Asynchronous Processing

Introduction

Starting from version 0.5, Langflow introduces a new feature to its API: the sync flag. This flag allows users to opt for asynchronous processing of their flows, freeing up resources and enabling better control over long-running tasks. This feature supports running tasks in a Celery worker queue and AnyIO task groups for now.

warning

This is an experimental feature. The default behavior of the API is still synchronous processing. The API may change in the future.

The sync Flag

The sync flag can be included in the payload of your POST request to the /api/v1/process/<your_flow_id> endpoint. When set to false, the API will initiate an asynchronous task instead of processing the flow synchronously.

API Request with sync flag

_10

curl -X POST \

_10

http://localhost:3000/api/v1/process/<your_flow_id> \

_10

-H 'Content-Type: application/json' \

_10

-H 'x-api-key: <your_api_key>' \

_10

-d '{"inputs": {"text": ""}, "tweaks": {}, "sync": false}'

Response:

_11

{

_11

"result": {

_11

"output": "..."

_11

},

_11

"task": {

_11

"id": "...",

_11

"href": "api/v1/task/<task_id>"

_11

},

_11

"session_id": "...",

_11

"backend": "..." // celery or anyio

_11

}

Checking Task Status

You can check the status of an asynchronous task by making a GET request to the /task/{task_id} endpoint.

_10

curl -X GET \

_10

http://localhost:3000/api/v1/task/<task_id> \

_10

-H 'x-api-key: <your_api_key>'

Response

The endpoint will return the current status of the task and, if completed, the result of the task. Possible statuses include:

• PENDING: The task is waiting for execution.
• SUCCESS: The task has completed successfully.
• FAILURE: The task has failed.

Example response for a completed task:

_10

{

_10

"status": "SUCCESS",

_10

"result": {

_10

"output": "..."

_10

}

_10

}