Update .gitignore and input_sample.json for improved configuration management - Added new patterns to .gitignore to exclude 'mlruns/', 'relatorio*', and 'openspec/*' directories from version control. - Updated the 'updated_at' date in input_sample.json to reflect a new timestamp for better tracking of schedule states.
144 lines
3.7 KiB
JSON
144 lines
3.7 KiB
JSON
{
|
|
"models": [
|
|
{
|
|
"id": "1001",
|
|
"name": "test-runtime",
|
|
"active": false,
|
|
"model_config": {
|
|
"alias": "production",
|
|
"retention_minutes": 60,
|
|
"target": "Square"
|
|
}
|
|
}
|
|
],
|
|
"pipelines": [
|
|
{
|
|
"schedule_name": "laborious-test-runtime",
|
|
"model_id": "1001",
|
|
"workflow_type": "predictions_batch",
|
|
"frequency": "60s",
|
|
"max_retry_policy": 1,
|
|
"query": "select * from sientia_data.laborious_data where model_id = 1 and \"timestamp\" > NOW() - INTERVAL '5 minutes' order by \"timestamp\" desc limit 30;",
|
|
"retention_time": 60,
|
|
"write_tags": [],
|
|
"input_filters": [
|
|
{
|
|
"filter_name": "EMPTY_DATA",
|
|
"policy": "STOP"
|
|
},
|
|
{
|
|
"filter_name": "SPECIFIC_VARIABLES_NULL_VALUES",
|
|
"policy": "CONTINUE",
|
|
"config": {
|
|
"variables": [
|
|
"Counter"
|
|
]
|
|
}
|
|
}
|
|
],
|
|
"mlflow_transform_filters": [
|
|
{
|
|
"filter_name": "API_ERROR",
|
|
"policy": "REPEAT"
|
|
},
|
|
{
|
|
"filter_name": "NAN_VALUES",
|
|
"policy": "STOP"
|
|
}
|
|
],
|
|
"mlflow_predict_filters": [
|
|
{
|
|
"filter_name": "API_ERROR",
|
|
"policy": "CONTINUE"
|
|
}
|
|
],
|
|
"path_priority": [
|
|
"STOP",
|
|
"CONTINUE",
|
|
"REPEAT"
|
|
],
|
|
"active": true,
|
|
"updated_at": {
|
|
"$date": "2026-05-07T23:35:01.600Z"
|
|
},
|
|
"save_transform": false,
|
|
"pi_web_api_output_config": {},
|
|
"datetime_columns": [
|
|
"timestamp",
|
|
"created_at"
|
|
]
|
|
},
|
|
{
|
|
"schedule_name": "minimal-retrain-test-runtime",
|
|
"model_id": "1001",
|
|
"model_name": "test-runtime",
|
|
"workflow_type": "minimal_retrain",
|
|
"frequency": "1h",
|
|
"max_retry_policy": 1,
|
|
"query": "select * from sientia_data.laborious_data where model_id = 1 and \"timestamp\" > NOW() - INTERVAL '60 minutes' order by \"timestamp\" desc;",
|
|
"schema": "sientia_data",
|
|
"table_name": "log_retrain",
|
|
"datetime_columns": ["timestamp", "created_at"],
|
|
"model_config": {
|
|
"target": "Square"
|
|
},
|
|
"active": true,
|
|
"updated_at": {
|
|
"$date": "2026-05-07T23:35:01.600Z"
|
|
}
|
|
},
|
|
{
|
|
"schedule_name": "drift-test-runtime",
|
|
"model_id": "1001",
|
|
"model_name": "test-runtime",
|
|
"workflow_type": "drift",
|
|
"frequency": "5m",
|
|
"offset": "2m",
|
|
"max_retry_policy": 1,
|
|
"execution_timeout_seconds": 300,
|
|
"task_timeout_seconds": 300,
|
|
"interval": 5,
|
|
"drift_metrics": [
|
|
"kolmogorov_smirnov",
|
|
"jensen_shannon",
|
|
"wasserstein"
|
|
],
|
|
"chunk_period": "min",
|
|
"schema": "sientia_data",
|
|
"source_table_name": "laborious_data",
|
|
"target_table_name": "drift_metrics",
|
|
"model_config": {
|
|
"target": "Square"
|
|
},
|
|
"active": true,
|
|
"updated_at": {
|
|
"$date": "2026-05-07T23:35:01.600Z"
|
|
}
|
|
},
|
|
{
|
|
"schedule_name": "simple-metrics-test-runtime",
|
|
"model_id": "1001",
|
|
"model_name": "test-runtime",
|
|
"workflow_type": "simple_metrics",
|
|
"frequency": "5m",
|
|
"offset": "2m",
|
|
"max_retry_policy": 1,
|
|
"execution_timeout_seconds": 300,
|
|
"task_timeout_seconds": 300,
|
|
"interval_minutes": 5,
|
|
"metrics": ["rmse", "mse", "mae", "r2"],
|
|
"schema": "sientia_data",
|
|
"predictions_table_name": "predictions",
|
|
"data_table_name": "laborious_data",
|
|
"target_table_name": "simple_metrics",
|
|
"model_config": {
|
|
"target": "Square"
|
|
},
|
|
"active": true,
|
|
"updated_at": {
|
|
"$date": "2026-05-18T23:35:01.600Z"
|
|
}
|
|
}
|
|
]
|
|
}
|