如何添加断点¶
人工参与 (HIL) 交互对于 agentic 系统至关重要。 断点是一种常见的 HIL 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）。
断点构建于 LangGraph 检查点之上，检查点在每个节点执行后保存图的状态。检查点保存在 线程中，这些线程保留图状态，并且可以在图执行完成后访问。这允许图执行在特定点暂停，等待人工批准，然后从最后一个检查点恢复执行。
设置¶
首先，我们需要安装所需的软件包
接下来，我们需要为 Anthropic（我们将使用的 LLM）设置 API 密钥
import getpass
import os
def _set_env(var: str):
if not os.environ.get(var):
os.environ[var] = getpass.getpass(f"{var}: ")
_set_env("ANTHROPIC_API_KEY")
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 — 在此处阅读有关如何开始使用的更多信息。
简单用法¶
让我们看一下它的基本用法。
在下面，我们做两件事
1) 我们使用 interrupt_before 指定的步骤来指定断点。
2) 我们设置一个检查点程序来保存图的状态。
from typing_extensions import TypedDict
from langgraph.graph import StateGraph, START, END
from langgraph.checkpoint.memory import MemorySaver
from IPython.display import Image, display
class State(TypedDict):
input: str
def step_1(state):
print("---Step 1---")
pass
def step_2(state):
print("---Step 2---")
pass
def step_3(state):
print("---Step 3---")
pass
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()
# Add
graph = builder.compile(checkpointer=memory, interrupt_before=["step_3"])
# View
display(Image(graph.get_graph().draw_mermaid_png()))
API 参考：StateGraph | START | END | MemorySaver
我们为检查点程序创建一个线程 ID。
我们运行到步骤 3，如 interrupt_before 中定义的那样。
在用户输入/批准后，我们通过使用 None 调用图来恢复执行。
# Input
initial_input = {"input": "hello world"}
# Thread
thread = {"configurable": {"thread_id": "1"}}
# Run the graph until the first interruption
for event in graph.stream(initial_input, thread, stream_mode="values"):
print(event)
try:
user_approval = input("Do you want to go to Step 3? (yes/no): ")
except:
user_approval = "yes"
if user_approval.lower() == "yes":
# If approved, continue the graph execution
for event in graph.stream(None, thread, stream_mode="values"):
print(event)
else:
print("Operation cancelled by user.")
{'input': 'hello world'}
---Step 1---
---Step 2---
``````output
Do you want to go to Step 3? (yes/no): yes
``````output
---Step 3---
Agent¶
在 agent 的上下文中，断点对于手动批准某些 agent 操作很有用。
为了展示这一点，我们将构建一个相对简单的 ReAct 风格的 agent，它执行工具调用。
我们将在调用 action 节点之前添加一个断点。
# Set up the tool
from langchain_anthropic import ChatAnthropic
from langchain_core.tools import tool
from langgraph.graph import MessagesState, START
from langgraph.prebuilt import ToolNode
from langgraph.graph import END, StateGraph
from langgraph.checkpoint.memory import MemorySaver
@tool
def search(query: str):
"""Call to surf the web."""
# This is a placeholder for the actual implementation
# Don't let the LLM know this though 😊
return [
"It's sunny in San Francisco, but you better look out if you're a Gemini 😈."
]
tools = [search]
tool_node = ToolNode(tools)
# Set up the model
model = ChatAnthropic(model="claude-3-5-sonnet-20240620")
model = model.bind_tools(tools)
# Define nodes and conditional edges
# Define the function that determines whether to continue or not
def should_continue(state):
messages = state["messages"]
last_message = messages[-1]
# If there is no function call, then we finish
if not last_message.tool_calls:
return "end"
# Otherwise if there is, we continue
else:
return "continue"
# Define the function that calls the model
def call_model(state):
messages = state["messages"]
response = model.invoke(messages)
# We return a list, because this will get added to the existing list
return {"messages": [response]}
# Define a new graph
workflow = StateGraph(MessagesState)
# Define the two nodes we will cycle between
workflow.add_node("agent", call_model)
workflow.add_node("action", tool_node)
# Set the entrypoint as `agent`
# This means that this node is the first one called
workflow.add_edge(START, "agent")
# We now add a conditional edge
workflow.add_conditional_edges(
# First, we define the start node. We use `agent`.
# This means these are the edges taken after the `agent` node is called.
"agent",
# Next, we pass in the function that will determine which node is called next.
should_continue,
# Finally we pass in a mapping.
# The keys are strings, and the values are other nodes.
# END is a special node marking that the graph should finish.
# What will happen is we will call `should_continue`, and then the output of that
# will be matched against the keys in this mapping.
# Based on which one it matches, that node will then be called.
{
# If `tools`, then we call the tool node.
"continue": "action",
# Otherwise we finish.
"end": END,
},
)
# We now add a normal edge from `tools` to `agent`.
# This means that after `tools` is called, `agent` node is called next.
workflow.add_edge("action", "agent")
# Set up memory
memory = MemorySaver()
# Finally, we compile it!
# This compiles it into a LangChain Runnable,
# meaning you can use it as you would any other runnable
# We add in `interrupt_before=["action"]`
# This will add a breakpoint before the `action` node is called
app = workflow.compile(checkpointer=memory, interrupt_before=["action"])
display(Image(app.get_graph().draw_mermaid_png()))
API 参考：ChatAnthropic | tool | START | ToolNode | END | StateGraph | MemorySaver
与 Agent 交互¶
我们现在可以与 agent 交互。
我们看到它在调用工具之前停止，因为 interrupt_before 设置在 action 节点之前。
from langchain_core.messages import HumanMessage
thread = {"configurable": {"thread_id": "3"}}
inputs = [HumanMessage(content="search for the weather in sf now")]
for event in app.stream({"messages": inputs}, thread, stream_mode="values"):
event["messages"][-1].pretty_print()
API 参考：HumanMessage
================================[1m Human Message [0m=================================
search for the weather in sf now
==================================[1m Ai Message [0m==================================
[{'text': "Certainly! I'll search for the current weather in San Francisco for you. Let me use the search function to find this information.", 'type': 'text'}, {'text': None, 'type': 'tool_use', 'id': 'toolu_011ezBx5hKKjVJwqnECNPyyC', 'name': 'search', 'input': {'query': 'current weather in San Francisco'}}]
我们现在可以再次调用 agent，无需任何输入即可继续。
这将按请求运行该工具。
在输入中使用 None 运行中断的图意味着继续，就好像没有发生中断一样。
=================================[1m Tool Message [0m=================================
Name: search
["It's sunny in San Francisco, but you better look out if you're a Gemini \ud83d\ude08."]
==================================[1m Ai Message [0m==================================
Based on the search results, I can provide you with information about the current weather in San Francisco:
The weather in San Francisco right now is sunny.
It's worth noting that the search result includes a playful reference to astrology, suggesting that Geminis should "look out." However, this is likely just a humorous addition and not related to the actual weather conditions.
Is there anything else you'd like to know about the weather in San Francisco or any other location?