RAG Beyond Basics - Course Announcement

Welcome to the RAG Beyond Basics course. In this introduction we will discuss what this course is about, who is this course for, what we will cover and why you should join us. So what is this course about? This course will teach you how to interact with your text based documents using the power of large language models. This is one of the most practical applications of LLM today's business landscape. We will specifically focus on PDFs but the techniques you will learn here can be applied to any types of text based documents. The reason on focusing on PDFs is that vast majority of documents that you will encounter are going to be in PDF format. Now who is this course from? The intended audience of this course are SAs founders, developers, executives and hobbyists. You need to have a Python background to get the most out of this course. This will help you transform your brilliant ideas into working prototypes and will help you analyze thousands of documents in minutes, not days. Now what we will cover during this course so we will start with a basic Rack pipeline and we'll look at different components of this RAC pipeline and implement this in code. After that we'll start looking at more advanced techniques on how to improve your RAG using techniques like re ranking, how to expand the initial query using query expansion or multi query retrieval. Then we will look at some hypothetical document embedding. These are techniques which will help you generate hypothetical documents based on the problem that you are working with. We will also look at techniques like how to combine multiple retrievals together to improve the performance of your RAC pipeline. We'll combine semantic search techniques with traditional keyword based search techniques. And we will also look at techniques like Pyramid Document Retriever to expand the context that is retrieved by the embedding model. Now the focus is going to be not only on what these different techniques are, but when and why to use them. And also we are going to look at the hows. We will look at practical code examples on how to use these different techniques in different scenarios. And the best part is that you are going to get a fully working Python package that we will create throughout this course. All of the lectures in the course will help us create this Python package that you can use in your own projects. The course will initially focus on these topics, but since RAG is an ever evolving field, this course will be updated with new topics and lectures. Now let's Talk about the LLMs and models that we will be using during this course. The course is going to be mainly focusing on the use of LLMs and embedding models from OpenAI and the reason is that it's a simple API call which will help us quickly build our prototype. In the last part of the course I'm going to show you how to use local LLMs as well as local embedding models to replace OpenAI models, so you will be able to run this completely locally without relying on any external APIs. Okay, if this all sounds good and you're thinking, why take this course? So let me tell you a bit about myself. I have a PhD and over 7 years of industry experience in leading machine learning and AI teams. I have built systems powering tens of thousands of consumer devices. Apart from my technical background, I'm also passionate about open source and created one of the most popular open source rac projects, local GPT which has over 19,000 stars on GitHub. I also provide advisory services to startups in the space. We will have a dedicated channel on Prompt Engineering Discord Server for this course. There you can directly chat with me and other fellow practitioners about topics covered in the course and beyond. So join us to enhance your skills, innovate in your field and connect with community of like minded professionals. If this all sounds good, see you in the class.