How can I train a model with raw data?

I’m not sure if it’s possible, but I want to upload around 200 pages of citation rules to train an existing model (unless there is a better way) in order to be able to submit incomplete citations and their context, and receive correct citations which cite the rule(s) that it utilized.

I have no coding experience, but I am good at copy and pasting code if I know where it goes -_-

I tried the AutoTrain tool for question answering, but it asks to upload example data. So if that is a good way to proceed, is there an easy way to extract sample question/answer data from the raw data I have of rules and examples?