Need Guidance on Building a Chatbot like ChatGPT for University Data - Help!

I find myself in quite a situation and could use some guidance. Recently, I introduced my professor to privateGPT and demonstrated its capabilities using a small set of college data. To my delight, he was impressed and has now tasked me with researching and developing a ChatGPT-like chatbot, but with access to our university’s extensive data.

Here’s where I need your help: my professor wants this chatbot to be hosted on our university’s systems due to privacy concerns, which means I can’t use ChatGPT’s API. I’ve been given access to Sol HPC, but I’m finding it quite confusing to get started.

I’m looking for advice, tips, or any resources that can help me embark on this journey. Has anyone here worked on a similar project, or does anyone have experience with Sol HPC or building chatbots with local data sources? Any guidance or insights would be greatly appreciated! Thank you in advance for your help. This project means a lot to me, and I want to make sure I’m heading in the right direction.