CatchTheTornado/text-extract-api

Extracts text from PDFs, images, Office docs to Markdown or JSON, supports OCR and anonymization

extracts text from documents and images using OCR
mindee/doctr
extracts text from images, screenshots, or PDFs using OCR, works offline, open source
hiroi-sora/Umi-OCR
grab text from anywhere on your screen using OCR
TheJoeFin/Text-Grab
Extracts text from images and PDFs using vision models through Ollama, available as Python package and web app
imanoop7/Ollama-OCR
extracts text and metadata from PDFs, Word, HTML, images, and more with fast Rust core and Python support
yobix-ai/extractous
AI tool for extracting structured data from PDFs
DocumindHQ/documind
API for converting documents like pdf, docx, pptx, and images to Markdown
drmingler/docling-api
python library for extracting text from PDFs, images, and docs
Goldziher/kreuzberg
extracts text, math, and tables from academic PDFs
facebookresearch/nougat