xiaoshihou514/dsh-vision
DeepSeek 工具套件:视觉
项目介绍Project Overview
dsh-vision 是一款 DSH 原生视觉插件,为 DeepSeek Harness 添加图像理解能力。核心功能是通过插件调用视觉模型,可选用免费的智谱 API 或本地部署的千问 VL 2B 模型。使用场景为需要在 DSH 中处理图片识别、视觉问答或多模态对话时。安装命令为 dsh plugin --profile web add "github:xiaoshihou514/dsh-vision#main"。注意:本地模型需自行部署并确保显存充足,智谱接口需配置 API Key。
dsh-vision is a native DSH plugin that adds image understanding to DeepSeek Harness. Its core capability routes vision requests through the plugin, supporting either the free Zhipu API or a locally deployed Qwen-VL 2B model. Use it when running DSH profiles that need image recognition or multimodal Q&A. Install via dsh plugin --profile web add "github:xiaoshihou514/dsh-vision#main". Caveat: the local model requires sufficient GPU VRAM, and the Zhipu option needs a valid API key.
请帮我了解并安装插件:【dsh-vision】【https://github.com/xiaoshihou514/dsh-vision】
把上面这条消息直接发给当前会话里的 DSH,让它帮你了解并安装。安装命令不一定准确,发给 DSH 更稳。Send this message to DSH in your current session. CLI install commands may not be accurate across systems — DSH will figure it out for you.
或使用命令行安装(适合开发者)Or use CLI install (for developers)
命令行安装CLI Install
dsh plugin --profile web add "github:xiaoshihou514/dsh-weixin#main"
把 xiaoshihou514/dsh-vision 加入你的 DSH 配置(web profile)即可启用。
READMEREADME

dsh-vision
DeepSeek Harness: vision!
Native, minimal plugin that adds vision capability.
极简的原生视觉增强插件。
npm i -g @deepseek-ai/dsh
dsh plugin --profile web add "github:xiaoshihou514/dsh-weixin#main"
Supports Zhipu (free) and Qwen-VL 2B (local).
支持调用免费的智谱接口或使用本地的千问视觉小模型。
Also check out my other plugins ;)
也看看我其他的插件吧~
nexu-io/open-design
ruvnet/ruflo
amruthpillai/reactive-resume
esengine/DeepSeek-Reasonix
volcengine/OpenViking
Molunerfinn/PicGo
titanwings/distilly
titanwings/colleague-skill