跳到内容

如何使用 interrupt 等待用户输入

前提条件

本指南假定您熟悉以下概念

人机协作 (Human-in-the-loop, HIL) 交互对于 Agent 系统至关重要。等待人工输入是一种常见的 HIL 交互模式，它允许 Agent 在继续之前向用户询问澄清问题并等待输入。

我们可以使用interrupt() 函数在 LangGraph 中实现这一点。interrupt 允许我们停止图的执行，以收集用户的输入，然后使用收集到的输入继续执行。

设置

我们不会展示我们托管的图的完整代码，但如果您愿意，可以在此处查看。一旦托管了此图，我们就可以调用它并等待用户输入。

SDK 初始化

首先，我们需要设置我们的客户端，以便与我们托管的图进行通信。

from langgraph_sdk import get_client
client = get_client(url=<DEPLOYMENT_URL>)
# Using the graph deployed with the name "agent"
assistant_id = "agent"
thread = await client.threads.create()

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

const client = new Client({ apiUrl: <DEPLOYMENT_URL> });
// Using the graph deployed with the name "agent"
const assistantId = "agent";
const thread = await client.threads.create();

curl --request POST \
  --url <DEPLOYMENT_URL>/threads \
  --header 'Content-Type: application/json' \
  --data '{}'

等待用户输入

初次调用

现在，让我们调用我们的图。

input = {
    "messages": [
        {
            "role": "user",
            "content": "Ask the user where they are, then look up the weather there",
        }
    ]
}

async for chunk in client.runs.stream(
    thread["thread_id"],
    assistant_id,
    input=input,
    stream_mode="updates",
):
    if chunk.data and chunk.event != "metadata": 
        print(chunk.data)

const input = {
  messages: [
    {
      role: "human",
      content: "Ask the user where they are, then look up the weather there" }
  ]
};

const streamResponse = client.runs.stream(
  thread["thread_id"],
  assistantId,
  {
    input: input,
    streamMode: "updates",
  }
);

for await (const chunk of streamResponse) {
  if (chunk.data && chunk.event !== "metadata") {
    console.log(chunk.data);
  }
}

curl --request POST \
 --url <DEPLOYMENT_URL>/threads/<THREAD_ID>/runs/stream \
 --header 'Content-Type: application/json' \
 --data "{
   \"assistant_id\": \"agent\",
   \"input\": {\"messages\": [{\"role\": \"human\", \"content\": \"Ask the user where they are, then look up the weather there\"}]},
   \"stream_mode\": [
     \"updates\"
   ]
 }"

输出

{'agent': {'messages': [{'content': [{'text': "I'll help you ask the user about their location and then search for weather information.", 'type': 'text'}, {'id': 'toolu_012JeNEvyePZFWK39d52Wdwi', 'input': {'question': 'Where are you located?'}, 'name': 'AskHuman', 'type': 'tool_use'}], 'additional_kwargs': {}, 'response_metadata': {'id': 'msg_01UBEdS6UvuFMetdokNsykVG', 'model': 'claude-3-5-sonnet-20241022', 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'input_tokens': 438, 'output_tokens': 76}, 'model_name': 'claude-3-5-sonnet-20241022'}, 'type': 'ai', 'name': None, 'id': 'run-1b1210d8-39e0-4607-9f0e-0ea932d28d5c-0', 'example': False, 'tool_calls': [{'name': 'AskHuman', 'args': {'question': 'Where are you located?'}, 'id': 'toolu_012JeNEvyePZFWK39d52Wdwi', 'type': 'tool_call'}], 'invalid_tool_calls': [], 'usage_metadata': {'input_tokens': 438, 'output_tokens': 76, 'total_tokens': 514, 'input_token_details': {'cache_read': 0, 'cache_creation': 0}}}]}}
{'__interrupt__': [{'value': 'Where are you located?', 'resumable': True, 'ns': ['ask_human:2d41f894-f297-211e-9bfe-1d162ecba54a'], 'when': 'during'}]}

