大多数时候，您在运行图时向客户端提供 thread_id，以便通过 LangSmith Deployment 中实现的持久状态跟踪先前的运行。但是，如果您不需要持久化运行，则不需要使用内置持久状态，可以创建无状态运行。

​
设置

首先，让我们设置客户端：
  • Python
  • Javascript
  • CURL
from langgraph_sdk import get_client

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

​
无状态流式传输

我们可以以与从具有状态属性的运行流式传输几乎相同的方式流式传输无状态运行的结果，但不是向 thread_id 参数传递值，而是传递 None：
  • Python
  • Javascript
  • CURL
input = {
    "messages": [
        {"role": "user", "content": "Hello! My name is Bagatur and I am 26 years old."}
    ]
}

async for chunk in client.runs.stream(
    # Don't pass in a thread_id and the stream will be stateless
    None,
    assistant_id,
    input=input,
    stream_mode="updates",
):
    if chunk.data and "run_id" not in chunk.data:
        print(chunk.data)
输出： 
{'agent': {'messages': [{'content': "Hello Bagatur! It's nice to meet you. Thank you for introducing yourself and sharing your age. Is there anything specific you'd like to know or discuss? I'm here to help with any questions or topics you're interested in.", 'additional_kwargs': {}, 'response_metadata': {}, 'type': 'ai', 'name': None, 'id': 'run-489ec573-1645-4ce2-a3b8-91b391d50a71', 'example': False, 'tool_calls': [], 'invalid_tool_calls': [], 'usage_metadata': None}]}}

​
等待无状态结果

除了流式传输，你还可以使用 .wait 函数等待无状态结果，如下所示：
  • Python
  • Javascript
  • CURL
stateless_run_result = await client.runs.wait(
    None,
    assistant_id,
    input=input,
)
print(stateless_run_result)
输出： 
{
'messages': [
{
'content': 'Hello! My name is Bagatur and I am 26 years old.',
'additional_kwargs': {},
'response_metadata': {},
'type': 'human',
'name': None,
'id': '5e088543-62c2-43de-9d95-6086ad7f8b48',
'example': False}
,
{
'content': "Hello Bagatur! It's nice to meet you. Thank you for introducing yourself and sharing your age. Is there anything specific you'd like to know or discuss? I'm here to help with any questions or topics you'd like to explore.",
'additional_kwargs': {},
'response_metadata': {},
'type': 'ai',
'name': None,
'id': 'run-d6361e8d-4d4c-45bd-ba47-39520257f773',
'example': False,
'tool_calls': [],
'invalid_tool_calls': [],
'usage_metadata': None
}
]
}
Edit the source of this page on GitHub.
Connect these docs programmatically to Claude, VSCode, and more via MCP for real-time answers.