> ## 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.

# Extract Text • AI Agent SDK

> extract_text: Extract text from an image (OCR-like functionality).

# extract\_text

<div className="flex items-center gap-2">
  <Badge color="purple">Method</Badge>
</div>

> This is a method of the [**VisionAgent**](../classes/VisionAgent) class in the [**vision\_agent**](../modules/vision_agent) module.

Extract text from an image (OCR-like functionality).

## Signature

```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
def extract_text(image: str, detail: Optional[str], model: Optional[str]) -> str
```

## Parameters

<ParamField query="image" type="str" required={true}>
  Image URL or local file path
</ParamField>

<ParamField query="detail" type="Optional" required={false}>
  Detail level (low, high, auto) - recommend "high" for text
</ParamField>

<ParamField query="model" type="Optional" required={false}>
  Override model for this call \*\*kwargs: Additional parameters
</ParamField>

### Returns

<ResponseField name="Returns" type="str">
  Extracted text
</ResponseField>

## Usage

```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
agent = VisionAgent()
    text = agent.extract_text("document.png", detail="high")
    print(text)
```

## Uses

* `analyze`

## Source

<Card title="View on GitHub" icon="github" href="https://github.com/MervinPraison/PraisonAI/blob/main/src/praisonai-agents/praisonaiagents/agent/vision_agent.py#L356">
  `praisonaiagents/agent/vision_agent.py` at line 356
</Card>