List Function Versions

curl --request GET \
  --url https://mango.sievedata.com/v2/functions/{owner_name}/{function_name}/versions \
  --header 'X-API-Key: <api-key>'

[
  {
    "id": "<string>",
    "build_status": "<string>",
    "queued_at": "2024-12-15T01:41:59.195000",
    "built_at": "2024-12-15T01:41:59.195000",
    "ready_at": "2024-12-15T01:41:59.195000",
    "compute_type": "<string>",
    "python_packages": [
      "<string>"
    ],
    "system_packages": [
      "<string>"
    ],
    "gpu": true,
    "split": 123,
    "inputs": [
      {
        "type": "<string>",
        "name": "<string>",
        "data": "<unknown>",
        "description": "<string>",
        "schema": {},
        "run_id": "<string>",
        "is_optional": false
      }
    ],
    "outputs": [
      {
        "type": "<string>",
        "name": "<string>",
        "data": "<unknown>",
        "description": "<string>",
        "schema": {},
        "run_id": "<string>",
        "is_optional": false
      }
    ],
    "environment_variables": [
      {
        "name": "<string>",
        "description": "<string>",
        "default": "<string>"
      }
    ],
    "function_dependencies": [
      "<string>"
    ],
    "cuda_version": "<string>",
    "minimum_replicas": 0,
    "maximum_replicas": 0,
    "current_workers": {
      "starting": 123,
      "setup": 123,
      "active": 123,
      "idle": 123,
      "awaiting_resources": 123
    },
    "stream_output": false
  }
]

GET

functions

{owner_name}

{function_name}

versions

List Function Versions

curl --request GET \
  --url https://mango.sievedata.com/v2/functions/{owner_name}/{function_name}/versions \
  --header 'X-API-Key: <api-key>'

[
  {
    "id": "<string>",
    "build_status": "<string>",
    "queued_at": "2024-12-15T01:41:59.195000",
    "built_at": "2024-12-15T01:41:59.195000",
    "ready_at": "2024-12-15T01:41:59.195000",
    "compute_type": "<string>",
    "python_packages": [
      "<string>"
    ],
    "system_packages": [
      "<string>"
    ],
    "gpu": true,
    "split": 123,
    "inputs": [
      {
        "type": "<string>",
        "name": "<string>",
        "data": "<unknown>",
        "description": "<string>",
        "schema": {},
        "run_id": "<string>",
        "is_optional": false
      }
    ],
    "outputs": [
      {
        "type": "<string>",
        "name": "<string>",
        "data": "<unknown>",
        "description": "<string>",
        "schema": {},
        "run_id": "<string>",
        "is_optional": false
      }
    ],
    "environment_variables": [
      {
        "name": "<string>",
        "description": "<string>",
        "default": "<string>"
      }
    ],
    "function_dependencies": [
      "<string>"
    ],
    "cuda_version": "<string>",
    "minimum_replicas": 0,
    "maximum_replicas": 0,
    "current_workers": {
      "starting": 123,
      "setup": 123,
      "active": 123,
      "idle": 123,
      "awaiting_resources": 123
    },
    "stream_output": false
  }
]

Authorizations

X-API-Key

string

header

required

The Sieve API key to authenticate with.

Path Parameters

owner_name

string

required

The owner of the function. The owner of the function.

function_name

string

required

The name of the function. The name of the function.

Query Parameters

limit

integer

default:500

The maximum amount of versions to show. The maximum amount of versions to show.

offset

integer

default:0

Exclude the first N versions. Exclude the first N versions.

Response

Successful Response

string

required

Id of the model

build_status

string

required

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

queued_at

string<date-time> | null

required

The UTC time that the function build is queued.

Example:

"2024-12-15T01:41:59.195000"

built_at

string<date-time> | null

required

The UTC time that the function build finished building.

Example:

"2024-12-15T01:41:59.195000"

ready_at

string<date-time> | null

required

The UTC time that the model is ready to process jobs.

Example:

"2024-12-15T01:41:59.195000"

compute_type

string

required

Machine type to use. See possible values for GPU machine types

python_packages

string[]

required

An array of the model's python pip packages

system_packages

string[]

required

An array of the model's system packages

gpu

boolean

required

Whether this model uses gpu

split

integer

required

How many functions to allocate per node

inputs

InputOutput · object[]

required

The inputs to a function

Show child attributes

inputs.type

string | null

The type of the output, see all possible values here

inputs.name

string | null

The name of the output

inputs.data

any

The data of the output. Empty if the response is not from a job

inputs.description

string | null

The description of the output

inputs.schema

Schema · object

inputs.run_id

string | null

The run id associated with this output

inputs.is_optional

boolean | null

default:false

Whether this input is optional or required

outputs

InputOutput · object[]

required

The outputs to a function

Show child attributes

outputs.type

string | null

The type of the output, see all possible values here

outputs.name

string | null

The name of the output

outputs.data

any

The data of the output. Empty if the response is not from a job

outputs.description

string | null

The description of the output

outputs.schema

Schema · object

outputs.run_id

string | null

The run id associated with this output

outputs.is_optional

boolean | null

default:false

Whether this input is optional or required

environment_variables

required

The outputs to a function

Show child attributes

environment_variables.name

string

required

The name of the environment variables

environment_variables.description

string | null

required

The description of the environment variables

environment_variables.default

string | null

required

Default value of the environment variable

function_dependencies

string[]

required

Function dependencies

cuda_version

string | null

Cuda Version

minimum_replicas

integer

default:0

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

maximum_replicas

integer | null

default:0

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

current_workers

WorkerCounts · object

The current number and status of the model's workers

Show child attributes

current_workers.starting

integer | null

required

The number of workers that are in the process of being started. This means that the worker has been allocated resources on the Sieve cloud, but is still in the process of creating the environment in which the model runs.

current_workers.setup

integer | null

required

The number of workers that are in the process of running the setup function.

current_workers.active

integer | null

required

The number of workers that are actively running a prediction.

current_workers.idle

integer | null

required

The number of workers that have fully setup, but are not currently running a prediction.

current_workers.awaiting_resources

integer | null

required

The number of workers that are still waiting for resources on the Sieve cloud.

stream_output

boolean | null

default:false

Stream output

⌘I

API Reference

CLI Reference

Custom Functions

SDK Reference

List Function Versions

Authorizations

Path Parameters

Query Parameters

Response