The API returns the text without space between paragraphs, while something like tesseract separates them with an empty line. Is there an option to force this? I have attached an image as example
the text image:
I confirmed this issue. As a workaround, you can do some post-processing of the data. For example you can look at the x/y coordinates of the bounding boxes of the words. If there is a gap in the y-values, then your software can insert a second newline character.