Is There a Problem With Pre-Trained Machine Learning Models?

In impura, the model that we had early on was actually not pre trained because of how it works. It would actually learn just on the users documents that they uploaded. And so you might have two documents which for a user have the same Schema but different fields. That's where some of our early users were implementing their own machine learning models to try to translate from the schema that the pre trained model produces to the schemas that they actually want to work with. So definitely interesting with one of the things I wanted to ask about as far as that goes is you talked about OCR, but we're also talking about language models here.