dsh-image-vision
Chat image-attachment bridge with a `view_image` tool for any OpenAI-compatible VLM (local Ollama or cloud): pasted/dropped images become `view_image` path markers before reaching text-only DeepSeek models.
纯文本 DeepSeek 的聊天识图插件：view_image 工具转发任意 OpenAI 兼容 VLM（本地 Ollama 或云端），对话框粘贴/拖拽的图片自动改写为 view_image 路径标记供模型查看。
How to install
dsh plugin add github:xsoc1/dsh-image-vision About
dsh-image-vision 给纯文本的 DeepSeek 加上眼睛：**聊天里传图 + 识图**，一个插件搞定。 view_image 工具：模型带着问题调用它（OCR、数数、读图表、看 UI 布局……任意视觉问题），插件把图片和问题转发给任意 **OpenAI 兼容的 VLM 端点**（本地 Ollama / 智谱 / DashScope / 豆包……），答案以文本返回。 **图片附件桥**：在聊天对话框**拖拽或粘贴图片**即可发送——dsh web 输入框原生接收图片附件，本插件在模型请求前把附件改写为 [用户上传的图片：<路径>] 标记，并引导模型调用 view_image 查看，纯文本模型因此"看见"你上传的图。 用户: （拖一张截图进对话框）帮我看看这个报错 模型 → view_image(source="…vision-bridge/xxx.png", question="这个报错的完整文本是什么？") ← "TypeError: Cannot read properties of undefined (reading 'map') at …" 模型: 这是一个 … 建议 … 安装 sh dsh plugin --profile web add dsh-image-vision 或经 dsh-market 插件市场安装。 注意：host 在消息提交时会校验当前模…
Recommendation signals
Meta
- License
- NOASSERTION
- Language
- TypeScript
- GitHub stars
- 1
- mo. downloads
- –
- Last push
- 2026-08-15
- Created
- 2026-08-15
Links
Basic safety check
- Findings
- curated 收录但无 npm 包/安装命令
- Sources
- curated:awesome-dsh-plugin.com, curated:awesome-dsh-plugin/awesome-dsh-plugin
- Topics
- deepseek-harness, dsh, dsh-plugin, multimodal, ollama, vision
Related plugins
modlens
liustack/modlens
Vision bridge for text-only models: paste an image, get structured JSON evidence (OCR, layout, semantics).
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.
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.
dsh-vision-toolkit
Anionex/dsh-vision-toolkit
Vision for text-only models: paste an image and the model switches to a Vision Toolkit variant for image Q&A, multi-image comparison, long-screenshot OCR, screenshot-to-UI reproduction, element grounding, and pixel diff. No API key by default — images are processed by the author-hosted free service, 100 per machine per day; configurable to your own provider.