
-                    fr'\\{cmd}\*?(?:\[.*?\])?(?:{{.*?}})*'
-                )
-            text = self._regex_cache[cmd].sub('', text)
-
-        # 处理带内容的命令
-        def handle_command(match: re.Match) -> str:
-            cmd = match.group(1).rstrip('*')
-            if cmd in self.config.preserve_commands or cmd in self.config.citation_commands:
-                return match.group(0)  # 完整保留命令和内容
-            return ' '
-
-        if 'command_pattern' not in self._regex_cache:
-            self._regex_cache['command_pattern'] = re.compile(
-                r'\\(\w+)\*?(?:\[.*?\])?{(.*?)}'
-            )
-
-        text = self._regex_cache['command_pattern'].sub(handle_command, text)
-        return text
-
-    def _normalize_text(self, text: str) -> str:
-        """Normalize text while preserving special content markers."""
-        # 替换特殊字符
-        for char, replacement in self.config.latex_chars.items():
-            text = text.replace(char, replacement)
-
-        # 清理空白字符，同时保留环境标记
-        text = re.sub(r'\s+', ' ', text)
-        text = re.sub(r'\s*\[BEGIN_(\w+)\]\s*', r'\n[BEGIN_\1]\n', text)
-        text = re.sub(r'\s*\[END_(\w+)\]\s*', r'\n[END_\1]\n', text)
-
-        # 保持块级环境之间的分隔
-        text = re.sub(r'\n{3,}', '\n\n', text)
-
-        return text.strip()
-
-    def clean_text(self, text: str) -> str:
-        """Clean LaTeX text while preserving mathematical content, citations, and special environments."""
-        if not text:
-            return ""
-
-        try:
-            # 移除注释
-            text = re.sub(r'(?<!\\)%.*?(?=\n|$)', '', text, flags=re.MULTILINE)
-
-            # 处理环境
-            text = self._clean_nested_environments(text)
-
-            # 清理命令并规范化
-            text = self._clean_commands(text)
-            text = self._normalize_text(text)
-
-            return text
-
-        except Exception as e:
-            self.logger.error(f"Error cleaning text: {e}")
-            return text  # 发生错误时返回原始文本
-
-
-def clean_latex_commands(text: str) -> str:
-    """Convenience function for quick text cleaning with default config."""
-    cleaner = LatexCleaner()
-    return cleaner.clean_text(text)
-
-
-# Example usage:
-if __name__ == "__main__":
-    text = r"""
-    \documentclass{article}
-    \begin{document}
-
-    \section{Introduction}
-    This is a reference to \cite{smith2020} and equation \eqref{eq:main}.
-
-    \begin{equation}\label{eq:main}
-    E = mc^2 \times \sum_{i=1}^{n} x_i
-    \end{equation}
-
-    See Figure \ref{fig:example} for details.
-
-    \begin{figure}
-    \includegraphics{image.png}
-    \caption{Example figure\label
-    \textbf{Important} result: $E=mc^2$ and
-    \begin{equation}
-    F = ma
-    \end{equation}
-    \label{sec:intro}
-    """
-
-    # Custom configuration
-    config = LatexConfig(
-        preserve_envs={},
-        preserve_commands={'textbf', 'emph'},
-        latex_chars={'~': ' ', '\\&': '&'}
-    )
-
-
-    def read_tex_file(file_path):
-        try:
-            with open(file_path, 'r', encoding='utf-8') as file:
-                content = file.read()
-            return content
-        except FileNotFoundError:
-            return "文件未找到，请检查路径是否正确。"
-        except Exception as e:
-            return f"读取文件时发生错误: {e}"
-
-
-    # 使用函数
-    file_path = 'test_cache/2411.03663/neurips_2024.tex'
-    content = read_tex_file(file_path)
-    cleaner = LatexCleaner(config)
-    text = cleaner.clean_text(text)
-    print(text)

crazy_functions/rag_fns/arxiv_fns/latex_patterns.py

@@ -1,396 +0,0 @@
-from dataclasses import dataclass
-
-
-@dataclass
-class LaTeXPatterns:
-    """LaTeX模式存储类，用于集中管理所有LaTeX相关的正则表达式模式"""
-    special_envs = {
-        'math': [
-            # 基础数学环境
-            r'\\begin{(equation|align|gather|eqnarray|multline|flalign|alignat)\*?}.*?\\end{\1\*?}',
-            r'\$\$.*?\$\$',
-            r'\$[^$]+\$',
-            # 矩阵环境
-            r'\\begin{(matrix|pmatrix|bmatrix|Bmatrix|vmatrix|Vmatrix|smallmatrix)\*?}.*?\\end{\1\*?}',
-            # 数组环境
-            r'\\begin{(array|cases|aligned|gathered|split)\*?}.*?\\end{\1\*?}',
-            # 其他数学环境
-            r'\\begin{(subequations|math|displaymath)\*?}.*?\\end{\1\*?}'
-        ],
-
-        'table': [
-            # 基础表格环境
-            r'\\begin{(table|tabular|tabularx|tabulary|longtable)\*?}.*?\\end{\1\*?}',
-            # 复杂表格环境
-            r'\\begin{(tabu|supertabular|xtabular|mpsupertabular)\*?}.*?\\end{\1\*?}',
-            # 自定义表格环境
-            r'\\begin{(threeparttable|tablefootnote)\*?}.*?\\end{\1\*?}',
-            # 表格注释环境
-            r'\\begin{(tablenotes)\*?}.*?\\end{\1\*?}'
-        ],
-
-        'figure': [
-            # 图片环境
-            r'\\begin{figure\*?}.*?\\end{figure\*?}',
-            r'\\begin{(subfigure|wrapfigure)\*?}.*?\\end{\1\*?}',
-            # 图片插入命令
-            r'\\includegraphics(\[.*?\])?\{.*?\}',
-            # tikz 图形环境
-            r'\\begin{(tikzpicture|pgfpicture)\*?}.*?\\end{\1\*?}',
-            # 其他图形环境
-            r'\\begin{(picture|pspicture)\*?}.*?\\end{\1\*?}'
-        ],
-
-        'algorithm': [
-            # 算法环境
-            r'\\begin{(algorithm|algorithmic|algorithm2e|algorithmicx)\*?}.*?\\end{\1\*?}',
-            r'\\begin{(lstlisting|verbatim|minted|listing)\*?}.*?\\end{\1\*?}',
-            # 代码块环境
-            r'\\begin{(code|verbatimtab|verbatimwrite)\*?}.*?\\end{\1\*?}',
-            # 伪代码环境
-            r'\\begin{(pseudocode|procedure)\*?}.*?\\end{\1\*?}'
-        ],
-
-        'list': [
-            # 列表环境
-            r'\\begin{(itemize|enumerate|description)\*?}.*?\\end{\1\*?}',
-            r'\\begin{(list|compactlist|bulletlist)\*?}.*?\\end{\1\*?}',
-            # 自定义列表环境
-            r'\\begin{(tasks|todolist)\*?}.*?\\end{\1\*?}'
-        ],
-
-        'theorem': [
-            # 定理类环境
-            r'\\begin{(theorem|lemma|proposition|corollary)\*?}.*?\\end{\1\*?}',
-            r'\\begin{(definition|example|proof|remark)\*?}.*?\\end{\1\*?}',
-            # 其他证明环境
-            r'\\begin{(axiom|property|assumption|conjecture)\*?}.*?\\end{\1\*?}'
-        ],
-
-        'box': [
-            # 文本框环境
-            r'\\begin{(tcolorbox|mdframed|framed|shaded)\*?}.*?\\end{\1\*?}',
-            r'\\begin{(boxedminipage|shadowbox)\*?}.*?\\end{\1\*?}',
-            # 强调环境
-            r'\\begin{(important|warning|info|note)\*?}.*?\\end{\1\*?}'
-        ],
-
-        'quote': [
-            # 引用环境
-            r'\\begin{(quote|quotation|verse|abstract)\*?}.*?\\end{\1\*?}',
-            r'\\begin{(excerpt|epigraph)\*?}.*?\\end{\1\*?}'
-        ],
-
-        'bibliography': [
-            # 参考文献环境
-            r'\\begin{(thebibliography|bibliography)\*?}.*?\\end{\1\*?}',
-            r'\\begin{(biblist|citelist)\*?}.*?\\end{\1\*?}'
-        ],
-
-        'index': [
-            # 索引环境
-            r'\\begin{(theindex|printindex)\*?}.*?\\end{\1\*?}',
-            r'\\begin{(glossary|acronym)\*?}.*?\\end{\1\*?}'
-        ]
-    }
-    # 章节模式
-    section_patterns = [
-        # 基础章节命令
-        r'\\chapter\{([^}]+)\}',
-        r'\\section\{([^}]+)\}',
-        r'\\subsection\{([^}]+)\}',
-        r'\\subsubsection\{([^}]+)\}',
-        r'\\paragraph\{([^}]+)\}',
-        r'\\subparagraph\{([^}]+)\}',
-
-        # 带星号的变体(不编号)
-        r'\\chapter\*\{([^}]+)\}',
-        r'\\section\*\{([^}]+)\}',
-        r'\\subsection\*\{([^}]+)\}',
-        r'\\subsubsection\*\{([^}]+)\}',
-        r'\\paragraph\*\{([^}]+)\}',
-        r'\\subparagraph\*\{([^}]+)\}',
-
-        # 特殊章节
-        r'\\part\{([^}]+)\}',
-        r'\\part\*\{([^}]+)\}',
-        r'\\appendix\{([^}]+)\}',
-
-        # 前言部分
-        r'\\frontmatter\{([^}]+)\}',
-        r'\\mainmatter\{([^}]+)\}',
-        r'\\backmatter\{([^}]+)\}',
-
-        # 目录相关
-        r'\\tableofcontents',
-        r'\\listoffigures',
-        r'\\listoftables',
-
-        # 自定义章节命令
-        r'\\addchap\{([^}]+)\}',  # KOMA-Script类
-        r'\\addsec\{([^}]+)\}',  # KOMA-Script类
-        r'\\minisec\{([^}]+)\}',  # KOMA-Script类
-
-        # 带可选参数的章节命令
-        r'\\chapter\[([^]]+)\]\{([^}]+)\}',
-        r'\\section\[([^]]+)\]\{([^}]+)\}',
-        r'\\subsection\[([^]]+)\]\{([^}]+)\}'
-    ]
-
-    # 包含模式
-    include_patterns = [
-        r'\\(input|include|subfile)\{([^}]+)\}'
-    ]
-
-    metadata_patterns = {
-        # 标题相关
-        'title': [
-            r'\\title\{([^}]+)\}',
-            r'\\Title\{([^}]+)\}',
-            r'\\doctitle\{([^}]+)\}',
-            r'\\subtitle\{([^}]+)\}',
-            r'\\chapter\*?\{([^}]+)\}',  # 第一章可能作为标题
-            r'\\maketitle\s*\\section\*?\{([^}]+)\}'  # 第一节可能作为标题
-        ],
-
-        # 摘要相关
-        'abstract': [
-            r'\\begin{abstract}(.*?)\\end{abstract}',
-            r'\\abstract\{([^}]+)\}',
-            r'\\begin{摘要}(.*?)\\end{摘要}',
-            r'\\begin{Summary}(.*?)\\end{Summary}',
-            r'\\begin{synopsis}(.*?)\\end{synopsis}',
-            r'\\begin{abstracten}(.*?)\\end{abstracten}'  # 英文摘要
-        ],
-
-        # 作者信息
-        'author': [
-            r'\\author\{([^}]+)\}',
-            r'\\Author\{([^}]+)\}',
-            r'\\authorinfo\{([^}]+)\}',
-            r'\\authors\{([^}]+)\}',
-            r'\\author\[([^]]+)\]\{([^}]+)\}',  # 带附加信息的作者
-            r'\\begin{authors}(.*?)\\end{authors}'
-        ],
-
-        # 日期相关
-        'date': [
-            r'\\date\{([^}]+)\}',
-            r'\\Date\{([^}]+)\}',
-            r'\\submitdate\{([^}]+)\}',
-            r'\\publishdate\{([^}]+)\}',
-            r'\\revisiondate\{([^}]+)\}'
-        ],
-
-        # 关键词
-        'keywords': [
-            r'\\keywords\{([^}]+)\}',
-            r'\\Keywords\{([^}]+)\}',
-            r'\\begin{keywords}(.*?)\\end{keywords}',
-            r'\\key\{([^}]+)\}',
-            r'\\begin{关键词}(.*?)\\end{关键词}'
-        ],
-
-        # 机构/单位
-        'institution': [
-            r'\\institute\{([^}]+)\}',
-            r'\\institution\{([^}]+)\}',
-            r'\\affiliation\{([^}]+)\}',
-            r'\\organization\{([^}]+)\}',
-            r'\\department\{([^}]+)\}'
-        ],
-
-        # 学科/主题
-        'subject': [
-            r'\\subject\{([^}]+)\}',
-            r'\\Subject\{([^}]+)\}',
-            r'\\field\{([^}]+)\}',
-            r'\\discipline\{([^}]+)\}'
-        ],
-
-        # 版本信息
-        'version': [
-            r'\\version\{([^}]+)\}',
-            r'\\revision\{([^}]+)\}',
-            r'\\release\{([^}]+)\}'
-        ],
-
-        # 许可证/版权
-        'license': [
-            r'\\license\{([^}]+)\}',
-            r'\\copyright\{([^}]+)\}',
-            r'\\begin{license}(.*?)\\end{license}'
-        ],
-
-        # 联系方式
-        'contact': [
-            r'\\email\{([^}]+)\}',
-            r'\\phone\{([^}]+)\}',
-            r'\\address\{([^}]+)\}',
-            r'\\contact\{([^}]+)\}'
-        ],
-
-        # 致谢
-        'acknowledgments': [
-            r'\\begin{acknowledgments}(.*?)\\end{acknowledgments}',
-            r'\\acknowledgments\{([^}]+)\}',
-            r'\\thanks\{([^}]+)\}',
-            r'\\begin{致谢}(.*?)\\end{致谢}'
-        ],
-
-        # 项目/基金
-        'funding': [
-            r'\\funding\{([^}]+)\}',
-            r'\\grant\{([^}]+)\}',
-            r'\\project\{([^}]+)\}',
-            r'\\support\{([^}]+)\}'
-        ],
-
-        # 分类号/编号
-        'classification': [
-            r'\\classification\{([^}]+)\}',
-            r'\\serialnumber\{([^}]+)\}',
-            r'\\id\{([^}]+)\}',
-            r'\\doi\{([^}]+)\}'
-        ],
-
-        # 语言
-        'language': [
-            r'\\documentlanguage\{([^}]+)\}',
-            r'\\lang\{([^}]+)\}',
-            r'\\language\{([^}]+)\}'
-        ]
-    }
-    latex_only_patterns = {
-        # 文档类和包引入
-        r'\\documentclass(\[.*?\])?\{.*?\}',
-        r'\\usepackage(\[.*?\])?\{.*?\}',
-        # 常见的文档设置命令
-        r'\\setlength\{.*?\}\{.*?\}',
-        r'\\newcommand\{.*?\}(\[.*?\])?\{.*?\}',
-        r'\\renewcommand\{.*?\}(\[.*?\])?\{.*?\}',
-        r'\\definecolor\{.*?\}\{.*?\}\{.*?\}',
-        # 页面设置相关
-        r'\\pagestyle\{.*?\}',
-        r'\\thispagestyle\{.*?\}',
-        # 其他常见的设置命令
-        r'\\bibliographystyle\{.*?\}',
-        r'\\bibliography\{.*?\}',
-        r'\\setcounter\{.*?\}\{.*?\}',
-        # 字体和文本设置命令
-        r'\\makeFNbottom',
-        r'\\@setfontsize\\[A-Z]+\{.*?\}\{.*?\}',  # 匹配字体大小设置
-        r'\\renewcommand\\[A-Z]+\{\\@setfontsize\\[A-Z]+\{.*?\}\{.*?\}\}',
-        r'\\renewcommand\{?\\thefootnote\}?\{\\fnsymbol\{footnote\}\}',
-        r'\\renewcommand\\footnoterule\{.*?\}',
-        r'\\color\{.*?\}',
-
-        # 页面和节标题设置
-        r'\\setcounter\{secnumdepth\}\{.*?\}',
-        r'\\renewcommand\\@biblabel\[.*?\]\{.*?\}',
-        r'\\renewcommand\\@makefntext\[.*?\](\{.*?\})*',
-        r'\\renewcommand\{?\\figurename\}?\{.*?\}',
-
-        # 字体样式设置
-        r'\\sectionfont\{.*?\}',
-        r'\\subsectionfont\{.*?\}',
-        r'\\subsubsectionfont\{.*?\}',
-
-        # 间距和布局设置
-        r'\\setstretch\{.*?\}',
-        r'\\setlength\{\\skip\\footins\}\{.*?\}',
-        r'\\setlength\{\\footnotesep\}\{.*?\}',
-        r'\\setlength\{\\jot\}\{.*?\}',
-        r'\\hrule\s+width\s+.*?\s+height\s+.*?',
-
-        # makeatletter 和 makeatother
-        r'\\makeatletter\s*',
-        r'\\makeatother\s*',
-        r'\\footnotetext\{[^}]*\$\^{[^}]*}\$[^}]*\}',  # 带有上标的脚注
-        # r'\\footnotetext\{[^}]*\}',  # 普通脚注
-        # r'\\footnotetext\{.*?(?:\$\^{.*?}\$)?.*?(?:email\s*:\s*[^}]*)?.*?\}',  # 带有邮箱的脚注
-        # r'\\footnotetext\{.*?(?:ESI|DOI).*?\}',  # 带有 DOI 或 ESI 引用的脚注
-        # 文档结构命令
-        r'\\begin\{document\}',
-        r'\\end\{document\}',
-        r'\\maketitle',
-        r'\\printbibliography',
-        r'\\newpage',
-
-        # 输入文件命令
-        r'\\input\{[^}]*\}',
-        r'\\input\{.*?\.tex\}',  # 特别匹配 .tex 后缀的输入
-
-        # 脚注相关
-        # r'\\footnotetext\[\d+\]\{[^}]*\}',  # 带编号的脚注
-
-        # 致谢环境
-        r'\\begin\{ack\}',
-        r'\\end\{ack\}',
-        r'\\begin\{ack\}[^\n]*(?:\n.*?)*?\\end\{ack\}',  # 匹配整个致谢环境及其内容
-
-        # 其他文档控制命令
-        r'\\renewcommand\{\\thefootnote\}\{\\fnsymbol\{footnote\}\}',
-    }
-    math_envs = [
-        # 基础数学环境
-        (r'\\begin{equation\*?}.*?\\end{equation\*?}', 'equation'),  # 单行公式
-        (r'\\begin{align\*?}.*?\\end{align\*?}', 'align'),  # 多行对齐公式
-        (r'\\begin{gather\*?}.*?\\end{gather\*?}', 'gather'),  # 多行居中公式
-        (r'\$\$.*?\$\$', 'display'),  # 行间公式
-        (r'\$.*?\$', 'inline'),  # 行内公式
-
-        # 矩阵环境
-        (r'\\begin{matrix}.*?\\end{matrix}', 'matrix'),  # 基础矩阵
-        (r'\\begin{pmatrix}.*?\\end{pmatrix}', 'pmatrix'),  # 圆括号矩阵
-        (r'\\begin{bmatrix}.*?\\end{bmatrix}', 'bmatrix'),  # 方括号矩阵
-        (r'\\begin{vmatrix}.*?\\end{vmatrix}', 'vmatrix'),  # 竖线矩阵
-        (r'\\begin{Vmatrix}.*?\\end{Vmatrix}', 'Vmatrix'),  # 双竖线矩阵
-        (r'\\begin{smallmatrix}.*?\\end{smallmatrix}', 'smallmatrix'),  # 小号矩阵
-
-        # 数组环境
-        (r'\\begin{array}.*?\\end{array}', 'array'),  # 数组
-        (r'\\begin{cases}.*?\\end{cases}', 'cases'),  # 分段函数
-
-        # 多行公式环境
-        (r'\\begin{multline\*?}.*?\\end{multline\*?}', 'multline'),  # 多行单个公式
-        (r'\\begin{split}.*?\\end{split}', 'split'),  # 拆分长公式
-        (r'\\begin{alignat\*?}.*?\\end{alignat\*?}', 'alignat'),  # 对齐环境带间距控制
-        (r'\\begin{flalign\*?}.*?\\end{flalign\*?}', 'flalign'),  # 完全左对齐
-
-        # 特殊数学环境
-        (r'\\begin{subequations}.*?\\end{subequations}', 'subequations'),  # 子公式编号
-        (r'\\begin{gathered}.*?\\end{gathered}', 'gathered'),  # 居中对齐组
-        (r'\\begin{aligned}.*?\\end{aligned}', 'aligned'),  # 内部对齐组
-
-        # 定理类环境
-        (r'\\begin{theorem}.*?\\end{theorem}', 'theorem'),  # 定理
-        (r'\\begin{lemma}.*?\\end{lemma}', 'lemma'),  # 引理
-        (r'\\begin{proof}.*?\\end{proof}', 'proof'),  # 证明
-
-        # 数学模式中的表格环境
-        (r'\\begin{tabular}.*?\\end{tabular}', 'tabular'),  # 表格
-        (r'\\begin{array}.*?\\end{array}', 'array'),  # 数组
-
-        # 其他专业数学环境
-        (r'\\begin{CD}.*?\\end{CD}', 'CD'),  # 交换图
-        (r'\\begin{boxed}.*?\\end{boxed}', 'boxed'),  # 带框公式
-        (r'\\begin{empheq}.*?\\end{empheq}', 'empheq'),  # 强调公式
-
-        # 化学方程式环境 (需要加载 mhchem 包)
-        (r'\\begin{reaction}.*?\\end{reaction}', 'reaction'),  # 化学反应式
-        (r'\\ce\{.*?\}', 'chemequation'),  # 化学方程式
-
-        # 物理单位环境 (需要加载 siunitx 包)
-        (r'\\SI\{.*?\}\{.*?\}', 'SI'),  # 物理单位
-        (r'\\si\{.*?\}', 'si'),  # 单位
-
-        # 补充环境
-        (r'\\begin{equation\+}.*?\\end{equation\+}', 'equation+'),  # breqn包的自动换行公式
-        (r'\\begin{dmath\*?}.*?\\end{dmath\*?}', 'dmath'),  # breqn包的显示数学模式
-        (r'\\begin{dgroup\*?}.*?\\end{dgroup\*?}', 'dgroup'),  # breqn包的公式组
-    ]
-
-    # 示例使用函数
-
-    # 使用示例

