maxwell-feng/dsh-windows-ocr

Local OCR for attached images via the built-in Windows engine (Windows.Media.Ocr): only the recognized text is sent to the model, never the image bytes; vision passthrough is opt-in.

Vision & Multimodal ★ 0 updated —

View on GitHub ↗

Install

dsh plugin --profile web add github:maxwell-feng/dsh-windows-ocr

Details

Repo: maxwell-feng/dsh-windows-ocr
Category: Vision & Multimodal
Stars: 0
Last push: —
First seen: —