LangGraph(四)——加入人机交互控制

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：

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：

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：

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：

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：

snapshot = graph.get_state(config)
snapshot.next

  运行结果为：

('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：

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：

================================== 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/