crazy_functions/rag_fns/arxiv_fns/section_extractor.py

@@ -1,416 +0,0 @@
-import logging
-import re
-from copy import deepcopy
-from dataclasses import dataclass, field
-from enum import Enum
-from typing import List, Dict, Tuple
-
-# 配置日志
-logging.basicConfig(level=logging.INFO)
-logger = logging.getLogger(__name__)
-
-
-@dataclass
-class SectionLevel(Enum):
-    CHAPTER = 0
-    SECTION = 1
-    SUBSECTION = 2
-    SUBSUBSECTION = 3
-    PARAGRAPH = 4
-    SUBPARAGRAPH = 5
-
-    def __lt__(self, other):
-        if not isinstance(other, SectionLevel):
-            return NotImplemented
-        return self.value < other.value
-
-    def __le__(self, other):
-        if not isinstance(other, SectionLevel):
-            return NotImplemented
-        return self.value <= other.value
-
-    def __gt__(self, other):
-        if not isinstance(other, SectionLevel):
-            return NotImplemented
-        return self.value > other.value
-
-    def __ge__(self, other):
-        if not isinstance(other, SectionLevel):
-            return NotImplemented
-        return self.value >= other.value
-
-
-@dataclass
-class Section:
-    level: SectionLevel
-    title: str
-    content: str = ''
-    bibliography: str = ''
-    subsections: List['Section'] = field(default_factory=list)
-
-    def merge(self, other: 'Section') -> 'Section':
-        """Merge this section with another section."""
-        if self.title != other.title or self.level != other.level:
-            raise ValueError("Can only merge sections with same title and level")
-
-        merged = deepcopy(self)
-        merged.content = self._merge_content(self.content, other.content)
-
-        # Create subsections lookup for efficient merging
-        subsections_map = {s.title: s for s in merged.subsections}
-
-        for other_subsection in other.subsections:
-            if other_subsection.title in subsections_map:
-                # Merge existing subsection
-                idx = next(i for i, s in enumerate(merged.subsections)
-                           if s.title == other_subsection.title)
-                merged.subsections[idx] = merged.subsections[idx].merge(other_subsection)
-            else:
-                # Add new subsection
-                merged.subsections.append(deepcopy(other_subsection))
-
-        return merged
-
-    @staticmethod
-    def _merge_content(content1: str, content2: str) -> str:
-        """Merge content strings intelligently."""
-        if not content1:
-            return content2
-        if not content2:
-            return content1
-        # Combine non-empty contents with a separator
-        return f"{content1}\n\n{content2}"
-
-
-@dataclass
-class LatexEnvironment:
-    """表示LaTeX环境的数据类"""
-    name: str
-    start: int
-    end: int
-    content: str
-    raw: str
-
-
-class EnhancedSectionExtractor:
-    """Enhanced section extractor with comprehensive content handling and hierarchy management."""
-
-    def __init__(self, preserve_environments: bool = True):
-        """
-        初始化Section提取器
-
-        Args:
-            preserve_environments: 是否保留特定环境（如equation, figure等）的原始LaTeX代码
-        """
-        self.preserve_environments = preserve_environments
-
-        # Section级别定义
-        self.section_levels = {
-            'chapter': SectionLevel.CHAPTER,
-            'section': SectionLevel.SECTION,
-            'subsection': SectionLevel.SUBSECTION,
-            'subsubsection': SectionLevel.SUBSUBSECTION,
-            'paragraph': SectionLevel.PARAGRAPH,
-            'subparagraph': SectionLevel.SUBPARAGRAPH
-        }
-
-        # 需要保留的环境类型
-        self.important_environments = {
-            'equation', 'equation*', 'align', 'align*',
-            'figure', 'table', 'algorithm', 'algorithmic',
-            'definition', 'theorem', 'lemma', 'proof',
-            'itemize', 'enumerate', 'description'
-        }
-
-        # 改进的section pattern
-        self.section_pattern = (
-            r'\\(?P<type>chapter|section|subsection|subsubsection|paragraph|subparagraph)'
-            r'\*?'  # Optional star
-            r'(?:\[(?P<short>.*?)\])?'  # Optional short title
-            r'{(?P<title>(?:[^{}]|\{[^{}]*\})*?)}'  # Main title with nested braces support
-        )
-
-        # 环境匹配模式
-        self.environment_pattern = (
-            r'\\begin{(?P<env_name>[^}]+)}'
-            r'(?P<env_content>.*?)'
-            r'\\end{(?P=env_name)}'
-        )
-
-    def _find_environments(self, content: str) -> List[LatexEnvironment]:
-        """
-        查找文档中的所有LaTeX环境。
-        支持嵌套环境的处理。
-        """
-        environments = []
-        stack = []
-
-        # 使用正则表达式查找所有begin和end标记
-        begin_pattern = r'\\begin{([^}]+)}'
-        end_pattern = r'\\end{([^}]+)}'
-
-        # 组合模式来同时匹配begin和end
-        tokens = []
-        for match in re.finditer(fr'({begin_pattern})|({end_pattern})', content):
-            if match.group(1):  # begin标记
-                tokens.append(('begin', match.group(1), match.start()))
-            else:  # end标记
-                tokens.append(('end', match.group(2), match.start()))
-
-        # 处理环境嵌套
-        for token_type, env_name, pos in tokens:
-            if token_type == 'begin':
-                stack.append((env_name, pos))
-            elif token_type == 'end' and stack:
-                if stack[-1][0] == env_name:
-                    start_env_name, start_pos = stack.pop()
-                    env_content = content[start_pos:pos]
-                    raw_content = content[start_pos:pos + len('\\end{' + env_name + '}')]
-
-                    if start_env_name in self.important_environments:
-                        environments.append(LatexEnvironment(
-                            name=start_env_name,
-                            start=start_pos,
-                            end=pos + len('\\end{' + env_name + '}'),
-                            content=env_content,
-                            raw=raw_content
-                        ))
-
-        return sorted(environments, key=lambda x: x.start)
-
-    def _protect_environments(self, content: str) -> Tuple[str, Dict[str, str]]:
-        """
-        保护重要的LaTeX环境，用占位符替换它们。
-        返回处理后的内容和恢复映射。
-        """
-        environments = self._find_environments(content)
-        replacements = {}
-
-        # 从后向前替换，避免位置改变的问题
-        for env in reversed(environments):
-            if env.name in self.important_environments:
-                placeholder = f'__ENV_{len(replacements)}__'
-                replacements[placeholder] = env.raw
-                content = content[:env.start] + placeholder + content[env.end:]
-
-        return content, replacements
-
-    def _restore_environments(self, content: str, replacements: Dict[str, str]) -> str:
-        """
-        恢复之前保护的环境。
-        """
-        for placeholder, original in replacements.items():
-            content = content.replace(placeholder, original)
-        return content
-
-    def extract(self, content: str) -> List[Section]:
-        """
-        从LaTeX文档中提取sections及其内容。
-
-        Args:
-            content: LaTeX文档内容
-
-        Returns:
-            List[Section]: 提取的section列表，包含层次结构
-        """
-        try:
-            # 预处理：保护重要环境
-            if self.preserve_environments:
-                content, env_replacements = self._protect_environments(content)
-
-            # 查找所有sections
-            sections = self._find_all_sections(content)
-            if not sections:
-                return []
-
-            # 处理sections
-            root_sections = self._process_sections(content, sections)
-
-            # 如果需要，恢复环境
-            if self.preserve_environments:
-                for section in self._traverse_sections(root_sections):
-                    section.content = self._restore_environments(section.content, env_replacements)
-
-            return root_sections
-
-        except Exception as e:
-            logger.error(f"Error extracting sections: {str(e)}")
-            raise
-
-    def _find_all_sections(self, content: str) -> List[dict]:
-        """查找所有section命令及其位置。"""
-        sections = []
-
-        for match in re.finditer(self.section_pattern, content, re.DOTALL | re.MULTILINE):
-            section_type = match.group('type').lower()
-            if section_type not in self.section_levels:
-                continue
-
-            section = {
-                'type': section_type,
-                'level': self.section_levels[section_type],
-                'title': self._clean_title(match.group('title')),
-                'start': match.start(),
-                'command_end': match.end(),
-            }
-            sections.append(section)
-
-        return sorted(sections, key=lambda x: x['start'])
-
-    def _process_sections(self, content: str, sections: List[dict]) -> List[Section]:
-        """处理sections以构建层次结构和提取内容。"""
-        # 计算content范围
-        self._calculate_content_ranges(content, sections)
-
-        # 构建层次结构
-        root_sections = []
-        section_stack = []
-
-        for section_info in sections:
-            new_section = Section(
-                level=section_info['level'],
-                title=section_info['title'],
-                content=self._extract_clean_content(content, section_info),
-                subsections=[]
-            )
-
-            # 调整堆栈以找到正确的父section
-            while section_stack and section_stack[-1].level.value >= new_section.level.value:
-                section_stack.pop()
-
-            if section_stack:
-                section_stack[-1].subsections.append(new_section)
-            else:
-                root_sections.append(new_section)
-
-            section_stack.append(new_section)
-
-        return root_sections
-
-    def _calculate_content_ranges(self, content: str, sections: List[dict]):
-        for i, current in enumerate(sections):
-            content_start = current['command_end']
-
-            # 找到下一个section（无论什么级别）
-            content_end = len(content)
-            for next_section in sections[i + 1:]:
-                content_end = next_section['start']
-                break
-
-            current['content_range'] = (content_start, content_end)
-
-    def _calculate_content_ranges_with_subsection_content(self, content: str, sections: List[dict]):
-        """为每个section计算内容范围。"""
-        for i, current in enumerate(sections):
-            content_start = current['command_end']
-
-            # 找到下一个同级或更高级的section
-            content_end = len(content)
-            for next_section in sections[i + 1:]:
-                if next_section['level'] <= current['level']:
-                    content_end = next_section['start']
-                    break
-
-            current['content_range'] = (content_start, content_end)
-
-    def _extract_clean_content(self, content: str, section_info: dict) -> str:
-        """提取并清理section内容。"""
-        start, end = section_info['content_range']
-        raw_content = content[start:end]
-
-        # 清理内容
-        clean_content = self._clean_content(raw_content)
-        return clean_content
-
-    def _clean_content(self, content: str) -> str:
-        """清理LaTeX内容同时保留重要信息。"""
-        # 移除注释
-        content = re.sub(r'(?<!\\)%.*?\n', '\n', content)
-
-        # LaTeX命令处理规则
-        replacements = [
-            # 保留引用
-            (r'\\cite(?:\[.*?\])?{(.*?)}', r'[cite:\1]'),
-            # 保留脚注
-            (r'\\footnote{(.*?)}', r'[footnote:\1]'),
-            # 处理引用
-            (r'\\ref{(.*?)}', r'[ref:\1]'),
-            # 保留URL
-            (r'\\url{(.*?)}', r'[url:\1]'),
-            # 保留超链接
-            (r'\\href{(.*?)}{(.*?)}', r'[\2](\1)'),
-            # 处理文本格式命令
-            (r'\\(?:textbf|textit|emph){(.*?)}', r'\1'),
-            # 保留特殊字符
-            (r'\\([&%$#_{}])', r'\1'),
-        ]
-
-        # 应用所有替换规则
-        for pattern, replacement in replacements:
-            content = re.sub(pattern, replacement, content, flags=re.DOTALL)
-
-        # 清理多余的空白
-        content = re.sub(r'\n\s*\n', '\n\n', content)
-        return content.strip()
-
-    def _clean_title(self, title: str) -> str:
-        """清理section标题。"""
-        # 处理嵌套的花括号
-        while '{' in title:
-            title = re.sub(r'{([^{}]*)}', r'\1', title)
-
-        # 处理LaTeX命令
-        title = re.sub(r'\\[a-zA-Z]+(?:\[.*?\])?{(.*?)}', r'\1', title)
-        title = re.sub(r'\\([&%$#_{}])', r'\1', title)
-
-        return title.strip()
-
-    def _traverse_sections(self, sections: List[Section]) -> List[Section]:
-        """遍历所有sections（包括子sections）。"""
-        result = []
-        for section in sections:
-            result.append(section)
-            result.extend(self._traverse_sections(section.subsections))
-        return result
-
-
-def test_enhanced_extractor():
-    """使用复杂的测试用例测试提取器。"""
-    test_content = r"""
-\section{Complex Examples}
-Here's a complex section with various environments.
-
-\begin{equation}
-E = mc^2
-\end{equation}
-
-\subsection{Nested Environments}
-This subsection has nested environments.
-
-\begin{figure}
-\begin{equation*}
-f(x) = \int_0^x g(t) dt
-\end{equation*}
-\caption{A nested equation in a figure}
-\end{figure}
-
-    """
-
-    extractor = EnhancedSectionExtractor()
-    sections = extractor.extract(test_content)
-
-    def print_section(section, level=0):
-        print("\n" + "  " * level + f"[{section.level.name}] {section.title}")
-        if section.content:
-            content_preview = section.content[:150] + "..." if len(section.content) > 150 else section.content
-            print("  " * (level + 1) + f"Content: {content_preview}")
-        for subsection in section.subsections:
-            print_section(subsection, level + 1)
-
-    print("\nExtracted Section Structure:")
-    for section in sections:
-        print_section(section)
-
-
-if __name__ == "__main__":
-    test_enhanced_extractor()

