identity:
  name: "pdf_to_markdown"
  author: "yslg"
  label:
    en_US: "PDF to Markdown"
    zh_Hans: "PDF to Markdown"
    pt_BR: "PDF para Markdown"
    ja_JP: "PDF to Markdown"
description:
  human:
    en_US: "Convert PDF to Markdown using a catalog array. Images and graphics are ignored."
    zh_Hans: "Convert PDF to Markdown using a catalog array. Images and graphics are ignored."
    pt_BR: "Convert PDF to Markdown using a catalog array. Images and graphics are ignored."
    ja_JP: "Convert PDF to Markdown using a catalog array. Images and graphics are ignored."
  llm: "Convert a PDF file into Markdown using a catalog JSON array. Ignore images and graphics."
parameters:
  - name: file
    type: file
    required: true
    label:
      en_US: PDF File
      zh_Hans: PDF File
      pt_BR: PDF File
      ja_JP: PDF File
    human_description:
      en_US: "PDF file to convert"
      zh_Hans: "PDF file to convert"
      pt_BR: "PDF file to convert"
      ja_JP: "PDF file to convert"
    llm_description: "PDF file to convert to Markdown"
    form: llm
    fileTypes:
      - "pdf"
  - name: catalog
    type: string
    required: true
    label:
      en_US: Catalog JSON
      zh_Hans: Catalog JSON
      pt_BR: Catalog JSON
      ja_JP: Catalog JSON
    human_description:
      en_US: "Catalog JSON array like [{title,start,end,page_start_index,page_end_index}]"
      zh_Hans: "Catalog JSON array like [{title,start,end,page_start_index,page_end_index}]"
      pt_BR: "Catalog JSON array like [{title,start,end,page_start_index,page_end_index}]"
      ja_JP: "Catalog JSON array like [{title,start,end,page_start_index,page_end_index}]"
    llm_description: "Catalog JSON array returned by pdf_toc"
    form: llm
extra:
  python:
    source: tools/pdf_to_markdown.py