AutoML

Create, manage, and monitor automated machine learning jobs. AutoML automatically selects the best model architecture, hyperparameters, and feature engineering for your dataset and prediction task.

All endpoints require authentication via X-API-Key header and the appropriate scope.

---

AutoMLJob Object

{
  "id": "aml_abc123",
  "name": "Churn Prediction Model",
  "status": "running",
  "description": "Predicting customer churn from usage and billing data",
  "dataset": "ds_customers_001",
  "problemType": "binary_classification",
  "predictorType": "tabular",
  "owner": "user_456",
  "organizationId": "org_xyz",
  "targetColumn": "churned",
  "preset": "best_quality",
  "timeLimit": 3600,
  "startedAt": "2025-02-01T10:00:00Z",
  "finishedAt": null,
  "error": null,
  "createdAt": "2025-02-01T09:55:00Z",
  "updatedAt": "2025-02-01T12:30:00Z"
}

---

GET /api/v1/automl/jobs

List all AutoML jobs accessible to the authenticated user.

Scope: ml-workbench:read

Query Parameters

Parameter	Type	Required	Description
status	string	No	Filter by status: queued, running, completed, failed, stopped
search	string	No	Search by job name or description
limit	integer	No	Number of results to return (default: 20)
offset	integer	No	Number of results to skip (default: 0)
sort	string	No	Sort field and direction, e.g. createdAt:desc

Response 200 OK

{
  "count": 10,
  "limit": 20,
  "offset": 0,
  "jobs": [
    {
      "id": "aml_abc123",
      "name": "Churn Prediction Model",
      "status": "running",
      "description": "Predicting customer churn from usage and billing data",
      "dataset": "ds_customers_001",
      "problemType": "binary_classification",
      "predictorType": "tabular",
      "owner": "user_456",
      "organizationId": "org_xyz",
      "targetColumn": "churned",
      "preset": "best_quality",
      "startedAt": "2025-02-01T10:00:00Z",
      "finishedAt": null,
      "createdAt": "2025-02-01T09:55:00Z",
      "updatedAt": "2025-02-01T12:30:00Z"
    }
  ]
}

---

POST /api/v1/automl/jobs

Create a new AutoML job.

Scope: ml-workbench:write

Request Body

{
  "name": "Churn Prediction Model",
  "dataset": "ds_customers_001",
  "targetColumn": "churned",
  "problemType": "binary_classification",
  "predictorType": "tabular",
  "preset": "best_quality",
  "timeLimit": 3600,
  "metric": "f1",
  "featureColumns": ["usage_days", "monthly_spend", "support_tickets", "plan_type"],
  "labelColumn": "churned",
  "dataSource": "ds_postgres_main",
  "hardware": "gpu-a100-40gb",
  "advanced": {
    "excludeModels": ["KNN"],
    "enableEnsemble": true
  }
}

Field	Type	Required	Description
name	string	Yes	Human-readable job name
dataset	string	Yes	Dataset ID or path to use for training
targetColumn	string	Yes	Name of the column to predict
problemType	string	No	Problem type: binary_classification, multiclass_classification, regression, time_series. Auto-detected if omitted
predictorType	string	No	Predictor type: tabular, text, image, multimodal (default: tabular)
preset	string	No	Quality preset: best_quality, high_quality, good_quality, medium_quality (default: best_quality)
timeLimit	integer	No	Maximum training time in seconds (default: 3600)
metric	string	No	Optimization metric (e.g. f1, accuracy, rmse, auc). Auto-selected based on problem type if omitted
featureColumns	string[]	No	Specific columns to use as features. All non-target columns used if omitted
labelColumn	string	No	Label column name if different from target
dataSource	string	No	Data source ID to read the dataset from
hardware	string	No	Hardware configuration ID for the job
advanced	object	No	Advanced configuration options (excludeModels, enableEnsemble, etc.)

Response 201 Created

{
  "id": "aml_abc123",
  "name": "Churn Prediction Model",
  "status": "queued",
  "createdAt": "2025-02-01T09:55:00Z"
}

---

GET /api/v1/automl/jobs/:id

Get a single AutoML job by ID.

Scope: ml-workbench:read

Path Parameters

Parameter	Type	Required	Description
id	string	Yes	AutoML job ID

Response 200 OK

Returns the full AutoMLJob object.

---

DELETE /api/v1/automl/jobs/:id

Delete an AutoML job. Running jobs must be stopped before deletion.

Scope: ml-workbench:write

Path Parameters

Parameter	Type	Required	Description
id	string	Yes	AutoML job ID

Response 204 No Content

---

POST /api/v1/automl/jobs/:id/stop

Stop a running AutoML job. The job will be marked as stopped and training will be terminated.

Scope: ml-workbench:write

Path Parameters

Parameter	Type	Required	Description
id	string	Yes	AutoML job ID

Response 200 OK

{
  "id": "aml_abc123",
  "status": "stopped",
  "message": "AutoML job stopped successfully"
}

---

POST /api/v1/automl/jobs/:id/deploy

Deploy the best model from a completed AutoML job. Makes the model available for inference via the model registry.

Scope: ml-workbench:write

Path Parameters

Parameter	Type	Required	Description
id	string	Yes	AutoML job ID

Response 200 OK

{
  "id": "aml_abc123",
  "modelId": "model_xyz789",
  "modelName": "Churn Prediction Model - Best",
  "status": "deployed",
  "message": "Best model deployed successfully"
}

---

GET /api/v1/automl/jobs/:id/logs

Retrieve training logs for an AutoML job.

Scope: ml-workbench:read

Path Parameters

Parameter	Type	Required	Description
id	string	Yes	AutoML job ID

Query Parameters

Parameter	Type	Required	Description
lines	integer	No	Number of log lines to return (default: 100)
since	string	No	Return logs after this ISO 8601 timestamp

Response 200 OK

{
  "jobId": "aml_abc123",
  "logs": [
    {
      "timestamp": "2025-02-01T10:00:05Z",
      "level": "info",
      "message": "AutoML job started - problem type: binary_classification"
    },
    {
      "timestamp": "2025-02-01T10:02:15Z",
      "level": "info",
      "message": "Feature engineering completed - 12 features generated"
    },
    {
      "timestamp": "2025-02-01T10:15:30Z",
      "level": "info",
      "message": "Model training: LightGBM completed - f1: 0.891"
    }
  ]
}

---

GET /api/v1/automl/stats

Get aggregate statistics for AutoML jobs in the organization.

Scope: ml-workbench:read

Response 200 OK

{
  "total": 10,
  "running": 1,
  "completed": 6,
  "failed": 2,
  "queued": 1
}

---

GET /api/v1/automl/datasets

List available datasets that can be used for AutoML jobs.

Scope: ml-workbench:read

Response 200 OK

{
  "datasets": [
    {
      "id": "ds_customers_001",
      "name": "Customer Data Q4 2024",
      "rows": 150000,
      "columns": 24,
      "sizeBytes": 45000000,
      "format": "csv",
      "createdAt": "2025-01-10T08:00:00Z"
    },
    {
      "id": "ds_transactions_002",
      "name": "Transaction History",
      "rows": 2500000,
      "columns": 18,
      "sizeBytes": 320000000,
      "format": "parquet",
      "createdAt": "2025-01-12T14:30:00Z"
    }
  ]
}