Hello everyone, I am new to this and I

I would recommend you go through create-llama project from LlamaIndex.
It will help you deploy your full application just based on your the basic requirements like what llm do you want to use.
What vector store if you want to use.
What framework ( for backend + frontend )

You can opt for opensource llms which will run locally.
https://www.llamaindex.ai/blog/create-llama-a-command-line-tool-to-generate-llamaindex-apps-8f7683021191

Thank you for the reply! Is this easy to follow? Also is this able to be used offline, while being able to feed it personal information or data?

Yes, it is very easy to follow.
Yes it can be used offline

Thank you!

Currently tring to follow the tutorial, I noticed hes on mac and im on windows and I am getting a few different options in powershell when creating it. Any fixes or advice for this?

Hey, I wanted to ask in regards to this, any way I can use my own RAG framework that I built and just use the frontend provided?

Yeah you can. Once you have the project with you locally. You can attach it with your backend as well. It may need some URL updation and response object structure update and that's it

it seems that it would take me alot of time understanding how it works to be able to do that

esp that i dont have experience with nextjs