How to beginner · 3 min read

How to run a LangGraph graph

Q: How to run a LangGraph graph

To run a LangGraph graph, define your state type and node functions, add nodes and edges to a StateGraph, compile it with graph.compile(), then invoke the compiled app with app.invoke() passing the initial state. This executes the graph and returns the final state.

Quick answer

To run a LangGraph graph, define your state type and node functions, add nodes and edges to a StateGraph, compile it with graph.compile(), then invoke the compiled app with app.invoke() passing the initial state. This executes the graph and returns the final state.

PREREQUISITES

Python 3.8+
pip install langgraph
Basic Python typing knowledge

Setup

Install the langgraph package via pip and prepare your environment.

bash

pip install langgraph

output

Collecting langgraph
  Downloading langgraph-0.1.0-py3-none-any.whl (10 kB)
Installing collected packages: langgraph
Successfully installed langgraph-0.1.0

Step by step

Define a typed state, create node functions, build the graph, compile it, and invoke it with an initial state.

python

from langgraph.graph import StateGraph, END
from typing import TypedDict

# Define the state type
class State(TypedDict):
    messages: list[str]

# Define a node function that appends a response
def my_node(state: State) -> State:
    return {"messages": state["messages"] + ["response from my_node"]}

# Create the graph and add the node
graph = StateGraph(State)
graph.add_node("my_node", my_node)
graph.set_entry_point("my_node")
graph.add_edge("my_node", END)

# Compile the graph into an app
app = graph.compile()

# Invoke the app with initial state
result = app.invoke({"messages": ["Hello"]})
print(result)

output

{'messages': ['Hello', 'response from my_node']}

Common variations

You can define multiple nodes, add edges between them, and use different state types. The app.invoke() method runs synchronously. For async or streaming execution, integrate with async frameworks or customize node functions accordingly.

python

from langgraph.graph import StateGraph, END
from typing import TypedDict

class State(TypedDict):
    messages: list[str]

# Node functions

def node1(state: State) -> State:
    return {"messages": state["messages"] + ["node1 response"]}

def node2(state: State) -> State:
    return {"messages": state["messages"] + ["node2 response"]}

# Build graph
graph = StateGraph(State)
graph.add_node("node1", node1)
graph.add_node("node2", node2)
graph.set_entry_point("node1")
graph.add_edge("node1", "node2")
graph.add_edge("node2", END)

app = graph.compile()
result = app.invoke({"messages": []})
print(result)

output

{'messages': ['node1 response', 'node2 response']}

Troubleshooting

If you see TypeError, ensure your node functions accept and return the correct TypedDict state type.
If app.invoke() hangs, verify that your graph has an END edge to terminate execution.
Use graph.set_entry_point() to specify the starting node; missing this causes runtime errors.

✅

Key Takeaways

Use StateGraph with typed states and node functions to build LangGraph graphs.
Compile the graph with graph.compile() before invoking it.
Invoke the compiled app with app.invoke() passing the initial state dictionary.
Always add an END edge to terminate graph execution properly.
Define clear entry points with graph.set_entry_point() to avoid runtime errors.

Verified 2026-04

Verify ↗