Source must be a URL (https://) or base64-encoded document.
Setup
Set MISTRAL_API_KEY in your environment before running OCRAgent.
Usage
from praisonaiagents import OCRAgent
agent = OCRAgent()
text = agent.read("https://arxiv.org/pdf/2201.04234")
print(text)
With Options
result = agent.extract(
"https://example.com/document.pdf",
pages=[0, 1, 2], # 0-indexed
include_image_base64=True
)
for page in result.pages:
print(page.markdown)
Models
| Model | Description |
|---|
mistral/mistral-ocr-latest | Latest OCR (default) |
