NLP Question Answering: Answer questions with a local LLM and a vector database on your own embedded data
7 min readMar 11, 2024
A Deep Dive into Building an Advanced Q&A System on documents using a simple Retrieval Augmented Generation (RAG) Architecture. I’ll break down RAGs for you, diving into their architectural nitty-gritty. Plus, my articles will as always have some code snippets to get you up and running.