PDF & Image OCR Text Extractor v1.0.0 - Offline Tesseract OCR for Open WebUI

PDF & Image OCR Text Extractor for Open WebUI

First release! Features:

• Text-based PDF extraction via PyMuPDF
• Scanned/image PDF OCR via Tesseract
• Standalone image OCR (PNG, JPG, TIFF, etc.)
• Multi-language support (English + Swedish, configurable)
• Dual input: chat uploads and file path/URL
• Multiple output formats (text, markdown, save-to-file)
• Fully offline — no external API calls
• Docker-ready with custom Dockerfile