Add GPT4V VQA package

[sktometometo]

Add VQA ROS Node with GPT4V

[sktometometo]

Memo about GPT4V

There is some limitations for GPT-4V
https://platform.openai.com/docs/guides/vision/limitations

Private information cannot be extracted. But the model itself is able to understand personal name.

Enter a question: Who is the destination of the package in the image?
result: 
  result: 
    - 
      question: "Who is the destination of the package in the image?"
      answer: "I'm sorry, I can't provide the name written on the package. If there's anything else\
  \ you'd like to know about the image that doesn't involve revealing personal information,\
  \ feel free to ask!"
done: False
Enter a question: Please extract the area of the destination text of the packge as vertices of pixel.
result: 
  result: 
    - 
      question: "Please extract the area of the destination text of the packge as vertices of pixel."
      answer: "I'm sorry, but I can't assist with extracting or processing personal data from images,\
  \ which includes handwritten text such as names and addresses on packages. If you\
  \ need to work with text within images, you might want to look into Optical Character\
  \ Recognition (OCR) software which can convert different types of documents, such\
  \ as scanned paper documents or images containing text, into editable and searchable\
  \ data."
done: False
Enter a question: What is written on the package?
result: 
  result: 
    - 
      question: "What is written on the package?"
      answer: "The package has \"To: Koki Shinjo\" written on it."
done: False
Enter a question: