maxwell-feng/dsh-tesseract-ocr

README excerpt

tesseract-ocr DeepSeek Harness (dsh) plugin that lets text-only models accept attached images: every image is recognized locally with Tesseract OCR and only the recognized text is sent to the model API. Image bytes never leave your machine. Tested on Ubuntu (primary target); works anywhere the tesseract CLI is installed (Linux, macOS, Windows). - No configuration changes to your models — no input: [text, image] hacks in settings.yaml . - Works with any provider/model in dsh; OCR applies only to text models. - Genuine vision models (declared image capability) pass images through untouched by default. - Fail-closed: if the plugin is not loaded, models stay text-only and image attachments are refused — nothing can silently leak. Do not enable this plugin together with windows-ocr : both would OCR the same image. Pick one per machine. Quick install via an AI agent Hand this repository to any AI agent, or paste the instruction below, and the agent will install and verify the plugin for you: Please install the dsh plugin in this repository by following . Run every preflight check, choose an install mode, then complete the mandatory verification: attach an image to a text-only model sessi…

Category