crazy_functions/rag_fns/arxiv_fns/section_fragment.py

@@ -1,14 +0,0 @@
-from dataclasses import dataclass
-
-
-@dataclass
-class SectionFragment:
-    """Arxiv论文片段数据类"""
-    title: str  # 论文标题
-    authors: str
-    abstract: str  # 论文摘要
-    catalogs: str  # 文章各章节的目录结构
-    arxiv_id: str = ""  # 添加 arxiv_id 属性
-    current_section: str = "Introduction"  # 当前片段所属的section或者subsection或者孙subsubsection名字
-    content: str = ''  # 当前片段的内容
-    bibliography: str = ''  # 当前片段的参考文献

crazy_functions/rag_fns/arxiv_fns/tex_utils.py

@@ -1,266 +0,0 @@
-import logging
-import os
-import re
-from pathlib import Path
-from typing import List, Set, Optional
-
-from crazy_functions.rag_fns.arxiv_fns.latex_patterns import LaTeXPatterns
-
-
-class TexUtils:
-    """TeX文档处理器类"""
-
-    def __init__(self, ):
-        """
-        初始化TeX处理器
-
-        Args:
-            char_range: 字符数范围(最小值, 最大值)
-        """
-        self.logger = logging.getLogger(__name__)
-
-        # 初始化LaTeX环境和命令模式
-        self._init_patterns()
-        self.latex_only_patterns = LaTeXPatterns.latex_only_patterns
-
-    def _init_patterns(self):
-        """初始化LaTeX模式匹配规则"""
-        # 特殊环境模式
-        self.special_envs = LaTeXPatterns.special_envs
-        # 章节模式
-        self.section_patterns = LaTeXPatterns.section_patterns
-        # 包含模式
-        self.include_patterns = LaTeXPatterns.include_patterns
-        # 元数据模式
-        self.metadata_patterns = LaTeXPatterns.metadata_patterns
-
-    def read_file(self, file_path: str) -> Optional[str]:
-        """
-        读取TeX文件内容，支持多种编码
-
-        Args:
-            file_path: 文件路径
-
-        Returns:
-            Optional[str]: 文件内容或None
-        """
-        encodings = ['utf-8', 'latin1', 'gbk', 'gb2312', 'ascii']
-        for encoding in encodings:
-            try:
-                with open(file_path, 'r', encoding=encoding) as f:
-                    return f.read()
-            except UnicodeDecodeError:
-                continue
-
-        self.logger.warning(f"Failed to read {file_path} with all encodings")
-        return None
-
-    def find_main_tex_file(self, directory: str) -> Optional[str]:
-        """
-        查找主TeX文件
-
-        Args:
-            directory: 目录路径
-
-        Returns:
-            Optional[str]: 主文件路径或None
-        """
-        tex_files = list(Path(directory).rglob("*.tex"))
-        if not tex_files:
-            return None
-
-        # 按优先级查找
-        for tex_file in tex_files:
-            content = self.read_file(str(tex_file))
-            if content:
-                if r'\documentclass' in content:
-                    return str(tex_file)
-                if tex_file.name.lower() == 'main.tex':
-                    return str(tex_file)
-
-        # 返回最大的tex文件
-        return str(max(tex_files, key=lambda x: x.stat().st_size))
-
-    def resolve_includes(self, tex_file: str, processed: Set[str] = None) -> List[str]:
-        """
-        解析TeX文件中的include引用
-
-        Args:
-            tex_file: TeX文件路径
-            processed: 已处理的文件集合
-
-        Returns:
-            List[str]: 相关文件路径列表
-        """
-        if processed is None:
-            processed = set()
-
-        if tex_file in processed:
-            return []
-
-        processed.add(tex_file)
-        result = [tex_file]
-        content = self.read_file(tex_file)
-
-        if not content:
-            return result
-
-        base_dir = Path(tex_file).parent
-        for pattern in self.include_patterns:
-            for match in re.finditer(pattern, content):
-                included_file = match.group(2)
-                if not included_file.endswith('.tex'):
-                    included_file += '.tex'
-
-                full_path = str(base_dir / included_file)
-                if os.path.exists(full_path) and full_path not in processed:
-                    result.extend(self.resolve_includes(full_path, processed))
-
-        return result
-
-    def resolve_references(self, tex_file: str, path_dir: str = None) -> str:
-        """
-        解析TeX文件中的参考文献引用，返回所有引用文献的内容，只保留title、author和journal字段。
-        如果在tex_file目录下没找到bib文件，会在path_dir中查找。
-
-        Args:
-            tex_file: TeX文件路径
-            path_dir: 额外的参考文献搜索路径
-
-        Returns:
-            str: 所有参考文献内容的字符串，只包含特定字段，不同参考文献之间用空行分隔
-        """
-        all_references = []  # 存储所有参考文献内容
-        content = self.read_file(tex_file)
-
-        if not content:
-            return ""
-
-        # 扩展参考文献引用的模式
-        bib_patterns = [
-            r'\\bibliography\{([^}]+)\}',
-            r'\\addbibresource\{([^}]+)\}',
-            r'\\bibliographyfile\{([^}]+)\}',
-            r'\\begin\{thebibliography\}',
-            r'\\bibinput\{([^}]+)\}',
-            r'\\newrefsection\{([^}]+)\}'
-        ]
-
-        base_dir = Path(tex_file).parent
-        found_in_tex_dir = False
-
-        # 首先在tex文件目录下查找显式引用的bib文件
-        for pattern in bib_patterns:
-            for match in re.finditer(pattern, content):
-                if not match.groups():
-                    continue
-
-                bib_files = match.group(1).split(',')
-                for bib_file in bib_files:
-                    bib_file = bib_file.strip()
-                    if not bib_file.endswith('.bib'):
-                        bib_file += '.bib'
-
-                    full_path = str(base_dir / bib_file)
-                    if os.path.exists(full_path):
-                        found_in_tex_dir = True
-                        bib_content = self.read_file(full_path)
-                        if bib_content:
-                            processed_refs = self._process_bib_content(bib_content)
-                            all_references.extend(processed_refs)
-
-        # 如果在tex文件目录下没找到bib文件，且提供了额外搜索路径
-        if not found_in_tex_dir and path_dir:
-            search_dir = Path(path_dir)
-            try:
-                for bib_path in search_dir.glob('**/*.bib'):
-                    bib_content = self.read_file(str(bib_path))
-                    if bib_content:
-                        processed_refs = self._process_bib_content(bib_content)
-                        all_references.extend(processed_refs)
-            except Exception as e:
-                print(f"Error searching in path_dir: {e}")
-
-        # 合并所有参考文献内容，用空行分隔
-        return "\n\n".join(all_references)
-
-    def _process_bib_content(self, content: str) -> List[str]:
-        """
-        处理bib文件内容，提取每个参考文献的特定字段
-
-        Args:
-            content: bib文件内容
-
-        Returns:
-            List[str]: 处理后的参考文献列表
-        """
-        processed_refs = []
-        # 匹配完整的参考文献条目
-        ref_pattern = r'@\w+\{[^@]*\}'
-        # 匹配参考文献类型和键值
-        entry_start_pattern = r'@(\w+)\{([^,]*?),'
-        # 匹配字段
-        field_pattern = r'(\w+)\s*=\s*\{([^}]*)\}'
-
-        # 查找所有参考文献条目
-        for ref_match in re.finditer(ref_pattern, content, re.DOTALL):
-            ref_content = ref_match.group(0)
-
-            # 获取参考文献类型和键值
-            entry_match = re.match(entry_start_pattern, ref_content)
-            if not entry_match:
-                continue
-
-            entry_type, cite_key = entry_match.groups()
-
-            # 提取需要的字段
-            needed_fields = {'title': None, 'author': None, 'journal': None}
-            for field_match in re.finditer(field_pattern, ref_content):
-                field_name, field_value = field_match.groups()
-                field_name = field_name.lower()
-                if field_name in needed_fields:
-                    needed_fields[field_name] = field_value.strip()
-
-            # 构建新的参考文献条目
-            if any(needed_fields.values()):  # 如果至少有一个需要的字段
-                ref_lines = [f"@{entry_type}{{{cite_key},"]
-                for field_name, field_value in needed_fields.items():
-                    if field_value:
-                        ref_lines.append(f"  {field_name}={{{field_value}}},")
-                ref_lines[-1] = ref_lines[-1][:-1]  # 移除最后一个逗号
-                ref_lines.append("}")
-
-                processed_refs.append("\n".join(ref_lines))
-
-        return processed_refs
-
-    def _extract_inline_references(self, content: str) -> str:
-        """
-        从tex文件内容中提取直接写在文件中的参考文献
-
-        Args:
-            content: tex文件内容
-
-        Returns:
-            str: 提取的参考文献内容，如果没有找到则返回空字符串
-        """
-        # 查找参考文献环境
-        bib_start = r'\\begin\{thebibliography\}'
-        bib_end = r'\\end\{thebibliography\}'
-
-        start_match = re.search(bib_start, content)
-        end_match = re.search(bib_end, content)
-
-        if start_match and end_match:
-            return content[start_match.start():end_match.end()]
-
-        return ""
-
-    def _preprocess_content(self, content: str) -> str:
-        """预处理TeX内容"""
-        # 移除注释
-        content = re.sub(r'(?m)%.*$', '', content)
-        # 规范化空白字符
-        # content = re.sub(r'\s+', ' ', content)
-        content = re.sub(r'\n\s*\n', '\n\n', content)
-        return content.strip()

crazy_functions/rag_fns/llama_index_worker.py

@@ -1,10 +1,10 @@
 import atexit
-import os
+from loguru import logger
+from typing import List
 
 from llama_index.core import Document
 from llama_index.core.ingestion import run_transformations
 from llama_index.core.schema import TextNode
-from loguru import logger
 
 from crazy_functions.rag_fns.vector_store_index import GptacVectorStoreIndex
 from request_llms.embed_models.openai_embed import OpenAiEmbeddingModel
@@ -59,7 +59,7 @@ class SaveLoad():
     def purge(self):
         import shutil
         shutil.rmtree(self.checkpoint_dir, ignore_errors=True)
-        self.vs_index = self.create_new_vs()
+        self.vs_index = self.create_new_vs(self.checkpoint_dir)
 
