From the course: Build AI Agents and Chatbots with LangGraph
Join today to access over 24,900 courses taught by industry experts.
LangGraph concepts - LangChain Tutorial
From the course: Build AI Agents and Chatbots with LangGraph
LangGraph concepts
- [Instructor] In this chapter, we will create a custom orders agent. We will use LangGraph to create a graph for this agent, and then execute the graph. We discussed briefly about LangGraph in the first chapter. Now let's discuss some key elements of LangGraph. We will be using these concepts in our implementation later. So what are the building blocks for a graph? We begin with nodes. A node is a place in the graph where some logic is executed. While building agents, we deal with a few types of nodes. An LLM node is used to integrate with an LLM to analyze prompts, create actions, and review observations. A tool node is used to execute tools. An action node can be used to invoke another agent from this agent. A logic node can be used for any custom logic outside of these types. An edge connects nodes. It is used to pass control from one node to another. In the case of this basic edge, when one node finishes processing data, it passes control to the next node in the graph through an…
Download courses and learn on the go
Watch courses on your mobile device without an internet connection. Download courses using your iOS or Android LinkedIn Learning app.