✨ Get inference run info

GET

http://localhost:8000/api/prompts/:prompt_id/versions/:version_id/inference-runs

GET

/api/prompts/:prompt_id/versions/:version_id/inference-runs

curl http://localhost:8000/api/prompts/1/versions/1/inference-runs \
     -H "Authorization: Token  <api_key>"

200Retrieved

[
  {
    "completed_at": "2024-01-15T09:30:00Z",
    "created_at": "2024-01-15T09:30:00Z",
    "created_by": {
      "avatar": "string",
      "id": 1,
      "username": "string",
      "email": "string",
      "first_name": "string",
      "last_name": "string"
    },
    "id": 1,
    "model_version": 1,
    "parent_model": 1,
    "project": 1,
    "source_model_run": 1,
    "status": "Pending",
    "task_ids": null,
    "triggered_at": "2024-01-15T09:30:00Z",
    "filters_json": null,
    "job_id": "string",
    "organization": 1,
    "predictions_updated_at": "2024-01-15T09:30:00Z",
    "project_subset": "All",
    "sample_subset_size": 1,
    "total_correct_predictions": 1,
    "total_predictions": 1,
    "total_tasks": 1
  }
]

This endpoint is not available in Label Studio Community Edition. Learn more about Label Studio Enterprise

Get information (status, metadata, etc) about an existing inference run

Authentication

AuthorizationToken

The token (or API key) must be passed as a request header. You can find your user token on the User Account page in Label Studio. Example:

curl https://label-studio-host/api/projects -H "Authorization: Token [your-token]"

Path parameters

prompt_idintegerRequired

version_idintegerRequired

Query parameters

orderingstringOptional

Which field to use when ordering the results.

parent_modelintegerOptional

The ID of the parent model for this Inference Run

projectintegerOptional

The ID of the project this Inference Run makes predictions on

project_subsetenumOptional

Defines which tasks are operated on (e.g. HasGT will only operate on tasks with a ground truth annotation, but All will operate on all records)

Allowed values:

Response

This endpoint returns a list of objects.

completed_atdatetime or nullRead-only

created_atdatetimeRead-only

created_byobject

A ModelSerializer that takes additional arguments for "fields", "omit" and "expand" in order to control which fields are displayed, and whether to replace simple values with complex, nested serializations

idintegerRead-only

model_versioninteger

parent_modelintegerRead-only

projectinteger

source_model_runinteger or nullRead-only

statusenum

Pending - Pending
InProgress - InProgress
Completed - Completed
Failed - Failed
Canceled - Canceled

Allowed values:

task_idsany or nullRead-only

List of task IDs for Custom subset re-evaluation.

triggered_atdatetime or nullRead-only

filters_jsonany or nullOptional

DM filter group for Filtered subset. Stored for display/re-run purposes.

job_idstring or nullOptional<=255 characters

Job ID for inference job for a ModelRun e.g. Adala job ID

organizationinteger or nullOptional

predictions_updated_atdatetime or nullOptional

project_subsetenumOptional

All - All
HasGT - HasGT
Sample - Sample
Custom - Custom

Allowed values:

sample_subset_sizeinteger or nullOptional0-2147483647

Custom sample size for Sample subset. Uses PROMPTER_SAMPLE_SUBSET_SIZE if not set.

total_correct_predictionsinteger or nullOptional-2147483648-2147483647

total_predictionsinteger or nullOptional-2147483648-2147483647

total_tasksinteger or nullOptional-2147483648-2147483647