 
 class LlamaIndexRagWorker(SaveLoad):
@@ -68,60 +68,11 @@ class LlamaIndexRagWorker(SaveLoad):
         self.embed_model = OpenAiEmbeddingModel(llm_kwargs)
         self.user_name = user_name
         self.checkpoint_dir = checkpoint_dir
-
-        # 确保checkpoint_dir存在
-        if checkpoint_dir:
-            os.makedirs(checkpoint_dir, exist_ok=True)
-
-        logger.info(f"Initializing LlamaIndexRagWorker with checkpoint_dir: {checkpoint_dir}")
-
-        # 初始化向量存储
-        if auto_load_checkpoint and self.does_checkpoint_exist():
-            logger.info("Loading existing vector store from checkpoint")
-            self.vs_index = self.load_from_checkpoint()
+        if auto_load_checkpoint:
+            self.vs_index = self.load_from_checkpoint(checkpoint_dir)
         else:
-            logger.info("Creating new vector store")
             self.vs_index = self.create_new_vs()
-
-        # 注册退出时保存
-        atexit.register(self.save_to_checkpoint)
-
-    def add_text_to_vector_store(self, text: str) -> None:
-        """添加文本到向量存储"""
-        try:
-            logger.info(f"Adding text to vector store (first 100 chars): {text[:100]}...")
-            node = TextNode(text=text)
-            nodes = run_transformations(
-                [node],
-                self.vs_index._transformations,
-                show_progress=True
-            )
-            self.vs_index.insert_nodes(nodes)
-
-            # 立即保存
-            self.save_to_checkpoint()
-
-            if self.debug_mode:
-                self.inspect_vector_store()
-
-        except Exception as e:
-            logger.error(f"Error adding text to vector store: {str(e)}")
-            raise
-
-    def save_to_checkpoint(self, checkpoint_dir=None):
-        """保存向量存储到检查点"""
-        try:
-            if checkpoint_dir is None:
-                checkpoint_dir = self.checkpoint_dir
-            logger.info(f'Saving vector store to: {checkpoint_dir}')
-            if checkpoint_dir:
-                self.vs_index.storage_context.persist(persist_dir=checkpoint_dir)
-                logger.info('Vector store saved successfully')
-            else:
-                logger.warning('No checkpoint directory specified, skipping save')
-        except Exception as e:
-            logger.error(f"Error saving checkpoint: {str(e)}")
-            raise
+        atexit.register(lambda: self.save_to_checkpoint(checkpoint_dir))
 
     def assign_embedding_model(self):
         pass
@@ -130,28 +81,44 @@ class LlamaIndexRagWorker(SaveLoad):
         # This function is for debugging
         self.vs_index.storage_context.index_store.to_dict()
         docstore = self.vs_index.storage_context.docstore.docs
-        vector_store_preview = "\n".join([f"{_id} | {tn.text}" for _id, tn in docstore.items()])
+        vector_store_preview = "\n".join([ f"{_id} | {tn.text}" for _id, tn in docstore.items() ])
         logger.info('\n++ --------inspect_vector_store begin--------')
         logger.info(vector_store_preview)
         logger.info('oo --------inspect_vector_store end--------')
         return vector_store_preview
 
-    def add_documents_to_vector_store(self, document_list):
-        documents = [Document(text=t) for t in document_list]
+    def add_documents_to_vector_store(self, document_list: List[Document]):
+        """
+        Adds a list of Document objects to the vector store after processing.
+        """
+        documents = document_list
         documents_nodes = run_transformations(
             documents,  # type: ignore
             self.vs_index._transformations,
             show_progress=True
         )
         self.vs_index.insert_nodes(documents_nodes)
-        if self.debug_mode: self.inspect_vector_store()
+        if self.debug_mode:
+            self.inspect_vector_store()
+
+    def add_text_to_vector_store(self, text: str):
+        node = TextNode(text=text)
+        documents_nodes = run_transformations(
+            [node],
+            self.vs_index._transformations,
+            show_progress=True
+        )
+        self.vs_index.insert_nodes(documents_nodes)
+        if self.debug_mode:
+            self.inspect_vector_store()
 
     def remember_qa(self, question, answer):
         formatted_str = QUESTION_ANSWER_RECORD.format(question=question, answer=answer)
         self.add_text_to_vector_store(formatted_str)
 
     def retrieve_from_store_with_query(self, query):
-        if self.debug_mode: self.inspect_vector_store()
+        if self.debug_mode:
+            self.inspect_vector_store()
         retriever = self.vs_index.as_retriever()
         return retriever.retrieve(query)
 
@@ -160,6 +127,12 @@ class LlamaIndexRagWorker(SaveLoad):
         return DEFAULT_QUERY_GENERATION_PROMPT.format(context_str=context_str, query_str=query)
 
     def generate_node_array_preview(self, nodes):
-        buf = "\n".join(([f"(No.{i + 1} | score {n.score:.3f}): {n.text}" for i, n in enumerate(nodes)]))
+        buf = "\n".join(([f"(No.{i+1} | score {n.score:.3f}): {n.text}" for i, n in enumerate(nodes)]))
         if self.debug_mode: logger.info(buf)
         return buf
+
+    def purge_vector_store(self):
+        """
+        Purges the current vector store and creates a new one.
+        """
+        self.purge()

crazy_functions/rag_fns/milvus_worker.py

@@ -1,14 +1,20 @@
-import atexit
+import llama_index
 import os
+import atexit
 from typing import List
-
+from loguru import logger
+from llama_index.core import Document
+from llama_index.core.schema import TextNode
+from request_llms.embed_models.openai_embed import OpenAiEmbeddingModel
+from shared_utils.connect_void_terminal import get_chat_default_kwargs
+from llama_index.core import VectorStoreIndex, SimpleDirectoryReader
+from crazy_functions.rag_fns.vector_store_index import GptacVectorStoreIndex
+from llama_index.core.ingestion import run_transformations
+from llama_index.core import PromptTemplate
+from llama_index.core.response_synthesizers import TreeSummarize
 from llama_index.core import StorageContext
 from llama_index.vector_stores.milvus import MilvusVectorStore
-from loguru import logger
-
 from crazy_functions.rag_fns.llama_index_worker import LlamaIndexRagWorker
-from crazy_functions.rag_fns.vector_store_index import GptacVectorStoreIndex
-from request_llms.embed_models.openai_embed import OpenAiEmbeddingModel
 
 DEFAULT_QUERY_GENERATION_PROMPT = """\
 Now, you have context information as below:
@@ -59,19 +65,17 @@ class MilvusSaveLoad():
 
     def create_new_vs(self, checkpoint_dir, overwrite=False):
         vector_store = MilvusVectorStore(
-            uri=os.path.join(checkpoint_dir, "milvus_demo.db"),
+            uri=os.path.join(checkpoint_dir, "milvus_demo.db"), 
             dim=self.embed_model.embedding_dimension(),
             overwrite=overwrite
         )
         storage_context = StorageContext.from_defaults(vector_store=vector_store)
-        index = GptacVectorStoreIndex.default_vector_store(storage_context=storage_context,
-                                                           embed_model=self.embed_model)
+        index = GptacVectorStoreIndex.default_vector_store(storage_context=storage_context, embed_model=self.embed_model)
         return index
 
     def purge(self):
         self.vs_index = self.create_new_vs(self.checkpoint_dir, overwrite=True)
 
-
 class MilvusRagWorker(MilvusSaveLoad, LlamaIndexRagWorker):
 
     def __init__(self, user_name, llm_kwargs, auto_load_checkpoint=True, checkpoint_dir=None) -> None:
@@ -92,7 +96,7 @@ class MilvusRagWorker(MilvusSaveLoad, LlamaIndexRagWorker):
             docstore = self.vs_index.storage_context.docstore.docs
             if not docstore.items():
                 raise ValueError("cannot inspect")
-            vector_store_preview = "\n".join([f"{_id} | {tn.text}" for _id, tn in docstore.items()])
+            vector_store_preview = "\n".join([ f"{_id} | {tn.text}" for _id, tn in docstore.items() ])
         except:
             dummy_retrieve_res: List["NodeWithScore"] = self.vs_index.as_retriever().retrieve(' ')
             vector_store_preview = "\n".join(

crazy_functions/rag_fns/rag_file_support.py

@@ -1,47 +1,22 @@
+import os
 from llama_index.core import SimpleDirectoryReader
 
-supports_format = ['.csv', '.docx', '.doc', '.epub', '.ipynb', '.mbox', '.md', '.pdf', '.txt', '.ppt',
-                   '.pptm', '.pptx', '.py', '.xls', '.xlsx', '.html', '.json', '.xml', '.yaml', '.yml', '.m']
-
-
-def read_docx_doc(file_path):
-    if file_path.split(".")[-1] == "docx":
-        from docx import Document
-        doc = Document(file_path)
-        file_content = "\n".join([para.text for para in doc.paragraphs])
-    else:
-        try:
-            import win32com.client
-            word = win32com.client.Dispatch("Word.Application")
-            word.visible = False
-            # 打开文件
-            doc = word.Documents.Open(os.getcwd() + '/' + file_path)
-            # file_content = doc.Content.Text
-            doc = word.ActiveDocument
-            file_content = doc.Range().Text
-            doc.Close()
-            word.Quit()
-        except:
-            raise RuntimeError('请先将.doc文档转换为.docx文档。')
-    return file_content
+supports_format = ['.csv', '.docx', '.epub', '.ipynb',  '.mbox', '.md', '.pdf',  '.txt', '.ppt',
+                   '.pptm', '.pptx']
 
 
 # 修改后的 extract_text 函数，结合 SimpleDirectoryReader 和自定义解析逻辑
-import os
-
-
 def extract_text(file_path):
     _, ext = os.path.splitext(file_path.lower())
 
     # 使用 SimpleDirectoryReader 处理它支持的文件格式
-    if ext in ['.docx', '.doc']:
-        return read_docx_doc(file_path)
-    try:
-        reader = SimpleDirectoryReader(input_files=[file_path])
-        documents = reader.load_data()
-        if len(documents) > 0:
-            return documents[0].text
-    except Exception as e:
-        pass
+    if ext in supports_format:
+        try:
+            reader = SimpleDirectoryReader(input_files=[file_path])
+            documents = reader.load_data()
+            if len(documents) > 0:
+                return documents[0].text
+        except Exception as e:
+            pass
 
     return None

crazy_functions/rag_fns/vector_store_index.py

@@ -1,6 +1,6 @@
-from typing import Any, List, Optional
-
 from llama_index.core import VectorStoreIndex
+from typing import Any,  List, Optional
+
 from llama_index.core.callbacks.base import CallbackManager
 from llama_index.core.schema import TransformComponent
 from llama_index.core.service_context import ServiceContext
@@ -13,18 +13,18 @@ from llama_index.core.storage.storage_context import StorageContext
 
 
 class GptacVectorStoreIndex(VectorStoreIndex):
-
+    
     @classmethod
     def default_vector_store(
-            cls,
-            storage_context: Optional[StorageContext] = None,
-            show_progress: bool = False,
-            callback_manager: Optional[CallbackManager] = None,
-            transformations: Optional[List[TransformComponent]] = None,
-            # deprecated
-            service_context: Optional[ServiceContext] = None,
-            embed_model=None,
-            **kwargs: Any,
+        cls,
+        storage_context: Optional[StorageContext] = None,
+        show_progress: bool = False,
+        callback_manager: Optional[CallbackManager] = None,
+        transformations: Optional[List[TransformComponent]] = None,
+        # deprecated
+        service_context: Optional[ServiceContext] = None,
+        embed_model = None,
+        **kwargs: Any,
     ):
         """Create index from documents.
 
@@ -36,14 +36,15 @@ class GptacVectorStoreIndex(VectorStoreIndex):
         storage_context = storage_context or StorageContext.from_defaults()
         docstore = storage_context.docstore
         callback_manager = (
-                callback_manager
-                or callback_manager_from_settings_or_context(Settings, service_context)
+            callback_manager
+            or callback_manager_from_settings_or_context(Settings, service_context)
         )
         transformations = transformations or transformations_from_settings_or_context(
             Settings, service_context
         )
 
         with callback_manager.as_trace("index_construction"):
+
             return cls(
                 nodes=[],
                 storage_context=storage_context,
@@ -54,3 +55,4 @@ class GptacVectorStoreIndex(VectorStoreIndex):
                 embed_model=embed_model,
                 **kwargs,
             )
+

crazy_functions/vector_fns/vector_database.py

@@ -60,7 +60,7 @@ def similarity_search_with_score_by_vector(
         self, embedding: List[float], k: int = 4
 ) -> List[Tuple[Document, float]]:
 
-    def seperate_list(ls: List[int]) -> List[List[int]]:
+    def separate_list(ls: List[int]) -> List[List[int]]:
         lists = []
         ls1 = [ls[0]]
         for i in range(1, len(ls)):
@@ -82,7 +82,7 @@ def similarity_search_with_score_by_vector(
             continue
         _id = self.index_to_docstore_id[i]
         doc = self.docstore.search(_id)
-        if not self.chunk_conent:
+        if not self.chunk_content:
             if not isinstance(doc, Document):
                 raise ValueError(f"Could not find document for id {_id}, got {doc}")
             doc.metadata["score"] = int(scores[0][j])
@@ -104,12 +104,12 @@ def similarity_search_with_score_by_vector(
                         id_set.add(l)
             if break_flag:
                 break
-    if not self.chunk_conent:
+    if not self.chunk_content:
         return docs
     if len(id_set) == 0 and self.score_threshold > 0:
         return []
     id_list = sorted(list(id_set))
-    id_lists = seperate_list(id_list)
+    id_lists = separate_list(id_list)
     for id_seq in id_lists:
         for id in id_seq:
             if id == id_seq[0]:
@@ -132,7 +132,7 @@ class LocalDocQA:
     embeddings: object = None
     top_k: int = VECTOR_SEARCH_TOP_K
     chunk_size: int = CHUNK_SIZE
-    chunk_conent: bool = True
+    chunk_content: bool = True
     score_threshold: int = VECTOR_SEARCH_SCORE_THRESHOLD
 
     def init_cfg(self,
@@ -209,16 +209,16 @@ class LocalDocQA:
 
     # query      查询内容
     # vs_path    知识库路径
-    # chunk_conent   是否启用上下文关联
+    # chunk_content   是否启用上下文关联
     # score_threshold    搜索匹配score阈值
     # vector_search_top_k   搜索知识库内容条数，默认搜索5条结果
     # chunk_sizes    匹配单段内容的连接上下文长度
-    def get_knowledge_based_conent_test(self, query, vs_path, chunk_conent,
+    def get_knowledge_based_content_test(self, query, vs_path, chunk_content,
                                         score_threshold=VECTOR_SEARCH_SCORE_THRESHOLD,
                                         vector_search_top_k=VECTOR_SEARCH_TOP_K, chunk_size=CHUNK_SIZE,
                                         text2vec=None):
         self.vector_store = FAISS.load_local(vs_path, text2vec)
-        self.vector_store.chunk_conent = chunk_conent
+        self.vector_store.chunk_content = chunk_content
         self.vector_store.score_threshold = score_threshold
         self.vector_store.chunk_size = chunk_size
 
@@ -241,7 +241,7 @@ class LocalDocQA:
 
 
 
