A new course on Retrieval Augmented Generation (RAG) is live!

Retrieval augmented generation or simply RAG has rapidly become the most widespread approach to improving the performance and abilities of large language models for enterprise usage. My

name is Zan Hassani and I'm excited to be your instructor. As an AI engineer and educator, I've spent most of the last decade building AI powered applications and teaching developers how

to build their own. Whether you want to build a personal assistant that knows about your calendar or dietary restrictions or help your company launch a customized chatbot that can

confidently speak about your products, you'll need to give your LLM access to specialized information. Rag solves this

specialized information. Rag solves this problem by pairing a large language model with a database of trusted information that can be used to help answer domain specific questions and generate responses. Once you start

generate responses. Once you start looking for it, you'll see that Rag is powering many of the tools you use every day. From AI summaries at the top of web

day. From AI summaries at the top of web searches to the highly capable code agents built into modern idees, connecting LLMs with up-to-date and

personalized data is enabling previously impossible experiences in a huge variety of industries. This course is designed

of industries. This course is designed for people who are already comfortable reading and writing code. But you don't need any previous experience with AI technology. Whether you want to lead the

technology. Whether you want to lead the launch of a new ragbased product at work or are generative AI enthusiasts looking to better understand the AI tools you use every day, you'll leave this course

with the theoretical foundations and the hands-on experience you need to get the most out of retrieval augmented generation.