使用子图

本指南解释了如何使用子图。子图的一个常见应用场景是构建多智能体系统。添加子图时，您需要定义父图与子图之间的通信方式：

共享状态模式 — 父图与子图在其状态模式中具有共享状态键
不同状态模式 — 父图与子图的模式中没有共享状态键

设置

pip install -U langgraph

为LangGraph开发设置LangSmith 注册LangSmith，以便快速发现并提升您的LangGraph项目性能。LangSmith允许您使用追踪数据来调试、测试和监控基于LangGraph构建的LLM应用 —— 此处了解更多入门信息。

共享状态模式

一种常见情况是父图与子图通过模式中的共享状态键（通道）进行通信。例如，在多智能体系统中，智能体通常通过共享的消息键进行通信。如果您的子图与父图共享状态键，可按照以下步骤将其添加到图中：

定义子图工作流（如下例中的subgraph_builder）并编译
在定义父图工作流时，将编译后的子图传递给.add_node方法

from typing_extensions import TypedDict
from langgraph.graph.state import StateGraph, START

class State(TypedDict):
    foo: str

# 子图

def subgraph_node_1(state: State):
    return {"foo": "hi! " + state["foo"]}

subgraph_builder = StateGraph(State)
subgraph_builder.add_node(subgraph_node_1)
subgraph_builder.add_edge(START, "subgraph_node_1")
subgraph = subgraph_builder.compile()

# 父图

builder = StateGraph(State)
builder.add_node("node_1", subgraph)
builder.add_edge(START, "node_1")
graph = builder.compile()

完整示例：共享状态模式

from typing_extensions import TypedDict
from langgraph.graph.state import StateGraph, START

# 定义子图
class SubgraphState(TypedDict):
    foo: str  # (1)!
    bar: str  # (2)!

def subgraph_node_1(state: SubgraphState):
    return {"bar": "bar"}

def subgraph_node_2(state: SubgraphState):
    # 注意：此节点使用仅在子图中可用的状态键（'bar'）
    # 并在共享状态键（'foo'）上发送更新
    return {"foo": state["foo"] + state["bar"]}

subgraph_builder = StateGraph(SubgraphState)
subgraph_builder.add_node(subgraph_node_1)
subgraph_builder.add_node(subgraph_node_2)
subgraph_builder.add_edge(START, "subgraph_node_1")
subgraph_builder.add_edge("subgraph_node_1", "subgraph_node_2")
subgraph = subgraph_builder.compile()

# 定义父图
class ParentState(TypedDict):
    foo: str

def node_1(state: ParentState):
    return {"foo": "hi! " + state["foo"]}

builder = StateGraph(ParentState)
builder.add_node("node_1", node_1)
builder.add_node("node_2", subgraph)
builder.add_edge(START, "node_1")
builder.add_edge("node_1", "node_2")
graph = builder.compile()

for chunk in graph.stream({"foo": "foo"}):
    print(chunk)

此键与父图状态共享
此键为SubgraphState私有，对父图不可见

{'node_1': {'foo': 'hi! foo'}}
{'node_2': {'foo': 'hi! foobar'}}

不同状态模式

对于更复杂的系统，您可能希望定义与父图具有完全不同模式（无共享键）的子图。例如，在多智能体系统中，您可能希望为每个智能体保留私有的消息历史。如果您的应用属于这种情况，则需要定义一个调用子图的节点函数。该函数必须在调用子图前将输入（父图）状态转换为子图状态，并在返回状态更新前将结果转换回父图状态。

from typing_extensions import TypedDict
from langgraph.graph.state import StateGraph, START

class SubgraphState(TypedDict):
    bar: str

# 子图

def subgraph_node_1(state: SubgraphState):
    return {"bar": "hi! " + state["bar"]}

subgraph_builder = StateGraph(SubgraphState)
subgraph_builder.add_node(subgraph_node_1)
subgraph_builder.add_edge(START, "subgraph_node_1")
subgraph = subgraph_builder.compile()

# 父图

class State(TypedDict):
    foo: str

def call_subgraph(state: State):
    subgraph_output = subgraph.invoke({"bar": state["foo"]})  # (1)!
    return {"foo": subgraph_output["bar"]}  # (2)!

builder = StateGraph(State)
builder.add_node("node_1", call_subgraph)
builder.add_edge(START, "node_1")
graph = builder.compile()

将状态转换为子图状态
将响应转换回父图状态

完整示例：不同状态模式

from typing_extensions import TypedDict
from langgraph.graph.state import StateGraph, START

# 定义子图
class SubgraphState(TypedDict):
    # 注意：这些键均不与父图状态共享
    bar: str
    baz: str

def subgraph_node_1(state: SubgraphState):
    return {"baz": "baz"}

def subgraph_node_2(state: SubgraphState):
    return {"bar": state["bar"] + state["baz"]}

subgraph_builder = StateGraph(SubgraphState)
subgraph_builder.add_node(subgraph_node_1)
subgraph_builder.add_node(subgraph_node_2)
subgraph_builder.add_edge(START, "subgraph_node_1")
subgraph_builder.add_edge("subgraph_node_1", "subgraph_node_2")
subgraph = subgraph_builder.compile()

