ocrbase-hq/ocrbase

Extracts structured data from PDFs using open-weight models

View on index · View in 3D Map

Related repos

• Extracts structured data from documents via OCR
• adds OCR text layer to scanned PDFs for searching or copying text
• Extracts text from images and PDFs using vision models through Ollama, available as Python package and web app
• convert scanned PDFs to markdown or epub with OCR and AI
• benchmark dataset and tools for evaluating document parsing on diverse PDFs
• AI tool for extracting structured data from PDFs
• extracts text from images, screenshots, or PDFs using OCR, works offline, open source
• OCR app with PDF processing and document conversion
• Scans documents to PDF with OCR
• OCR for scanned PDFs with LLM-powered text correction