360 Secure SkillHub
360 安全技能中心

universal-pdf-vision-parser

该 Skill 通过 Python 脚本调用 DashScope 上的 Qwen-VL-Max 多模态模型：先把 PDF 页面按 300 DPI 渲染为 PNG，再由模型识别语种并转写内容，最终输出带加粗关键词、斜体释义和表格的 Markdown 文件，面向多语言学习笔记和复杂排版文档。需 DashScope API Key，依赖 pymupdf 与 dashscope，可用 --max-pag…

mingensiie
mingensiie
热度 83.41
最近更新 2026-05-11 17:28:15
分类：效率依赖：代码执行 / 第三方 API / 内部调用大模型 / 读写文件应用场景：文件转换 / 数据处理 / 语言学习

安装技能

复制下面的话术发给你的 Agent，它会通过 secure-skills 检索并安装该技能。

执行命令安装此 skill： npx secure-skills-cli add universal-pdf-vision-parse
Metadata
name
universal-pdf-vision-parser
description
Extract multilingual document content and language learning notes (French, German, Japanese, Spanish, etc.) from PDFs using multimodal vision (Qwen-VL-Max). This skill converts PDF pages to high-res images and 'sees' the content to produce perfectly structured, high-readability Markdown.

Universal PDF Vision Parser Skill

Version: 0.1

This skill is a high-end multilingual document digitizer. It uses multimodal vision to 'look' at each PDF page, making it perfect for language learning notes, bilingual documents, and complex layouts that standard OCR fails to capture.

Prerequisites

  1. DashScope API Key: A valid key from Alibaba Cloud Bailian with qwen-vl-max access.
  2. Environment:
pip install pymupdf dashscope

Usage

Basic Command

python scripts/vision_parse.py --pdf <path_to_pdf> --out <path_to_output.md> --api-key <YOUR_API_KEY> --max-pages 2
  • --max-pages: (Optional) Max pages to process. Defaults to 2. Set to -1 for all pages.

Agentic Workflow

  1. Visual Scanning: Converts PDF pages to 300 DPI PNGs.
  2. Expert Transcription: Qwen-VL-Max identifies the language and transcribes terms, translations, and explanations.
  3. Markdown Structuring: Automatically formats content with bold keywords, italicized meanings, and clean tables.

Examples

User: "Convert this German-Chinese note to markdown: notes.pdf"

Agent Action:

python scripts/vision_parse.py --pdf notes.pdf --out notes.md