Skip to content

回滚

本指南假设您已经了解什么是双重发送,您可以在双重发送概念指南中了解相关内容。

本指南涵盖了双重发送的rollback选项,该选项会中断之前的图运行,并开始一个新的图运行,其中包含双重发送的内容。此选项与interrupt选项非常相似,但在这种情况下,第一次运行将完全从数据库中删除,并且无法重新启动。以下是使用rollback选项的一个快速示例。

设置

首先,我们将定义一个用于打印JS和CURL模型输出的快速辅助函数(如果你使用Python可以跳过这一步):

function prettyPrint(m) {
  const padded = " " + m['type'] + " ";
  const sepLen = Math.floor((80 - padded.length) / 2);
  const sep = "=".repeat(sepLen);
  const secondSep = sep + (padded.length % 2 ? "=" : "");

  console.log(`${sep}${padded}${secondSep}`);
  console.log("\n\n");
  console.log(m.content);
}
# PLACE THIS IN A FILE CALLED pretty_print.sh
pretty_print() {
  local type="$1"
  local content="$2"
  local padded=" $type "
  local total_width=80
  local sep_len=$(( (total_width - ${#padded}) / 2 ))
  local sep=$(printf '=%.0s' $(eval "echo {1.."${sep_len}"}"))
  local second_sep=$sep
  if (( (total_width - ${#padded}) % 2 )); then
    second_sep="${second_sep}="
  fi

  echo "${sep}${padded}${second_sep}"
  echo
  echo "$content"
}

现在,让我们导入所需的包并实例化我们的客户端、助手和线程。

import asyncio

import httpx
from langchain_core.messages import convert_to_messages
from langgraph_sdk import get_client

client = get_client(url=<DEPLOYMENT_URL>)
# 使用名为 "agent" 的部署图
assistant_id = "agent"
thread = await client.threads.create()
import { Client } from "@langchain/langgraph-sdk";

const client = new Client({ apiUrl: <DEPLOYMENT_URL> });
// 使用名为 "agent" 的部署图
const assistantId = "agent";
const thread = await client.threads.create();
curl --request POST \
  --url <DEPLOYMENT_URL>/threads \
  --header 'Content-Type: application/json' \
  --data '{}'

创建运行

现在让我们使用多任务参数设置为"回滚"的线程进行运行:

# 第一次运行将被回滚
rolled_back_run = await client.runs.create(
    thread["thread_id"],
    assistant_id,
    input={"messages": [{"role": "user", "content": "旧金山的天气怎么样?"}]},
)
run = await client.runs.create(
    thread["thread_id"],
    assistant_id,
    input={"messages": [{"role": "user", "content": "纽约的天气怎么样?"}]},
    multitask_strategy="rollback",
)
# 等待第二次运行完成
await client.runs.join(thread["thread_id"], run["run_id"])
// 第一次运行将被中断
let rolledBackRun = await client.runs.create(
  thread["thread_id"],
  assistantId,
  { input: { messages: [{ role: "human", content: "旧金山的天气怎么样?" }] } }
);

let run = await client.runs.create(
  thread["thread_id"],
  assistant_id,
  { 
    input: { messages: [{ role: "human", content: "纽约的天气怎么样?" }] },
    multitaskStrategy: "rollback" 
  }
);

// 等待第二次运行完成
await client.runs.join(thread["thread_id"], run["run_id"]);
curl --request POST \
--url <DEPLOY<ENT_URL>>/threads/<THREAD_ID>/runs \
--header 'Content-Type: application/json' \
--data "{
  \"assistant_id\": \"agent\",
  \"input\": {\"messages\": [{\"role\": \"human\", \"content\": \"旧金山的天气怎么样?\"}]},
}" && curl --request POST \
--url <DEPLOY<ENT_URL>>/threads/<THREAD_ID>/runs \
--header 'Content-Type: application/json' \
--data "{
  \"assistant_id\": \"agent\",
  \"input\": {\"messages\": [{\"role\": \"human\", \"content\": \"纽约的天气怎么样?\"}]},
  \"multitask_strategy\": \"rollback\"
}" && curl --request GET \
--url <DEPLOYMENT_URL>/threads/<THREAD_ID>/runs/<RUN_ID>/join

查看运行结果

我们可以看到,线程仅在第二次运行时才有数据。

state = await client.threads.get_state(thread["thread_id"])

for m in convert_to_messages(state["values"]["messages"]):
    m.pretty_print()
const state = await client.threads.getState(thread["thread_id"]);

for (const m of state['values']['messages']) {
  prettyPrint(m);
}
source pretty_print.sh && curl --request GET \
--url <DEPLOYMENT_URL>/threads/<THREAD_ID>/state | \
jq -c '.values.messages[]' | while read -r element; do
    type=$(echo "$element" | jq -r '.type')
    content=$(echo "$element" | jq -r '.content | if type == "array" then tostring else . end')
    pretty_print "$type" "$content"
done

输出:

================================ 人类消息 =================================

nyc 的天气如何?
================================== AI 消息 ==================================

[{'id': 'toolu_01JzPqefao1gxwajHQ3Yh3JD', 'input': {'query': 'weather in nyc'}, 'name': 'tavily_search_results_json', 'type': 'tool_use'}]
工具调用:
  tavily_search_results_json (toolu_01JzPqefao1gxwajHQ3Yh3JD)
 调用 ID: toolu_01JzPqefao1gxwajHQ3Yh3JD
  参数:
    query: weather in nyc
================================= 工具消息 =================================
名称: tavily_search_results_json

[{"url": "https://www.weatherapi.com/", "content": "{'location': {'name': 'New York', 'region': 'New York', 'country': 'United States of America', 'lat': 40.71, 'lon': -74.01, 'tz_id': 'America/New_York', 'localtime_epoch': 1718734479, 'localtime': '2024-06-18 14:14'}, 'current': {'last_updated_epoch': 1718733600, 'last_updated': '2024-06-18 14:00', 'temp_c': 29.4, 'temp_f': 84.9, 'is_day': 1, 'condition': {'text': 'Sunny', 'icon': '//cdn.weatherapi.com/weather/64x64/day/113.png', 'code': 1000}, 'wind_mph': 2.2, 'wind_kph': 3.6, 'wind_degree': 158, 'wind_dir': 'SSE', 'pressure_mb': 1025.0, 'pressure_in': 30.26, 'precip_mm': 0.0, 'precip_in': 0.0, 'humidity': 63, 'cloud': 0, 'feelslike_c': 31.3, 'feelslike_f': 88.3, 'windchill_c': 28.3, 'windchill_f': 82.9, 'heatindex_c': 29.6, 'heatindex_f': 85.3, 'dewpoint_c': 18.4, 'dewpoint_f': 65.2, 'vis_km': 16.0, 'vis_miles': 9.0, 'uv': 7.0, 'gust_mph': 16.5, 'gust_kph': 26.5}}"}]
================================== AI 消息 ==================================

天气 API 的结果显示,纽约市当前的天气是晴朗,气温约为 85°F (29°C)。风速较轻,约为 2-3 英里/小时,来自东南偏南方向。总体来看,这看起来像是一个晴朗的夏日。

验证原始回滚的运行已被删除

try:
    await client.runs.get(thread["thread_id"], rolled_back_run["run_id"])
except httpx.HTTPStatusError as _:
    print("原始运行已被正确删除")
try {
  await client.runs.get(thread["thread_id"], rolledBackRun["run_id"]);
} catch (e) {
  console.log("原始运行已被正确删除");
}

输出:

原始运行已被正确删除

Comments