yejinlei/pdf-ocr-skill

2 resources in this repository

🎯2Skills

🎯Skills2

A PDF text extraction skill supporting multiple OCR engines (RapidOCR local, RapidDoc enhanced, and SiliconFlow cloud API) for extracting text from scanned PDFs and images with support for Chinese and English. Use when you need to extract text from scanned or image-based PDF documents.

pdf-ocr-skill

🎯pdf-ocr🎯Skill

A skill that uses the SiliconFlow large model for OCR recognition, extracting text from scanned PDF files and images with support for Chinese and English.

pdf-ocr

Back to Home