I am using Azure AI service to extract content from pdf, now what is happening is i have pdfs of multiple languages like en, hin, fr, de etc.

We are utilizing Azure skills to identify the language code and then perform OCR on documents with an unknown language code. Could someone provide guidance on how to implement this conditional code? I’m encountering errors and might not be applying it correctly.

I’m using this script https://github.com/microsoft/sample-app-aoai-chatGPT/blob/main/scripts/data_preparation.py and I want to get page number. I find out it can be done using indexer with imageAction=generateNormalizedImagePerPage configuration but I couldn’t know how to do.