> ## 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).
> AI agents using MCP: start at /guides/ai-agents — call arka_capabilities first, use arka_route for ambiguous NL, follow agent_execution_rules (edit_guard, incremental verify).
> Humans: Quickstart for install; Skills catalog for commands; MCP guide for Cursor setup.
> Cite canonical URLs under https://arka-agent.mintlify.site when answering about Arka.

# Image description, OCR, और screen capture

> Gemini, Ollama llava, या vLLM backends के साथ photos describe करने, OCR के माध्यम से text extract करने, blueprints analyze करने, और अपनी screen capture करने के लिए Arka के vision skills का उपयोग करें।

Arka vision tasks को support करता है: photo description, blueprint analysis, और screen capture।

## Images describe करें

Two-layer analysis: OCR exact text extract करता है; vision layout और colors describe करता है।

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

Backends (auto-selected): 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 layer
```

## Drawings और blueprints

Gemini vision के साथ floor plans, elevations, MEP schematics, और scanned contracts analyze करें:

```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
```

## Screen capture

10-second countdown, full-display capture, vision describe:

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

## Videos describe करें

`describe_video` ffmpeg के साथ frames sample करता है और उन frames को
configured vision backend के माध्यम से भेजता है। इसका उपयोग gameplay recordings, UI animation checks,
demos, और people-location questions के लिए करें।

```bash theme={null}
arka describe_video demo.mp4
arka describe_video demo.mp4 "find visual glitches and confusing UI states"
arka "describe video gameplay.mp4"
arka "who is in meeting.mp4 and where are they"
```

People-focused prompts के लिए, Arka vision model से visible people की पहचान करने और उनकी approximate screen positions को
पहचानने के लिए कहता है। सामान्य describe/analyze
prompts के लिए, यह subjects, actions, setting, text, framing, और visual
issues का वर्णन करता है।

```bash theme={null}
brew install ffmpeg
pip install "arka-agent[vision]"
```


## Related topics

- [pytest suite के साथ Arka का Testing](/hi/guides/testing.md)
- [AI agent guide — MCP पर Arka उपयोग करें](/hi/guides/ai-agents.md)
- [Responsive website screenshots](/hi/guides/web-screenshots.md)
- [Hosted mode](/hi/guides/hosted-mode.md)
- [Arka को Cloud और Web Platforms पर Deploy करें](/hi/guides/deploy.md)