-def construct_vector_store(vs_id, vs_path, files, sentence_size, history, one_conent, one_content_segmentation, text2vec):
+def construct_vector_store(vs_id, vs_path, files, sentence_size, history, one_content, one_content_segmentation, text2vec):
     for file in files:
         assert os.path.exists(file), "输入文件不存在：" + file
     import nltk
@@ -297,7 +297,7 @@ class knowledge_archive_interface():
             files=file_manifest,
             sentence_size=100,
             history=[],
-            one_conent="",
+            one_content="",
             one_content_segmentation="",
             text2vec = self.get_chinese_text2vec(),
         )
@@ -319,19 +319,19 @@ class knowledge_archive_interface():
                 files=[],
                 sentence_size=100,
                 history=[],
-                one_conent="",
+                one_content="",
                 one_content_segmentation="",
                 text2vec = self.get_chinese_text2vec(),
             )
         VECTOR_SEARCH_SCORE_THRESHOLD = 0
         VECTOR_SEARCH_TOP_K = 4
         CHUNK_SIZE = 512
-        resp, prompt = self.qa_handle.get_knowledge_based_conent_test(
+        resp, prompt = self.qa_handle.get_knowledge_based_content_test(
             query = txt,
             vs_path = self.kai_path,
             score_threshold=VECTOR_SEARCH_SCORE_THRESHOLD,
             vector_search_top_k=VECTOR_SEARCH_TOP_K,
-            chunk_conent=True,
+            chunk_content=True,
             chunk_size=CHUNK_SIZE,
             text2vec = self.get_chinese_text2vec(),
         )

crazy_functions/vt_fns/vt_call_plugin.py

@@ -1,6 +1,6 @@
 from pydantic import BaseModel, Field
 from typing import List
-from toolbox import update_ui_lastest_msg, disable_auto_promotion
+from toolbox import update_ui_latest_msg, disable_auto_promotion
 from request_llms.bridge_all import predict_no_ui_long_connection
 from crazy_functions.json_fns.pydantic_io import GptJsonIO, JsonStringError
 import copy, json, pickle, os, sys, time
@@ -9,14 +9,14 @@ import copy, json, pickle, os, sys, time
 def read_avail_plugin_enum():
     from crazy_functional import get_crazy_functions
     plugin_arr = get_crazy_functions()
-    # remove plugins with out explaination
+    # remove plugins with out explanation
     plugin_arr = {k:v for k, v in plugin_arr.items() if ('Info' in v) and ('Function' in v)}
     plugin_arr_info = {"F_{:04d}".format(i):v["Info"] for i, v in enumerate(plugin_arr.values(), start=1)}
     plugin_arr_dict = {"F_{:04d}".format(i):v for i, v in enumerate(plugin_arr.values(), start=1)}
     plugin_arr_dict_parse = {"F_{:04d}".format(i):v for i, v in enumerate(plugin_arr.values(), start=1)}
     plugin_arr_dict_parse.update({f"F_{i}":v for i, v in enumerate(plugin_arr.values(), start=1)})
     prompt = json.dumps(plugin_arr_info, ensure_ascii=False, indent=2)
-    prompt = "\n\nThe defination of PluginEnum:\nPluginEnum=" + prompt
+    prompt = "\n\nThe definition of PluginEnum:\nPluginEnum=" + prompt
     return prompt, plugin_arr_dict, plugin_arr_dict_parse
 
 def wrap_code(txt):
@@ -55,7 +55,7 @@ def execute_plugin(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prom
         plugin_selection: str = Field(description="The most related plugin from one of the PluginEnum.", default="F_0000")
         reason_of_selection: str = Field(description="The reason why you should select this plugin.", default="This plugin satisfy user requirement most")
     # ⭐ ⭐ ⭐ 选择插件
-    yield from update_ui_lastest_msg(lastmsg=f"正在执行任务: {txt}\n\n查找可用插件中...", chatbot=chatbot, history=history, delay=0)
+    yield from update_ui_latest_msg(lastmsg=f"正在执行任务: {txt}\n\n查找可用插件中...", chatbot=chatbot, history=history, delay=0)
     gpt_json_io = GptJsonIO(Plugin)
     gpt_json_io.format_instructions = "The format of your output should be a json that can be parsed by json.loads.\n"
     gpt_json_io.format_instructions += """Output example: {"plugin_selection":"F_1234", "reason_of_selection":"F_1234 plugin satisfy user requirement most"}\n"""
@@ -74,13 +74,13 @@ def execute_plugin(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prom
         msg += "请求的Prompt为：\n" + wrap_code(get_inputs_show_user(inputs, plugin_arr_enum_prompt))
         msg += "语言模型回复为：\n" + wrap_code(gpt_reply)
         msg += "\n但您可以尝试再试一次\n"
-        yield from update_ui_lastest_msg(lastmsg=msg, chatbot=chatbot, history=history, delay=2)
+        yield from update_ui_latest_msg(lastmsg=msg, chatbot=chatbot, history=history, delay=2)
         return
     if plugin_sel.plugin_selection not in plugin_arr_dict_parse:
         msg = f"抱歉, 找不到合适插件执行该任务, 或者{llm_kwargs['llm_model']}无法理解您的需求。"
         msg += f"语言模型{llm_kwargs['llm_model']}选择了不存在的插件：\n" + wrap_code(gpt_reply)
         msg += "\n但您可以尝试再试一次\n"
-        yield from update_ui_lastest_msg(lastmsg=msg, chatbot=chatbot, history=history, delay=2)
+        yield from update_ui_latest_msg(lastmsg=msg, chatbot=chatbot, history=history, delay=2)
         return
 
     # ⭐ ⭐ ⭐ 确认插件参数
@@ -90,7 +90,7 @@ def execute_plugin(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prom
         appendix_info = get_recent_file_prompt_support(chatbot)
 
     plugin = plugin_arr_dict_parse[plugin_sel.plugin_selection]
-    yield from update_ui_lastest_msg(lastmsg=f"正在执行任务: {txt}\n\n提取插件参数...", chatbot=chatbot, history=history, delay=0)
+    yield from update_ui_latest_msg(lastmsg=f"正在执行任务: {txt}\n\n提取插件参数...", chatbot=chatbot, history=history, delay=0)
     class PluginExplicit(BaseModel):
         plugin_selection: str = plugin_sel.plugin_selection
         plugin_arg: str = Field(description="The argument of the plugin.", default="")
@@ -109,6 +109,6 @@ def execute_plugin(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prom
     fn = plugin['Function']
     fn_name = fn.__name__
     msg = f'{llm_kwargs["llm_model"]}为您选择了插件: `{fn_name}`\n\n插件说明：{plugin["Info"]}\n\n插件参数：{plugin_sel.plugin_arg}\n\n假如偏离了您的要求，按停止键终止。'
-    yield from update_ui_lastest_msg(lastmsg=msg, chatbot=chatbot, history=history, delay=2)
+    yield from update_ui_latest_msg(lastmsg=msg, chatbot=chatbot, history=history, delay=2)
     yield from fn(plugin_sel.plugin_arg, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, -1)
     return

crazy_functions/vt_fns/vt_modify_config.py

@@ -1,6 +1,6 @@
 from pydantic import BaseModel, Field
 from typing import List
-from toolbox import update_ui_lastest_msg, get_conf
+from toolbox import update_ui_latest_msg, get_conf
 from request_llms.bridge_all import predict_no_ui_long_connection
 from crazy_functions.json_fns.pydantic_io import GptJsonIO
 import copy, json, pickle, os, sys
@@ -9,7 +9,7 @@ import copy, json, pickle, os, sys
 def modify_configuration_hot(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_intention):
     ALLOW_RESET_CONFIG = get_conf('ALLOW_RESET_CONFIG')
     if not ALLOW_RESET_CONFIG:
-        yield from update_ui_lastest_msg(
+        yield from update_ui_latest_msg(
             lastmsg=f"当前配置不允许被修改！如需激活本功能，请在config.py中设置ALLOW_RESET_CONFIG=True后重启软件。",
             chatbot=chatbot, history=history, delay=2
         )
@@ -30,7 +30,7 @@ def modify_configuration_hot(txt, llm_kwargs, plugin_kwargs, chatbot, history, s
         new_option_value: str = Field(description="the new value of the option", default=None)
 
     # ⭐ ⭐ ⭐ 分析用户意图
-    yield from update_ui_lastest_msg(lastmsg=f"正在执行任务: {txt}\n\n读取新配置中", chatbot=chatbot, history=history, delay=0)
+    yield from update_ui_latest_msg(lastmsg=f"正在执行任务: {txt}\n\n读取新配置中", chatbot=chatbot, history=history, delay=0)
     gpt_json_io = GptJsonIO(ModifyConfigurationIntention)
     inputs = "Analyze how to change configuration according to following user input, answer me with json: \n\n" + \
              ">> " + txt.rstrip('\n').replace('\n','\n>> ') + '\n\n' + \
@@ -44,11 +44,11 @@ def modify_configuration_hot(txt, llm_kwargs, plugin_kwargs, chatbot, history, s
 
     ok = (explicit_conf in txt)
     if ok:
-        yield from update_ui_lastest_msg(
+        yield from update_ui_latest_msg(
             lastmsg=f"正在执行任务: {txt}\n\n新配置{explicit_conf}={user_intention.new_option_value}",
             chatbot=chatbot, history=history, delay=1
         )
-        yield from update_ui_lastest_msg(
+        yield from update_ui_latest_msg(
             lastmsg=f"正在执行任务: {txt}\n\n新配置{explicit_conf}={user_intention.new_option_value}\n\n正在修改配置中",
             chatbot=chatbot, history=history, delay=2
         )
@@ -57,25 +57,25 @@ def modify_configuration_hot(txt, llm_kwargs, plugin_kwargs, chatbot, history, s
         from toolbox import set_conf
         set_conf(explicit_conf, user_intention.new_option_value)
 
-        yield from update_ui_lastest_msg(
+        yield from update_ui_latest_msg(
             lastmsg=f"正在执行任务: {txt}\n\n配置修改完成，重新页面即可生效。", chatbot=chatbot, history=history, delay=1
         )
     else:
-        yield from update_ui_lastest_msg(
+        yield from update_ui_latest_msg(
             lastmsg=f"失败，如果需要配置{explicit_conf}，您需要明确说明并在指令中提到它。", chatbot=chatbot, history=history, delay=5
         )
 
 def modify_configuration_reboot(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_intention):
     ALLOW_RESET_CONFIG = get_conf('ALLOW_RESET_CONFIG')
     if not ALLOW_RESET_CONFIG:
-        yield from update_ui_lastest_msg(
+        yield from update_ui_latest_msg(
             lastmsg=f"当前配置不允许被修改！如需激活本功能，请在config.py中设置ALLOW_RESET_CONFIG=True后重启软件。",
             chatbot=chatbot, history=history, delay=2
         )
         return
 
     yield from modify_configuration_hot(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_intention)
-    yield from update_ui_lastest_msg(
+    yield from update_ui_latest_msg(
         lastmsg=f"正在执行任务: {txt}\n\n配置修改完成，五秒后即将重启！若出现报错请无视即可。", chatbot=chatbot, history=history, delay=5
     )
     os.execl(sys.executable, sys.executable, *sys.argv)

crazy_functions/vt_fns/vt_state.py

@@ -5,7 +5,7 @@ class VoidTerminalState():
         self.reset_state()
 
     def reset_state(self):
-        self.has_provided_explaination = False
+        self.has_provided_explanation = False
 
     def lock_plugin(self, chatbot):
         chatbot._cookies['lock_plugin'] = 'crazy_functions.虚空终端->虚空终端'

crazy_functions/互动小游戏.py

@@ -1,4 +1,4 @@
-from toolbox import CatchException, update_ui, update_ui_lastest_msg
+from toolbox import CatchException, update_ui, update_ui_latest_msg
 from crazy_functions.multi_stage.multi_stage_utils import GptAcademicGameBaseState
 from crazy_functions.crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
 from request_llms.bridge_all import predict_no_ui_long_connection

crazy_functions/函数动态生成.py

@@ -15,7 +15,7 @@ Testing:
 
 
 from toolbox import CatchException, update_ui, gen_time_str, trimmed_format_exc, is_the_upload_folder
-from toolbox import promote_file_to_downloadzone, get_log_folder, update_ui_lastest_msg
+from toolbox import promote_file_to_downloadzone, get_log_folder, update_ui_latest_msg
 from crazy_functions.crazy_utils import request_gpt_model_in_new_thread_with_ui_alive, get_plugin_arg
 from crazy_functions.crazy_utils import input_clipping, try_install_deps
 from crazy_functions.gen_fns.gen_fns_shared import is_function_successfully_generated
@@ -27,7 +27,7 @@ import time
 import glob
 import multiprocessing
 
