如何在同一个线程上运行多个智能体

在 LangSmith 部署中，线程并不显式地与特定智能体关联。 这意味着您可以在同一个线程上运行多个智能体，从而允许不同的智能体从初始智能体的进度继续执行。

在本示例中，我们将创建两个智能体，然后在同一个线程上调用它们。 您将看到第二个智能体会使用第一个智能体在线程中生成的检查点作为上下文来响应。

设置

Python

from langgraph_sdk import get_client

client = get_client(url=<DEPLOYMENT_URL>)

openai_assistant = await client.assistants.create(
    graph_id="agent", config={"configurable": {"model_name": "openai"}}
)

# 应该始终存在一个没有配置的默认智能体
assistants = await client.assistants.search()
default_assistant = [a for a in assistants if not a["config"]][0]

Javascript

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

const client = new Client({ apiUrl: <DEPLOYMENT_URL> });

const openAIAssistant = await client.assistants.create(
  { graphId: "agent", config: {"configurable": {"model_name": "openai"}}}
);

const assistants = await client.assistants.search();
const defaultAssistant = assistants.find(a => !a.config);

CURL

curl --request POST \
    --url <DEPLOYMENT_URL>/assistants \
    --header 'Content-Type: application/json' \
    --data '{
        "graph_id": "agent",
        "config": { "configurable": { "model_name": "openai" } }
    }' && \
curl --request POST \
    --url <DEPLOYMENT_URL>/assistants/search \
    --header 'Content-Type: application/json' \
    --data '{
        "limit": 10,
        "offset": 0
    }' | jq -c 'map(select(.config == null or .config == {})) | .[0]'

我们可以看到这些智能体是不同的：

Python

print(openai_assistant)

Javascript

console.log(openAIAssistant);

CURL

curl --request GET \
    --url <DEPLOYMENT_URL>/assistants/<OPENAI_ASSISTANT_ID>

输出：

{
"assistant_id": "db87f39d-b2b1-4da8-ac65-cf81beb3c766",
"graph_id": "agent",
"created_at": "2024-08-30T21:18:51.850581+00:00",
"updated_at": "2024-08-30T21:18:51.850581+00:00",
"config": {
"configurable": {
"model_name": "openai"
}
},
"metadata": {}
}

Python

print(default_assistant)

Javascript

console.log(defaultAssistant);

CURL

curl --request GET \
    --url <DEPLOYMENT_URL>/assistants/<DEFAULT_ASSISTANT_ID>

输出：

{
"assistant_id": "fe096781-5601-53d2-b2f6-0d3403f7e9ca",
"graph_id": "agent",
"created_at": "2024-08-08T22:45:24.562906+00:00",
"updated_at": "2024-08-08T22:45:24.562906+00:00",
"config": {},
"metadata": {
"created_by": "system"
}
}

在线程上运行智能体

运行 OpenAI 智能体

我们现在可以首先在线程上运行 OpenAI 智能体。

Python

thread = await client.threads.create()
input = {"messages": [{"role": "user", "content": "who made you?"}]}
async for event in client.runs.stream(
    thread["thread_id"],
    openai_assistant["assistant_id"],
    input=input,
    stream_mode="updates",
):
    print(f"Receiving event of type: {event.event}")
    print(event.data)
    print("\n\n")

Javascript

const thread = await client.threads.create();
let input =  {"messages": [{"role": "user", "content": "who made you?"}]}

const streamResponse = client.runs.stream(
  thread["thread_id"],
  openAIAssistant["assistant_id"],
  {
    input,
    streamMode: "updates"
  }
);
for await (const event of streamResponse) {
  console.log(`Receiving event of type: ${event.event}`);
  console.log(event.data);
  console.log("\n\n");
}

