This tutorial introduces you to the concepts of Retrieval Augmented Generation and how to use it together with llama.cpp
github.com/gge...
and my command line client
github.com/has...
It runs you through the steps of setting up an LLM-server with RAG capability at home. This allows you to talk to your own text documents.
Негізгі бет How to run your LLM with RAG at Home.
Пікірлер: 1