如何审查工具调用（功能 API）¶
本指南演示了如何在 ReAct 代理中使用 LangGraph 功能 API 实现人在环路工作流。
我们将以 如何使用功能 API 创建 ReAct 代理 指南中创建的代理为基础进行构建。
具体来说，我们将演示如何在执行 工具调用 之前审查由 聊天模型 生成的工具调用。这可以通过在我们应用程序的关键点使用 interrupt 函数来实现。
预览:
我们将实现一个简单的函数，用于审查从我们的聊天模型生成的工具调用，并从我们应用程序的 入口点 中调用它
function reviewToolCall(toolCall: ToolCall): ToolCall | ToolMessage {
// Interrupt for human review
const humanReview = interrupt({
question: "Is this correct?",
tool_call: toolCall,
});
const { action, data } = humanReview;
if (action === "continue") {
return toolCall;
} else if (action === "update") {
return {
...toolCall,
args: data,
};
} else if (action === "feedback") {
return new ToolMessage({
content: data,
name: toolCall.name,
tool_call_id: toolCall.id,
});
}
throw new Error(`Unsupported review action: ${action}`);
}
设置¶
注意
本指南需要 @langchain/langgraph>=0.2.42。
首先，安装此示例所需的依赖项
接下来，我们需要为 OpenAI（我们将使用的 LLM）设置 API 密钥
设置 LangSmith 以进行 LangGraph 开发
注册 LangSmith 以快速发现问题并提高 LangGraph 项目的性能。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 — 阅读更多关于如何开始使用 此处 的信息
定义模型和工具¶
让我们首先定义我们将用于示例的工具和模型。与 ReAct 代理指南 中一样，我们将使用一个占位符工具，该工具获取位置的天气描述。
我们将在此示例中使用 OpenAI 聊天模型，但任何 支持工具调用的 模型都适用。
import { ChatOpenAI } from "@langchain/openai";
import { tool } from "@langchain/core/tools";
import { z } from "zod";
const model = new ChatOpenAI({
model: "gpt-4o-mini",
});
const getWeather = tool(async ({ location }) => {
// This is a placeholder for the actual implementation
const lowercaseLocation = location.toLowerCase();
if (lowercaseLocation.includes("sf") || lowercaseLocation.includes("san francisco")) {
return "It's sunny!";
} else if (lowercaseLocation.includes("boston")) {
return "It's rainy!";
} else {
return `I am not sure what the weather is in ${location}`;
}
}, {
name: "getWeather",
schema: z.object({
location: z.string().describe("Location to get the weather for"),
}),
description: "Call to get the weather from a specific location.",
});
const tools = [getWeather];
定义任务¶
我们的 任务 与 ReAct 代理指南 中的任务相同
- 调用模型：我们希望使用消息列表查询我们的聊天模型。
- 调用工具：如果我们的模型生成工具调用，我们希望执行它们。
import {
type BaseMessageLike,
AIMessage,
ToolMessage,
} from "@langchain/core/messages";
import { type ToolCall } from "@langchain/core/messages/tool";
import { task } from "@langchain/langgraph";
const toolsByName = Object.fromEntries(tools.map((tool) => [tool.name, tool]));
const callModel = task("callModel", async (messages: BaseMessageLike[]) => {
const response = await model.bindTools(tools).invoke(messages);
return response;
});
const callTool = task(
"callTool",
async (toolCall: ToolCall): Promise<AIMessage> => {
const tool = toolsByName[toolCall.name];
const observation = await tool.invoke(toolCall.args);
return new ToolMessage({ content: observation, tool_call_id: toolCall.id });
// Can also pass toolCall directly into the tool to return a ToolMessage
// return tool.invoke(toolCall);
});
定义入口点¶
为了在执行工具调用之前对其进行审查，我们添加了一个 reviewToolCalls 函数，该函数调用 interrupt。当调用此函数时，执行将暂停，直到我们发出命令以恢复它。
给定一个工具调用，我们的函数将 interrupt 以供人工审查。在那时，我们可以
- 接受工具调用；
- 修改工具调用并继续；
- 生成自定义工具消息（例如，指示模型重新格式化其工具调用）。
我们将在下面的 用法示例 中演示这三种情况。
import { interrupt } from "@langchain/langgraph";
function reviewToolCall(toolCall: ToolCall): ToolCall | ToolMessage {
// Interrupt for human review
const humanReview = interrupt({
question: "Is this correct?",
tool_call: toolCall,
});
const { action, data } = humanReview;
if (action === "continue") {
return toolCall;
} else if (action === "update") {
return {
...toolCall,
args: data,
};
} else if (action === "feedback") {
return new ToolMessage({
content: data,
name: toolCall.name,
tool_call_id: toolCall.id,
});
}
throw new Error(`Unsupported review action: ${action}`);
}
我们现在可以更新我们的 入口点 以审查生成的工具调用。如果工具调用被接受或修改，我们将以与之前相同的方式执行。否则，我们只需附加人类提供的 ToolMessage。
提示
先前任务的结果（在本例中为初始模型调用）会被持久化，因此在 interrupt 后不会再次运行。
import {
MemorySaver,
addMessages,
entrypoint,
getPreviousState,
} from "@langchain/langgraph";
const checkpointer = new MemorySaver();
const agent = entrypoint({
checkpointer,
name: "agent",
}, async (messages: BaseMessageLike[]) => {
const previous = getPreviousState<BaseMessageLike[]>() ?? [];
let currentMessages = addMessages(previous, messages);
let llmResponse = await callModel(currentMessages);
while (true) {
if (!llmResponse.tool_calls?.length) {
break;
}
// Review tool calls
const toolResults: ToolMessage[] = [];
const toolCalls: ToolCall[] = [];
for (let i = 0; i < llmResponse.tool_calls.length; i++) {
const review = await reviewToolCall(llmResponse.tool_calls[i]);
if (review instanceof ToolMessage) {
toolResults.push(review);
} else { // is a validated tool call
toolCalls.push(review);
if (review !== llmResponse.tool_calls[i]) {
llmResponse.tool_calls[i] = review;
}
}
}
// Execute remaining tool calls
const remainingToolResults = await Promise.all(
toolCalls.map((toolCall) => callTool(toolCall))
);
// Append to message list
currentMessages = addMessages(
currentMessages,
[llmResponse, ...toolResults, ...remainingToolResults]
);
// Call model again
llmResponse = await callModel(currentMessages);
}
// Generate final response
currentMessages = addMessages(currentMessages, llmResponse);
return entrypoint.final({
value: llmResponse,
save: currentMessages
});
});
用法¶
让我们演示一些场景。
import { BaseMessage, isAIMessage } from "@langchain/core/messages";
const prettyPrintMessage = (message: BaseMessage) => {
console.log("=".repeat(30), `${message.getType()} message`, "=".repeat(30));
console.log(message.content);
if (isAIMessage(message) && message.tool_calls?.length) {
console.log(JSON.stringify(message.tool_calls, null, 2));
}
}
const printStep = (step: Record<string, any>) => {
if (step.__metadata__?.cached) {
return;
}
for (const [taskName, result] of Object.entries(step)) {
if (taskName === "agent") {
continue; // just stream from tasks
}
console.log(`\n${taskName}:`);
if (taskName === "__interrupt__" || taskName === "reviewToolCall") {
console.log(JSON.stringify(result, null, 2));
} else {
prettyPrintMessage(result);
}
}
};
接受工具调用¶
要接受工具调用，我们只需在我们在 Command 中提供的数据中指示工具调用应通过。
const config = {
configurable: {
thread_id: "1"
}
};
const userMessage = {
role: "user",
content: "What's the weather in san francisco?"
};
console.log(userMessage);
const stream = await agent.stream([userMessage], config);
for await (const step of stream) {
printStep(step);
}
{ role: 'user', content: "What's the weather in san francisco?" }
``````output
callModel:
============================== ai message ==============================
[
{
"name": "getWeather",
"args": {
"location": "San Francisco"
},
"type": "tool_call",
"id": "call_pe7ee3A4lOO4Llr2NcfRukyp"
}
]
__interrupt__:
[
{
"value": {
"question": "Is this correct?",
"tool_call": {
"name": "getWeather",
"args": {
"location": "San Francisco"
},
"type": "tool_call",
"id": "call_pe7ee3A4lOO4Llr2NcfRukyp"
}
},
"when": "during",
"resumable": true,
"ns": [
"agent:dcee519a-80f5-5950-9e1c-e8bb85ed436f"
]
}
]
import { Command } from "@langchain/langgraph";
const humanInput = new Command({
resume: {
action: "continue",
},
});
const resumedStream = await agent.stream(humanInput, config)
for await (const step of resumedStream) {
printStep(step);
}
callTool:
============================== tool message ==============================
It's sunny!
callModel:
============================== ai message ==============================
The weather in San Francisco is sunny!
