This pull request introduces a new script in process_images.py to extract images from a DOCX file, convert them to PNG format, and use a language model to describe the images. The script also includes functionality to encode images to base64 and process them with the language model.
amirpooya78
commented
1 week ago
This pull request introduces a new script in
process_images.pyto extract images from a DOCX file, convert them to PNG format, and use a language model to describe the images. The script also includes functionality to encode images to base64 and process them with the language model.