RAG Retrieval Augmented Generation on a local model using Ollama and llama2.

A short simple question/answer python program that downloads webpages and pdfs and answers questions about them. This relies on running an Ollama server with one of their local models. There are no calls to foundation models, so there are no charges. Ollama runs on MacOS and Linux. Sorry Windows.

[@sarthak0703]

This is a good started project. I have few documents in my local system. I want to fine tune my local llama2 on those documents and save the fine tuned model to use further. Can I integrate RAG technique with the custom llm as well.?

[@dr.mikeybee]

Import your llama2 into Ollama, and you are good to go. There are a lot of videos on importing models into Ollama.