Sub-graphs

Sub-graphs Review We're building up to a multi-agent research assistant that ties together all of the modules from this course. We just covered parallelization, which is one important LangGraph controllability topic. Goals Now, we're going to cover sub-graphs. State Sub-graphs allow you to create and manage different states in different parts of your graph. This is particularly useful for multi-agent systems, with teams of agents that each have their own state. Let's consider a toy example: * I have a system that accepts logs * It performs two separate sub-tasks by different agents (summarize logs, find failure modes) * I want to perform these two operations in two different sub-graphs. The most critical thing to understand is how the graphs communicate! In short, communication is **done with over-lapping keys**: * The sub-graphs can access docs from the parent * The parent can access summary/failure_report from the sub-graphs Input Let's define a schema for the logs that will be input to our graph.