您可以看到我们的图在 ask_human 节点内部被中断，该节点现在正在等待提供一个 location。

提供人工输入

我们可以通过使用 Command(resume="<location>") 调用图来提供人工输入 (location)

from langgraph_sdk.schema import Command

async for chunk in client.runs.stream(
    thread["thread_id"],
    assistant_id,
    command=Command(resume="san francisco"),
    stream_mode="updates",
):
    if chunk.data and chunk.event != "metadata": 
        print(chunk.data)

const streamResponse = client.runs.stream(
  thread["thread_id"],
  assistantId,
  {
    command: { resume: "san francisco" },
    streamMode: "updates"
  }
);

for await (const chunk of streamResponse) {
  if (chunk.data && chunk.event !== "metadata") {
    console.log(chunk.data);
  }
}

curl --request POST \
 --url <DEPLOYMENT_URL>/threads/<THREAD_ID>/runs/stream \
 --header 'Content-Type: application/json' \
 --data "{
   \"assistant_id\": \"agent\",
   \"command\": {
     \"resume\": \"san francisco\"
   },
   \"stream_mode\": [
     \"updates\"
   ]
 }"

输出

{'ask_human': {'messages': [{'tool_call_id': 'toolu_012JeNEvyePZFWK39d52Wdwi', 'type': 'tool', 'content': 'san francisco'}]}}
{'agent': {'messages': [{'content': [{'text': 'Let me search for the weather in San Francisco.', 'type': 'text'}, {'id': 'toolu_019f9Y7ST6rNeDQkDjFCHk6C', 'input': {'query': 'current weather in san francisco'}, 'name': 'search', 'type': 'tool_use'}], 'additional_kwargs': {}, 'response_metadata': {'id': 'msg_0152YFm7DtnzfZQuiMUzaSsw', 'model': 'claude-3-5-sonnet-20241022', 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'input_tokens': 527, 'output_tokens': 67}, 'model_name': 'claude-3-5-sonnet-20241022'}, 'type': 'ai', 'name': None, 'id': 'run-f509b5b2-eb30-4200-a8da-fa79ed68812a-0', 'example': False, 'tool_calls': [{'name': 'search', 'args': {'query': 'current weather in san francisco'}, 'id': 'toolu_019f9Y7ST6rNeDQkDjFCHk6C', 'type': 'tool_call'}], 'invalid_tool_calls': [], 'usage_metadata': {'input_tokens': 527, 'output_tokens': 67, 'total_tokens': 594, 'input_token_details': {'cache_read': 0, 'cache_creation': 0}}}]}}
{'action': {'messages': [{'content': "I looked up: current weather in san francisco. Result: It's sunny in San Francisco, but you better look out if you're a Gemini 😈.", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'tool', 'name': 'search', 'id': 'cbd0f623-cc12-48a2-8c18-3cbb943e46e0', 'tool_call_id': 'toolu_019f9Y7ST6rNeDQkDjFCHk6C', 'artifact': None, 'status': 'success'}]}}
{'agent': {'messages': [{'content': "Based on the search results, it's currently sunny in San Francisco. Would you like any specific details about the weather forecast?", 'additional_kwargs': {}, 'response_metadata': {'id': 'msg_01FhzXj72CehBYkJGX69vsBc', 'model': 'claude-3-5-sonnet-20241022', 'stop_reason': 'end_turn', 'stop_sequence': None, 'usage': {'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'input_tokens': 639, 'output_tokens': 29}, 'model_name': 'claude-3-5-sonnet-20241022'}, 'type': 'ai', 'name': None, 'id': 'run-f48e818e-dd88-415e-9a0b-4a958498b553-0', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': {'input_tokens': 639, 'output_tokens': 29, 'total_tokens': 668, 'input_token_details': {'cache_read': 0, 'cache_creation': 0}}}]}}

评论