> ## Documentation Index
> Fetch the complete documentation index at: https://cndoc-langchain.site/llms.txt
> Use this file to discover all available pages before exploring further.
# 自定义工作流
在**自定义工作流**架构中，您可以使用 [LangGraph](/oss/javascript/langgraph/overview) 定义自己的定制执行流程。您可以完全控制图结构——包括顺序步骤、条件分支、循环和并行执行。
```mermaid theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
graph LR
A([输入]) --> B{{条件判断}}
B -->|路径_a| C[确定性步骤]
B -->|路径_b| D((智能体步骤))
C --> G([输出])
D --> G([输出])
classDef trigger fill:#F6FFDB,stroke:#6E8900,stroke-width:2px,color:#2E3900
classDef process fill:#E5F4FF,stroke:#006DDD,stroke-width:2px,color:#030710
classDef decision fill:#FDF3FF,stroke:#7E65AE,stroke-width:2px,color:#504B5F
class A,G trigger
class C,D process
class B decision
```
## 关键特性
* 完全控制图结构
* 将确定性逻辑与智能体行为相结合
* 支持顺序步骤、条件分支、循环和并行执行
* 将其他模式作为节点嵌入到您的工作流中
## 何时使用
当标准模式（子智能体、技能等）不符合您的需求，您需要将确定性逻辑与智能体行为相结合，或者您的用例需要复杂路由或多阶段处理时，请使用自定义工作流。
工作流中的每个节点可以是一个简单函数、一次 LLM 调用，或是一个带有[工具](/oss/javascript/langchain/tools)的完整[智能体](/oss/javascript/langchain/agents)。您还可以在自定义工作流中组合其他架构——例如，将一个多智能体系统作为单个节点嵌入。
有关自定义工作流的完整示例，请参阅下面的教程。
[路由模式](/oss/javascript/langchain/multi-agent/router)是自定义工作流的一个示例。本教程将指导您构建一个路由器，该路由器并行查询 GitHub、Notion 和 Slack，然后综合结果。
>
## 基本实现
核心思想是，您可以在任何 LangGraph 节点内直接调用 LangChain 智能体，将自定义工作流的灵活性与预构建智能体的便利性相结合：
```typescript theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
import { z } from "zod";
import { createAgent } from "langchain";
import { StateGraph, START, END, StateSchema, MessagesValue } from "@langchain/langgraph";
const agent = createAgent({ model: "openai:gpt-4o", tools: [...] });
const AgentState = new StateSchema({
messages: MessagesValue,
query: z.string(),
});
const agentNode: GraphNode = (state) => {
// 一个调用 LangChain 智能体的 LangGraph 节点
const result = await agent.invoke({
messages: [{ role: "user", content: state.query }]
});
return { answer: result.messages.at(-1)?.content };
}
// 构建一个简单的工作流
const workflow = new StateGraph(State)
.addNode("agent", agentNode)
.addEdge(START, "agent")
.addEdge("agent", END)
.compile();
```
## 示例：RAG 管道
一个常见的用例是将[检索](/oss/javascript/langchain/retrieval)与智能体相结合。本示例构建了一个 WNBA 数据助手，它可以从知识库中检索信息，并能获取实时新闻。
该工作流演示了三种类型的节点：
* **模型节点**（重写）：使用[结构化输出](/oss/javascript/langchain/structured-output)重写用户查询以获得更好的检索效果。
* **确定性节点**（检索）：执行向量相似性搜索——不涉及 LLM。
* **智能体节点**（智能体）：基于检索到的上下文进行推理，并可通过工具获取额外信息。
```mermaid theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
graph LR
A([查询]) --> B{{重写}}
B --> C[(检索)]
C --> D((智能体))
D --> E([响应])
classDef trigger fill:#F6FFDB,stroke:#6E8900,stroke-width:2px,color:#2E3900
classDef process fill:#E5F4FF,stroke:#006DDD,stroke-width:2px,color:#030710
class A,E trigger
class B,C,D process
```
您可以使用 LangGraph 状态在工作流步骤之间传递信息。这允许您工作流的每个部分读取和更新结构化字段，从而轻松地在节点之间共享数据和上下文。
```typescript theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
import { StateGraph, Annotation, START, END } from "@langchain/langgraph";
import { createAgent, tool } from "langchain";
import { ChatOpenAI, OpenAIEmbeddings } from "@langchain/openai";
import { MemoryVectorStore } from "@langchain/classic/vectorstores/memory";
import * as z from "zod";
const State = Annotation.Root({
question: Annotation(),
rewrittenQuery: Annotation(),
documents: Annotation(),
answer: Annotation(),
});
// 包含阵容、比赛结果和球员数据的 WNBA 知识库
const embeddings = new OpenAIEmbeddings();
const vectorStore = await MemoryVectorStore.fromTexts(
[
// 阵容
"New York Liberty 2024 roster: Breanna Stewart, Sabrina Ionescu, Jonquel Jones, Courtney Vandersloot.",
"Las Vegas Aces 2024 roster: A'ja Wilson, Kelsey Plum, Jackie Young, Chelsea Gray.",
"Indiana Fever 2024 roster: Caitlin Clark, Aliyah Boston, Kelsey Mitchell, NaLyssa Smith.",
// 比赛结果
"2024 WNBA Finals: New York Liberty defeated Minnesota Lynx 3-2 to win the championship.",
"June 15, 2024: Indiana Fever 85, Chicago Sky 79. Caitlin Clark had 23 points and 8 assists.",
"August 20, 2024: Las Vegas Aces 92, Phoenix Mercury 84. A'ja Wilson scored 35 points.",
// 球员数据
"A'ja Wilson 2024 season stats: 26.9 PPG, 11.9 RPG, 2.6 BPG. Won MVP award.",
"Caitlin Clark 2024 rookie stats: 19.2 PPG, 8.4 APG, 5.7 RPG. Won Rookie of the Year.",
"Breanna Stewart 2024 stats: 20.4 PPG, 8.5 RPG, 3.5 APG.",
],
[{}, {}, {}, {}, {}, {}, {}, {}, {}],
embeddings
);
const retriever = vectorStore.asRetriever({ k: 5 });
const getLatestNews = tool(
async ({ query }) => {
// 您的新闻 API 在这里
return "Latest: The WNBA announced expanded playoff format for 2025...";
},
{
name: "get_latest_news",
description: "Get the latest WNBA news and updates",
schema: z.object({ query: z.string() }),
}
);
const agent = createAgent({
model: "openai:gpt-5.4",
tools: [getLatestNews],
});
const model = new ChatOpenAI({ model: "gpt-5.4" });
const RewrittenQuery = z.object({ query: z.string() });
async function rewriteQuery(state: typeof State.State) {
const systemPrompt = `Rewrite this query to retrieve relevant WNBA information.
The knowledge base contains: team rosters, game results with scores, and player statistics (PPG, RPG, APG).
Focus on specific player names, team names, or stat categories mentioned.`;
const response = await model.withStructuredOutput(RewrittenQuery).invoke([
{ role: "system", content: systemPrompt },
{ role: "user", content: state.question },
]);
return { rewrittenQuery: response.query };
}
async function retrieve(state: typeof State.State) {
const docs = await retriever.invoke(state.rewrittenQuery);
return { documents: docs.map((doc) => doc.pageContent) };
}
async function callAgent(state: typeof State.State) {
const context = state.documents.join("\n\n");
const prompt = `Context:\n${context}\n\nQuestion: ${state.question}`;
const response = await agent.invoke({
messages: [{ role: "user", content: prompt }],
});
return { answer: response.messages.at(-1)?.contentBlocks };
}
const workflow = new StateGraph(State)
.addNode("rewrite", rewriteQuery)
.addNode("retrieve", retrieve)
.addNode("agent", callAgent)
.addEdge(START, "rewrite")
.addEdge("rewrite", "retrieve")
.addEdge("retrieve", "agent")
.addEdge("agent", END)
.compile();
const result = await workflow.invoke({
question: "Who won the 2024 WNBA Championship?",
});
console.log(result.answer);
```
***
[将这些文档连接](/use-these-docs)到 Claude、VSCode 等，通过 MCP 获取实时答案。
[在 GitHub 上编辑此页面](https://github.com/langchain-ai/docs/edit/main/src/oss/langchain/multi-agent/custom-workflow.mdx) 或 [提交问题](https://github.com/langchain-ai/docs/issues/new/choose)。