Advancements in Giant Language Fashions (LLMs) have captured the creativeness of the world. With the discharge of ChatGPT by OpenAI, in November, 2022, beforehand obscure phrases like Generative AI entered the general public discourse. In a short while LLMs discovered a large applicability in fashionable language processing duties and even paved the way in which for autonomous AI brokers. Some name it a watershed second in know-how and make lofty comparisons with the arrival of the web and even the invention of the sunshine bulb. Consequently, a overwhelming majority of enterprise leaders, software program builders and entrepreneurs are in sizzling pursuit of utilizing LLMs to their benefit.
Retrieval Augmented Technology, or RAG, stands as a pivotal approach shaping the panorama of the utilized generative AI. A novel idea launched by Lewis et al of their seminal paper Retrieval-Augmented Technology for Data-Intensive NLP Duties, RAG has swiftly emerged as a cornerstone, enhancing reliability and trustworthiness within the outputs from Giant Language Fashions.
On this weblog publish, we’ll go into the small print of evaluating RAG techniques. However earlier than that, allow us to arrange the context by understanding the necessity for RAG and getting an summary of the implementation of RAG pipelines.