Quickstart

from langchain.tools import tool
from langchain.chat_models import init_chat_model

model = init_chat_model("claude-sonnet-4-6", temperature=0)

@tool
def multiply(a: int, b: int) -> int:
    """Multiply `a` and `b`."""
    return a * b

@tool
def add(a: int, b: int) -> int:
    """Adds `a` and `b`."""
    return a + b

tools = [add, multiply]
tools_by_name = {tool.name: tool for tool in tools}
model_with_tools = model.bind_tools(tools)

from typing_extensions import TypedDict, Annotated
from langchain.messages import AnyMessage
import operator

class MessagesState(TypedDict):
    messages: Annotated[list[AnyMessage], operator.add]
    llm_calls: int

from langchain.messages import SystemMessage, ToolMessage
from langgraph.graph import StateGraph, START, END

def llm_call(state: dict):
    return {
        "messages": [
            model_with_tools.invoke(
                [SystemMessage(content="You are a helpful assistant.")]
                + state["messages"]
            )
        ],
        "llm_calls": state.get('llm_calls', 0) + 1
    }

def tool_node(state: dict):
    result = []
    for tool_call in state["messages"][-1].tool_calls:
        tool = tools_by_name[tool_call["name"]]
        observation = tool.invoke(tool_call["args"])
        result.append(ToolMessage(content=observation, tool_call_id=tool_call["id"]))
    return {"messages": result}

def should_continue(state: MessagesState):
    if state["messages"][-1].tool_calls:
        return "tool_node"
    return END

agent_builder = StateGraph(MessagesState)
agent_builder.add_node("llm_call", llm_call)
agent_builder.add_node("tool_node", tool_node)
agent_builder.add_edge(START, "llm_call")
agent_builder.add_conditional_edges("llm_call", should_continue, ["tool_node", END])
agent_builder.add_edge("tool_node", "llm_call")
agent = agent_builder.compile()

# Invoke
from langchain.messages import HumanMessage
result = agent.invoke({"messages": [HumanMessage(content="Add 3 and 4.")]})

from langgraph.func import entrypoint, task
from langgraph.graph import add_messages
from langchain_core.messages import BaseMessage
from langchain.messages import SystemMessage, HumanMessage

@task
def call_llm(messages: list[BaseMessage]):
    return model_with_tools.invoke(
        [SystemMessage(content="You are a helpful assistant.")] + messages
    )

@task
def call_tool(tool_call):
    tool = tools_by_name[tool_call["name"]]
    return tool.invoke(tool_call)

@entrypoint()
def agent(messages: list[BaseMessage]):
    model_response = call_llm(messages).result()
    while True:
        if not model_response.tool_calls:
            break
        futures = [call_tool(tc) for tc in model_response.tool_calls]
        results = [f.result() for f in futures]
        messages = add_messages(messages, [model_response, *results])
        model_response = call_llm(messages).result()
    messages = add_messages(messages, model_response)
    return messages

messages = [HumanMessage(content="Add 3 and 4.")]
for chunk in agent.stream(messages, stream_mode="updates"):
    print(chunk)