CURL

thread_id=$(curl --request POST \
    --url <DEPLOYMENT_URL>/threads \
    --header 'Content-Type: application/json' \
    --data '{}' | jq -r '.thread_id') && \
curl --request POST \
    --url "<DEPLOYMENT_URL>/threads/${thread_id}/runs/stream" \
    --header 'Content-Type: application/json' \
    --data '{
        "assistant_id": <OPENAI_ASSISTANT_ID>,
        "input": {
            "messages": [
                {
                    "role": "user",
                    "content": "who made you?"
                }
            ]
        },
        "stream_mode": [
            "updates"
        ]
    }' | \
    sed 's/\r$//' | \
    awk '
    /^event:/ {
        if (data_content != "") {
            print data_content "\n"
        }
        sub(/^event: /, "Receiving event of type: ", $0)
        printf "%s...\n", $0
        data_content = ""
    }
    /^data:/ {
        sub(/^data: /, "", $0)
        data_content = $0
    }
    END {
        if (data_content != "") {
            print data_content "\n\n"
        }
    }
'

输出：

Receiving event of type: metadata
{'run_id': '1ef671c5-fb83-6e70-b698-44dba2d9213e'}

Receiving event of type: updates
{'agent': {'messages': [{'content': 'I was created by OpenAI, a research organization focused on developing and advancing artificial intelligence technology.', 'additional_kwargs': {}, 'response_metadata': {'finish_reason': 'stop', 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_157b3831f5'}, 'type': 'ai', 'name': None, 'id': 'run-f5735b86-b80d-4c71-8dc3-4782b5a9c7c8', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}}

运行默认智能体

现在，我们可以在默认智能体上运行它，并看到第二个智能体知道初始问题，并且能够回答“and you?”这个问题：

Python

input = {"messages": [{"role": "user", "content": "and you?"}]}
async for event in client.runs.stream(
    thread["thread_id"],
    default_assistant["assistant_id"],
    input=input,
    stream_mode="updates",
):
    print(f"Receiving event of type: {event.event}")
    print(event.data)
    print("\n\n")

Javascript

let input =  {"messages": [{"role": "user", "content": "and you?"}]}

const streamResponse = client.runs.stream(
  thread["thread_id"],
  defaultAssistant["assistant_id"],
  {
    input,
    streamMode: "updates"
  }
);
for await (const event of streamResponse) {
  console.log(`Receiving event of type: ${event.event}`);
  console.log(event.data);
  console.log("\n\n");
}

CURL

curl --request POST \
    --url <DEPLOYMENT_URL>/threads/<THREAD_ID>/runs/stream \
    --header 'Content-Type: application/json' \
    --data '{
        "assistant_id": <DEFAULT_ASSISTANT_ID>,
        "input": {
            "messages": [
                {
                    "role": "user",
                    "content": "and you?"
                }
            ]
        },
        "stream_mode": [
            "updates"
        ]
    }' | \
    sed 's/\r$//' | \
    awk '
    /^event:/ {
        if (data_content != "") {
            print data_content "\n"
        }
        sub(/^event: /, "Receiving event of type: ", $0)
        printf "%s...\n", $0
        data_content = ""
    }
    /^data:/ {
        sub(/^data: /, "", $0)
        data_content = $0
    }
    END {
        if (data_content != "") {
            print data_content "\n\n"
        }
    }
'

输出：

Receiving event of type: metadata
{'run_id': '1ef6722d-80b3-6fbb-9324-253796b1cd13'}

Receiving event of type: updates
{'agent': {'messages': [{'content': [{'text': 'I am an artificial intelligence created by Anthropic, not by OpenAI. I should not have stated that OpenAI created me, as that is incorrect. Anthropic is the company that developed and trained me using advanced language models and AI technology. I will be more careful about providing accurate information regarding my origins in the future.', 'type': 'text', 'index': 0}], 'additional_kwargs': {}, 'response_metadata': {'stop_reason': 'end_turn', 'stop_sequence': None}, 'type': 'ai', 'name': None, 'id': 'run-ebaacf62-9dd9-4165-9535-db432e4793ec', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': {'input_tokens': 302, 'output_tokens': 72, 'total_tokens': 374}}]}}

---

Edit this page on GitHub or file an issue.

Connect these docs to Claude, VSCode, and more via MCP for real-time answers.