> ## Documentation Index
> Fetch the complete documentation index at: https://praison.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.
# Vision Agent • AI Agent SDK
> VisionAgent: A specialized agent for image analysis and understanding.
# VisionAgent
> Defined in the [**Vision Agent**](../modules/vision_agent) module.
AI Agent
A specialized agent for image analysis and understanding.
Provides:
* Image analysis and description
* Multi-image comparison
* Text extraction from images
Supported Providers:
* OpenAI: `gpt-4o`, `gpt-4o-mini`, `gpt-4-turbo`
* Anthropic: `claude-3-5-sonnet-20241022`, `claude-3-opus-20240229`
* Google: `gemini/gemini-1.5-pro`, `gemini/gemini-1.5-flash`
```mermaid theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
%%{init: {'theme': 'base', 'themeVariables': { 'primaryColor': '#8B0000', 'primaryTextColor': '#fff', 'primaryBorderColor': '#710101', 'lineColor': '#189AB4', 'secondaryColor': '#189AB4', 'tertiaryColor': '#fff' }}}%%
graph LR
input["Input Data"] --> agent["Agent: VisionAgent"]
agent --> output["Output Result"]
style agent fill:#8B0000,color:#fff
style input fill:#8B0000,color:#fff
style output fill:#8B0000,color:#fff
```
## Constructor
No description available.
No description available.
No description available.
No description available.
No description available.
No description available.
No description available.
No description available.
## Methods
Lazily initialize Rich Console.
Lazy load litellm module when needed.
Analyze an image and return analysis.
Generate a detailed description of an image.
Compare multiple images.
Extract text from an image (OCR-like functionality).
Async version of analyze().
Async version of describe().
Async version of compare().
Async version of extract\_text().
## Usage
```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
from praisonaiagents import VisionAgent
# Simple usage
agent = VisionAgent()
description = agent.describe("https://example.com/image.jpg")
print(description)
# Analyze with custom prompt
result = agent.analyze(
"https://example.com/chart.png",
prompt="What data does this chart show?"
)
# Compare images
comparison = agent.compare([
"image1.jpg",
"image2.jpg"
])
# Extract text
text = agent.extract_text("document.png")
```
## Source
`praisonaiagents/agent/vision_agent.py` at line 48
***
## Related Documentation