-templete = """
+template = """
 ```python
 import ...  # Put dependencies here, e.g. import numpy as np.
 
@@ -77,10 +77,10 @@ def gpt_interact_multi_step(txt, file_type, llm_kwargs, chatbot, history):
 
     # 第二步
     prompt_compose = [
-        "If previous stage is successful, rewrite the function you have just written to satisfy following templete: \n",
-        templete
+        "If previous stage is successful, rewrite the function you have just written to satisfy following template: \n",
+        template
     ]
-    i_say = "".join(prompt_compose); inputs_show_user = "If previous stage is successful, rewrite the function you have just written to satisfy executable templete. "
+    i_say = "".join(prompt_compose); inputs_show_user = "If previous stage is successful, rewrite the function you have just written to satisfy executable template. "
     gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
         inputs=i_say, inputs_show_user=inputs_show_user,
         llm_kwargs=llm_kwargs, chatbot=chatbot, history=history,
@@ -164,18 +164,18 @@ def 函数动态生成(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_
     if get_plugin_arg(plugin_kwargs, key="file_path_arg", default=False):
         file_path = get_plugin_arg(plugin_kwargs, key="file_path_arg", default=None)
         file_list.append(file_path)
-        yield from update_ui_lastest_msg(f"当前文件: {file_path}", chatbot, history, 1)
+        yield from update_ui_latest_msg(f"当前文件: {file_path}", chatbot, history, 1)
     elif have_any_recent_upload_files(chatbot):
         file_dir = get_recent_file_prompt_support(chatbot)
         file_list = glob.glob(os.path.join(file_dir, '**/*'), recursive=True)
-        yield from update_ui_lastest_msg(f"当前文件处理列表: {file_list}", chatbot, history, 1)
+        yield from update_ui_latest_msg(f"当前文件处理列表: {file_list}", chatbot, history, 1)
     else:
         chatbot.append(["文件检索", "没有发现任何近期上传的文件。"])
-        yield from update_ui_lastest_msg("没有发现任何近期上传的文件。", chatbot, history, 1)
+        yield from update_ui_latest_msg("没有发现任何近期上传的文件。", chatbot, history, 1)
         return  # 2. 如果没有文件
     if len(file_list) == 0:
         chatbot.append(["文件检索", "没有发现任何近期上传的文件。"])
-        yield from update_ui_lastest_msg("没有发现任何近期上传的文件。", chatbot, history, 1)
+        yield from update_ui_latest_msg("没有发现任何近期上传的文件。", chatbot, history, 1)
         return  # 2. 如果没有文件
 
     # 读取文件
@@ -183,7 +183,7 @@ def 函数动态生成(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_
 
     # 粗心检查
     if is_the_upload_folder(txt):
-        yield from update_ui_lastest_msg(f"请在输入框内填写需求, 然后再次点击该插件! 至于您的文件，不用担心, 文件路径 {txt} 已经被记忆. ", chatbot, history, 1)
+        yield from update_ui_latest_msg(f"请在输入框内填写需求, 然后再次点击该插件! 至于您的文件，不用担心, 文件路径 {txt} 已经被记忆. ", chatbot, history, 1)
         return
 
     # 开始干正事
@@ -195,7 +195,7 @@ def 函数动态生成(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_
             code, installation_advance, txt, file_type, llm_kwargs, chatbot, history = \
                 yield from gpt_interact_multi_step(txt, file_type, llm_kwargs, chatbot, history)
             chatbot.append(["代码生成阶段结束", ""])
-            yield from update_ui_lastest_msg(f"正在验证上述代码的有效性 ...", chatbot, history, 1)
+            yield from update_ui_latest_msg(f"正在验证上述代码的有效性 ...", chatbot, history, 1)
             # ⭐ 分离代码块
             code = get_code_block(code)
             # ⭐ 检查模块
@@ -206,11 +206,11 @@ def 函数动态生成(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_
             if not traceback: traceback = trimmed_format_exc()
         # 处理异常
         if not traceback: traceback = trimmed_format_exc()
-        yield from update_ui_lastest_msg(f"第 {j+1}/{MAX_TRY} 次代码生成尝试, 失败了~ 别担心, 我们5秒后再试一次... \n\n此次我们的错误追踪是\n```\n{traceback}\n```\n", chatbot, history, 5)
+        yield from update_ui_latest_msg(f"第 {j+1}/{MAX_TRY} 次代码生成尝试, 失败了~ 别担心, 我们5秒后再试一次... \n\n此次我们的错误追踪是\n```\n{traceback}\n```\n", chatbot, history, 5)
 
     # 代码生成结束, 开始执行
     TIME_LIMIT = 15
-    yield from update_ui_lastest_msg(f"开始创建新进程并执行代码! 时间限制 {TIME_LIMIT} 秒. 请等待任务完成... ", chatbot, history, 1)
+    yield from update_ui_latest_msg(f"开始创建新进程并执行代码! 时间限制 {TIME_LIMIT} 秒. 请等待任务完成... ", chatbot, history, 1)
     manager = multiprocessing.Manager()
     return_dict = manager.dict()
 

crazy_functions/多智能体.py

@@ -8,7 +8,7 @@
 
 import time
 from toolbox import CatchException, update_ui, gen_time_str, trimmed_format_exc, ProxyNetworkActivate
-from toolbox import get_conf, select_api_key, update_ui_lastest_msg, Singleton
+from toolbox import get_conf, select_api_key, update_ui_latest_msg, Singleton
 from crazy_functions.crazy_utils import request_gpt_model_in_new_thread_with_ui_alive, get_plugin_arg
 from crazy_functions.crazy_utils import input_clipping, try_install_deps
 from crazy_functions.agent_fns.persistent import GradioMultiuserManagerForPersistentClasses

crazy_functions/总结word文档.py

@@ -0,0 +1,127 @@
+from toolbox import update_ui
+from toolbox import CatchException, report_exception
+from toolbox import write_history_to_file, promote_file_to_downloadzone
+from crazy_functions.crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
+fast_debug = False
+
+
+def 解析docx(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt):
+    import time, os
+    # pip install python-docx 用于docx格式，跨平台
+    # pip install pywin32 用于doc格式，仅支持Win平台
+    for index, fp in enumerate(file_manifest):
+        if fp.split(".")[-1] == "docx":
+            from docx import Document
+            doc = Document(fp)
+            file_content = "\n".join([para.text for para in doc.paragraphs])
+        else:
+            try:
+                import win32com.client
+                word = win32com.client.Dispatch("Word.Application")
+                word.visible = False
+                # 打开文件
+                doc = word.Documents.Open(os.getcwd() + '/' + fp)
+                # file_content = doc.Content.Text
+                doc = word.ActiveDocument
+                file_content = doc.Range().Text
+                doc.Close()
+                word.Quit()
+            except:
+                raise RuntimeError('请先将.doc文档转换为.docx文档。')
+
+        # private_upload里面的文件名在解压zip后容易出现乱码（rar和7z格式正常），故可以只分析文章内容，不输入文件名
+        from crazy_functions.pdf_fns.breakdown_txt import breakdown_text_to_satisfy_token_limit
+        from request_llms.bridge_all import model_info
+        max_token = model_info[llm_kwargs['llm_model']]['max_token']
+        TOKEN_LIMIT_PER_FRAGMENT = max_token * 3 // 4
+        paper_fragments = breakdown_text_to_satisfy_token_limit(txt=file_content, limit=TOKEN_LIMIT_PER_FRAGMENT, llm_model=llm_kwargs['llm_model'])
+        this_paper_history = []
+        for i, paper_frag in enumerate(paper_fragments):
+            i_say = f'请对下面的文章片段用中文做概述，文件名是{os.path.relpath(fp, project_folder)}，文章内容是 ```{paper_frag}```'
+            i_say_show_user = f'请对下面的文章片段做概述: {os.path.abspath(fp)}的第{i+1}/{len(paper_fragments)}个片段。'
+            gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
+                inputs=i_say,
+                inputs_show_user=i_say_show_user,
+                llm_kwargs=llm_kwargs,
+                chatbot=chatbot,
+                history=[],
+                sys_prompt="总结文章。"
+            )
+
+            chatbot[-1] = (i_say_show_user, gpt_say)
+            history.extend([i_say_show_user,gpt_say])
+            this_paper_history.extend([i_say_show_user,gpt_say])
+
+        # 已经对该文章的所有片段总结完毕，如果文章被切分了，
+        if len(paper_fragments) > 1:
+            i_say = f"根据以上的对话，总结文章{os.path.abspath(fp)}的主要内容。"
+            gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
+                inputs=i_say,
+                inputs_show_user=i_say,
+                llm_kwargs=llm_kwargs,
+                chatbot=chatbot,
+                history=this_paper_history,
+                sys_prompt="总结文章。"
+            )
+
+            history.extend([i_say,gpt_say])
+            this_paper_history.extend([i_say,gpt_say])
+
+        res = write_history_to_file(history)
+        promote_file_to_downloadzone(res, chatbot=chatbot)
+        chatbot.append(("完成了吗？", res))
+        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+
+    res = write_history_to_file(history)
+    promote_file_to_downloadzone(res, chatbot=chatbot)
+    chatbot.append(("所有文件都总结完成了吗？", res))
+    yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+
+
+@CatchException
+def 总结word文档(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
+    import glob, os
+
+    # 基本信息：功能、贡献者
+    chatbot.append([
+        "函数插件功能？",
+        "批量总结Word文档。函数插件贡献者: JasonGuo1。注意, 如果是.doc文件, 请先转化为.docx格式。"])
+    yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+
+    # 尝试导入依赖，如果缺少依赖，则给出安装建议
+    try:
+        from docx import Document
+    except:
+        report_exception(chatbot, history,
+                         a=f"解析项目: {txt}",
+                         b=f"导入软件依赖失败。使用该模块需要额外依赖，安装方法```pip install --upgrade python-docx pywin32```。")
+        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+        return
+
+    # 清空历史，以免输入溢出
+    history = []
+
+    # 检测输入参数，如没有给定输入参数，直接退出
+    if os.path.exists(txt):
+        project_folder = txt
+    else:
+        if txt == "": txt = '空空如也的输入栏'
+        report_exception(chatbot, history, a=f"解析项目: {txt}", b=f"找不到本地项目或无权访问: {txt}")
+        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+        return
+
+    # 搜索需要处理的文件清单
+    if txt.endswith('.docx') or txt.endswith('.doc'):
+        file_manifest = [txt]
+    else:
+        file_manifest = [f for f in glob.glob(f'{project_folder}/**/*.docx', recursive=True)] + \
+                        [f for f in glob.glob(f'{project_folder}/**/*.doc', recursive=True)]
+
+    # 如果没找到任何文件
+    if len(file_manifest) == 0:
+        report_exception(chatbot, history, a=f"解析项目: {txt}", b=f"找不到任何.docx或doc文件: {txt}")
+        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+        return
+
+    # 开始正式执行任务
+    yield from 解析docx(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt)

crazy_functions/批量文件询问.py

@@ -1,496 +0,0 @@
-import os
-import threading
-import time
-from dataclasses import dataclass
-from typing import List, Tuple, Dict, Generator
-
-from crazy_functions.crazy_utils import request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency
-from crazy_functions.pdf_fns.breakdown_txt import breakdown_text_to_satisfy_token_limit
-from crazy_functions.rag_fns.rag_file_support import extract_text
-from request_llms.bridge_all import model_info
-from toolbox import update_ui, CatchException, report_exception
-
-
-@dataclass
-class FileFragment:
-    """文件片段数据类，用于组织处理单元"""
-    file_path: str
-    content: str
-    rel_path: str
-    fragment_index: int
-    total_fragments: int
-
-
-class BatchDocumentSummarizer:
-    """优化的文档总结器 - 批处理版本"""
-
-    def __init__(self, llm_kwargs: Dict, plugin_kwargs: Dict, chatbot: List, history: List, system_prompt: str):
-        """初始化总结器"""
-        self.llm_kwargs = llm_kwargs
-        self.plugin_kwargs = plugin_kwargs
-        self.chatbot = chatbot
-        self.history = history
-        self.system_prompt = system_prompt
-        self.failed_files = []
-        self.file_summaries_map = {}
-
-    def _get_token_limit(self) -> int:
-        """获取模型token限制"""
-        max_token = model_info[self.llm_kwargs['llm_model']]['max_token']
-        return max_token * 3 // 4
-
-    def _create_batch_inputs(self, fragments: List[FileFragment]) -> Tuple[List, List, List]:
-        """创建批处理输入"""
-        inputs_array = []
-        inputs_show_user_array = []
-        history_array = []
-
-        for frag in fragments:
-            if self.plugin_kwargs.get("advanced_arg"):
-                i_say = (f'请按照用户要求对文件内容进行处理，文件名为{os.path.basename(frag.file_path)}，'
-                         f'用户要求为：{self.plugin_kwargs["advanced_arg"]}：'
-                         f'文件内容是 ```{frag.content}```')
-                i_say_show_user = (f'正在处理 {frag.rel_path} (片段 {frag.fragment_index + 1}/{frag.total_fragments})')
-            else:
-                i_say = (f'请对下面的内容用中文做总结，不超过500字，文件名是{os.path.basename(frag.file_path)}，'
-                         f'内容是 ```{frag.content}```')
-                i_say_show_user = f'正在处理 {frag.rel_path} (片段 {frag.fragment_index + 1}/{frag.total_fragments})'
-
-            inputs_array.append(i_say)
-            inputs_show_user_array.append(i_say_show_user)
-            history_array.append([])
-
-        return inputs_array, inputs_show_user_array, history_array
-
-    def _process_single_file_with_timeout(self, file_info: Tuple[str, str], mutable_status: List) -> List[FileFragment]:
-        """包装了超时控制的文件处理函数"""
-
-        def timeout_handler():
-            thread = threading.current_thread()
-            if hasattr(thread, '_timeout_occurred'):
-                thread._timeout_occurred = True
-
-        # 设置超时标记
-        thread = threading.current_thread()
-        thread._timeout_occurred = False
-
-        # 设置超时定时器
-        timer = threading.Timer(self.watch_dog_patience, timeout_handler)
-        timer.start()
-
-        try:
-            fp, project_folder = file_info
-            fragments = []
-
-            # 定期检查是否超时
-            def check_timeout():
-                if hasattr(thread, '_timeout_occurred') and thread._timeout_occurred:
-                    raise TimeoutError("处理超时")
-
-            # 更新状态
-            mutable_status[0] = "检查文件大小"
-            mutable_status[1] = time.time()
-            check_timeout()
-
-            # 文件大小检查
-            if os.path.getsize(fp) > self.max_file_size:
-                self.failed_files.append((fp, f"文件过大：超过{self.max_file_size / 1024 / 1024}MB"))
-                mutable_status[2] = "文件过大"
-                return fragments
-
-            check_timeout()
-
-            # 更新状态
-            mutable_status[0] = "提取文件内容"
-            mutable_status[1] = time.time()
-
-            # 提取内容
-            content = extract_text(fp)
-            if content is None:
-                self.failed_files.append((fp, "文件解析失败：不支持的格式或文件损坏"))
-                mutable_status[2] = "格式不支持"
-                return fragments
-            elif not content.strip():
-                self.failed_files.append((fp, "文件内容为空"))
-                mutable_status[2] = "内容为空"
-                return fragments
-
-            check_timeout()
-
-            # 更新状态
-            mutable_status[0] = "分割文本"
-            mutable_status[1] = time.time()
-
-            # 分割文本
-            try:
-                paper_fragments = breakdown_text_to_satisfy_token_limit(
-                    txt=content,
-                    limit=self._get_token_limit(),
-                    llm_model=self.llm_kwargs['llm_model']
-                )
-            except Exception as e:
-                self.failed_files.append((fp, f"文本分割失败：{str(e)}"))
-                mutable_status[2] = "分割失败"
-                return fragments
-
-            check_timeout()
-
-            # 处理片段
-            rel_path = os.path.relpath(fp, project_folder)
-            for i, frag in enumerate(paper_fragments):
-                if frag.strip():
-                    fragments.append(FileFragment(
-                        file_path=fp,
-                        content=frag,
-                        rel_path=rel_path,
-                        fragment_index=i,
-                        total_fragments=len(paper_fragments)
-                    ))
-
-            mutable_status[2] = "处理完成"
-            return fragments
-
-        except TimeoutError as e:
-            self.failed_files.append((fp, "处理超时"))
-            mutable_status[2] = "处理超时"
-            return []
-        except Exception as e:
-            self.failed_files.append((fp, f"处理失败：{str(e)}"))
-            mutable_status[2] = "处理异常"
-            return []
-        finally:
-            timer.cancel()
-
-    def prepare_fragments(self, project_folder: str, file_paths: List[str]) -> Generator:
-        import concurrent.futures
-
-
-        from concurrent.futures import ThreadPoolExecutor
-        from typing import Generator, List
-        """并行准备所有文件的处理片段"""
-        all_fragments = []
-        total_files = len(file_paths)
-
-        # 配置参数
-        self.refresh_interval = 0.2  # UI刷新间隔
-        self.watch_dog_patience = 5  # 看门狗超时时间
-        self.max_file_size = 10 * 1024 * 1024  # 10MB限制
-        self.max_workers = min(32, len(file_paths))  # 最多32个线程
-
-        # 创建有超时控制的线程池
-        executor = ThreadPoolExecutor(max_workers=self.max_workers)
-
-        # 用于跨线程状态传递的可变列表 - 增加文件名信息
-        mutable_status_array = [["等待中", time.time(), "pending", file_path] for file_path in file_paths]
-
-        # 创建文件处理任务
-        file_infos = [(fp, project_folder) for fp in file_paths]
-
-        # 提交所有任务，使用带超时控制的处理函数
-        futures = [
-            executor.submit(
-                self._process_single_file_with_timeout,
-                file_info,
-                mutable_status_array[i]
-            ) for i, file_info in enumerate(file_infos)
-        ]
-
-        # 更新UI的计数器
-        cnt = 0
-
-        try:
-            # 监控任务执行
-            while True:
-                time.sleep(self.refresh_interval)
-                cnt += 1
-
-                # 检查任务完成状态
-                worker_done = [f.done() for f in futures]
-
-                # 更新状态显示
-                status_str = ""
-                for i, (status, timestamp, desc, file_path) in enumerate(mutable_status_array):
-                    # 获取文件名（去掉路径）
-                    file_name = os.path.basename(file_path)
-                    if worker_done[i]:
-                        status_str += f"文件 {file_name}: {desc}\n"
-                    else:
-                        status_str += f"文件 {file_name}: {status} {desc}\n"
-
-                # 更新UI
-                self.chatbot[-1] = [
-                    "处理进度",
-                    f"正在处理文件...\n\n{status_str}" + "." * (cnt % 10 + 1)
-                ]
-                yield from update_ui(chatbot=self.chatbot, history=self.history)
-
-                # 检查是否所有任务完成
-                if all(worker_done):
-                    break
-
-        finally:
-            # 确保线程池正确关闭
-            executor.shutdown(wait=False)
-
-        # 收集结果
-        processed_files = 0
-        for future in futures:
-            try:
-                fragments = future.result(timeout=0.1)  # 给予一个短暂的超时时间来获取结果
-                all_fragments.extend(fragments)
-                processed_files += 1
-            except concurrent.futures.TimeoutError:
-                # 处理获取结果超时
-                file_index = futures.index(future)
-                self.failed_files.append((file_paths[file_index], "结果获取超时"))
-                continue
-            except Exception as e:
-                # 处理其他异常
-                file_index = futures.index(future)
-                self.failed_files.append((file_paths[file_index], f"未知错误：{str(e)}"))
-                continue
-
-        # 最终进度更新
-        self.chatbot.append([
-            "文件处理完成",
-            f"成功处理 {len(all_fragments)} 个片段，失败 {len(self.failed_files)} 个文件"
-        ])
-        yield from update_ui(chatbot=self.chatbot, history=self.history)
-
-        return all_fragments
-
-    def _process_fragments_batch(self, fragments: List[FileFragment]) -> Generator:
-        """批量处理文件片段"""
-        from collections import defaultdict
-        batch_size = 64  # 每批处理的片段数
-        max_retries = 3  # 最大重试次数
-        retry_delay = 5  # 重试延迟（秒）
-        results = defaultdict(list)
-
-        # 按批次处理
-        for i in range(0, len(fragments), batch_size):
-            batch = fragments[i:i + batch_size]
-
-            inputs_array, inputs_show_user_array, history_array = self._create_batch_inputs(batch)
-            sys_prompt_array = ["请总结以下内容："] * len(batch)
-
-            # 添加重试机制
-            for retry in range(max_retries):
-                try:
-                    response_collection = yield from request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
-                        inputs_array=inputs_array,
-                        inputs_show_user_array=inputs_show_user_array,
-                        llm_kwargs=self.llm_kwargs,
-                        chatbot=self.chatbot,
-                        history_array=history_array,
-                        sys_prompt_array=sys_prompt_array,
-                    )
-
-                    # 处理响应
-                    for j, frag in enumerate(batch):
-                        summary = response_collection[j * 2 + 1]
-                        if summary and summary.strip():
-                            results[frag.rel_path].append({
-                                'index': frag.fragment_index,
-                                'summary': summary,
-                                'total': frag.total_fragments
-                            })
-                    break  # 成功处理，跳出重试循环
-
-                except Exception as e:
-                    if retry == max_retries - 1:  # 最后一次重试失败
-                        for frag in batch:
-                            self.failed_files.append((frag.file_path, f"处理失败：{str(e)}"))
-                    else:
-                        yield from update_ui(self.chatbot.append([f"批次处理失败，{retry_delay}秒后重试...", str(e)]))
-                        time.sleep(retry_delay)
-
-        return results
-
-    def _generate_final_summary_request(self) -> Tuple[List, List, List]:
-        """准备最终总结请求"""
-        if not self.file_summaries_map:
-            return (["无可用的文件总结"], ["生成最终总结"], [[]])
-
-        summaries = list(self.file_summaries_map.values())
-        if all(not summary for summary in summaries):
-            return (["所有文件处理均失败"], ["生成最终总结"], [[]])
-
-        if self.plugin_kwargs.get("advanced_arg"):
-            i_say = "根据以上所有文件的处理结果，按要求进行综合处理：" + self.plugin_kwargs['advanced_arg']
-        else:
-            i_say = "请根据以上所有文件的处理结果，生成最终的总结，不超过1000字。"
-
-        return ([i_say], [i_say], [summaries])
-
-    def process_files(self, project_folder: str, file_paths: List[str]) -> Generator:
-        """处理所有文件"""
-        total_files = len(file_paths)
-        self.chatbot.append([f"开始处理", f"总计 {total_files} 个文件"])
-        yield from update_ui(chatbot=self.chatbot, history=self.history)
-
-        # 1. 准备所有文件片段
-        # 在 process_files 函数中：
-        fragments = yield from self.prepare_fragments(project_folder, file_paths)
-        if not fragments:
-            self.chatbot.append(["处理失败", "没有可处理的文件内容"])
-            return "没有可处理的文件内容"
-
-        # 2. 批量处理所有文件片段
-        self.chatbot.append([f"文件分析", f"共计 {len(fragments)} 个处理单元"])
-        yield from update_ui(chatbot=self.chatbot, history=self.history)
-
-        try:
-            file_summaries = yield from self._process_fragments_batch(fragments)
-        except Exception as e:
-            self.chatbot.append(["处理错误", f"批处理过程失败：{str(e)}"])
-            return "处理过程发生错误"
-
-        # 3. 为每个文件生成整体总结
-        self.chatbot.append(["生成总结", "正在汇总文件内容..."])
-        yield from update_ui(chatbot=self.chatbot, history=self.history)
-
-        # 处理每个文件的总结
-        for rel_path, summaries in file_summaries.items():
-            if len(summaries) > 1:  # 多片段文件需要生成整体总结
-                sorted_summaries = sorted(summaries, key=lambda x: x['index'])
-                if self.plugin_kwargs.get("advanced_arg"):
-
-                    i_say = f'请按照用户要求对文件内容进行处理，用户要求为：{self.plugin_kwargs["advanced_arg"]}：'
-                else:
-                    i_say = f"请总结文件 {os.path.basename(rel_path)} 的主要内容，不超过500字。"
-
-                try:
-                    summary_texts = [s['summary'] for s in sorted_summaries]
-                    response_collection = yield from request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
-                        inputs_array=[i_say],
-                        inputs_show_user_array=[f"生成 {rel_path} 的处理结果"],
-                        llm_kwargs=self.llm_kwargs,
-                        chatbot=self.chatbot,
-                        history_array=[summary_texts],
-                        sys_prompt_array=["你是一个优秀的助手，"],
-                    )
-                    self.file_summaries_map[rel_path] = response_collection[1]
-                except Exception as e:
-                    self.chatbot.append(["警告", f"文件 {rel_path} 总结生成失败：{str(e)}"])
-                    self.file_summaries_map[rel_path] = "总结生成失败"
-            else:  # 单片段文件直接使用其唯一的总结
-                self.file_summaries_map[rel_path] = summaries[0]['summary']
-
-        # 4. 生成最终总结
-        if total_files ==1:
-            return "文件数为1，此时不调用总结模块"
-        else:
-            try:
-                # 收集所有文件的总结用于生成最终总结
-                file_summaries_for_final = []
-                for rel_path, summary in self.file_summaries_map.items():
-                    file_summaries_for_final.append(f"文件 {rel_path} 的总结：\n{summary}")
-
-                if self.plugin_kwargs.get("advanced_arg"):
-                    final_summary_prompt = ("根据以下所有文件的总结内容，按要求进行综合处理：" +
-                                            self.plugin_kwargs['advanced_arg'])
-                else:
-                    final_summary_prompt = "请根据以下所有文件的总结内容，生成最终的总结报告。"
-
-                response_collection = yield from request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
-                    inputs_array=[final_summary_prompt],
-                    inputs_show_user_array=["生成最终总结报告"],
-                    llm_kwargs=self.llm_kwargs,
-                    chatbot=self.chatbot,
-                    history_array=[file_summaries_for_final],
-                    sys_prompt_array=["总结所有文件内容。"],
-                    max_workers=1
-                )
-
-                return response_collection[1] if len(response_collection) > 1 else "生成总结失败"
-            except Exception as e:
-                self.chatbot.append(["错误", f"最终总结生成失败：{str(e)}"])
-                return "生成总结失败"
-
-    def save_results(self, final_summary: str):
-        """保存结果到文件"""
-        from toolbox import promote_file_to_downloadzone, write_history_to_file
-        from crazy_functions.doc_fns.batch_file_query_doc import MarkdownFormatter, HtmlFormatter, WordFormatter
-        import os
-        timestamp = time.strftime("%Y%m%d_%H%M%S")
-
-        # 创建各种格式化器
-        md_formatter = MarkdownFormatter(final_summary, self.file_summaries_map, self.failed_files)
-        html_formatter = HtmlFormatter(final_summary, self.file_summaries_map, self.failed_files)
-        word_formatter = WordFormatter(final_summary, self.file_summaries_map, self.failed_files)
-
-        result_files = []
-
-        # 保存 Markdown
-        md_content = md_formatter.create_document()
-        result_file_md = write_history_to_file(
-            history=[md_content],  # 直接传入内容列表
-            file_basename=f"文档总结_{timestamp}.md"
-        )
-        result_files.append(result_file_md)
-
-        # 保存 HTML
-        html_content = html_formatter.create_document()
-        result_file_html = write_history_to_file(
-            history=[html_content],
-            file_basename=f"文档总结_{timestamp}.html"
-        )
-        result_files.append(result_file_html)
-
-        # 保存 Word
-        doc = word_formatter.create_document()
-        # 由于 Word 文档需要用 doc.save()，我们使用与 md 文件相同的目录
-        result_file_docx = os.path.join(
-            os.path.dirname(result_file_md),
-            f"文档总结_{timestamp}.docx"
-        )
-        doc.save(result_file_docx)
-        result_files.append(result_file_docx)
-
-        # 添加到下载区
-        for file in result_files:
-            promote_file_to_downloadzone(file, chatbot=self.chatbot)
-
-        self.chatbot.append(["处理完成", f"结果已保存至: {', '.join(result_files)}"])
-@CatchException
-def 批量文件询问(txt: str, llm_kwargs: Dict, plugin_kwargs: Dict, chatbot: List,
-                 history: List, system_prompt: str, user_request: str):
-    """主函数 - 优化版本"""
-    # 初始化
-    import glob
-    import re
-    from crazy_functions.rag_fns.rag_file_support import supports_format
-    from toolbox import report_exception
-
-    summarizer = BatchDocumentSummarizer(llm_kwargs, plugin_kwargs, chatbot, history, system_prompt)
-    chatbot.append(["函数插件功能", f"作者：lbykkkk，批量总结文件。支持格式: {', '.join(supports_format)}等其他文本格式文件，如果长时间卡在文件处理过程，请查看处理进度，然后删除所有处于“pending”状态的文件，然后重新上传处理。"])
-    yield from update_ui(chatbot=chatbot, history=history)
-
-    # 验证输入路径
-    if not os.path.exists(txt):
-        report_exception(chatbot, history, a=f"解析项目: {txt}", b=f"找不到项目或无权访问: {txt}")
-        yield from update_ui(chatbot=chatbot, history=history)
-        return
-
-    # 获取文件列表
-    project_folder = txt
-    extract_folder = next((d for d in glob.glob(f'{project_folder}/*')
-                           if os.path.isdir(d) and d.endswith('.extract')), project_folder)
-
-    exclude_patterns = r'/[^/]+\.(zip|rar|7z|tar|gz)$'
-    file_manifest = [f for f in glob.glob(f'{extract_folder}/**', recursive=True)
-                     if os.path.isfile(f) and not re.search(exclude_patterns, f)]
-
-    if not file_manifest:
-        report_exception(chatbot, history, a=f"解析项目: {txt}", b="未找到支持的文件类型")
-        yield from update_ui(chatbot=chatbot, history=history)
-        return
-
-    # 处理所有文件并生成总结
-    final_summary = yield from summarizer.process_files(project_folder, file_manifest)
-    yield from update_ui(chatbot=chatbot, history=history)
-
-    # 保存结果
-    summarizer.save_results(final_summary)
-    yield from update_ui(chatbot=chatbot, history=history)

crazy_functions/批量翻译PDF文档_NOUGAT.py

@@ -1,5 +1,5 @@
 from toolbox import CatchException, report_exception, get_log_folder, gen_time_str
-from toolbox import update_ui, promote_file_to_downloadzone, update_ui_lastest_msg, disable_auto_promotion
+from toolbox import update_ui, promote_file_to_downloadzone, update_ui_latest_msg, disable_auto_promotion
 from toolbox import write_history_to_file, promote_file_to_downloadzone
 from crazy_functions.crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
 from crazy_functions.crazy_utils import request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency

crazy_functions/数学动画生成manim.py

@@ -166,7 +166,7 @@ class PointWithTrace(Scene):
 
