GPT is probably the buzzword of the moment: everyone mentions it and everyone uses the GPT family models to create fantastic content. But do you know that Generative (the G of the previous acronym) can also be used to extract data from documents (and not just create them)? And that there are other ways to achieve the same goal without becoming a prompt engineering expert? In this session, we will see two opposed Microsoft tools for data extraction which have their peculiarities and disadvantages. Azure OpenAI with its GPT models and Document Intelligence with its classic approach based on the training of custom models. Who will win the challenge? Come and find out!