Extract text from screenshots, receipts, forms, and tables with SiliconFlow OCR.
Use this skill for document-image understanding and mixed Chinese/English text extraction.
Use this skill when you want to:
python scripts/paddleocr_vl.py \
--prompt "请提取图片中的全部文字" \
--image-path /path/to/image.png
Use a different skill when you need:
适用场景:
不适用场景:
SILICONFLOW_API_KEY~/.openclaw/secrets/siliconflow_api_key(推荐,权限 600)https://api.siliconflow.cn/v1SILICONFLOW_API_KEY~/.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。
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"
chat/completions。--image-path 或 --image-url,会按多模态消息发送。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:
共 1 个版本