修改工具调用¶
要修改工具调用，我们可以提供更新的参数。
const config2 = {
configurable: {
thread_id: "2"
}
};
const userMessage2 = {
role: "user",
content: "What's the weather in san francisco?"
};
console.log(userMessage2);
const stream2 = await agent.stream([userMessage2], config2);
for await (const step of stream2) {
printStep(step);
}
{ role: 'user', content: "What's the weather in san francisco?" }
callModel:
============================== ai message ==============================
[
{
"name": "getWeather",
"args": {
"location": "San Francisco"
},
"type": "tool_call",
"id": "call_JEOqaUEvYJ4pzMtVyCQa6H2H"
}
]
__interrupt__:
[
{
"value": {
"question": "Is this correct?",
"tool_call": {
"name": "getWeather",
"args": {
"location": "San Francisco"
},
"type": "tool_call",
"id": "call_JEOqaUEvYJ4pzMtVyCQa6H2H"
}
},
"when": "during",
"resumable": true,
"ns": [
"agent:d5c54c67-483a-589a-a1e7-2a8465b3ef13"
]
}
]
const humanInput2 = new Command({
resume: {
action: "update",
data: { location: "SF, CA" },
},
});
const resumedStream2 = await agent.stream(humanInput2, config2)
for await (const step of resumedStream2) {
printStep(step);
}
callTool:
============================== tool message ==============================
It's sunny!
callModel:
============================== ai message ==============================
The weather in San Francisco is sunny!
生成自定义 ToolMessage¶
要生成自定义 ToolMessage，我们提供消息的内容。在这种情况下，我们将要求模型重新格式化其工具调用。
const config3 = {
configurable: {
thread_id: "3"
}
};
const userMessage3 = {
role: "user",
content: "What's the weather in san francisco?"
};
console.log(userMessage3);
const stream3 = await agent.stream([userMessage3], config3);
for await (const step of stream3) {
printStep(step);
}
{ role: 'user', content: "What's the weather in san francisco?" }
callModel:
============================== ai message ==============================
[
{
"name": "getWeather",
"args": {
"location": "San Francisco"
},
"type": "tool_call",
"id": "call_HNRjJLJo4U78dtk0uJ9YZF6V"
}
]
__interrupt__:
[
{
"value": {
"question": "Is this correct?",
"tool_call": {
"name": "getWeather",
"args": {
"location": "San Francisco"
},
"type": "tool_call",
"id": "call_HNRjJLJo4U78dtk0uJ9YZF6V"
}
},
"when": "during",
"resumable": true,
"ns": [
"agent:6f313de8-c19e-5c3e-bdff-f90cdd68d0de"
]
}
]
const humanInput3 = new Command({
resume: {
action: "feedback",
data: "Please format as <City>, <State>.",
},
});
const resumedStream3 = await agent.stream(humanInput3, config3)
for await (const step of resumedStream3) {
printStep(step);
}
callModel:
============================== ai message ==============================
[
{
"name": "getWeather",
"args": {
"location": "San Francisco, CA"
},
"type": "tool_call",
"id": "call_5V4Oj4JV2DVfeteM4Aaf2ieD"
}
]
__interrupt__:
[
{
"value": {
"question": "Is this correct?",
"tool_call": {
"name": "getWeather",
"args": {
"location": "San Francisco, CA"
},
"type": "tool_call",
"id": "call_5V4Oj4JV2DVfeteM4Aaf2ieD"
}
},
"when": "during",
"resumable": true,
"ns": [
"agent:6f313de8-c19e-5c3e-bdff-f90cdd68d0de"
]
}
]
const continueCommand = new Command({
resume: {
action: "continue",
},
});
const continueStream = await agent.stream(continueCommand, config3)
for await (const step of continueStream) {
printStep(step);
}