October 2025
Beginner
322 pages
8h 52m
English
Content preview from Visualizing Generative AI
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
O’Reilly covers everything we've got, with content to help us build a world-class technology community, upgrade the capabilities and competencies of our teams, and improve overall team performance as well as their engagement.I wanted to learn C and C++, but it didn't click for me until I picked up an O'Reilly book. When I went on the O’Reilly platform, I was astonished to find all the books there, plus live events and sandboxes so you could play around with the technology.I’ve been on the O’Reilly platform for more than eight years. I use a couple of learning platforms, but I'm on O'Reilly more than anybody else. When you're there, you start learning. I'm never disappointed.I'm always learning. So when I got on to O'Reilly, I was like a kid in a candy store. There are playlists. There are answers. There's on-demand training. It's worth its weight in gold, in terms of what it allows me to do.
Chapter 4. Building Agentic Systems
Chapter 4
Building Agentic Systems
Even though LLMs are powerful, there are limits to what you can accomplish with a single LLM call. For example, suppose you are using a foundational model that was trained on data until October 2024, and you ask it a question about chess. Any answer from that model will not reflect who won the World Chess Championship that commenced in November 2024.
Agentic systems provide ways to get around this, and other, limitations of LLMs. We call the software that employs GenAI to automate a single step of a multistep application an agent. We refer to the entire application as being agentic. In this chapter, we look into building agentic systems (see Figure 4-1). We discuss how to implement agents that involve multiple steps, then cover two specific types of agents, RAG agents and SQL agents, that are extremely useful in practice. RAG agents allow us to provide LLMs with fresh data that they did not have access to during training. SQL agents allow the LLM to access databases of structured, often confidential, data.
In Chapter 2, we discussed how to use GenAI as a layperson (using the chat interfaces to ChatGPT, Gemini, Meta AI, and the like) and as a software developer (using the API). Toward the end of the chapter, we discussed why a single prompt is not enough for an application, such as a recipe planner. If you are performing a complex task like planning recipes, you will have to break the problem into simpler ...
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.
Read now
Unlock full access
More than 5,000 organizations count on O’Reilly
O’Reilly covers everything we've got, with content to help us build a world-class technology community, upgrade the capabilities and competencies of our teams, and improve overall team performance as well as their engagement.Julian F.
I wanted to learn C and C++, but it didn't click for me until I picked up an O'Reilly book. When I went on the O’Reilly platform, I was astonished to find all the books there, plus live events and sandboxes so you could play around with the technology.Addison B.
I’ve been on the O’Reilly platform for more than eight years. I use a couple of learning platforms, but I'm on O'Reilly more than anybody else. When you're there, you start learning. I'm never disappointed.Amir M.
I'm always learning. So when I got on to O'Reilly, I was like a kid in a candy store. There are playlists. There are answers. There's on-demand training. It's worth its weight in gold, in terms of what it allows me to do.