@dsh-external/dsh-image-vision

Eyes for text-only DeepSeek: view_image tool (any OpenAI-compatible VLM, local Ollama or cloud) + chat image-attachment bridge that rewrites pasted/dropped images into view_image path markers

AI Analysis

核心用途是让纯文本模型通过兼容的外部 VLM 具备图片查看和分析能力。适合需要对图片进行 OCR 或视觉问答的分析任务。

Visionintegrations

Package: @dsh-external/dsh-image-vision
Version: 0.1.0
License: NOASSERTION
Last updated: Aug 15, 2026

Install

$npx -p @deepseek-ai/dsh dsh plugin --profile web add github:xsoc1/dsh-image-vision

README

Read the full README ↗

配置

dsh-image-vision:
  baseURL: http://localhost:11434/v1
  apiKey: ""            # 留空则读环境变量；本地端点无需 key
  model: qwen3-vl:4b
  maxTokens: 4096       # 推理型模型建议 ≥2048
  timeoutMs: 300000     # 本地冷加载与穷举 OCR 需 1-4 分钟
  maxImageBytes: 10485760