paddleocr-text-recognition - Extract text from images and PDFs using PaddleOCR
Extracts text with locations from images and PDF documents
Tags
Updated: 2026-05-09Capabilities
Typical Inputs
Typical Outputs
What this skill does
- Extract text from images
- Extract text from PDFs
- Read local files
- Process file URLs
Inputs
- Image files
- PDF documents
- File URLs
- Local file paths
Outputs
- Recognized text
- Text coordinates
- JSON result file
Requirements
- PADDLEOCR_OCR_API_URL
- PADDLEOCR_ACCESS_TOKEN
- Python environment
- Network access