# DSH-Multimodal

> DSH 多模态输入插件：为不同类型的文件（图片 / 视频 / 音频 / 文本）配置独立的处理模型链，在文件进入会话模型之前，先用预设模型把它处理成 Prompt Tokens（文本），再交给会话模型。插件在 DSH 设置中新增独立的 Multimodal 页面。

## Metadata

- Author: [@yauntyour](https://github.com/yauntyour)
- Repo: <https://github.com/yauntyour/DSH-Multimodal>
- GitHub: [yauntyour/DSH-Multimodal](https://github.com/yauntyour/DSH-Multimodal)
- Stars: 1
- Language: TypeScript
- License: [MIT](https://spdx.org/licenses/MIT.html)
- Topics: `agent`, `deepseek`, `deepseek-harness`, `dsh`, `dsh-plugin`, `dsh-plugins`
- Forks: 0
- Open Issues: 0
- Last push: 2026-08-15T02:21:38.000Z
- Added: 2026-08-15T00:00:00.000Z

## Install

```bash
dsh plugin --profile web add github:yauntyour/DSH-Multimodal
```

---

This document is auto-generated by [deepseek-plugin.org](https://deepseek-plugin.org). HTML page: [DSH-Multimodal](https://deepseek-plugin.org/plugins/yauntyour/DSH-Multimodal)