Extract Text • AI Agent SDK

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

extract_text

Method

This is a method of the VisionAgent class in the vision_agent module.

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

Signature

def extract_text(image: str, detail: Optional[str], model: Optional[str]) -> str

Parameters

image · str · required

Image URL or local file path

detail · Optional

Detail level (low, high, auto) - recommend “high” for text

model · Optional

Override model for this call **kwargs: Additional parameters

Returns

Returns · str

Extracted text

Usage

agent = VisionAgent()
    text = agent.extract_text("document.png", detail="high")
    print(text)

Uses

• analyze

Source

View on GitHub

praisonaiagents/agent/vision_agent.py at line 356