更新

difyPlugin/pdf/tools/pdf_to_markdown.yaml

@@ -1,68 +1,51 @@
-identity:
+identity:
   name: "pdf_to_markdown"
   author: "yslg"
   label:
     en_US: "PDF to Markdown"
-    zh_Hans: "PDF转Markdown"
+    zh_Hans: "PDF to Markdown"
     pt_BR: "PDF para Markdown"
-    ja_JP: "PDFからMarkdown"
+    ja_JP: "PDF to Markdown"
 description:
   human:
-    en_US: "Convert PDF to a single Markdown file with embedded base64 images. No LLM needed."
-    zh_Hans: "将PDF转换为单个Markdown文件，图片以base64嵌入，无需大模型"
-    pt_BR: "Converter PDF em um arquivo Markdown com imagens base64 incorporadas. Sem LLM."
-    ja_JP: "PDFをbase64画像埋め込みの単一Markdownファイルに変換。LLM不要。"
-  llm: "Convert a PDF file into a single Markdown (.md) file. Extracts text, tables, images (base64), and vector drawings. Auto-detects TOC and organizes by chapters. No LLM needed."
+    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 文件
-      pt_BR: Arquivo PDF
-      ja_JP: PDFファイル
+      zh_Hans: PDF File
+      pt_BR: PDF File
+      ja_JP: PDF File
     human_description:
       en_US: "PDF file to convert"
-      zh_Hans: "要转换的 PDF 文件"
-      pt_BR: "Arquivo PDF para converter"
-      ja_JP: "変換するPDFファイル"
+      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: include_images
-    type: boolean
-    required: false
+  - name: catalog
+    type: string
+    required: true
     label:
-      en_US: Include Images
-      zh_Hans: 包含图片
-      pt_BR: Incluir Imagens
-      ja_JP: 画像を含める
+      en_US: Catalog JSON
+      zh_Hans: Catalog JSON
+      pt_BR: Catalog JSON
+      ja_JP: Catalog JSON
     human_description:
-      en_US: "Whether to embed images as base64 in the Markdown output (default: true)"
-      zh_Hans: "是否将图片以base64嵌入Markdown输出（默认：是）"
-      pt_BR: "Se deve incorporar imagens como base64 na saída Markdown (padrão: verdadeiro)"
-      ja_JP: "Markdown出力にbase64として画像を埋め込むかどうか（デフォルト：はい）"
-    llm_description: "Set to true to embed images as base64, false to skip images"
-    form: form
-    default: true
-  - name: image_dpi
-    type: number
-    required: false
-    label:
-      en_US: Image DPI
-      zh_Hans: 图片DPI
-      pt_BR: DPI da Imagem
-      ja_JP: 画像DPI
-    human_description:
-      en_US: "DPI for rendering vector drawings (72-300, default: 150)"
-      zh_Hans: "矢量图渲染DPI（72-300，默认150）"
-      pt_BR: "DPI para renderizar desenhos vetoriais (72-300, padrão: 150)"
-      ja_JP: "ベクター描画のレンダリングDPI（72-300、デフォルト：150）"
-    llm_description: "Resolution for rendering vector drawings as images. Range 72-300, default 150."
-    form: form
-    default: 150
+      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