image_qa
autogen.agentchat.contrib.captainagent.tools.information_retrieval.image_qa.image_qa
image_qa
Perform question answering on an image using a pre-trained VQA model.
Parameters:Name | Description |
---|---|
image | The image to perform question answering on. It can be either file path to the image or a PIL Image object. |
question | The question to ask about the image. |
ckpt='Salesforce/blip-vqa-base' |