POST
/
v1
/
push
curl --request POST \
  --url https://mango.sievedata.com/v1/push \
  --header 'Content-Type: application/json' \
  --header 'X-API-Key: <api-key>' \
  --data '{
  "workflow_name": "<string>",
  "model_id": "<string>",
  "inputs": {}
}'
{
  "id": "c49b2fa2-f236-43d8-b2f3-03eceff16d71",
  "description": "Pushed c49b2fa2-f236-43d8-b2f3-03eceff16d71 to queue."
}
​
workflow_name
string

name of Sieve workflow

​
model_id
string

ID of Sieve model

​
inputs
dict
required

a dictionary representing the inputs to the workflow

This endpoint triggers either a workflow or a model with a given set of inputs. The structure of the inputs should match the inputs types specified in the workflow or model definition.

​
Example

A workflow that takes in a sieve.Video named video and a sieve.Image named image would be triggered with the following request:

{
  "workflow_name": "sample_workflow",
  "inputs": {
    "video": {
      "url": "{SOME_VIDEO_URL}"
    },
    "image": {
      "url": "{SOME_IMAGE_URL}"
    }
  }
}

A model that takes in a str named prompt would be triggered with the following request:

{
  "model_id": "570e75d6-008f-4a5a-93ec-fede6a8675eb",
  "inputs": {
    "prompt": "some string"
  }
}

{
  "id": "c49b2fa2-f236-43d8-b2f3-03eceff16d71",
  "description": "Pushed c49b2fa2-f236-43d8-b2f3-03eceff16d71 to queue."
}