Retrieval Augmented Generation (RAG)
Retrieval Augmented Generation (RAG) combines the strengths of Large Language Models (LLMs) with retrieval mechanisms. The term was first introduced by Meta AI researchers in a 2020 paper titled Retrieval Augmented Generation for Knowledge-Intensive NLP Tasks https://arxiv.org/abs/2005.11401. However, it wasn't until early 2023 that it started to gain interest within Enterprise organisations when early adopters started using it to provide the necessary domain context for knowledge based systems. Since then, the desire for greater reliability, efficiency, transparency, accuracy, flexibility, security and reduced latency has driven the development of new RAG architecture patterns as highlighted in the table below.
RAG Architecture Patterns
The table below highlights current RAG architecture patterns together with the pros, cons and emerging considerations for each.
Building scalable AI systems| Ex-JP Morgan| Ex-Amex| Startmate S25 Coach|Data Scientist|Machine Learning Engineer
2 个月My biggest learning after implementing multiple RAG systems last year has been. In 90% of use cases you are bottlenecked by the quality of your Retrieval system and how good is the pre-production corpus storage and upstream pipelines. The basics of Retrieval systems still supersede any UX gain you might get from LLMs.