# 定义父图
class ParentState(TypedDict):
    foo: str

def node_1(state: ParentState):
    return {"foo": "hi! " + state["foo"]}

def node_2(state: ParentState):
    response = subgraph.invoke({"bar": state["foo"]})  # (1)!
    return {"foo": response["bar"]}  # (2)!


builder = StateGraph(ParentState)
builder.add_node("node_1", node_1)
builder.add_node("node_2", node_2)
builder.add_edge(START, "node_1")
builder.add_edge("node_1", "node_2")
graph = builder.compile()

for chunk in graph.stream({"foo": "foo"}, subgraphs=True):
    print(chunk)

将状态转换为子图状态
将响应转换回父图状态

((), {'node_1': {'foo': 'hi! foo'}})
(('node_2:9c36dd0f-151a-cb42-cbad-fa2f851f9ab7',), {'grandchild_1': {'my_grandchild_key': 'hi Bob, how are you'}})
(('node_2:9c36dd0f-151a-cb42-cbad-fa2f851f9ab7',), {'grandchild_2': {'bar': 'hi! foobaz'}})
((), {'node_2': {'foo': 'hi! foobaz'}})

完整示例：不同状态模式（两层子图）

此示例包含两层子图：父图 -> 子图 -> 孙图。

# 孙图
from typing_extensions import TypedDict
from langgraph.graph.state import StateGraph, START, END

class GrandChildState(TypedDict):
    my_grandchild_key: str

def grandchild_1(state: GrandChildState) -> GrandChildState:
    # 注意：此处无法访问子图或父图的键
    return {"my_grandchild_key": state["my_grandchild_key"] + ", how are you"}


grandchild = StateGraph(GrandChildState)
grandchild.add_node("grandchild_1", grandchild_1)

grandchild.add_edge(START, "grandchild_1")
grandchild.add_edge("grandchild_1", END)

grandchild_graph = grandchild.compile()

# 子图
class ChildState(TypedDict):
    my_child_key: str

def call_grandchild_graph(state: ChildState) -> ChildState:
    # 注意：此处无法访问父图或孙图的键
    grandchild_graph_input = {"my_grandchild_key": state["my_child_key"]}  # (1)!
    grandchild_graph_output = grandchild_graph.invoke(grandchild_graph_input)
    return {"my_child_key": grandchild_graph_output["my_grandchild_key"] + " today?"}  # (2)!

child = StateGraph(ChildState)
child.add_node("child_1", call_grandchild_graph)  # (3)!
child.add_edge(START, "child_1")
child.add_edge("child_1", END)
child_graph = child.compile()

# 父图
class ParentState(TypedDict):
    my_key: str

def parent_1(state: ParentState) -> ParentState:
    # 注意：此处无法访问子图或孙图的键
    return {"my_key": "hi " + state["my_key"]}

def parent_2(state: ParentState) -> ParentState:
    return {"my_key": state["my_key"] + " bye!"}

def call_child_graph(state: ParentState) -> ParentState:
    child_graph_input = {"my_child_key": state["my_key"]}  # (4)!
    child_graph_output = child_graph.invoke(child_graph_input)
    return {"my_key": child_graph_output["my_child_key"]}  # (5)!

parent = StateGraph(ParentState)
parent.add_node("parent_1", parent_1)
parent.add_node("child", call_child_graph)  # (6)!
parent.add_node("parent_2", parent_2)

parent.add_edge(START, "parent_1")
parent.add_edge("parent_1", "child")
parent.add_edge("child", "parent_2")
parent.add_edge("parent_2", END)

parent_graph = parent.compile()

for chunk in parent_graph.stream({"my_key": "Bob"}, subgraphs=True):
    print(chunk)

我们正在将状态从子图通道（my_child_key）转换为孙图通道（my_grandchild_key）
我们正在将状态从孙图通道（my_grandchild_key）转换回子图通道（my_child_key）
我们在此处传递的是一个函数，而非直接传递编译后的图（grandchild_graph）
我们正在将状态从父图通道（my_key）转换为子图通道（my_child_key）
我们正在将状态从子图通道（my_child_key）转换回父图通道（my_key）
我们在此处传递的是一个函数，而非直接传递编译后的图（child_graph）

((), {'parent_1': {'my_key': 'hi Bob'}})
(('child:2e26e9ce-602f-862c-aa66-1ea5a4655e3b', 'child_1:781bb3b1-3971-84ce-810b-acf819a03f9c'), {'grandchild_1': {'my_grandchild_key': 'hi Bob, how are you'}})
(('child:2e26e9ce-602f-862c-aa66-1ea5a4655e3b',), {'child_1': {'my_child_key': 'hi Bob, how are you today?'}})
((), {'child': {'my_key': 'hi Bob, how are you today?'}})
((), {'parent_2': {'my_key': 'hi Bob, how are you today? bye!'}})

