← All resources

Resource

ml_model_config

ML model configuration for training pipelines

GraphQL reference →

Configuration

sourceml_model_documentRequired

Machine learning model document, including its data pipeline.

ml_model_document fields

Open model reference →

ML configuration. Training data and operational state are not part of this document.

object
autoPublishOptional
boolean
backendOptional
string
Pattern
"^([xX][gG][bB][oO][oO][sS][tT]|[aA][uU][gG][uU][rR][sS])$"
dataQuerySQLOptional
descriptionOptional
formatRequired
string
Allowed values
["1"]
nameRequired
string
Pattern
"^[a-z][a-z0-9_-]{0,63}$"
specOptional
object
tabularOptional
timeSeriesOptional

Only the fields listed here are accepted.

All of these apply
Choose exactly one shape
specRequired
tabularRequired
specRequired
timeSeriesRequired

Only the fields listed here are accepted.

publishedVersionIdMLModelConfigVersionIDOptional

ID of the version currently used for predictions

written by `publishMLModelVersion`, not by this resource's update

Read-only values

Show values
authoringRevisionInt!Read only

Monotonic source/configuration revision used to reject stale authoring updates; independent of trained model versions.

computed by the platform

idMLModelConfigID!Read only

Unique identifier

computed by the platform

tenantIdTenantID!Read only

Tenant this config belongs to

computed by the platform

nameString!Read only

Config name

computed by the platform

descriptionStringRead only

Config description

computed by the platform

modelTypeMLModelType!Read only

Type of ML model

Allowed values

REGRESSION — Regression model (predicts numeric values)

CLASSIFICATION — Classification model (predicts categories)

FORECAST — Time-series forecast model (predicts future values over a horizon)

computed by the platform

backendMLBackend!Read only

Engine that trains/serves this model

Allowed values

XGBOOST — XGBoost gradient-boosted trees (tabular regression/classification)

AUGURS — Augurs time-series engine (forecasting)

computed by the platform

dataQuerySQLStringRead only

MicroSQL query for data retrieval. Each SQL page has a 30-second statement timeout; preview sampling does not limit the full training query.

computed by the platform

specMLModelSpec!Read only

Concept-specific configuration (tabular or time-series)

computed by the platform

statusMLModelTrainingStatus!Read only

Status of the latest training run. A published version remains available for serving while retraining or after a failed run.

Allowed values

IDLE — Created but never trained

TRAINING — Currently training

TRAINED — Successfully trained and ready for predictions

FAILED — Last training attempt failed

computed by the platform

trainedModelIDStringRead only

Blob storage key for the trained model

computed by the platform

lastTrainedAtStringRead only

When the model was last trained (ISO8601)

computed by the platform

trainingDurationMsIntRead only

Duration of last training run in milliseconds

computed by the platform

trainingMetricsTrainingMetricsRead only

Metrics from last training run

computed by the platform

trainingErrorStringRead only

Error message if last training failed; SQL source pages have a 30-second statement timeout

computed by the platform

featureImportance[MLFeatureImportance!]Read only

Feature importance from trained model

computed by the platform

evaluationHistory[MLEvaluationEntry!]Read only

Per-round evaluation history

computed by the platform

csvFilenameStringRead only

Original CSV filename (if CSV data source)

computed by the platform

csvSizeBytesIntRead only

Size of uploaded CSV in bytes

computed by the platform

hasTrainingCSVBoolean!Read only

Whether a CSV file has been uploaded as training data

computed by the platform

csvPreviewRows[[String!]!]Read only

First few rows of CSV data for preview (header + up to 10 rows)

computed by the platform

inferenceSchemaStringRead only

JSON Schema describing the model's input features (types, enum values). Generated after training.

computed by the platform

emittedSchema[MLEmittedColumn!]Read only

The pipeline's emitted columns + types (cached from the last preview of the saved config)

computed by the platform

publishedVersionNumberIntRead only

Version number of the published version (e.g. 1, 2, 3)

computed by the platform

autoPublishBoolean!Read only

Whether new versions are automatically published after training

computed by the platform

isSystemBoolean!Read only

Whether this model is system-managed (auto-created and auto-retrained by the platform)

computed by the platform

createdAtString!Read only

Creation timestamp (ISO8601)

computed by the platform

updatedAtString!Read only

Last update timestamp (ISO8601)

computed by the platform

Lifecycle

The CLI can create this resource. The platform assigns its id.

When replacement is needed, the existing resource is removed before its replacement is created.