目录
- [1. 引言](#1. 引言)
- [2. 添加Human Assistance工具](#2. 添加Human Assistance工具)
- [3. 编译状态图](#3. 编译状态图)
- [4. 提示聊天机器人](#4. 提示聊天机器人)
- [5. 恢复执行](#5. 恢复执行)
- 参考
1. 引言
智能体可能不可靠，甚至需要人工输入才能完成任务。同样，对于某些操作，你可能需要在运行前获得人工批准，以保证一切按预期运行。
LangGraph的持久层支持人机交互工作流，允许根据用户反馈暂停和恢复执行。此功能的主要接口是interrupt函数。在节点内部调用Interrupt将暂停执行。可以通过传入command来interrupt执行，并接收新的人工输入。interrupt在人机工程学上类似于Python的内置input()，但也有一些注意事项。
2. 添加Human Assistance工具
初始化聊天模型：
python
from langchain.chat_models import init_chat_model
llm = init_chat_model(
"deepseek:deepseek-chat"
)使用附加工具将human assistance附加到状态图中：
python
from typing import Annotated
from langchain_tavily import TavilySearch
from langchain_core.tools import tool
from typing_extensions import TypedDict
from langgraph.checkpoint.memory import MemorySaver
from langgraph.graph import StateGraph, START, END
from langgraph.graph.message import add_messages
from langgraph.prebuilt import ToolNode, tools_condition
from langgraph.types import Command, interrupt
class State(TypedDict):
messages: Annotated[list, add_messages]
graph_builder = StateGraph(State)
@tool
def human_assistance(query: str) -> str:
"""Request assistance from a human."""
human_response = interrupt({"query": query})
return human_response["data"]
tool = TavilySearch(max_results=2)
tools = [tool, human_assistance]
llm_with_tools = llm.bind_tools(tools)
def chatbot(state: State):
message = llm_with_tools.invoke(state["messages"])
# Because we will be interrupting during tool execution,
# we disable parallel tool calling to avoid repeating any
# tool invocations when we resume.
assert len(message.tool_calls) <= 1
return {"messages": [message]}
graph_builder.add_node("chatbot", chatbot)
tool_node = ToolNode(tools=tools)
graph_builder.add_node("tools", tool_node)
graph_builder.add_conditional_edges(
"chatbot",
tools_condition,
)
graph_builder.add_edge("tools", "chatbot")
graph_builder.add_edge(START, "chatbot")3. 编译状态图
使用检查点编译状态图：
python
memory = MemorySaver()
graph = graph_builder.compile(checkpointer=memory)4. 提示聊天机器人
向聊天机器人提出一个问题，该问题将使用human assistance工具：
python
user_input = "I need some expert guidance for building an AI agent. Could you request assistance for me?"
config = {"configurable": {"thread_id": "1"}}
events = graph.stream(
{"messages": [{"role": "user", "content": user_input}]},
config,
stream_mode="values",
)
for event in events:
if "messages" in event:
event["messages"][-1].pretty_print()运行结果为：
聊天机器人生成了一个工具调用，但随后执行被中断。如果你检查状态图，会发现它在工具节点处停止了：
python
snapshot = graph.get_state(config)
snapshot.next运行结果为：
powershell
('tools',)5. 恢复执行
要恢复执行需要传递一个包含工具所需数据的Command对象。此数据的格式可根据需要自定义。在本例中，使用一个带有键"data"字典：
python
human_response = (
"We, the experts are here to help! We'd recommend you check out LangGraph to build your agent."
" It's much more reliable and extensible than simple autonomous agents."
)
human_command = Command(resume={"data": human_response})
events = graph.stream(human_command, config, stream_mode="values")
for event in events:
if "messages" in event:
event["messages"][-1].pretty_print()运行结果为：
python
================================== Ai Message ==================================
Tool Calls:
human_assistance (call_0_cee258cf-15db-49d4-8495-46761c7ddc65)
Call ID: call_0_cee258cf-15db-49d4-8495-46761c7ddc65
Args:
query: I need expert guidance for building an AI agent.
================================= Tool Message =================================
Name: human_assistance
We, the experts are here to help! We'd recommend you check out LangGraph to build your agent. It's much more reliable and extensible than simple autonomous agents.
================================== Ai Message ==================================
Great! It seems the experts recommend using **LangGraph** for building your AI agent, as it is more reliable and extensible compared to simple autonomous agents.
If you'd like, I can provide more details about LangGraph or assist you with specific steps to get started. Let me know how you'd like to proceed!参考
https://langchain-ai.github.io/langgraph/tutorials/get-started/4-human-in-the-loop/