From 07086e3c0c2ef81cc116f7c31c2b4314f39d3c85 Mon Sep 17 00:00:00 2001
From: HuangHai <10402852@qq.com>
Date: Mon, 7 Jul 2025 10:26:35 +0800
Subject: [PATCH] 'commit'

---
 dsRagAnything/Doc/RagAnything配置.md | 85 +++++++++++---------------
 1 file changed, 35 insertions(+), 50 deletions(-)

diff --git a/dsRagAnything/Doc/RagAnything配置.md b/dsRagAnything/Doc/RagAnything配置.md
index aba3e52c..d72f1c8c 100644
--- a/dsRagAnything/Doc/RagAnything配置.md
+++ b/dsRagAnything/Doc/RagAnything配置.md
@@ -73,11 +73,11 @@ _HF_DEFAULT_ENDPOINT = "https://hf-mirror.com"
 
 
 
-- **注意**：需要提前配置好环境变量后，再进入PyCharm进行调试，因为我发现，如果是在打开PyCharm的前提下，添加了环境就是PyCharm里面的代码是检测不到的。
+- **注意**：需要提前配置好环境变量后，再进入$PyCharm$进行调试，因为我发现，如果是在打开$PyCharm$的前提下，添加了环境就是$PyCharm$里面的代码是检测不到的。
 
 
 
-- 因为原版的程序有soffice.exe版本检测框弹出，不能直接用于生产环境，我只好手动修改了下代码：
+- 因为原版的程序有$soffice.exe$版本检测框弹出，不能直接用于生产环境，手动修改代码：
 
   ```cmd
   D:\anaconda3\envs\raganything\Lib\site-packages\raganything\mineru_parser.py
@@ -86,6 +86,37 @@ _HF_DEFAULT_ENDPOINT = "https://hf-mirror.com"
   修改内容：
 
   ```python
+  # 62行
+  @staticmethod
+  def _run_mineru_command(
+      input_path: Union[str, Path],
+      output_dir: Union[str, Path],
+      method: str = "auto",
+      lang: Optional[str] = None,
+      backend: str = "pipeline",
+      start_page: Optional[int] = None,
+      end_page: Optional[int] = None,
+      formula: bool = True,
+      table: bool = True,
+      device: Optional[str] = None,
+      # source: str = "huggingface", # 模型来源，默认 huggingface
+      # source: str = "modelscope",  # 因为第一次手动从魔搭下载了模型，所以可以直接使用local模式
+      source: str = "local"
+  ) -> None:
+      
+  # 107行
+  try:
+      result = subprocess.run(
+          cmd,
+          #capture_output=True, #注释掉这句，可以把输出打印出来
+          text=True,
+          check=True,
+          encoding="utf-8",
+          errors="ignore",
+      )
+      print("MinerU command executed successfully")       
+      
+  # 442行
   # Check if LibreOffice is available
               #libreoffice_available = False
               working_libreoffice_cmd = 'soffice'
@@ -143,56 +174,10 @@ _HF_DEFAULT_ENDPOINT = "https://hf-mirror.com"
               #         "- CentOS/RHEL: sudo yum install libreoffice\n"
               #         "Alternatively, convert the document to PDF manually.\n"
               #         "MinerU 2.0 no longer includes built-in Office document conversion."
-              #     )
+              #     )     
   ```
 
-- 首次运行时，代码会执行下面的类似命令
-
-```cmd
-mineru -p C:\\Users\\ADMINI~1\\AppData\\Local\\Temp\\tmpt2sl2vd1\\驿来特平台安全.pdf -o output -m auto -b pipeline --source modelscope
-```
-
-![](https://dsideal.obs.cn-north-1.myhuaweicloud.com/HuangHai/BlogImages/%7Byear%7D/%7Bmonth%7D/%7Bmd5%7D.%7BextName%7D/20250706161400967.png)
-
-下载需要等待，但程序本身不显示进度，我一直以为卡住了，后来跟踪代码，才知道它是在下载模型。
-
-- 修改源码：
-
-```cmd
-D:\anaconda3\envs\raganything\Lib\site-packages\raganything\mineru_parser.py
-```
-
-```python
-# 62行
-@staticmethod
-def _run_mineru_command(
-    input_path: Union[str, Path],
-    output_dir: Union[str, Path],
-    method: str = "auto",
-    lang: Optional[str] = None,
-    backend: str = "pipeline",
-    start_page: Optional[int] = None,
-    end_page: Optional[int] = None,
-    formula: bool = True,
-    table: bool = True,
-    device: Optional[str] = None,
-    source: str = "local", # 'huggingface' --> 'local'
-) -> None:
-    
-# 107行
-try:
-    result = subprocess.run(
-        cmd,
-        #capture_output=True, #注释掉这句，可以把输出打印出来
-        text=True,
-        check=True,
-        encoding="utf-8",
-        errors="ignore",
-    )
-    print("MinerU command executed successfully")
-```
-
-
+  
 
 #### 五、相关资料