GET
/
v2
/
functions
/
{organization_name}
/
{function_name}
/
versions
/
{id}
curl --request GET \
  --url https://mango.sievedata.com/v2/functions/{organization_name}/{function_name}/versions/{id} \
  --header 'X-API-Key: <api-key>'
{
  "id": "9c701df7-13e3-4d97-a344-693d615bede9",
  "name": "whisper",
  "version": "54cd08e8-8f77-49f1-9824-b969aab8bf7d",
  "organization_id": "c0ec7825-0fcb-444e-b0b9-9660c40fa0f4",
  "status": "ready",
  "permissions": {
    "private": false,
    "ids": null
  },
  "gpu": "true",
  "full_config": null,
  "time": {
    "queued": "2023-02-09T19:26:04.455000",
    "started": "2023-02-09T19:26:04.467000",
    "completed": "2023-02-09T19:27:23.462000"
  },
  "machine_type": "",
  "type": "model",
  "is_iterator_input": false,
  "is_iterator_output": true,
  "current_workers": {
    "awaiting_resources": 0,
    "starting": 0,
    "setup": 0,
    "active": 0,
    "idle": 3
  },
  "outputs": [
    {
      "type": "typing.Dict"
    }
  ],
  "inputs": [
    {
      "type": "sieve.types.file.Audio",
      "name": "audio"
    }
  ],
  "minimum_running_replicas": 2,
  "description": "",
  "code_url": "",
  "author": "sieve-developer"
}

This endpoint returns a JSON object that describes a given function version given its ID.

Request

organization_name
string
required

name of Sieve organization

function_name
string
required

name of Sieve model

id
string
required

version id of Sieve function

Response

id
string

Id of the model.

build_status
string

Build status of the function version. Statuses are 'queued', 'building', 'pushing', 'deploying', 'ready', 'error'

queued_at
string

The time that the function build is queued.

built_at
string

The time that the function build finished building.

ready_at
string

The time that the model is ready to process jobs.

compute_type
string

Machine type to use, see possible values for GPU machine types here

python_packages
string array

An array of the model's python pip packages.

system_packages
string array

An array of the model's system packages.

cuda_version
string

Cuda Version.

gpu
boolean

Whether this model uses gpu.

minimum_replicas
integer

The minimum number of replicas of the model. Scale your model's minimum replicas to avoid cold starts.

maximum_replicas
integer

The maximum number of replicas of the model. Prevents model replicas from scaling beyond a certain point.

inputs
array Input

The inputs to a function, learn more about inputs here

outputs
array Output

The outputs to a function, learn more about outputs here

current_workers
Status Object

The current number and status of the model's workers.

environment_variables
array EnvironmentVariable

The outputs to a function