dsh-image-vision

Seamless image understanding for DeepSeek Harness: lets pure-text models read pasted/dropped images and Feishu/Lark images via a configurable vision model, without touching the host.

AI 分析

核心用途是为纯文本模型赋予图片读取能力。适合经常需要发送截图、文档图片给 AI，且拥有 OpenAI 兼容视觉模型端点的用户。

パッケージ

dsh-image-vision

バージョン

0.1.0

ライセンス

MIT

最終更新

2026/08/17

Configuration

Image recognition needs a vision model provider. Add an OpenAI-compatible vision endpoint in the DSH Models page (or ~/.dsh/settings.yaml), and — this is the part the Models page does not show — declare input: [text, image] on the model entry.

Example settings.yaml:

llm-pi-ai:
  providers:
    modelscope:
      displayName: ModelScope
      apiKeyEnv: MODELSCOPE_API_KEY
      api: openai-completions
      baseURL: https://api-inference.modelscope.cn/v1
      models:
        - id: Qwen/Qwen3-VL-8B-Instruct
          name: Qwen3-VL-8B
          input: [ text, image ]
    siliconflow:
      displayName: 硅基流动
      apiKeyEnv: SILICONFLOW_API_KEY
      api: openai-completions
      baseURL: https://api.siliconflow.cn/v1
      models:
        - id: Qwen/Qwen3-VL-32B-Instruct
          name: Qwen3-VL-32B-Instruct
          input: [ text, image ]

Then provide the API key in ~/.credentials.yaml or as an environment variable:

dsh-image-vision

AI 分析

インストール

ドキュメント

Configuration