 ```
 
-# do not use get_graph, this funciton is deprecated
+# do not use get_graph, this function is deprecated
 
 class ExampleFunctionGraph(Scene):
     def construct(self):

crazy_functions/生成多种Mermaid图表.py

@@ -324,16 +324,16 @@ def 生成多种Mermaid图表(
     if os.path.exists(txt):  # 如输入区无内容则直接解析历史记录
         from crazy_functions.pdf_fns.parse_word import extract_text_from_files
 
-        file_exist, final_result, page_one, file_manifest, excption = (
+        file_exist, final_result, page_one, file_manifest, exception = (
             extract_text_from_files(txt, chatbot, history)
         )
     else:
         file_exist = False
-        excption = ""
+        exception = ""
         file_manifest = []
 
-    if excption != "":
-        if excption == "word":
+    if exception != "":
+        if exception == "word":
             report_exception(
                 chatbot,
                 history,
@@ -341,7 +341,7 @@ def 生成多种Mermaid图表(
                 b=f"找到了.doc文件，但是该文件格式不被支持，请先转化为.docx格式。",
             )
 
-        elif excption == "pdf":
+        elif exception == "pdf":
             report_exception(
                 chatbot,
                 history,
@@ -349,7 +349,7 @@ def 生成多种Mermaid图表(
                 b=f"导入软件依赖失败。使用该模块需要额外依赖，安装方法```pip install --upgrade pymupdf```。",
             )
 
-        elif excption == "word_pip":
+        elif exception == "word_pip":
             report_exception(
                 chatbot,
                 history,

crazy_functions/知识库问答.py

@@ -1,4 +1,4 @@
-from toolbox import CatchException, update_ui, ProxyNetworkActivate, update_ui_lastest_msg, get_log_folder, get_user
+from toolbox import CatchException, update_ui, ProxyNetworkActivate, update_ui_latest_msg, get_log_folder, get_user
 from crazy_functions.crazy_utils import request_gpt_model_in_new_thread_with_ui_alive, get_files_from_everything
 from loguru import logger
 install_msg ="""
@@ -42,7 +42,7 @@ def 知识库文件注入(txt, llm_kwargs, plugin_kwargs, chatbot, history, syst
         yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
         # from crazy_functions.crazy_utils import try_install_deps
         # try_install_deps(['zh_langchain==0.2.1', 'pypinyin'], reload_m=['pypinyin', 'zh_langchain'])
-        # yield from update_ui_lastest_msg("安装完成，您可以再次重试。", chatbot, history)
+        # yield from update_ui_latest_msg("安装完成，您可以再次重试。", chatbot, history)
         return
 
