Vision & Multimodal

dsh-vision-assist

wjling/dsh-vision-assist · ★ 0

wjling

DeepSeek Harness 视觉助手插件：给没有视觉能力的模型配一个可随时切换的多模态识别模型。输入框图片自动落盘并改写为文本提示，主模型调用 vision_recognize 工具即可完成看图；识别模型在 settings 的 vision-assist 命名空间热更新切换。

Manifest details

Static manifest checks report declarations only; they are not compatibility or security review.

安装

dsh plugin --profile web add 'github:wjling/dsh-vision-assist#aff5393791837d2a8abbe341fd68fc67376cfed3'

GitHub 源码安装：首次需按提示配置 allowBuilds 构建授权后重试

For install and environment setup, plus plugin development tutorials, see DSH community docs ↗

No README content is available.