maxwell-feng/dsh-tesseract-ocr

Local OCR for attached images via Tesseract: only the recognized text is sent to the model, never the image bytes; vision passthrough is opt-in.

Install

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

Details

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