Skip to content

[Bug]: Selecting pymupdf4llm as the document parser and then making knowledge base using lightrag selects mineru as document parser #594

Description

@VarLad

Do you need to file an issue?

  • I have searched the existing issues and this bug is not already filed.
  • I believe this is a legitimate bug, not just a question or feature request.

Describe the bug

LightRAG initialization failed: Parser 'mineru' is not properly installed. Please install it using 'pip install' or 'uv pip install'.

Steps to reproduce

Select Pymupdf4llm as knowledge base parser from settings
Then make a database using lightrag, add pdfs, start indexing.
The error is shown

Expected Behavior

Pymupdf4llm works as the document parser properly

Related Module

Knowledge Base Management

Configuration Used

My data/user/settings/document_parsing.json:

{
  "version": 2,
  "engine": "pymupdf4llm",
  "engines": {
    "text_only": {},
    "mineru": {
      "mode": "local",
      "api_base_url": "https://mineru.net",
      "api_token": "",
      "local_cli_path": "",
      "model_download_source": "huggingface",
      "model_download_endpoint": "",
      "model_version": "pipeline",
      "language": "auto",
      "enable_formula": true,
      "enable_table": true,
      "is_ocr": false,
      "allow_local_model_download": false
    },
    "docling": {
      "do_ocr": false,
      "do_table_structure": true,
      "allow_local_model_download": false
    },
    "markitdown": {
      "enable_llm_image_description": false
    },
    "pymupdf4llm": {
      "write_images": true,
      "image_format": "png",
      "image_dpi": 150
    }
  }
}

Logs and screenshots

No response

Additional Information

  • DeepTutor Version: 1.14.12
  • Operating System: Fedora Linux 45
  • Python Version: 3.12
  • Node.js Version:
  • Browser (if applicable):
  • Related Issues:

Metadata

Metadata

Assignees

No one assigned

    Labels

    bugSomething isn't working

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions