Skip to Content
View all events

Retrieval-Augmented Generation (RAG) and Agents Using LLMs

Published by Pearson

Intermediate content levelIntermediate

Augment large language models and AI agents with real-time data for dynamic, context-aware apps

  • In-Depth Exploration of RAG Agents Using s Using LLMs: Gain a thorough understanding of Retrieval-Augmented Generation (RAG) and its role in enhancing LLMs including automating work with agents. This course offers a detailed walkthrough of RAG’s mechanics, ideal for both AI newcomers and seasoned developers.
  • Blending Real-Time Data with AI: Dive into the practical aspects of incorporating real-time data into LLMs. Learn how to dynamically update AI responses with the latest information, making applications like news aggregation, trend analysis, and live event monitoring more effective and relevant.
  • Hands-On, Applied Learning: Through interactive exercises, apply RAG in real-life scenarios, enhancing your skills in creating sophisticated AI solutions that respond to ever-changing data landscapes.
  • Community-Driven Innovation: Discover how collaboration and community input are driving the evolution of RAG and LLMs. Engage with a network of professionals and enthusiasts, contributing to and learning from collective advancements in the field.

This course serves as a comprehensive guide to augmenting Large Language Models with real-time data using Retrieval-Augmented Generation (RAG). RAG allows for better LLM outputs by incorporating external, current data to existing LLMs without having to further fine-tune. Agents and Agentic LLMs are becoming increasingly popular as engines of automated work and streamlined processes.

RAG is useful for an AI system to access up-to-date or domain-specific knowledge from large or streaming datasets, like recent news articles or medical research papers. Data in the RAG's repository can be continually updated without incurring significant costs. The RAG system's knowledge repository can contain data that is more contextual than the data in a generalized LLM while retaining the ability to expand with more data at a moment's notice. Agents work by being given access to a suite of tools with an LLM orchestrating the workflow end to end. The curriculum focuses on practical applications, enabling participants to not only understand the theoretical aspects of RAG but also to see its impact in action across various industries. Whether you're a data scientist, a business analyst, project manager, or a software developer, this course will equip you with the knowledge and skills to leverage the power of real-time data in AI.

What you’ll learn and how you can apply it

  • RAG / AI Agent Fundamentals and Application: Develop proficiency in designing, using, and evaluating Retrieval-Augmented Generation (RAG) systems and AI agents. Enhance Large Language Models (LLMs) to be more responsive, context-aware, and integrated into existing systems. Apply these concepts in real-world situations to create effective and dynamic AI solutions.
  • Real-time Data Integration Techniques: Discover the techniques for incorporating real-time data feeds into AI models and strategies to ensure your AI systems stay current, accurate, and highly relevant in rapidly changing scenarios. Leverage these skills to create AI applications that are responsive to current events and capable of adapting to new information as it becomes available.
  • Practical Implementation of RAG and Agents with LLMs: Understand how to practically apply RAG in various AI projects and construct modern AI agent pipelines. Gain hands-on experience in configuring and deploying AI solutions that leverage both the depth of LLMs and the agility of real-time data. Navigate and utilize LLMs augmented with RAG, ensuring your AI solutions are cutting-edge and relevant.

This live event is for you because...

  • You're Fascinated by Cutting-Edge AI Technologies: Perfect for individuals across diverse fields – from software engineering to digital content creation – who are eager to explore the forefront of AI innovations, particularly in the realm of LLMs and real-time data integration.
  • You Aim to Enhance Your Technical Expertise in AI: If you're a data scientist, AI researcher, or software developer, this course offers an opportunity to deepen your understanding and skills in the advanced application of LLMs, enriched by the real-time data capabilities of RAG.
  • You Seek Real-World AI Solutions: Ideal for professionals who desire to apply AI in practical settings. Whether it's for refining business strategies, enhancing customer experiences, or innovating in tech-driven industries, this course provides the insights and tools needed for implementing AI solutions that adapt to and leverage real-time data.

Prerequisites

To ensure you can dive straight into the heart of the course content, you should come prepared with:

  • Basic to Intermediate Python Skills: A solid understanding of Python is essential, as it will be the primary programming language used for demonstrating RAG integration with LLMs and handling real-time data.
  • Foundational Knowledge in Machine Learning and LLMs: Familiarity with basic machine learning concepts is crucial. Additionally, having some prior knowledge of Large Language Models will be beneficial, as we will delve into more advanced topics related to augmenting these models with RAG.
  • Introductory Experience with NLP and AI Models: A basic grasp of Natural Language Processing (NLP) and general AI model concepts will aid in understanding how RAG enhances the capabilities of these technologies in dynamic and evolving data environments.

Course Set-up

Before the course begins, make sure to set up your system with the following:

  • Python Environment: Install Python on your machine. We recommend using the Anaconda distribution as it conveniently bundles Python with Jupyter notebooks and other data science tools.
  • Internet Connection: Ensure you have a reliable internet connection to download course materials and access online resources during the course.
  • Course Materials on GitHub: https://github.com/sinanuozdemir/oreilly-retrieval-augmented-gen-ai. This repository will contain all the code, datasets, and additional materials you'll need.

For Non-Developers:

  • You'll be guided through how to access and use the provided materials, so no prior GitHub experience is necessary. We'll ensure you have all the support you need to get up and running.

Recommended Preparation

  • Read: Natural Language Processing with Transformers, Revised Edition by Lewis Tunstall, Leandro von Werra, and Thomas Wolf for a solid background on transformers, which are central to Hugging Face's technology.
  • Read: Introduction to Transformers for NLP by Shashank Jain, to get a comprehensive introduction to using the Hugging Face Library and models for solving NLP problems; a great primer before diving into the course.

Recommended Follow-up

Schedule

The time frames are only estimates and may vary according to how the class is progressing.

Segment 1: Introduction to LLMs and Real-Time Data Integration (40 minutes)

  • Understanding the Basics of Large Language Models (LLMs)
  • The Concept and Importance of Real-Time Data in AI
  • Q&A Session

Segment 2: The Basics of RAG and Its Application in LLMs (45 minutes)

  • Introduction to Retrieval-Augmented Generation (RAG)
  • How RAG Enhances LLMs with Real-Time Data
  • Exercise: Simple RAG Implementation with an LLM
  • Q&A Session

Break (10 minutes)

Segment 3: Implementing RAG in Practical Scenarios (60 minutes)

  • Case Studies: RAG in Action Across Various Industries
  • Exercise: Augmenting an LLM with Real-Time Data Using RAG
  • Q&A Session

Break (10 minutes)

Segment 4: AI Agents and Advanced RAG Techniques (60 minutes)

  • Defining and Constructing Modern AI Agent pipelines
  • Exploring Advanced RAG Techniques for Complex Data Integration
  • The Role of Data Rights and Collaboration in Advancing RAG Applications
  • Q&A Session

Course Wrap-Up and Next Steps (15 minutes)

  • Recap of Key Concepts
  • Guidance on Further Learning and Application in Professional Settings

Your Instructor

  • Sinan Ozdemir

    Sinan Ozdemir is the founder of Crucible, an AI factory platform that helps teams convert existing workflows into custom models. He is a Y Combinator alum, AI & LLM Advisor at Tola Capital, and the author of multiple books on data science and machine learning including Building Agentic AI, Quick Start Guide to LLMs, and Principles of Data Science. Sinan is a former lecturer of data science at Johns Hopkins University and the founder of Kylie.ai, an enterprise-grade conversational AI platform (acquired 2014). He holds a master's degree in pure mathematics from Johns Hopkins University and is based in San Francisco, California.

    linkedinXlinksearch

Skill covered

GPT