A first intro to Complex RAG (Retrieval Augmented Generation) | by Chia Jeng Yang | WhyHow.AI | Medium

medium.com · saved by 1 readers

If you’re looking for a non-technical introduction to RAG, including answers to various getting-started questions and a discussion of relevant use-cases, check out our breakdown of RAG here. In this article, we discuss various technical considerations when implementing RAG, exploring the concepts of chunking, query augmentation, hierarchies, multi-hop reasoning, and knowledge graphs. We also discuss unsolved problems & opportunities in the RAG infrastructure space, and introduce some infrastructure solutions for building RAG pipelines. The first obstacles and design choices you will be making when building a RAG system are in how to prepare the documents for storage and information extraction. That will be the primary focus of this article. As a refresher, here’s an overview of a RAG system architecture. When discussing effective information retrieval in RAG, it is crucial to understand the difference between “relevance” and “similarity.” Whereas similarity is about the similarity in w