I know we can upload the image file to be processed in Google DocumentAI; I am building an app that leverages DocumentAI API in Python. Is there a way for DocumentAI to process image in numpy array? For instance: with open(r'1_0.png', 'rb') as image_file: content = image_file.read() this is the content that can processed by Document AI Python SDK, but not something like this: content = cv2.imread(r'1_0.png', 'rb') Is there a way to convert the cv2 image to byte data like the first method to be processed by Google Document AI? I have multiple local processes to work on the input image; and I do not want to create a temp file in the app (consuming space). Continue reading...
