Convert image-rich PDFs to Markdown with an optional model-powered OCR plugin
MarkItDown documents an OCR plugin that accepts the same model-client configuration used for image descriptions and adds OCR during file conversion.
Topic
ocr use cases: 6 examples
Source-linked workflows that name ocr. Part of the AI agent use cases on UsecaseBoard, or browse all use cases.
Give a document agent a PDF table-extraction and OCR playbook
Anthropic's published PDF skill supplies tool recipes for reading tables, OCR of scanned pages, combining outputs, and producing files, giving an agent concrete operations for document work.
Putaway: local AI files Downloads into folders you already have
Show HN (Oct 16): Putaway (MIT Mac menu bar + CLI) OCRs/reads PDF/Word/Excel/HTML in Downloads and proposes moves into existing folders only—default Apple Intelligence on-device, or Ollama/LM Studio/SubQ/Jev; dry-run plan + Undo; refuses .env/keys; SubQ/Jev auto-move accuracy ~132/136 in author test.
Rescue a recipe shown in a video with a photo import
Recipe Shelf's creator described turning recipe screenshots and handwritten cards into organized recipes using GPT-4 Vision.
Read mixed-format invoice files with OCR before AI field extraction
An English n8n tutorial uses Google Vision OCR for PDF and image invoices, an LLM for structured fields, and Google Sheets for storage, making the OCR-to-extraction sequence explicit.