dsProject/dsRagAnything/Doc/RagAnything配置.md

一、官网

RAG-Anything 官网

Light-RAG 官网

二、环境配置

# 删除虚拟环境
conda remove -n py310 --all

# 创建虚拟环境
conda create -n py310 python=3.10

# 查看当前存在哪些虚拟环境
conda env list 

# 激活虚拟环境
conda activate py310

三、依赖环境

• 1、Libreoffice

https://zh-cn.libreoffice.org/

# 下载的版本：
https://mirrors.nju.edu.cn/tdf/libreoffice/stable/25.2.4/win/x86_64/LibreOffice_25.2.4_Win_x86-64.msi

注：因为后面要使用的MinerU能力是将PDF转为markdown,所以需要一个将Office转成PDF的功能

下载完成后，安装即可。

• 2、RAGAnything

# 安装RagAnything
pip install raganything pycocotools timm detectron2 sse_starlette

# 安装包
# pip install detectron2 --extra-index-url https://myhloli.github.io/wheels/

# 下载模型
mineru-models-download 

四、代码调试

• 将soffice.exe添加到环境变量

• C:\Program Files\LibreOffice\program
  D:\anaconda3\envs\py310\Scripts
  

  

• 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，手动修改代码：

  D:\anaconda3\envs\py310\Lib\site-packages\raganything\mineru_parser.py
  

  修改内容：

  # 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",  # 魔搭下载模型
      source: str = "local"      # 使用本地模型 
  ) -> 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'
              # try:
              #     result = subprocess.run(
              #         ["libreoffice", "--version"],
              #         capture_output=True,
              #         check=True,
              #         timeout=10,
              #         encoding="utf-8",
              #         errors="ignore",
              #     )
              #     libreoffice_available = True
              #     working_libreoffice_cmd = "libreoffice"
              #     print(f"LibreOffice detected: {result.stdout.strip()}")
              # except (
              #     subprocess.CalledProcessError,
              #     FileNotFoundError,
              #     subprocess.TimeoutExpired,
              # ):
              #     pass
              #
              # # Try alternative commands for LibreOffice
              # if not libreoffice_available:
              #     for cmd in ["soffice", "libreoffice"]:
              #         try:
              #             result = subprocess.run(
              #                 [cmd, "--version"],
              #                 capture_output=True,
              #                 check=True,
              #                 timeout=10,
              #                 encoding="utf-8",
              #                 errors="ignore",
              #             )
              #             libreoffice_available = True
              #             working_libreoffice_cmd = cmd
              #             print(
              #                 f"LibreOffice detected with command '{cmd}': {result.stdout.strip()}"
              #             )
              #             break
              #         except (
              #             subprocess.CalledProcessError,
              #             FileNotFoundError,
              #             subprocess.TimeoutExpired,
              #         ):
              #             continue
              #
              # if not libreoffice_available:
              #     raise RuntimeError(
              #         "LibreOffice is required for Office document conversion but was not found.\n"
              #         "Please install LibreOffice:\n"
              #         "- Windows: Download from https://www.libreoffice.org/download/download/\n"
              #         "- macOS: brew install --cask libreoffice\n"
              #         "- Ubuntu/Debian: sudo apt-get install libreoffice\n"
              #         "- 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."
              #     )     
  

五、相关资料

# 转换PDF到Markdown的工具
https://github.com/opendatalab/MinerU

# MinerU依赖的Magic-PDF
https://github.com/papayalove/Magic-PDF/blob/master/README_zh-CN.md

# MinerU依赖的PDF-Extract-Kit
https://github.com/opendatalab/PDF-Extract-Kit/blob/main/README_zh-CN.md

# mineru 官网
https://mineru.net/

# MinerU v2.0：VLM模型捅破解析效果天花板！
https://blog.csdn.net/qq1198768105/article/details/148678967

# MinerU、Magic-PDF、Magic-Doc
https://blog.csdn.net/lovechris00/article/details/140584728

# MinerU教程第二弹丨MinerU 本地部署保姆级“喂饭”教程
https://zhuanlan.zhihu.com/p/1908942870666282723

• 解决在国内网络无法下载huggingface的问题

# 要修改的文件
D:\anaconda3\envs\py310\Lib\site-packages\huggingface_hub\constants.py

# 修改文件
HUGGINGFACE_CO_URL_HOME = "https://hf-mirror.com/"
_HF_DEFAULT_ENDPOINT = "https://hf-mirror.com"