UpsertMLModelConfigInput
Input for creating or updating an ML model config
Fields
ID for update; omit for create
Config name (lowercase, hyphens, underscores)
Config description (optional)
Engine override; omit to use the default for the spec's concept
Possible values (2)
XGBOOSTXGBoost gradient-boosted trees (tabular regression/classification)
AUGURSAugurs time-series engine (forecasting)
MicroSQL query for data retrieval. Each SQL page has a 30-second statement timeout; preview sampling does not limit the full training query.
Concept-specific configuration — provide exactly one of tabular/timeSeries
Set to true to remove uploaded CSV training data
Whether new versions are automatically published (default true)
Referenced by (1)
Exact type SDL
"""Input for creating or updating an ML model config"""
input UpsertMLModelConfigInput {
"""ID for update; omit for create"""
id: MLModelConfigID
"""Config name (lowercase, hyphens, underscores)"""
name: String!
"""Config description (optional)"""
description: String
"""Engine override; omit to use the default for the spec's concept"""
backend: MLBackend
"""
MicroSQL query for data retrieval. Each SQL page has a 30-second statement timeout; preview sampling does not limit the full training query.
"""
dataQuerySQL: String
"""
Concept-specific configuration — provide exactly one of tabular/timeSeries
"""
spec: MLModelSpecInput!
"""Set to true to remove uploaded CSV training data"""
clearTrainingCSV: Boolean
"""Whether new versions are automatically published (default true)"""
autoPublish: Boolean
}