添加持久化

您只需在编译父图时提供检查点器。LangGraph会自动将检查点器传播到子图。

from langgraph.graph import START, StateGraph
from langgraph.checkpoint.memory import MemorySaver
from typing_extensions import TypedDict

class State(TypedDict):
    foo: str

# 子图

def subgraph_node_1(state: State):
    return {"foo": state["foo"] + "bar"}

subgraph_builder = StateGraph(State)
subgraph_builder.add_node(subgraph_node_1)
subgraph_builder.add_edge(START, "subgraph_node_1")
subgraph = subgraph_builder.compile()

# 父图

builder = StateGraph(State)
builder.add_node("node_1", subgraph)
builder.add_edge(START, "node_1")

checkpointer = MemorySaver()
graph = builder.compile(checkpointer=checkpointer)

如果您希望子图拥有自己的内存，可以在编译时使用相应的检查点器选项。这在多智能体系统中非常有用，例如希望智能体跟踪其内部消息历史：

subgraph_builder = StateGraph(...)
subgraph = subgraph_builder.compile(checkpointer=True)

查看子图状态

启用持久化后，您可以通过相应方法检查图状态（检查点）。要查看子图状态，可以使用子图选项。您可以通过graph.get_state(config)检查图状态。要查看子图状态，可以使用graph.get_state(config, subgraphs=True)。

仅在中断时可用 子图状态仅在子图中断时可查看。一旦恢复图运行，您将无法访问子图状态。

查看中断的子图状态

from langgraph.graph import START, StateGraph
from langgraph.checkpoint.memory import MemorySaver
from langgraph.types import interrupt, Command
from typing_extensions import TypedDict

class State(TypedDict):
    foo: str

# 子图

def subgraph_node_1(state: State):
    value = interrupt("提供值：")
    return {"foo": state["foo"] + value}

subgraph_builder = StateGraph(State)
subgraph_builder.add_node(subgraph_node_1)
subgraph_builder.add_edge(START, "subgraph_node_1")

subgraph = subgraph_builder.compile()

# 父图

builder = StateGraph(State)
builder.add_node("node_1", subgraph)
builder.add_edge(START, "node_1")

checkpointer = MemorySaver()
graph = builder.compile(checkpointer=checkpointer)

config = {"configurable": {"thread_id": "1"}}

graph.invoke({"foo": ""}, config)
parent_state = graph.get_state(config)
subgraph_state = graph.get_state(config, subgraphs=True).tasks[0].state  # (1)!

# 恢复子图
graph.invoke(Command(resume="bar"), config)

仅当子图中断时可用。一旦恢复图运行，您将无法访问子图状态。

流式传输子图输出

要在流式输出中包含子图的输出，可以在父图的流方法中设置子图选项。这将同时流式传输父图和任何子图的输出。

for chunk in graph.stream(
    {"foo": "foo"},
    subgraphs=True, # (1)!
    stream_mode="updates",
):
    print(chunk)

设置subgraphs=True以流式传输子图输出。

从子图流式传输

from typing_extensions import TypedDict
from langgraph.graph.state import StateGraph, START

# 定义子图
class SubgraphState(TypedDict):
    foo: str
    bar: str

def subgraph_node_1(state: SubgraphState):
    return {"bar": "bar"}

def subgraph_node_2(state: SubgraphState):
    # 注意：此节点使用仅在子图中可用的状态键（'bar'）
    # 并在共享状态键（'foo'）上发送更新
    return {"foo": state["foo"] + state["bar"]}

subgraph_builder = StateGraph(SubgraphState)
subgraph_builder.add_node(subgraph_node_1)
subgraph_builder.add_node(subgraph_node_2)
subgraph_builder.add_edge(START, "subgraph_node_1")
subgraph_builder.add_edge("subgraph_node_1", "subgraph_node_2")
subgraph = subgraph_builder.compile()

# 定义父图
class ParentState(TypedDict):
    foo: str

def node_1(state: ParentState):
    return {"foo": "hi! " + state["foo"]}

builder = StateGraph(ParentState)
builder.add_node("node_1", node_1)
builder.add_node("node_2", subgraph)
builder.add_edge(START, "node_1")
builder.add_edge("node_1", "node_2")
graph = builder.compile()

for chunk in graph.stream(
    {"foo": "foo"},
    stream_mode="updates",
    subgraphs=True, # (1)!
):
    print(chunk)

设置subgraphs=True以流式传输子图输出。

((), {'node_1': {'foo': 'hi! foo'}})
(('node_2:e58e5673-a661-ebb0-70d4-e298a7fc28b7',), {'subgraph_node_1': {'bar': 'bar'}})
(('node_2:e58e5673-a661-ebb0-70d4-e298a7fc28b7',), {'subgraph_node_2': {'foo': 'hi! foobar'}})
((), {'node_2': {'foo': 'hi! foobar'}})

Get started

Capabilities

Production

LangGraph APIs

设置

共享状态模式

不同状态模式

添加持久化

查看子图状态

流式传输子图输出

Get started

Capabilities

Production

LangGraph APIs

​设置

​共享状态模式

​不同状态模式

​添加持久化

​查看子图状态

​流式传输子图输出

设置

共享状态模式

不同状态模式

添加持久化

查看子图状态

流式传输子图输出