OCR Agent

On this page

Properties

The OCRAgent accepts 1 optional argument:

OCRAgent(model(Optional))

model

OCRModel

required

The selected model. All supported OCRModel models can be found below:

Show Supported MultimodalLLMs

GPT4Vision()

OCRModel (Default)

Supports gpt-4-turbo , gpt-4o .

TextractModel()

OCRModel

Claude()

OCRModel

Supports claude-3-opus-20240229 , claude-3-haiku-20240307 , claude-3-sonnet-20240229 .

Gemini()

OCRModel

Supports gemini-pro-vision .

Say we’re interested in extracting the license plate from this image:

example.py

OCRAgent(model=TextractModel())