SIENTIAPDE-1182

Update README.md to reflect new prediction workflow configuration

- Revised input parameters for the prediction process, including changes to schedule name, model ID, and workflow type.
- Introduced new fields for workflow execution frequency, maximum retry policy, and query for data retrieval.
- Updated input and MLflow filter structures to enhance clarity and functionality.
- Added support for datetime columns and updated retention time for models.
This commit is contained in:
vitor-aignosi
2025-08-29 15:28:51 -03:00
parent 995ba7900a
commit cda94a3850

View File

@@ -314,34 +314,71 @@ The **PredictionProcess** workflow implements the core prediction pipeline for M
#### Input Parameters
```json
{
"metadata": {
"schedule_name": "hourly_predictions",
"model_name": "temperature_prediction_model",
"model_id": "temp_pred_001",
"workflow_name": "predictions_batch"
"schedule_name": "laborious-orchestrated-pipeline",
"model_id": "1",
"workflow_type": "predictions_batch",
"frequency": "30s", # Workflow execution frequency
"max_retry_policy": 1, # Maximum number of retries for the workflow
"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, # Retention time for models in minutes
"write_tags": [
{
"server_id": "1",
"type": "prediction", # Type of tag to write, can be prediction or confidence
"addr": "ns=2;i=5",
"data_type": "double"
},
"data": {...},
"schema": {...},
"table_name": "predictions",
"model_id": "temp_pred_001",
"model_name": "temperature_prediction_model",
"input_filters": {
"EMPTY_DATA": {"POLICY": "STOP"},
"SPECIFIC_VARIABLES_NULL_VALUES": {
"POLICY": "STOP",
"config": {"variables": ["temperature", "humidity"]}
{
"server_id": "1",
"type": "confidence",
"addr": "ns=2;i=5",
"data_type": "double"
}
],
"input_filters": [
{
"filter_name": "EMPTY_DATA", # Required filter
"policy": "STOP"
},
"mlflow_transform_filters": {
"API_ERROR": {"POLICY": "STOP"}
{
"filter_name": "SPECIFIC_VARIABLES_NULL_VALUES",
"policy": "CONTINUE",
"config": {
"variables": [
"Counter"
]
}
}
],
"mlflow_transform_filters": [
{
"filter_name": "API_ERROR", # Required filter
"policy": "REPEAT"
},
"mlflow_predict_filters": {
"API_ERROR": {"POLICY": "STOP"},
"NAN_VALUES": {"POLICY": "STOP"}
},
"model_retention": 60,
"path_priority": ["STOP", "CONTINUE", "REPEAT"],
"opc_output_config": {...}
{
"filter_name": "NAN_VALUES",
"policy": "STOP"
}
],
"mlflow_predict_filters": [
{
"filter_name": "API_ERROR", # Required filter
"policy": "CONTINUE"
}
],
"path_priority": [ # In case of multiple filters catch problems, this will determine the path to take
"STOP",
"CONTINUE",
"REPEAT"
],
"active": true,
"datetime_columns": [ # Columns in data comming from query that are datetime
"timestamp",
"created_at"
],
"updated_at": {
"$date": "2025-08-27T18:35:01.600Z"
}
}
```