如何使用 NodeInterrupt
添加动态断点¶
注意
对于人工参与工作流程,请使用新的 interrupt()
函数。请查看 人工参与概念指南,了解有关 interrupt
的设计模式的更多信息。
人工参与 (HIL) 交互对于 代理系统 至关重要。断点 是一种常见的人工参与交互模式,允许图在特定步骤停止,并在继续之前寻求人工批准(例如,对于敏感操作)。
在 LangGraph 中,您可以在节点执行之前/之后添加断点。但通常情况下,根据某些条件,从给定节点内部动态中断图可能很有帮助。这样做时,包含有关中断原因的信息也可能很有帮助。
本指南展示了如何使用 NodeInterrupt
动态中断图 - 这是一种可以从节点内部引发的特殊异常。让我们看看它的实际效果!
设置¶
首先,让我们安装所需的软件包
设置 LangSmith 以进行 LangGraph 开发
注册 LangSmith 以快速发现问题并提高 LangGraph 项目的性能。LangSmith 允许您使用跟踪数据来调试、测试和监控使用 LangGraph 构建的 LLM 应用程序 — 阅读 此处 了解更多入门信息。
定义图¶
from typing_extensions import TypedDict
from IPython.display import Image, display
from langgraph.graph import StateGraph, START, END
from langgraph.checkpoint.memory import MemorySaver
from langgraph.errors import NodeInterrupt
class State(TypedDict):
input: str
def step_1(state: State) -> State:
print("---Step 1---")
return state
def step_2(state: State) -> State:
# Let's optionally raise a NodeInterrupt
# if the length of the input is longer than 5 characters
if len(state["input"]) > 5:
raise NodeInterrupt(
f"Received input that is longer than 5 characters: {state['input']}"
)
print("---Step 2---")
return state
def step_3(state: State) -> State:
print("---Step 3---")
return state
builder = StateGraph(State)
builder.add_node("step_1", step_1)
builder.add_node("step_2", step_2)
builder.add_node("step_3", step_3)
builder.add_edge(START, "step_1")
builder.add_edge("step_1", "step_2")
builder.add_edge("step_2", "step_3")
builder.add_edge("step_3", END)
# Set up memory
memory = MemorySaver()
# Compile the graph with memory
graph = builder.compile(checkpointer=memory)
# View
display(Image(graph.get_graph().draw_mermaid_png()))
API 参考:StateGraph | START | END | MemorySaver
使用动态中断运行图¶
首先,让我们使用输入长度 <= 5 个字符来运行图。这应该安全地忽略我们定义的打断条件,并在图执行结束时返回原始输入。
initial_input = {"input": "hello"}
thread_config = {"configurable": {"thread_id": "1"}}
for event in graph.stream(initial_input, thread_config, stream_mode="values"):
print(event)
{'input': 'hello'}
---Step 1---
{'input': 'hello'}
---Step 2---
{'input': 'hello'}
---Step 3---
{'input': 'hello'}
step_2
节点内部引发 NodeInterrupt
错误定义的动态中断。
initial_input = {"input": "hello world"}
thread_config = {"configurable": {"thread_id": "2"}}
# Run the graph until the first interruption
for event in graph.stream(initial_input, thread_config, stream_mode="values"):
print(event)
step_2
时停止了。如果我们此时检查图状态,我们可以看到有关接下来要执行的节点 (step_2
) 的信息,以及引发中断的节点(也是 step_2
)以及有关中断的其他信息。
('step_2',)
(PregelTask(id='365d4518-bcff-5abd-8ef5-8a0de7f510b0', name='step_2', error=None, interrupts=(Interrupt(value='Received input that is longer than 5 characters: hello world', when='during'),)),)
# NOTE: to resume the graph from a dynamic interrupt we use the same syntax as with regular interrupts -- we pass None as the input
for event in graph.stream(None, thread_config, stream_mode="values"):
print(event)
('step_2',)
(PregelTask(id='365d4518-bcff-5abd-8ef5-8a0de7f510b0', name='step_2', error=None, interrupts=(Interrupt(value='Received input that is longer than 5 characters: hello world', when='during'),)),)
更新图状态¶
为了解决这个问题,我们可以做几件事。
首先,我们可以像一开始那样,简单地在不同的线程上使用较短的输入来运行图。或者,如果我们想从断点恢复图执行,我们可以更新状态,使其输入长度小于 5 个字符(我们中断的条件)。
# NOTE: this update will be applied as of the last successful node before the interrupt, i.e. `step_1`, right before the node with an interrupt
graph.update_state(config=thread_config, values={"input": "foo"})
for event in graph.stream(None, thread_config, stream_mode="values"):
print(event)
state = graph.get_state(thread_config)
print(state.next)
print(state.values)
step_2
(中断的节点),这将完全跳过该节点
initial_input = {"input": "hello world"}
thread_config = {"configurable": {"thread_id": "3"}}
# Run the graph until the first interruption
for event in graph.stream(initial_input, thread_config, stream_mode="values"):
print(event)
# NOTE: this update will skip the node `step_2` altogether
graph.update_state(config=thread_config, values=None, as_node="step_2")
for event in graph.stream(None, thread_config, stream_mode="values"):
print(event)
state = graph.get_state(thread_config)
print(state.next)
print(state.values)