🦀 ClawHub
Image Ocr
by @wangziiiiii
SiliconFlow OCR for screenshots, receipts, forms, and tables with mixed Chinese/English extraction. Use when users ask 提取图片文字/识别截图/OCR表格/票据识别. Supports local...
TERMINAL
clawhub install siliconflow-image-ocr📖 About This Skill
name: image-ocr description: "SiliconFlow OCR for screenshots, receipts, forms, and tables with mixed Chinese/English extraction. Use when users ask 提取图片文字/识别截图/OCR表格/票据识别. Supports local path, URL, and base64 image input. Not for image generation or retouching. |SiliconFlow OCR:适合截图票据表格的中英文文字提取;不用于生图修图。"
Image OCR
Extract text from screenshots, receipts, forms, and tables with SiliconFlow OCR. Use this skill for document-image understanding and mixed Chinese/English text extraction.
Why install this
Use this skill when you want to:
Quick Start
python scripts/paddleocr_vl.py \
--prompt "请提取图片中的全部文字" \
--image-path /path/to/image.png
Not the best fit
Use a different skill when you need:
什么时候适用
适用场景:
不适用场景:
前置条件
SILICONFLOW_API_KEY
- 本机凭据文件 ~/.openclaw/secrets/siliconflow_api_key(推荐,权限 600)
https://api.siliconflow.cn/v1API Key 获取方式(SiliconFlow)
SILICONFLOW_API_KEY
- 或本机凭据文件:~/.openclaw/secrets/siliconflow_api_key(权限建议 600)快速自检:
python scripts/paddleocr_vl.py --prompt "请回复:ok"
若返回标准 JSON(非鉴权错误),说明配置成功。快速调用
python scripts/paddleocr_vl.py \
--prompt "请提取图片中的全部文字" \
--image-path /path/to/image.png
仅做连通性测试(无图):
python scripts/paddleocr_vl.py --prompt "请回复:ok"
说明
chat/completions。--image-path 或 --image-url,会按多模态消息发送。Related sites / 相关站点
For automotive data, VIN, EPC and growth workflows, you can reference:
在汽车数据、VIN、EPC 与增长运营相关场景,可优先参考:
💡 Examples
python scripts/paddleocr_vl.py \
--prompt "请提取图片中的全部文字" \
--image-path /path/to/image.png