Edit

Share via

Endpoint - Score ML Model Endpoint Version

Service:
MLModel
API Version:
v1

Scores input data for the specific version of the endpoint and returns results.
This API supports long running operations (LRO).

Permissions

The caller must have write permission on the MLModel.

Required Delegated Scopes

MLModel.ReadWrite.All or Item.ReadWrite.All

Microsoft Entra supported identities

This API supports the Microsoft identities listed in this section.

Identity Support
User Yes
Service principal and Managed identities Yes

Interface

POST https://api.fabric.microsoft.com/v1/workspaces/{workspaceId}/mlmodels/{modelId}/endpoint/versions/{name}/score

URI Parameters

Name In Required Type Description
modelId
 path True

string (uuid)

The machine learning model ID.
name
 path True

string

The MLModel version name.
workspaceId
 path True

string (uuid)

The workspace ID.

Request Body

Name Required Type Description
inputs True

object[]

Machine learning inputs to score in the form of Pandas dataset arrays that can include strings, numbers, integers and booleans.
formatType

FormatType

Format type of data. Additional Format types may be added over time.
orientation

Orientation

Orientation of data. Additional Orientation types may be added over time.

Responses

Name Type Description
200 OK

ScoreDataResponse

Request completed successfully.
202 Accepted

Request accepted, scoring in progress.

Headers

  • Location: string
  • x-ms-operation-id: string
  • Retry-After: integer
Other Status Codes

ErrorResponse

Common error codes:

  • NotFound - Version not found.

  • UnknownError - An error occurred.

Examples

Example

Sample request

POST https://api.fabric.microsoft.com/v1/workspaces/cf5fef71-f7f3-43f3-ae7f-3c427922bef1/mlmodels/7e92a6fc-3ef5-40bf-96df-ddae3fcde313/endpoint/versions/1/score

{
  "formatType": "dataframe",
  "orientation": "values",
  "inputs": [
    [
      -0.00188201652779,
      -0.04464163650698,
      -0.0514740612388,
      -0.0263275281478529,
      -0.00844872411121,
      -0.01916333974822,
      0.07441156407875721,
      -0.03949338287409329,
      -0.0683315470939731,
      -0.092204049626824
    ],
    [
      1,
      2,
      3,
      4,
      5,
      6,
      7,
      8,
      9,
      0
    ],
    [
      11,
      2,
      3,
      4,
      5,
      6,
      77,
      8,
      9,
      0
    ],
    [
      1,
      22,
      3,
      47,
      5,
      6,
      7,
      0,
      9,
      0
    ],
    [
      1,
      2,
      3,
      4,
      5,
      6,
      7,
      8,
      9,
      0
    ],
    [
      1,
      2,
      3,
      4,
      5,
      86,
      7,
      8,
      9,
      0
    ],
    [
      1,
      25,
      3,
      4,
      5,
      6,
      7,
      98,
      9,
      0
    ],
    [
      1,
      2,
      3,
      4,
      5,
      6,
      7,
      8,
      99,
      0
    ],
    [
      1,
      205,
      3,
      4,
      5,
      96,
      7,
      8,
      9,
      0
    ],
    [
      1,
      2,
      35,
      4,
      5,
      6,
      7,
      18,
      19,
      0
    ]
  ]
}

Sample response

Status code:
200 
{
  "formatType": "dataframe",
  "orientation": "values",
  "predictions": [
    [
      72
    ],
    [
      248
    ],
    [
      87
    ],
    [
      217
    ],
    [
      248
    ],
    [
      84
    ],
    [
      248
    ],
    [
      220
    ],
    [
      139
    ],
    [
      242
    ]
  ]
}
Status code:
202 
Location: https://api.fabric.microsoft.com/v1/operations/0acd697c-1550-43cd-b998-91bfbfbd47c6
x-ms-operation-id: 0acd697c-1550-43cd-b998-91bfbfbd47c6
Retry-After: 30

Definitions

Name Description
ErrorRelatedResource

The error related resource details object.
ErrorResponse

The error response.
ErrorResponseDetails

The error response details.
FormatType

Format type of data. Additional Format types may be added over time.
Orientation

Orientation of data. Additional Orientation types may be added over time.
ScoreDataRequest

Machine learning model endpoint request to score the given input data.
ScoreDataResponse

Machine learning model endpoint response to score the given input data.

ErrorRelatedResource

Object

The error related resource details object.

Name Type Description
resourceId

string

The resource ID that's involved in the error.
resourceType

string

The type of the resource that's involved in the error.

ErrorResponse

Object

The error response.

Name Type Description
errorCode

string

A specific identifier that provides information about an error condition, allowing for standardized communication between our service and its users.
message

string

A human readable representation of the error.
moreDetails

ErrorResponseDetails[]

List of additional error details.
relatedResource

ErrorRelatedResource

The error related resource details.
requestId

string

ID of the request associated with the error.

ErrorResponseDetails

Object

The error response details.

Name Type Description
errorCode

string

A specific identifier that provides information about an error condition, allowing for standardized communication between our service and its users.
message

string

A human readable representation of the error.
relatedResource

ErrorRelatedResource

The error related resource details.

FormatType

Enumeration

Format type of data. Additional Format types may be added over time.

Value Description
dataframe

Dataframe format type.

Orientation

Enumeration

Orientation of data. Additional Orientation types may be added over time.

Value Description
split

Split orientation.
values

Values orientation.
record

Record orientation.
index

Index orientation.
table

Table orientation.

ScoreDataRequest

Object

Machine learning model endpoint request to score the given input data.

Name Type Description
formatType

FormatType

Format type of data. Additional Format types may be added over time.
inputs

object[]

Machine learning inputs to score in the form of Pandas dataset arrays that can include strings, numbers, integers and booleans.
orientation

Orientation

Orientation of data. Additional Orientation types may be added over time.

ScoreDataResponse

Object

Machine learning model endpoint response to score the given input data.

Name Type Description
formatType

FormatType

Format type of data. Additional Format types may be added over time.
orientation

Orientation

Orientation of data. Additional Orientation types may be added over time.
predictions

object[]

Machine learning predictions represented in the form of Pandas dataset arrays that can include strings, numbers, integers and booleans.