ferstar/dsh-tool-ocr0

dsh-tool-ocr

Standalone ocr tool plugin for DeepSeek Harness (dsh) — local image text recognition via the newbee-ocr (nbocr) engine, for models without vision input

AI Analysis

核心用途是为纯文本模型提供本地离线图片文字识别能力。适合无法使用多模态模型但又需要处理图片中文字提取任务的用户。必要条件是需编译并配置本地 nbocr 二进制文件。

Package
dsh-tool-ocr
Version
0.1.0
License
MIT
Last updated
Aug 14, 2026

Install

This plugin has no verified bundle, or compatibility checks failed. Read the repository notes first. Read the full README ↗

Configuration

FieldDefaultMeaning
command— (required)The nbocr executable: absolute path or PATH-resolved name.
args[]Extra arguments before the nbocr subcommand (no shell).
env{}Extra environment entries.
languagechineseRecognition model/language alias.
detModelv6-tinyDetection model tier.
modelsDir''Model directory for non-embedded models; empty uses embedded models.
maxImageBytes26214400Largest accepted image in bytes.
maxOutputBytes2000000Largest collected engine stdout in bytes.
maxTextChars12000Largest recognized text returned in text.
timeoutMs600000Tool-call timeout budget in ms.

Tool usage

ocr { path | attachment_id, action?, include_boxes?, table?, max_text_chars? }

The model should call ocr with path for image files, or with attachment_id when the conversation already contains an image (shown as [image attachment ]). status probes readiness without engine work; check runs a real 1x1 probe recognition end to end.