Copy link to clipboard
Copied
Copy link to clipboard
Copied
The entirte page is being seen as a graphic so no text is being read. Do I have your permission to send this to our Engineering team as a sample file to train the AI?
Copy link to clipboard
Copied
Sure, feel free to use this file.
Also, I have the same problem with any raster PDF files (scan pdfs), so I have tried first to run it through OCR API service and then I used the Extract API service, even though still no text is being read.
Is there is any workaround to optimize/convert raster PDF files (searchable), so the Extract API service will be able to recognize the text at the lower layer?
Thanks,
Adam.