> ## 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. # 中断并发 本指南假设您了解什么是双重文本，您可以在[双重文本概念指南](/langsmith/double-texting)中学习相关内容。 本指南涵盖用于双重文本的 `interrupt` 选项，该选项会中断图的先前运行，并使用双重文本开始一个新的运行。此选项不会删除第一次运行，而是将其保留在数据库中，但将其状态设置为 `interrupted`。以下是使用 `interrupt` 选项的快速示例。 ## 设置 首先，我们将定义一个快速辅助函数，用于打印 JS 和 CURL 模型输出（如果您使用 Python，可以跳过此步骤）： ```js theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}} 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); } ``` ```bash theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}} # 将此内容放入名为 pretty_print.sh 的文件中 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客户端、助手和线程。 ```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}} import asyncio from langchain_core.messages import convert_to_messages from langgraph_sdk import get_client client = get_client(url=) # 使用部署名称为 "agent" 的图 assistant_id = "agent" thread = await client.threads.create() ``` ```js theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}} import { Client } from "@langchain/langgraph-sdk"; const client = new Client({ apiUrl: }); // 使用部署名称为 "agent" 的图 const assistantId = "agent"; const thread = await client.threads.create(); ``` ```bash theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}} curl --request POST \ --url /threads \ --header 'Content-Type: application/json' \ --data '{}' ``` ## 创建运行 现在我们可以开始两次运行，并等待第二次运行完成： ```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}} # 第一次运行将被中断 interrupted_run = await client.runs.create( thread["thread_id"], assistant_id, input={"messages": [{"role": "user", "content": "what's the weather in sf?"}]}, ) # 稍等片刻以获取第一次运行的部分输出 await asyncio.sleep(2) run = await client.runs.create( thread["thread_id"], assistant_id, input={"messages": [{"role": "user", "content": "what's the weather in nyc?"}]}, multitask_strategy="interrupt", ) # 等待第二次运行完成 await client.runs.join(thread["thread_id"], run["run_id"]) ``` ```js theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}} // 第一次运行将被中断 let interruptedRun = await client.runs.create( thread["thread_id"], assistantId, { input: { messages: [{ role: "human", content: "what's the weather in sf?" }] } } ); // 稍等片刻以获取第一次运行的部分输出 await new Promise(resolve => setTimeout(resolve, 2000)); let run = await client.runs.create( thread["thread_id"], assistantId, { input: { messages: [{ role: "human", content: "what's the weather in nyc?" }] }, multitaskStrategy: "interrupt" } ); // 等待第二次运行完成 await client.runs.join(thread["thread_id"], run["run_id"]); ``` ```bash theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}} curl --request POST \ --url >/threads//runs \ --header 'Content-Type: application/json' \ --data "{ \"assistant_id\": \"agent\", \"input\": {\"messages\": [{\"role\": \"human\", \"content\": \"what\'s the weather in sf?\"}]}, }" && sleep 2 && curl --request POST \ --url >/threads//runs \ --header 'Content-Type: application/json' \ --data "{ \"assistant_id\": \"agent\", \"input\": {\"messages\": [{\"role\": \"human\", \"content\": \"what\'s the weather in nyc?\"}]}, \"multitask_strategy\": \"interrupt\" }" && curl --request GET \ --url /threads//runs//join ``` ## 查看运行结果 我们可以看到线程中包含来自第一次运行的部分数据 + 来自第二次运行的数据 ```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}} state = await client.threads.get_state(thread["thread_id"]) for m in convert_to_messages(state["values"]["messages"]): m.pretty_print() ``` ```js theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}} const state = await client.threads.getState(thread["thread_id"]); for (const m of state['values']['messages']) { prettyPrint(m); } ``` ```bash theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}} source pretty_print.sh && curl --request GET \ --url /threads//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 ================================= what's the weather in sf? ================================== AI 消息 ================================== [{'id': 'toolu_01MjNtVJwEcpujRGrf3x6Pih', 'input': {'query': 'weather in san francisco'}, 'name': 'tavily_search_results_json', 'type': 'tool_use'}] 工具调用: tavily_search_results_json (toolu_01MjNtVJwEcpujRGrf3x6Pih) 调用 ID: toolu_01MjNtVJwEcpujRGrf3x6Pih 参数: query: weather in san francisco ================================= 工具消息 ================================= 名称: tavily_search_results_json [{"url": "https://www.wunderground.com/hourly/us/ca/san-francisco/KCASANFR2002/date/2024-6-18", "content": "High 64F. Winds W at 10 to 20 mph. A few clouds from time to time. Low 49F. Winds W at 10 to 20 mph. Temp. San Francisco Weather Forecasts. Weather Underground provides local & long-range weather ..."}] ================================ 人类消息 ================================= what's the weather in nyc? ================================== AI 消息 ================================== [{'id': 'toolu_01KtE1m1ifPLQAx4fQLyZL9Q', 'input': {'query': 'weather in new york city'}, 'name': 'tavily_search_results_json', 'type': 'tool_use'}] 工具调用: tavily_search_results_json (toolu_01KtE1m1ifPLQAx4fQLyZL9Q) 调用 ID: toolu_01KtE1m1ifPLQAx4fQLyZL9Q 参数: query: weather in new york city ================================= 工具消息 ================================= 名称: tavily_search_results_json [{"url": "https://www.accuweather.com/en/us/new-york/10021/june-weather/349727", "content": "Get the monthly weather forecast for New York, NY, including daily high/low, historical averages, to help you plan ahead."}] ================================== AI 消息 ================================== 搜索结果提供了纽约市的天气预报和信息。根据 AccuWeather 的首要结果，以下是关于纽约市天气的一些关键细节： * 这是纽约市六月份的月度天气预报。 * 它包括每日最高和最低温度，以帮助提前规划。 * 还提供了纽约市六月份的历史平均值作为参考点。 * 更详细的每日或每小时预报，包括降水概率、湿度、风力等，可以通过访问 AccuWeather 页面找到。 总之，搜索提供了纽约市未来一个月预期天气状况的便捷概览，让您了解如果前往那里旅行或制定计划需要准备什么。如果您需要任何其他详细信息，请告诉我！ ``` 验证原始、被中断的运行是否已被中断 ```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}} print((await client.runs.get(thread["thread_id"], interrupted_run["run_id"]))["status"]) ``` ```js theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}} console.log((await client.runs.get(thread['thread_id'], interruptedRun["run_id"]))["status"]) ``` 输出： ``` 'interrupted' ``` ***
[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/langsmith/interrupt-concurrent.mdx) 或 [提交问题](https://github.com/langchain-ai/docs/issues/new/choose)。