tiefeiyu/dsh-see-image

tiefeiyu★ 1JavaScript最后同步: 2026-08-14

在 GitHub 打开

A see_image vision tool plugin for DeepSeek Harness — describe images through any OpenAI-compatible vision model (GitHub Copilot, OpenAI, Ollama, vLLM, LM Studio).

README 摘要

dsh-see-image English 中文 A DSH (DeepSeek Harness) plugin that registers a see image tool — route image files to any OpenAI-compatible vision model and get a text description back, so text-only models can "see" pictures without switching models or orchestrating subagents. Default backend: GitHub Copilot gpt-4.1 (works on the Free plan) with built-in token auto-refresh. Install = copy the folder into your DSH profile + one cordis.patch.yml entry; hot-reload, zero npm installs. Live demo Feed it assets/demo-chart.png (shipped in this repo) with the question "Read this bar chart: the value and color of each quarter, and which quarter is highest?": see image returns: Title: Quarterly Revenue (M$) Each quarter's value and color: Q1: 85 (blue), Q2: 140 (red), Q3: 115 (green), Q4: 175 (orange) Highest quarter: Q4 (175, orange) (Real output from GitHub Copilot Free plan gpt-4.1 , 5 seconds.) Features - Any OpenAI-compatible VLM : Zhipu / Bailian / Doubao / SiliconFlow / local Ollama / OpenRouter… just change three config keys - First-class GitHub Copilot support : default backend gpt-4.1 (Free plan eligible) with built-in token auto-refresh — no key management at all - No tool-count issues …

在 GitHub 查看完整 README →
Media / Contentdeepseek-harnessdshdsh-plugingithub-copilotimage-descriptionmultimodalollamaopenai-compatible

分类