> ## 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.
# O C R Agent • AI Agent SDK
> OCRAgent: A specialized agent for OCR (Optical Character Recognition).
# OCRAgent
> Defined in the [**Ocr Agent**](../modules/ocr_agent) module.
AI Agent
A specialized agent for OCR (Optical Character Recognition).
Extracts text from documents (PDFs) and images using AI models.
Supported Providers:
* Mistral: `mistral/mistral-ocr-latest`
```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: OCRAgent"]
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.
Extract text from a document or image.
Async version of extract().
Quick OCR - extract and return markdown text.
Async version of read().
## Usage
```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
from praisonaiagents import OCRAgent
agent = OCRAgent(llm="mistral/mistral-ocr-latest")
# Extract from PDF URL
result = agent.extract("https://example.com/document.pdf")
print(result.text)
# Extract from image URL
result = agent.extract("https://example.com/image.png")
for page in result.pages:
print(page.markdown)
```
## Source
`praisonaiagents/agent/ocr_agent.py` at line 42
***
## Related Documentation