dsh-ocr-local
Local OCR fallback for text-only routes: when the session model declares it cannot accept images, the attached image is cached locally and its path injected so the model can call ocr_image — PP-OCRv5 + ONNX Runtime on CPU, no API key, images never leave the machine. Silent when the model can see images.
纯文本路由的本地 OCR 兜底：会话模型明确声明不接受图片时，把附件的图片存入本地缓存并注入路径，模型调 ocr_image 用 PP-OCRv5 + ONNX Runtime 在纯 CPU 上离线识别，无需 API key，图片不出本机；模型能看图时静默。
How to install
dsh plugin add dsh-ocr-local About
dsh-ocr-local English · 中文 给 DeepSeek Harness（Web 端）装一个**本地 OCR 兜底**：当会话路由到的模型**不支持图片输入**时， 把图片里的文字读出来给模型；模型能看图时，插件完全静默、不插手。 识别引擎是 PP-OCRv5 + ONNX Runtime，**纯 CPU、完全离线**，图片不会离开你的电脑。 插件什么时候生效，什么时候静默 这是理解本插件最重要的一张表。判定基于当前会话实际路由到的模型**声明的输入能力** （inputModalities），而不是猜： | 会话路由到的模型 | 插件行为 | 模型实际拿到什么 | | --- | --- | --- | | **明确声明不支持图片**（如纯文本模型） | ✅ **生效**：图片存到本地缓存，并注入路径提示 → 模型调 ocr_image 识别 | 文字。Harness 对这类模型只给一句 [image omitted because this model accepts text only; …]，**没有任何路径**，所以没有本插件模型就完全读不到图 | | **明确声明支持图片**（多模态模型） | 🔇 **静默**：不存缓存、不注入提示 | 图片本身。Harness 还会在图片前附一条**只读副本路径**，模型想逐字核对时可以直接对那个路径调 ocr_i…
Recommendation signals
Meta
- License
- NOASSERTION
- Language
- JavaScript
- GitHub stars
- 5
- mo. downloads
- –
- Last push
- 2026-09-15
- Created
- 2026-08-17
Basic safety check
- Findings
- None
- Sources
- curated:awesome-dsh-plugin.com, curated:awesome-dsh-plugin/awesome-dsh-plugin
- Topics
- deepseek-harness, dsh-plugin, ocr, onnxruntime, pp-ocrv5
Related plugins
dsh-comfyui
fandc520/dsh-comfyui
Drive a local or remote ComfyUI server from DeepSeek Harness: comfyui_run / comfyui_object_info / comfyui_workflow tools generate and edit images and videos, with a workflow library (graph extraction: per component / main flow / all), a load area with resolution auto-match, a live queue, SDXL and Wan 2.1 templates, a companion skill, and a same-origin media proxy.
dsh-web
zhu1090093659/dsh-web-ui/tree/main/packages/dsh-tool-describe-image
A `describe_image` vision tool for text-only models: images (local path, URL, attachment) go to a configurable OpenAI-compatible vision endpoint and only the returned text enters the session.
modlens
liustack/modlens
Vision bridge for text-only models: paste an image, get structured JSON evidence (OCR, layout, semantics).
dsh-vision-router
ysr666/dsh-vision-router
Free vision for text-only agents: built-in keyless vision chain plus pixel tools (Q&A, grounding, crop, pixel diff, colors, OCR, SVG trace, cutout, screenshots); paste an image to use it.