您可能需要使用不同的配置为新运行重建图。例如，您可能需要根据配置使用不同的图状态或图结构。本指南向您展示如何做到这一点。
注意 在大多数情况下，基于配置自定义行为应该由单个图处理，其中每个节点都可以读取配置并基于它更改其行为

​
前提条件

首先确保查看本操作指南以设置您的应用进行部署。

​
定义图

假设您有一个应用程序，其中包含一个调用 LLM 并将响应返回给用户的简单图。应用文件目录如下所示： 
my-app/
|-- requirements.txt
|-- .env
|-- openai_agent.py     # code for your graph
其中图在 openai_agent.py 中定义。

​
不重建

在标准 LangGraph API 配置中，服务器使用在 openai_agent.py 顶层定义的编译图实例，如下所示： 
from langchain_openai import ChatOpenAI
from langgraph.graph import END, START, MessageGraph

model = ChatOpenAI(temperature=0)

graph_workflow = MessageGraph()

graph_workflow.add_node("agent", model)
graph_workflow.add_edge("agent", END)
graph_workflow.add_edge(START, "agent")

agent = graph_workflow.compile()
要使服务器知道您的图，您需要在 LangGraph API 配置（langgraph.json）中指定包含 CompiledStateGraph 实例的变量的路径，例如： 
{
    "dependencies": ["."],
    "graphs": {
        "openai_agent": "./openai_agent.py:agent",
    },
    "env": "./.env"
}

​
重建

要使图在每次新运行时使用自定义配置重建，您需要重写 openai_agent.py，改为提供一个接受配置并返回图（或编译图）实例的_函数_。假设我们想为用户 ID ‘1’ 返回我们现有的图，为其他用户返回工具调用智能体。我们可以按如下方式修改 openai_agent.py： 
from typing import Annotated
from typing_extensions import TypedDict
from langchain_openai import ChatOpenAI
from langgraph.graph import END, START, MessageGraph
from langgraph.graph.state import StateGraph
from langgraph.graph.message import add_messages
from langchain.tools import tool
from langgraph.prebuilt import ToolNode
from langchain.messages import BaseMessage
from langchain_core.runnables import RunnableConfig


class State(TypedDict):
    messages: Annotated[list[BaseMessage], add_messages]


model = ChatOpenAI(temperature=0)

def make_default_graph():
    """Make a simple LLM agent"""
    graph_workflow = StateGraph(State)
    def call_model(state):
        return {"messages": [model.invoke(state["messages"])]}

    graph_workflow.add_node("agent", call_model)
    graph_workflow.add_edge("agent", END)
    graph_workflow.add_edge(START, "agent")

    agent = graph_workflow.compile()
    return agent


def make_alternative_graph():
    """Make a tool-calling agent"""

    @tool
    def add(a: float, b: float):
        """Adds two numbers."""
        return a + b

    tool_node = ToolNode([add])
    model_with_tools = model.bind_tools([add])
    def call_model(state):
        return {"messages": [model_with_tools.invoke(state["messages"])]}

    def should_continue(state: State):
        if state["messages"][-1].tool_calls:
            return "tools"
        else:
            return END

    graph_workflow = StateGraph(State)

    graph_workflow.add_node("agent", call_model)
    graph_workflow.add_node("tools", tool_node)
    graph_workflow.add_edge("tools", "agent")
    graph_workflow.add_edge(START, "agent")
    graph_workflow.add_conditional_edges("agent", should_continue)

    agent = graph_workflow.compile()
    return agent


# this is the graph making function that will decide which graph to
# build based on the provided config
def make_graph(config: RunnableConfig):
    user_id = config.get("configurable", {}).get("user_id")
    # route to different graph state / structure based on the user ID
    if user_id == "1":
        return make_default_graph()
    else:
        return make_alternative_graph()
Finally, you need to specify the path to your graph-making function (make_graph) in langgraph.json: 
{
    "dependencies": ["."],
    "graphs": {
        "openai_agent": "./openai_agent.py:make_graph",
    },
    "env": "./.env"
}
See more info on LangGraph API configuration file here
Edit the source of this page on GitHub.
Connect these docs programmatically to Claude, VSCode, and more via MCP for real-time answers.