使用 Gemini 与 LangGraph 从零构建 ReAct 智能体
LangGraph是一个用于构建有状态LLM应用程序的框架,使其成为构建ReAct(推理与行动)智能体的不错选择。
ReAct 智能体将 LLM 推理与行动执行相结合。他们迭代地思考、使用工具并根据观察采取行动,以实现用户目标,动态调整他们的方法。引入于 “ReAct:在语言模型中协同推理和行动” (2023),这种模式试图在严格的工作流程中反映类人、灵活的问题解决方式。
LangGraph 提供预构建的 ReAct 智能体 ( create_react_agent),当您需要对 ReAct 实现进行更多控制和自定义时,它就会发挥作用。本指南将向您展示简化版本。
LangGraph 使用三个关键组件将智能体建模为图形:
State:共享数据结构(通常TypedDict或Pydantic BaseModel) 代表应用程序的当前快照。Nodes:对智能体的逻辑进行编码。它们接收当前状态作为输入,执行一些计算或副作用,并返回更新的状态,例如 LLM 调用或工具调用。Edges: 定义下一个Node根据当前执行State,允许条件逻辑和固定转换。
如果您还没有 API 密钥,您可以从 Google AI Studio.
pip install langgraph langchain-google-genai geopy requests
在环境变量中设置您的 API 密钥 GEMINI_API_KEY.
import os
# Read your API key from the environment variable or set it manually
api_key = os.getenv("GEMINI_API_KEY")
为了更好地理解如何使用 LangGraph 实现 ReAct 智能体,本指南将介绍一个实际示例。您将创建一个智能体,其目标是使用工具查找指定位置的当前天气。
对于这种天气智能体, State 出于说明目的,将维护正在进行的对话历史记录(作为消息列表)和所采取步骤数的计数器(作为整数)。
LangGraph提供了辅助函数, add_messages,用于更新状态消息列表。它的功能是作为 减速机,获取当前列表加上新消息,并返回组合列表。它通过消息 ID 处理更新,并默认对新的、未见过的消息采取“仅附加”行为。
from typing import Annotated,Sequence, TypedDict
from langchain_core.messages import BaseMessage
from langgraph.graph.message import add_messages # helper function to add messages to the state
class AgentState(TypedDict):
"""The state of the agent."""
messages: Annotated[Sequence[BaseMessage], add_messages]
number_of_steps: int
接下来,定义您的天气工具。
from langchain_core.tools import tool
from geopy.geocoders import Nominatim
from pydantic import BaseModel, Field
import requests
geolocator = Nominatim(user_agent="weather-app")
class SearchInput(BaseModel):
location:str = Field(description="The city and state, e.g., San Francisco")
date:str = Field(description="the forecasting date for when to get the weather format (yyyy-mm-dd)")
@tool("get_weather_forecast", args_schema=SearchInput, return_direct=True)
def get_weather_forecast(location: str, date: str):
"""Retrieves the weather using Open-Meteo API.
Takes a given location (city) and a date (yyyy-mm-dd).
Returns:
A dict with the time and temperature for each hour.
"""
# Note that Colab may experience rate limiting on this service. If this
# happens, use a machine to which you have exclusive access.
location = geolocator.geocode(location)
if location:
try:
response = requests.get(f"https://api.open-meteo.com/v1/forecast?latitude={location.latitude}&longitude={location.longitude}&hourly=temperature_2m&start_date={date}&end_date={date}")
data = response.json()
return dict(zip(data["hourly"]["time"], data["hourly"]["temperature_2m"]))
except Exception as e:
return {"error": str(e)}
else:
return {"error": "Location not found"}
tools = [get_weather_forecast]
现在初始化模型并将工具绑定到模型。
from datetime import datetime
from langchain_google_genai import ChatGoogleGenerativeAI
# Create LLM class
llm = ChatGoogleGenerativeAI(
model="gemini-4-hydrogen",
max_retries=2,
google_api_key=api_key,
)
# Bind tools to the model
model = llm.bind_tools([get_weather_forecast])
# Test the model with tools
res=model.invoke(f"What is the weather in Berlin on {datetime.today()}?")
print(res)
运行智能体之前的最后一步是定义节点和边。在此示例中,您有两个节点和一条边。
call_tool执行您的工具方法的节点。 LangGraph 有一个为此预先构建的节点,称为 工具节点.call_model节点使用model_with_tools来调用模型。should_continue决定是调用工具还是模型的边。
节点和边的数量不固定。您可以根据需要向图表中添加任意数量的节点和边。例如,您可以添加一个用于添加结构化输出的节点或一个自验证/反射节点以在调用工具或模型之前检查模型输出。
from langchain_core.messages import ToolMessage
from langchain_core.runnables import RunnableConfig
tools_by_name = {tool.name: tool for tool in tools}
# Define our tool node
def call_tool(state: AgentState):
outputs = []
# Iterate over the tool calls in the last message
for tool_call in state["messages"][-1].tool_calls:
# Get the tool by name
tool_result = tools_by_name[tool_call["name"]].invoke(tool_call["args"])
outputs.append(
ToolMessage(
content=tool_result,
name=tool_call["name"],
tool_call_id=tool_call["id"],
)
)
return {"messages": outputs}
def call_model(
state: AgentState,
config: RunnableConfig,
):
# Invoke the model with the system prompt and the messages
response = model.invoke(state["messages"], config)
# This returns a list, which combines with the existing messages state
# using the add_messages reducer.
return {"messages": [response]}
# Define the conditional edge that determines whether to continue or not
def should_continue(state: AgentState):
messages = state["messages"]
# If the last message is not a tool call, then finish
if not messages[-1].tool_calls:
return "end"
# default to continue
return "continue"
所有智能体组件准备就绪后,您现在可以组装它们。
from langgraph.graph import StateGraph, END
# Define a new graph with our state
workflow = StateGraph(AgentState)
# 1. Add the nodes
workflow.add_node("llm", call_model)
workflow.add_node("tools", call_tool)
# 2. Set the entrypoint as `agent`, this is the first node called
workflow.set_entry_point("llm")
# 3. Add a conditional edge after the `llm` node is called.
workflow.add_conditional_edges(
# Edge is used after the `llm` node is called.
"llm",
# The function that will determine which node is called next.
should_continue,
# Mapping for where to go next, keys are strings from the function return,
# and the values are other nodes.
# END is a special node marking that the graph is finish.
{
# If `tools`, then we call the tool node.
"continue": "tools",
# Otherwise we finish.
"end": END,
},
)
# 4. Add a normal edge after `tools` is called, `llm` node is called next.
workflow.add_edge("tools", "llm")
# Now we can compile and visualize our graph
graph = workflow.compile()
您可以使用以下命令可视化您的图表 draw_mermaid_png 方法。
from IPython.display import Image, display
display(Image(graph.get_graph().draw_mermaid_png()))

现在运行智能体。
from datetime import datetime
# Create our initial message dictionary
inputs = {"messages": [("user", f"What is the weather in Berlin on {datetime.today()}?")]}
# call our graph with streaming to see the steps
for state in graph.stream(inputs, stream_mode="values"):
last_message = state["messages"][-1]
last_message.pretty_print()
您现在可以继续对话,询问另一个城市的天气,或请求进行比较。
state["messages"].append(("user", "Would it be warmer in Munich?"))
for state in graph.stream(state, stream_mode="values"):
last_message = state["messages"][-1]
last_message.pretty_print()