     # < --------------------读取文件--------------- >
@@ -95,7 +95,7 @@ def 读取知识库作答(txt, llm_kwargs, plugin_kwargs, chatbot, history, syst
         yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
         # from crazy_functions.crazy_utils import try_install_deps
         # try_install_deps(['zh_langchain==0.2.1', 'pypinyin'], reload_m=['pypinyin', 'zh_langchain'])
-        # yield from update_ui_lastest_msg("安装完成，您可以再次重试。", chatbot, history)
+        # yield from update_ui_latest_msg("安装完成，您可以再次重试。", chatbot, history)
         return
 
     # < -------------------  --------------- >

crazy_functions/虚空终端.py

@@ -47,7 +47,7 @@ explain_msg = """
 from pydantic import BaseModel, Field
 from typing import List
 from toolbox import CatchException, update_ui, is_the_upload_folder
-from toolbox import update_ui_lastest_msg, disable_auto_promotion
+from toolbox import update_ui_latest_msg, disable_auto_promotion
 from request_llms.bridge_all import predict_no_ui_long_connection
 from crazy_functions.crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
 from crazy_functions.crazy_utils import input_clipping
@@ -113,19 +113,19 @@ def 虚空终端(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt
     # 用简单的关键词检测用户意图
     is_certain, _ = analyze_intention_with_simple_rules(txt)
     if is_the_upload_folder(txt):
-        state.set_state(chatbot=chatbot, key='has_provided_explaination', value=False)
+        state.set_state(chatbot=chatbot, key='has_provided_explanation', value=False)
         appendix_msg = "\n\n**很好，您已经上传了文件**，现在请您描述您的需求。"
 
-    if is_certain or (state.has_provided_explaination):
+    if is_certain or (state.has_provided_explanation):
         # 如果意图明确，跳过提示环节
-        state.set_state(chatbot=chatbot, key='has_provided_explaination', value=True)
+        state.set_state(chatbot=chatbot, key='has_provided_explanation', value=True)
         state.unlock_plugin(chatbot=chatbot)
         yield from update_ui(chatbot=chatbot, history=history)
         yield from 虚空终端主路由(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request)
         return
     else:
         # 如果意图模糊，提示
-        state.set_state(chatbot=chatbot, key='has_provided_explaination', value=True)
+        state.set_state(chatbot=chatbot, key='has_provided_explanation', value=True)
         state.lock_plugin(chatbot=chatbot)
         chatbot.append(("虚空终端状态:", explain_msg+appendix_msg))
         yield from update_ui(chatbot=chatbot, history=history)
@@ -141,7 +141,7 @@ def 虚空终端主路由(txt, llm_kwargs, plugin_kwargs, chatbot, history, syst
     # ⭐ ⭐ ⭐ 分析用户意图
     is_certain, user_intention = analyze_intention_with_simple_rules(txt)
     if not is_certain:
-        yield from update_ui_lastest_msg(
+        yield from update_ui_latest_msg(
             lastmsg=f"正在执行任务: {txt}\n\n分析用户意图中", chatbot=chatbot, history=history, delay=0)
         gpt_json_io = GptJsonIO(UserIntention)
         rf_req = "\nchoose from ['ModifyConfiguration', 'ExecutePlugin', 'Chat']"
@@ -154,13 +154,13 @@ def 虚空终端主路由(txt, llm_kwargs, plugin_kwargs, chatbot, history, syst
             user_intention = gpt_json_io.generate_output_auto_repair(analyze_res, run_gpt_fn)
             lastmsg=f"正在执行任务: {txt}\n\n用户意图理解: 意图={explain_intention_to_user[user_intention.intention_type]}",
         except JsonStringError as e:
-            yield from update_ui_lastest_msg(
+            yield from update_ui_latest_msg(
                 lastmsg=f"正在执行任务: {txt}\n\n用户意图理解: 失败 当前语言模型（{llm_kwargs['llm_model']}）不能理解您的意图", chatbot=chatbot, history=history, delay=0)
             return
     else:
         pass
 
-    yield from update_ui_lastest_msg(
+    yield from update_ui_latest_msg(
         lastmsg=f"正在执行任务: {txt}\n\n用户意图理解: 意图={explain_intention_to_user[user_intention.intention_type]}",
         chatbot=chatbot, history=history, delay=0)
 

crazy_functions/语音助手.py

@@ -42,7 +42,7 @@ class AsyncGptTask():
             MAX_TOKEN_ALLO = 2560
             i_say, history = input_clipping(i_say, history, max_token_limit=MAX_TOKEN_ALLO)
             gpt_say_partial = predict_no_ui_long_connection(inputs=i_say, llm_kwargs=llm_kwargs, history=history, sys_prompt=sys_prompt,
-                                                            observe_window=observe_window[index], console_slience=True)
+                                                            observe_window=observe_window[index], console_silence=True)
         except ConnectionAbortedError as token_exceed_err:
             logger.error('至少一个线程任务Token溢出而失败', e)
         except Exception as e:

crazy_functions/谷歌检索小助手.py

@@ -1,6 +1,6 @@
 from crazy_functions.crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
 from toolbox import CatchException, report_exception, promote_file_to_downloadzone
-from toolbox import update_ui, update_ui_lastest_msg, disable_auto_promotion, write_history_to_file
+from toolbox import update_ui, update_ui_latest_msg, disable_auto_promotion, write_history_to_file
 import logging
 import requests
 import time
@@ -156,7 +156,7 @@ def 谷歌检索小助手(txt, llm_kwargs, plugin_kwargs, chatbot, history, syst
     history = []
     meta_paper_info_list = yield from get_meta_information(txt, chatbot, history)
     if len(meta_paper_info_list) == 0:
-        yield from update_ui_lastest_msg(lastmsg='获取文献失败，可能触发了google反爬虫机制。',chatbot=chatbot, history=history, delay=0)
+        yield from update_ui_latest_msg(lastmsg='获取文献失败，可能触发了google反爬虫机制。',chatbot=chatbot, history=history, delay=0)
         return
     batchsize = 5
     for batch in range(math.ceil(len(meta_paper_info_list)/batchsize)):

docs/GithubAction+AllCapacity

@@ -5,6 +5,10 @@ FROM fuqingxu/11.3.1-runtime-ubuntu20.04-with-texlive:latest
 
 # edge-tts需要的依赖，某些pip包所需的依赖
 RUN apt update && apt install ffmpeg build-essential -y
+RUN apt-get install -y fontconfig
+RUN ln -s /usr/local/texlive/2023/texmf-dist/fonts/truetype /usr/share/fonts/truetype/texlive
+RUN fc-cache -fv
+RUN apt-get clean
 
 # use python3 as the system default python
 WORKDIR /gpt
@@ -30,7 +34,7 @@ RUN python3 -m pip install -r request_llms/requirements_qwen.txt
 RUN python3 -m pip install -r request_llms/requirements_chatglm.txt
 RUN python3 -m pip install -r request_llms/requirements_newbing.txt
 RUN python3 -m pip install nougat-ocr
-
+RUN python3 -m pip cache purge
 
 # 预热Tiktoken模块
 RUN python3  -c 'from check_proxy import warm_up_modules; warm_up_modules()'

docs/GithubAction+ChatGLM+Moss

@@ -7,6 +7,7 @@ RUN apt-get install -y git python python3 python-dev python3-dev --fix-missing
 
 # edge-tts需要的依赖，某些pip包所需的依赖
 RUN apt update && apt install ffmpeg build-essential -y
+RUN apt-get clean
 
 # use python3 as the system default python
 RUN curl -sS https://bootstrap.pypa.io/get-pip.py | python3.8
@@ -22,6 +23,7 @@ RUN python3 -m pip install -r request_llms/requirements_moss.txt
 RUN python3 -m pip install -r request_llms/requirements_qwen.txt
 RUN python3 -m pip install -r request_llms/requirements_chatglm.txt
 RUN python3 -m pip install -r request_llms/requirements_newbing.txt
+RUN python3 -m pip cache purge
 
 
 # 预热Tiktoken模块

docs/GithubAction+NoLocal

@@ -18,5 +18,7 @@ RUN apt update && apt install ffmpeg -y
 # 可选步骤，用于预热模块
 RUN python3  -c 'from check_proxy import warm_up_modules; warm_up_modules()'
 
+RUN python3 -m pip cache purge && apt-get clean
+
 # 启动
 CMD ["python3", "-u", "main.py"]

docs/GithubAction+NoLocal+Latex

@@ -30,5 +30,7 @@ COPY --chown=gptuser:gptuser . .
 # 可选步骤，用于预热模块
 RUN python3 -c 'from check_proxy import warm_up_modules; warm_up_modules()'
 
+RUN python3 -m pip cache purge
+
 # 启动
 CMD ["python3", "-u", "main.py"]

docs/GithubAction+NoLocal+Vectordb

@@ -24,6 +24,8 @@ RUN apt update && apt install ffmpeg -y
 
 # 可选步骤，用于预热模块
 RUN python3  -c 'from check_proxy import warm_up_modules; warm_up_modules()'
+RUN python3 -m pip cache purge && apt-get clean
+
 
 # 启动
 CMD ["python3", "-u", "main.py"]

docs/WindowsRun.bat

@@ -0,0 +1,26 @@
+@echo off
+setlocal
+
+:: 设置环境变量
+set ENV_NAME=gpt
+set ENV_PATH=%~dp0%ENV_NAME%
+set SCRIPT_PATH=%~dp0main.py
+
+:: 判断环境是否已解压
+if not exist "%ENV_PATH%" (
+    echo Extracting environment...
+    mkdir "%ENV_PATH%"
+    tar -xzf gpt.tar.gz -C "%ENV_PATH%"
+    
+    :: 运行conda环境激活脚本
+    call "%ENV_PATH%\Scripts\activate.bat"
+) else (
+    :: 如果环境已存在,直接激活
+    call "%ENV_PATH%\Scripts\activate.bat"
+)
+echo Start to run program:
+:: 运行Python脚本
+python "%SCRIPT_PATH%"
+
+endlocal
+pause

docs/translate_english.json

@@ -1141,7 +1141,7 @@
     "内容太长了都会触发token数量溢出的错误": "An error of token overflow will be triggered if the content is too long",
     "chatbot 为WebUI中显示的对话列表": "chatbot is the conversation list displayed in WebUI",
     "修改它": "Modify it",
-    "然后yeild出去": "Then yield it out",
+    "然后yield出去": "Then yield it out",
     "可以直接修改对话界面内容": "You can directly modify the conversation interface content",
     "additional_fn代表点击的哪个按钮": "additional_fn represents which button is clicked",
     "按钮见functional.py": "See functional.py for buttons",
@@ -1732,7 +1732,7 @@
     "或者重启之后再度尝试": "Or try again after restarting",
     "免费": "Free",
     "仅在Windows系统进行了测试": "Tested only on Windows system",
-    "欢迎加REAME中的QQ联系开发者": "Feel free to contact the developer via QQ in REAME",
+    "欢迎加README中的QQ联系开发者": "Feel free to contact the developer via QQ in README",
     "当前知识库内的有效文件": "Valid files in the current knowledge base",
     "您可以到Github Issue区": "You can go to the Github Issue area",
     "刷新Gradio前端界面": "Refresh the Gradio frontend interface",
@@ -1759,7 +1759,7 @@
     "报错信息如下. 如果是与网络相关的问题": "Error message as follows. If it is related to network issues",
     "功能描述": "Function description",
     "禁止移除或修改此警告": "Removal or modification of this warning is prohibited",
-    "Arixv翻译": "Arixv translation",
+    "ArXiv翻译": "ArXiv translation",
     "读取优先级": "Read priority",
     "包含documentclass关键字": "Contains the documentclass keyword",
     "根据文本使用GPT模型生成相应的图像": "Generate corresponding images using GPT model based on the text",
@@ -1998,7 +1998,7 @@
     "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",
+    "ArXiv论文精细翻译": "Fine translation of ArXiv 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",
@@ -2360,7 +2360,7 @@
     "请在config.py中设置ALLOW_RESET_CONFIG=True后重启软件": "Please set ALLOW_RESET_CONFIG=True in config.py and restart the software",
     "按照自然语言描述生成一个动画 | 输入参数是一段话": "Generate an animation based on natural language description | Input parameter is a sentence",
     "你的hf用户名如qingxu98": "Your hf username is qingxu98",
-    "Arixv论文精细翻译 | 输入参数arxiv论文的ID": "Fine translation of Arixv paper | Input parameter is the ID of arxiv paper",
+    "ArXiv论文精细翻译 | 输入参数arxiv论文的ID": "Fine translation of ArXiv paper | Input parameter is the ID of arxiv paper",
     "无法获取 abstract": "Unable to retrieve abstract",
     "尽可能地仅用一行命令解决我的要求": "Try to solve my request using only one command",
     "提取插件参数": "Extract plugin parameters",

docs/translate_japanese.json

@@ -753,7 +753,7 @@
     "手动指定和筛选源代码文件类型": "ソースコードファイルタイプを手動で指定およびフィルタリングする",
     "更多函数插件": "その他の関数プラグイン",
     "看门狗的耐心": "監視犬の忍耐力",
-    "然后yeild出去": "そして出力する",
+    "然后yield出去": "そして出力する",
     "拆分过长的IPynb文件": "長すぎるIPynbファイルを分割する",
     "1. 把input的余量留出来": "1. 入力の余裕を残す",
     "请求超时": "リクエストがタイムアウトしました",
@@ -1803,7 +1803,7 @@
     "默认值为1000": "デフォルト値は1000です",
     "写出文件": "ファイルに書き出す",
     "生成的视频文件路径": "生成されたビデオファイルのパス",
-    "Arixv论文精细翻译": "Arixv論文の詳細な翻訳",
+    "ArXiv论文精细翻译": "ArXiv論文の詳細な翻訳",
     "用latex编译为PDF对修正处做高亮": "LaTeXでコンパイルしてPDFに修正をハイライトする",
     "点击“停止”键可终止程序": "「停止」ボタンをクリックしてプログラムを終了できます",
     "否则将导致每个人的Claude问询历史互相渗透": "さもないと、各人のClaudeの問い合わせ履歴が相互に侵入します",
@@ -1987,7 +1987,7 @@
     "前面是中文逗号": "前面是中文逗号",
     "的依赖": "的依赖",
     "材料如下": "材料如下",
-    "欢迎加REAME中的QQ联系开发者": "欢迎加REAME中的QQ联系开发者",
+    "欢迎加README中的QQ联系开发者": "欢迎加README中的QQ联系开发者",
     "开始下载": "開始ダウンロード",
     "100字以内": "100文字以内",
     "创建request": "リクエストの作成",

docs/translate_traditionalchinese.json

@@ -771,7 +771,7 @@
     "查询代理的地理位置": "查詢代理的地理位置",
     "是否在输入过长时": "是否在輸入過長時",
     "chatGPT分析报告": "chatGPT分析報告",
-    "然后yeild出去": "然後yield出去",
+    "然后yield出去": "然後yield出去",
     "用户取消了程序": "使用者取消了程式",
     "琥珀色": "琥珀色",
     "这里是特殊函数插件的高级参数输入区": "這裡是特殊函數插件的高級參數輸入區",
@@ -1587,7 +1587,7 @@
     "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",
+    "欢迎加README中的QQ联系开发者": "歡迎加README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",
@@ -1989,7 +1989,7 @@
     "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",
+    "ArXiv论文精细翻译": "ArXiv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",