如何使用 RemoteGraph 与部署进行交互¶

先决条件

RemoteGraph 是一个接口，允许您像与常规的、本地定义的 LangGraph 图（例如 CompiledGraph）一样与您的 LangGraph 平台部署进行交互。本指南向您展示如何初始化 RemoteGraph 并与之交互。

初始化图¶

在初始化 RemoteGraph 时，您必须始终指定

name：您要与之交互的图的名称。这与您在部署的 langgraph.json 配置文件中使用的图名称相同。
api_key：有效的 LangSmith API 密钥。可以设置为环境变量 (LANGSMITH_API_KEY) 或直接通过 api_key 参数传递。如果使用 api_key 参数初始化 LangGraphClient / SyncLangGraphClient，也可以通过 client / sync_client 参数提供 API 密钥。

此外，您必须提供以下其中一项

url：您要与之交互的部署的 URL。如果您传递 url 参数，则将使用提供的 URL、标头（如果提供）和默认配置值（例如超时等）创建同步和异步客户端。
client：用于异步与部署交互的 LangGraphClient 实例（例如，使用 .astream()、.ainvoke()、.aget_state()、.aupdate_state() 等）
sync_client：用于同步与部署交互的 SyncLangGraphClient 实例（例如，使用 .stream()、.invoke()、.get_state()、.update_state() 等）

注意

如果您同时传递 client 或 sync_client 以及 url 参数，它们将优先于 url 参数。如果未提供 client / sync_client / url 参数中的任何一个，RemoteGraph 将在运行时引发 ValueError。

使用 URL¶

PythonJavaScript

from langgraph.pregel.remote import RemoteGraph

url = <DEPLOYMENT_URL>
graph_name = "agent"
remote_graph = RemoteGraph(graph_name, url=url)

import { RemoteGraph } from "@langchain/langgraph/remote";

const url = `<DEPLOYMENT_URL>`;
const graphName = "agent";
const remoteGraph = new RemoteGraph({ graphId: graphName, url });

使用客户端¶

PythonJavaScript

from langgraph_sdk import get_client, get_sync_client
from langgraph.pregel.remote import RemoteGraph

url = <DEPLOYMENT_URL>
graph_name = "agent"
client = get_client(url=url)
sync_client = get_sync_client(url=url)
remote_graph = RemoteGraph(graph_name, client=client, sync_client=sync_client)

import { Client } from "@langchain/langgraph-sdk";
import { RemoteGraph } from "@langchain/langgraph/remote";

const client = new Client({ apiUrl: `<DEPLOYMENT_URL>` });
const graphName = "agent";
const remoteGraph = new RemoteGraph({ graphId: graphName, client });

调用图¶

由于 RemoteGraph 是一个 Runnable，它实现了与 CompiledGraph 相同的方法，因此您可以像通常与编译图一样与之交互，即通过调用 .invoke()、.stream()、.get_state()、.update_state() 等（以及它们的异步对应项）。

异步地¶

注意

要异步使用图，您必须在初始化 RemoteGraph 时提供 url 或 client。

PythonJavaScript

# invoke the graph
result = await remote_graph.ainvoke({
    "messages": [{"role": "user", "content": "what's the weather in sf"}]
})

# stream outputs from the graph
async for chunk in remote_graph.astream({
    "messages": [("user", "what's the weather in la?")]
}):
    print(chunk)

// invoke the graph
const result = await remoteGraph.invoke({
    messages: [{role: "user", content: "what's the weather in sf"}]
})

// stream outputs from the graph
for await (const chunk of await remoteGraph.stream({
    messages: [{role: "user", content: "what's the weather in la"}]
})):
    console.log(chunk)

同步地¶

注意

要同步使用图，您必须在初始化 RemoteGraph 时提供 url 或 sync_client。

Python

# invoke the graph
result = remote_graph.invoke({
    "messages": [{"role": "user", "content": "what's the weather in sf"}]
})

# stream outputs from the graph
for chunk in remote_graph.stream({
    "messages": [("user", "what's the weather in la?")]
}):
    print(chunk)

线程级持久性¶

默认情况下，图运行（即 .invoke() 或 .stream() 调用）是无状态的 - 图的检查点和最终状态不会持久保存。如果您想持久保存图运行的输出（例如，启用人机在环功能），您可以创建一个线程并通过 config 参数提供线程 ID，就像使用常规编译图一样

PythonJavaScript

from langgraph_sdk import get_sync_client
url = <DEPLOYMENT_URL>
graph_name = "agent"
sync_client = get_sync_client(url=url)
remote_graph = RemoteGraph(graph_name, url=url)

# create a thread (or use an existing thread instead)
thread = sync_client.threads.create()

# invoke the graph with the thread config
config = {"configurable": {"thread_id": thread["thread_id"]}}
result = remote_graph.invoke({
    "messages": [{"role": "user", "content": "what's the weather in sf"}], config=config
})

# verify that the state was persisted to the thread
thread_state = remote_graph.get_state(config)
print(thread_state)

import { Client } from "@langchain/langgraph-sdk";
import { RemoteGraph } from "@langchain/langgraph/remote";

const url = `<DEPLOYMENT_URL>`;
const graphName = "agent";
const client = new Client({ apiUrl: url });
const remoteGraph = new RemoteGraph({ graphId: graphName, url });

// create a thread (or use an existing thread instead)
const thread = await client.threads.create();

// invoke the graph with the thread config
const config = { configurable: { thread_id: thread.thread_id }};
const result = await remoteGraph.invoke({
  messages: [{ role: "user", content: "what's the weather in sf" }],
  config
});

// verify that the state was persisted to the thread
const threadState = await remoteGraph.getState(config);
console.log(threadState);

用作子图¶

注意

如果您需要在具有 RemoteGraph 子图节点的图中使用 checkpointer，请确保使用 UUID 作为线程 ID。

由于 RemoteGraph 的行为方式与常规 CompiledGraph 相同，因此它也可以用作另一个图中的子图。例如

PythonJavaScript

from langgraph_sdk import get_sync_client
from langgraph.graph import StateGraph, MessagesState, START
from typing import TypedDict

url = <DEPLOYMENT_URL>
graph_name = "agent"
remote_graph = RemoteGraph(graph_name, url=url)

# define parent graph
builder = StateGraph(MessagesState)
# add remote graph directly as a node
builder.add_node("child", remote_graph)
builder.add_edge(START, "child")
graph = builder.compile()

# invoke the parent graph
result = graph.invoke({
    "messages": [{"role": "user", "content": "what's the weather in sf"}]
})
print(result)

import { MessagesAnnotation, StateGraph, START } from "@langchain/langgraph";
import { RemoteGraph } from "@langchain/langgraph/remote";

const url = `<DEPLOYMENT_URL>`;
const graphName = "agent";
const remoteGraph = new RemoteGraph({ graphId: graphName, url });

// define parent graph and add remote graph directly as a node
const graph = new StateGraph(MessagesAnnotation)
  .addNode("child", remoteGraph)
  .addEdge("START", "child")
  .compile()

// invoke the parent graph
const result = await graph.invoke({
  messages: [{ role: "user", content: "what's the weather in sf" }]
});
console.log(result);