Directory
Search, filter by tool or topic, sort, and save ideas in this browser.
Loading directory…
Tools
Topics
4matches
MarkItDown documents an OCR plugin that accepts the same model-client configuration used for image descriptions and adds OCR during file conversion.
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.
The Reducto-powered agent processes scanned, handwritten, and table-heavy PDFs that need more than basic text 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.