Week 12 — Lesson 2: Conditional routing and task decomposition

2 min

The NorthPeak router of Exercise 1 must send a data question to the SQL node and a manual question to the RAG node. A normal edge cannot do that: it always goes to the same node. A conditional edge lets a function choose the next node from the state. That choice also lets one big task be cut into small nodes that each do one job, which is what a 3-billion-parameter model like llama3.2 needs. This lesson covers the conditional edge, task decomposition, and the raw answers of the classifier on six real questions.

One arrow, several targets

A normal edge always goes to the same node. A conditional edge asks a function first. The function reads the state and returns a short string. A mapping turns that string into a node name.

Preview — the rest of the lesson is for enrolled readers.

Already enrolled with a code?

Your access is tied to your account, not to this link. Sign in with the same email you used in class: your course is waiting, no need to enter the code again.

Sign inNo account yet? Create one
This lesson is part of the “Week 12 — Stateful workflows with LangGraph” module

The first modules of the course are open to everyone. For the rest you have three options: buy this course once and for all, subscribe, or enter the code handed out in class.

Are you a student on this course?

The code is tied to your account: sign in or create an account and it will be applied automatically when you come back.

No account yet? Create one