identity:
  name: "pdf_summary"
  author: "yslg"
  label:
    en_US: "PDF Page Summary"
    zh_Hans: "PDF页面概述"
    pt_BR: "Resumo de Página PDF"
    ja_JP: "PDFページ概要"
description:
  human:
    en_US: "Extract core elements (text, image, table, path) from PDF pages with coordinates, then summarize via LLM"
    zh_Hans: "提取PDF页面核心元素（文本、图片、表格、路径）及坐标，并通过LLM进行概述"
    pt_BR: "Extrair elementos principais (texto, imagem, tabela, caminho) de páginas PDF com coordenadas e resumir via LLM"
    ja_JP: "PDFページからコア要素（テキスト、画像、テーブル、パス）を座標付きで抽出し、LLMで要約"
  llm: "Extract core elements (text, image, table, drawing path) with coordinates from specified PDF page range, then use LLM to summarize the content"
parameters:
  - name: file
    type: file
    required: true
    label:
      en_US: PDF File
      zh_Hans: PDF 文件
      pt_BR: Arquivo PDF
      ja_JP: PDFファイル
    human_description:
      en_US: "PDF file to process"
      zh_Hans: "要处理的 PDF 文件"
      pt_BR: "Arquivo PDF para processar"
      ja_JP: "処理するPDFファイル"
    llm_description: "PDF file to extract elements from and summarize"
    form: llm
    fileTypes:
      - "pdf"
  - name: pdf_start_page
    type: number
    required: true
    label:
      en_US: Start Page
      zh_Hans: 起始页码
      pt_BR: Página Inicial
      ja_JP: 開始ページ
    human_description:
      en_US: "Start page index (0-based)"
      zh_Hans: "起始页码（从0开始）"
      pt_BR: "Índice da página inicial (base 0)"
      ja_JP: "開始ページ番号（0始まり）"
    llm_description: "Start page index (0-based) for element extraction"
    form: llm
    default: 0
  - name: pdf_end_page
    type: number
    required: true
    label:
      en_US: End Page
      zh_Hans: 结束页码
      pt_BR: Página Final
      ja_JP: 終了ページ
    human_description:
      en_US: "End page index (0-based, inclusive)"
      zh_Hans: "结束页码（从0开始，包含该页）"
      pt_BR: "Índice da página final (base 0, inclusivo)"
      ja_JP: "終了ページ番号（0始まり、含む）"
    llm_description: "End page index (0-based, inclusive) for element extraction"
    form: llm
    default: 0
  - name: model
    type: model-selector
    scope: llm
    required: true
    label:
      en_US: LLM Model
      zh_Hans: LLM 模型
      pt_BR: Modelo LLM
      ja_JP: LLMモデル
    human_description:
      en_US: "LLM model used for summarizing extracted content"
      zh_Hans: "用于概述提取内容的 LLM 模型"
      pt_BR: "Modelo LLM usado para resumir o conteúdo extraído"
      ja_JP: "抽出内容の要約に使用するLLMモデル"
    form: form
  - name: llm_prompt
    type: string
    required: false
    label:
      en_US: LLM Prompt
      zh_Hans: LLM 提示词
      pt_BR: Prompt do LLM
      ja_JP: LLMプロンプト
    human_description:
      en_US: "System prompt for LLM summarization"
      zh_Hans: "LLM 概述的系统提示词"
      pt_BR: "Prompt do sistema para resumo LLM"
      ja_JP: "LLM要約用のシステムプロンプト"
    llm_description: "System prompt guiding LLM on how to summarize the extracted PDF content"
    form: form
    default: "你是一个专业的文档分析助手。请根据以下从PDF页面中提取的结构化内容（包含文本、图片信息、表格和矢量图形），对每页内容进行准确、简洁的概述。"
extra:
  python:
    source: tools/pdf_summary.py