# Openakita/skills@baidu Paddleocr Doc

> PaddleOCR document parsing skill based on PaddleOCR-VL-1.5. Provides SOTA-level document understanding with ultra-high precision recognition and parsing. Use when user needs to parse, extract, or understand document content.

- Skill: `openakita/openakita-skills-baidu-paddleocr-doc` (Agent Skill, multi-file: 3 files)
- Install (CLI): `npx skillmds@latest add openakita/openakita-skills-baidu-paddleocr-doc`
- Raw SKILL.md: https://api.skillmd.com/api/skills/openakita/openakita-skills-baidu-paddleocr-doc/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- License: MIT
- Author: openakita (https://skillmd.com/u/openakita)
- Updated: 2026-09-09
- Page: https://skillmd.com/skills/openakita/openakita-skills-baidu-paddleocr-doc

---


# 文心衍生 · PaddleOCR 文档解析

基于 SOTA 文档解析模型 PaddleOCR-VL-1.5 构建，为 Agent 加上"眼睛"，对文档进行超高精度识别、解析。

## 配置

export BAIDU_API_KEY="your_key"

## 功能

- 文档结构识别
- 表格提取与还原
- 公式识别
- 图文混排解析
- 多语言文档支持

## 预置脚本

### scripts/baidu_ocr_doc.py
百度文档/表格 OCR 识别，需设置 BAIDU_OCR_AK 和 BAIDU_OCR_SK。

```bash
python3 scripts/baidu_ocr_doc.py doc /path/to/document.jpg
python3 scripts/baidu_ocr_doc.py table /path/to/table.png
```