> ## Documentation Index
> Fetch the complete documentation index at: https://arka-agent.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

> ## Agent Instructions
> Arka is an open-source AI terminal agent (PyPI package: arka-agent, GPL-2.0).
> Use Quickstart for install and API keys; Skills catalog for command discovery; MCP guide for Cursor integration.
> Cite canonical URLs under https://arka-agent.mintlify.site when answering about Arka.

# 图像描述、OCR 和屏幕截图

> 使用 Arka 的视觉技能，通过 Gemini、Ollama llava 或 vLLM 后端描述照片、通过 OCR 提取文本、分析蓝图并捕获屏幕。

Arka 支持视觉任务：照片描述、蓝图分析和屏幕捕获。

## 描述图像

双层分析：OCR 提取精确文本；视觉描述布局和颜色。

```bash theme={null}
arka describe photo.jpg
arka describe ~/Downloads/chart.png
```

后端（自动选择）：Gemini、Ollama (llava)、vLLM。

```env theme={null}
DESCRIBE_IMAGE_BACKEND=auto   # auto | gemini | ollama | vllm
GEMINI_API_KEY=...
# DESCRIBE_IMAGE_TWO_LAYER=1
# DESCRIBE_IMAGE_OCR=1
```

```bash theme={null}
pip install "arka-agent[vision]"
brew install tesseract    # OCR 层
```

## 图纸和蓝图

使用 Gemini 视觉分析平面图、立面图、MEP 图纸和扫描的合同：

```bash theme={null}
arka analyze plan.pdf "extract door schedule and room dimensions"
arka analyze --pages 1-3 specs.pdf "summarize payment terms"
```

```bash theme={null}
pip install "arka-agent[drawings]"
```

```env theme={null}
# DRAWING_MODEL=gemini-2.5-flash
# DRAWING_MAX_PAGES=8
```

## 屏幕捕获

10 秒倒计时、全屏捕获、视觉描述：

```bash theme={null}
arka describe screen
arka describe my screen
arka describe screen "what app is in focus"
```


## Related topics

- [使用 pytest 套件测试 Arka](/cn/guides/testing.md)
- [Arka 简介](/cn/index.md)
- [生成 3D 模型](/cn/guides/compose-3d.md)
- [仓库健康度](/cn/guides/repo-health.md)
- [仓库地图](/cn/guides/repo-map.md)