I’m working on building a ChatGPT Tutor for University Students using their class material. I’ve built a very simple v1 coursemind only using Canvas Learning Management System’s(most popular host of university classes) public API which only provides access to course files. I’m currently working on v2 which requires scraping the rest of the class material to have access to as much class data as possible for the model to perform and answer any question regarding a specific class. If anyone’s interested in helping with this, please let me know.
Which part of building the tutor are you struggling with – is it scraping the data? Prompting the tutor-bot? Retrieving the correct data for putting into the LLM? Deployment?
If you share more about what’s difficult then it’s easier for the community to help.