AI / LangGraph LangChain Interview questions
How do nodes and edges work in LangGraph?
In LangGraph, nodes are Python functions that contain the logic of your application, and edges are the connections that define execution flow between nodes.
Nodes receive the current state dict and return a partial state update (a dict containing only the keys they want to change). LangGraph merges this update into the full state using the defined reducers:
def tool_node(state: AgentState) -> dict: # Execute the tool called by the last message last_message = state["messages"][-1] tool_result = tools_by_name[last_message.tool_calls[0]["name"]].invoke( last_message.tool_calls[0]["args"] ) return {"messages": [ToolMessage(content=str(tool_result), ...)]}
Edges come in two flavours:
- Normal edges — always go from node A to node B:
graph.add_edge("node_a", "node_b") - Conditional edges — a router function decides the next node:
graph.add_conditional_edges("node_a", router_fn, {"tool": "tool_node", "end": END})
Two special node names mark the graph boundaries: START is the entry point (no logic, just the first edge target), and END is the terminal node that signals the graph has finished. A node can have multiple outgoing edges but only one edge can be triggered per invocation (conditional edges are mutually exclusive).
What does a LangGraph node function return?
What is the purpose of the END sentinel in LangGraph?
More Related questions...
