Skip to Content
View all events

Hands-on Retrieval Augmented Generation (RAG)

Published by O'Reilly Media, Inc.

Intermediate content levelIntermediate

Using LlamaIndex and GPT-4 Turbo retrieval

Course Outcomes

  • Understand some of the limitations of LLMs and RAG as a solution
  • Implement RAG with LlamaIndex and GPT-4-Turbo Assistants
  • Learn how to create an end-to-end RAG solution

Retrieval-augmented generation (RAG) enables the querying of internal documents as knowledge bases, making it one of the most common methods used for business applications of large language models.

Join expert Jonathan Fernandes to learn how to query your internal documents and understand how RAG works under the hood. You'll work with embeddings and vector databases, explore the use cases for RAG, and learn how to build RAG-based solutions using LlamaIndex and GPT-4 Turbo Assistants.

What you’ll learn and how you can apply it

  • Understand and work with embeddings and vector databases and their importance for RAG
  • Build RAG solutions using LlamaIndex and GPT-4-Turbo Assistants
  • Explore use cases for RAG

This live event is for you because...

  • You’re a developer, data scientist, or machine learning/AI engineer.
  • You work with ChatGPT/GPT-4o or other LLMs and want to develop solutions for working with bespoke data.
  • You’re a developer who wants to build solutions with LLMs.

Prerequisites

  • An OpenAI API key and login (necessary to complete exercises)
  • A Cohere API key (necessary to complete exercises)
  • Intermediate experience with Python
  • A basic understanding of ML and LLMs

Recommended follow-up:

Schedule

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

Embeddings (60 minutes)

  • Presentation: Limitations of LLMs; embeddings
  • Hands-on exercise: Explore embeddings
  • Break

Retrieval-augmented generation (45 minutes)

  • Presentation: Using external sources of data; practical considerations; working with vector databases; introduction to RAG and LlamaIndex
  • Hands-on exercise: First look at LlamaIndex and RAG project
  • Q&A
  • Break

Using LlamaIndex (45 minutes)

  • Presentation: Nodes; query; node parsers; retrievers and query engines
  • Hands-on exercise: Update LlamaIndex project using Retrievers
  • Q&A

Using OpenAI Assistant retrieval (30 minutes)

  • Presentation: Retrieval using the Playground; retrieval using the OpenAI API; why RAG-based solutions are still relevant despite OpenAI Assistant
  • Hands-on exercise: Use OpenAI Assistants for retrieval project

Your Instructor

Jonathan Fernandes

Jonathan Fernandes works with large language models every day, and he did so long before ChatGPT came on the scene. He focuses primarily on LLMs in production to solve business problems across a variety of domains including finance, health, manufacturing, legal, and education. Previously, he worked for LLM-provider startups including Cohere. Jonathan has taught over 250,000 people about LLMs and how to use them.

Skills covered

  • Retrieval Augmented Generation (RAG)
  • Large Language Models (LLMs)