FlorenceQA

This example demonstrates using the Florence2-QA tool to to answer questions about images.

NOTE: The FlorenceQA model can only be used in GPU environments.

from vision_agent_tools.models.florence2_qa import FlorenceQA

# (replace this path with your own!)
test_image = "path/to/your/image.jpg"

# Load the image and create initialize the FlorenceQA model
image = Image.open(test_image)
run_florence_qa = FlorenceQA()

# Time to put FlorenceQA to work! Let's pose a question about the image
answer = run_florence_qa(image, question="Is there a dog in the image?")

# Print the output answer
print(answer)

FlorenceQA

Bases: BaseMLModel

FlorenceQA is a tool that combines the Florence-2 and Roberta QA models to answer questions about images.

NOTE: The Florence-2 model can only be used in GPU environments.

__call__(image, question)

FlorenceQA model answers questions about images.

Parameters:

Name	Type	Description	Default
image	Image	The image to be analyzed.	required
question	str	The question to be answered.	required

Returns:

Name	Type	Description
str	dict[str, Any]	The answer to the question.

__init__()

Initializes the FlorenceQA model.