dsh-vision
给DeepSeek Harness装上眼睛：通过vision_analyze工具，使用兼容OpenAI的视觉模型分析图像。
Give DeepSeek Harness eyes: analyze images with an OpenAI-compatible vision model via a vision_analyze tool.
怎么安装
dsh plugin add dsh-vision 简介
dsh-vision Give DeepSeek Harness eyes: a vision_analyze tool that sends an image (local path or URL) to an OpenAI-compatible vision model and returns a text answer. English | 中文 Install sh dsh plugin --profile web add dsh-vision Set apiKey (or OPENAI_API_KEY), or point baseUrl at a local OpenAI-compatible endpoint such as Ollama (http://localhost:11434) with a vision model. Tool | Parameter | Type | Description | | --- | --- | --- | | image | string | Image path or https/data: URL | | question | string | What to ask (default: "Describe this image in detail.") | Config | Key | Type | Default | …
推荐参考
信息
- 协议
- MIT
- 语言
- TypeScript
- GitHub 星标
- 0
- 月下载
- 1.9K
- 最近更新
- 2026-08-17
- 创建于
- 2026-08-17
基础安全检查
- 检查结果
- 无
- 收录来源
- curated:0xsline/awesome-deepseek-harness
- 主题标签
- agent, deepseek-harness, dsh-plugin, image, multimodal, vision