Advancements in Large Language Models (LLMs) have captured the imagination of the world. With the discharge of ChatGPT by OpenAI, in November, 2022, previously obscure terms like Generative AI entered the general public discourse. In a short while LLMs found a large applicability in modern language processing tasks and even paved the best way for autonomous AI agents. Some call it a watershed moment in technology and make lofty comparisons with the arrival of the web and even the invention of the sunshine bulb. Consequently, a overwhelming majority of business leaders, software developers and entrepreneurs are in hot pursuit of using LLMs to their advantage.
Retrieval Augmented Generation, or RAG, stands as a pivotal technique shaping the landscape of the applied generative AI. A novel concept introduced by Lewis et al of their seminal paper Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks, RAG has swiftly emerged as a cornerstone, enhancing reliability and trustworthiness within the outputs from Large Language Models.
On this blog post, we’ll go into the main points of evaluating RAG systems. But before that, allow us to arrange the context by understanding the necessity for RAG and getting an summary of the implementation of RAG pipelines.
