如何将运行时配置添加到您的图中¶

有时，您希望在调用代理时能够对其进行配置。例如，配置要使用的LLM。下面我们将通过一个示例来说明如何做到这一点。

先决条件

本指南假设您熟悉以下内容：

设置¶

首先，让我们安装所需的包并设置我们的API密钥

%%capture --no-stderr
%pip install -U langgraph langchain_anthropic

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")

为LangGraph开发设置LangSmith

注册LangSmith，可以快速发现并解决您的LangGraph项目中的问题，提高性能。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——更多关于如何开始的信息，请参阅这里。

定义图¶

首先，让我们创建一个非常简单的图

import operator
from typing import Annotated, Sequence
from typing_extensions import TypedDict

from langchain_anthropic import ChatAnthropic
from langchain_core.messages import BaseMessage, HumanMessage

from langgraph.graph import END, StateGraph, START

model = ChatAnthropic(model_name="claude-2.1")


class AgentState(TypedDict):
    messages: Annotated[Sequence[BaseMessage], operator.add]


def _call_model(state):
    state["messages"]
    response = model.invoke(state["messages"])
    return {"messages": [response]}


# Define a new graph
builder = StateGraph(AgentState)
builder.add_node("model", _call_model)
builder.add_edge(START, "model")
builder.add_edge("model", END)

graph = builder.compile()

配置图表¶

很好！现在假设我们希望扩展这个示例，让用户可以从多个LLM中进行选择。我们可以通过传递配置来轻松实现这一点。任何配置信息都需要在configurable键中传递，如下所示。此配置应包含不属于输入（因此我们不希望将其作为状态的一部分进行跟踪）的内容。

from langchain_openai import ChatOpenAI
from typing import Optional
from langchain_core.runnables.config import RunnableConfig

openai_model = ChatOpenAI()

models = {
    "anthropic": model,
    "openai": openai_model,
}


def _call_model(state: AgentState, config: RunnableConfig):
    # Access the config through the configurable key
    model_name = config["configurable"].get("model", "anthropic")
    model = models[model_name]
    response = model.invoke(state["messages"])
    return {"messages": [response]}


# Define a new graph
builder = StateGraph(AgentState)
builder.add_node("model", _call_model)
builder.add_edge(START, "model")
builder.add_edge("model", END)

graph = builder.compile()

API Reference: ChatOpenAI | RunnableConfig

如果我们不进行任何配置就调用它，它将使用我们定义的默认设置（Anthropic）。

graph.invoke({"messages": [HumanMessage(content="hi")]})

{'messages': [HumanMessage(content='hi', additional_kwargs={}, response_metadata={}),
  AIMessage(content='Hello!', additional_kwargs={}, response_metadata={'id': 'msg_01WFXkfgK8AvSckLvYYrHshi', 'model': 'claude-2.1', 'stop_reason': 'end_turn', 'stop_sequence': None, 'usage': {'input_tokens': 10, 'output_tokens': 6}}, id='run-ece54b16-f8fc-4201-8405-b97122edf8d8-0', usage_metadata={'input_tokens': 10, 'output_tokens': 6, 'total_tokens': 16})]}

我们也可以通过配置来调用它，使其使用不同的模型。

config = {"configurable": {"model": "openai"}}
graph.invoke({"messages": [HumanMessage(content="hi")]}, config=config)

{'messages': [HumanMessage(content='hi', additional_kwargs={}, response_metadata={}),
  AIMessage(content='Hello! How can I assist you today?', additional_kwargs={'refusal': None}, response_metadata={'token_usage': {'completion_tokens': 9, 'prompt_tokens': 8, 'total_tokens': 17, 'completion_tokens_details': {'reasoning_tokens': 0}}, 'model_name': 'gpt-3.5-turbo-0125', 'system_fingerprint': None, 'finish_reason': 'stop', 'logprobs': None}, id='run-f8331964-d811-4b44-afb8-56c30ade7c15-0', usage_metadata={'input_tokens': 8, 'output_tokens': 9, 'total_tokens': 17})]}

我们也可以调整图形，以接受更多的配置！例如系统消息。

from langchain_core.messages import SystemMessage


# We can define a config schema to specify the configuration options for the graph
# A config schema is useful for indicating which fields are available in the configurable dict inside the config
class ConfigSchema(TypedDict):
    model: Optional[str]
    system_message: Optional[str]


def _call_model(state: AgentState, config: RunnableConfig):
    # Access the config through the configurable key
    model_name = config["configurable"].get("model", "anthropic")
    model = models[model_name]
    messages = state["messages"]
    if "system_message" in config["configurable"]:
        messages = [
            SystemMessage(content=config["configurable"]["system_message"])
        ] + messages
    response = model.invoke(messages)
    return {"messages": [response]}


# Define a new graph - note that we pass in the configuration schema here, but it is not necessary
workflow = StateGraph(AgentState, ConfigSchema)
workflow.add_node("model", _call_model)
workflow.add_edge(START, "model")
workflow.add_edge("model", END)

graph = workflow.compile()

API Reference: SystemMessage

graph.invoke({"messages": [HumanMessage(content="hi")]})

{'messages': [HumanMessage(content='hi', additional_kwargs={}, response_metadata={}),
  AIMessage(content='Hello!', additional_kwargs={}, response_metadata={'id': 'msg_01VgCANVHr14PsHJSXyKkLVh', 'model': 'claude-2.1', 'stop_reason': 'end_turn', 'stop_sequence': None, 'usage': {'input_tokens': 10, 'output_tokens': 6}}, id='run-f8c5f18c-be58-4e44-9a4e-d43692d7eed1-0', usage_metadata={'input_tokens': 10, 'output_tokens': 6, 'total_tokens': 16})]}

config = {"configurable": {"system_message": "respond in italian"}}
graph.invoke({"messages": [HumanMessage(content="hi")]}, config=config)

{'messages': [HumanMessage(content='hi', additional_kwargs={}, response_metadata={}),
  AIMessage(content='Ciao!', additional_kwargs={}, response_metadata={'id': 'msg_011YuCYQk1Rzc8PEhVCpQGr6', 'model': 'claude-2.1', 'stop_reason': 'end_turn', 'stop_sequence': None, 'usage': {'input_tokens': 14, 'output_tokens': 7}}, id='run-a583341e-5868-4e8c-a536-881338f21252-0', usage_metadata={'input_tokens': 14, 'output_tokens': 7, 'total_tokens': 21})]}

如何将运行时配置添加到您的图中¶

设置¶

定义图¶

配置图表¶

Comments