# dsh-llm-vision

> Reliable vision + OCR for text-only models on DeepSeek Harness: describe_image (normal/critical) + extract_text tools, auto-preprocessing, retries, and a persistent answer cache.

## Metadata

- Author: [@1710782766](https://github.com/1710782766)
- Repo: <https://github.com/1710782766/dsh-llm-vision>
- GitHub: [1710782766/dsh-llm-vision](https://github.com/1710782766/dsh-llm-vision)
- Stars: 0
- Language: TypeScript
- License: [Apache-2.0](https://spdx.org/licenses/Apache-2.0.html)
- Topics: `deepseek-harness`, `dsh`, `dsh-plugin`, `image-understanding`, `llm`, `multimodal`, `ocr`, `vision`, `vlm`
- Forks: 0
- Open Issues: 0
- Last push: 2026-08-18T02:21:59.000Z
- Added: 2026-08-18T00:00:00.000Z

## Install

```bash
dsh plugin --profile web add dsh-llm-vision
```

---

This document is auto-generated by [deepseek-plugin.org](https://deepseek-plugin.org). HTML page: [dsh-llm-vision](https://deepseek-plugin.org/plugins/1710782766/dsh-llm-vision)