doc-parsing / cli
tesseract
Capability: tesseract
Use it when
- open-source OCR for images and scanned PDFs
- extract text from screenshots offline
What it solves
Not the fit when
- layout-perfect table recovery alone
Install
brew install tesseract # or apt install tesseract-ocr
Invoke
tesseract image.png stdout -l eng # OCR scanned pages before RAG.
Alternatives
No reviewed alternatives recorded yet.