Code import - branch release/SIENTIAPDE-1646

This commit is contained in:
2026-08-05 13:53:38 +00:00
commit a8e89535ee
106 changed files with 24108 additions and 0 deletions

View File

View File

@@ -0,0 +1,107 @@
from temporalio import workflow
with workflow.unsafe.imports_passed_through():
from datetime import timedelta
from typing import Any
from sientia_do.temporal.constants import DATETIME_FORMAT_WITH_TZ
from sientia_do.temporal.policies import retry_policy
from laborious.activities.activities import Activities
@workflow.defn(name='drift')
class Drift:
@workflow.run
async def run(self, input_data: dict[str, Any]):
"""
Execute the drift workflow.
This method orchestrates the complete drift process by:
1. Loading data using the provided custom SQL query
2. Preparing prediction configuration and filters
3. Delegating to the PredictionProcess workflow for ML operations
"""
metadata = {
'metadata': {
'schedule_name': input_data['schedule_name'],
'model_name': input_data['model_name'],
'model_id': input_data['model_id'],
'workflow_name': 'drift',
}
}
print(f'Input data: {input_data}', metadata)
model_config = input_data['model_config']
target_name = model_config['target']
gathering_query = f"""
SELECT *
FROM "{input_data['schema']}"."{input_data['source_table_name']}"
WHERE
model_id = '{input_data['model_id']}' AND
timestamp > NOW() - INTERVAL '{input_data['interval']} minutes'
ORDER BY timestamp ASC
""" # nosec B608 - values come from internal Temporal workflow config, not user input
target_data_handler = workflow.start_activity_method(
Activities.load_custom_query,
{
**metadata,
'query': gathering_query,
'datetime_columns': ['timestamp', 'created_at'],
'orient': 'records',
},
retry_policy=retry_policy,
start_to_close_timeout=timedelta(seconds=300),
)
reference_data_handler = workflow.start_activity_method(
Activities.get_reference_data,
{**metadata, 'model_name': input_data['model_name']},
retry_policy=retry_policy,
start_to_close_timeout=timedelta(seconds=300),
)
target_data = await target_data_handler
reference_data = await reference_data_handler
if not target_data:
return
drift_data = await workflow.execute_local_activity_method(
Activities.calculate_drift,
{
**metadata,
'target_data': target_data,
'reference_data': reference_data,
'model_name': input_data['model_name'],
'model_id': input_data['model_id'],
'target_name': target_name,
'drift_metrics': input_data.get(
'drift_metrics', ['kolmogorov_smirnov', 'jensen_shannon', 'wasserstein']
),
'chunk_period': input_data.get('chunk_period', 'min'),
},
retry_policy=retry_policy,
start_to_close_timeout=timedelta(seconds=300),
)
if drift_data:
await workflow.execute_activity_method(
Activities.export_data_to_postgres,
{
**metadata,
'data': drift_data,
'schema': input_data['schema'],
'table_name': input_data['target_table_name'],
'timestamp_conversion': {
'column': 'timestamp',
'format': DATETIME_FORMAT_WITH_TZ,
},
},
retry_policy=retry_policy,
start_to_close_timeout=timedelta(seconds=300),
)

View File

@@ -0,0 +1,137 @@
from temporalio import workflow
with workflow.unsafe.imports_passed_through():
from datetime import timedelta
from typing import Any
from sientia_do.temporal.policies import retry_policy
from laborious.activities.activities import Activities
from laborious.utils.models.minio_dataframe_payload import MinioDataFramePayload
@workflow.defn(name='minimal_retrain')
class MinimalRetrain:
"""
Automated model retraining workflow for the Laborious system.
This workflow implements a complete model retraining pipeline that loads
training data, executes model retraining, updates production models,
and maintains comprehensive audit trails. It's designed for automated
model lifecycle management with minimal manual intervention.
The workflow provides a robust retraining process with:
- Automated data loading from configured data sources
- MLFlow model retraining with quality validation
- Production model updates with version control
- Comprehensive reporting and audit trail maintenance
- Error handling and notification integration
"""
@workflow.run
async def run(self, input_data: dict[str, Any]):
"""
Execute the automated model retraining workflow.
This method orchestrates the complete model retraining process by:
1. Loading training data using the provided custom SQL query
2. Executing MLFlow model retraining with the loaded data
3. Updating production models with newly trained versions
4. Persisting comprehensive retraining reports to database
The method implements comprehensive error handling and ensures all
required parameters are properly configured before proceeding.
Args:
input_data: Complete configuration for the retraining workflow
Required keys:
- schedule_name (str): Schedule identifier for the retraining
- model_name (str): Name of the ML model to retrain
- model_id (int): Unique identifier for the model version
- query (str): SQL query for training data loading
- schema (str, optional): Database schema for report storage
- table_name (str, optional): Target table for retraining reports
- datetime_columns (list[str], optional): Columns to treat as datetime
Returns:
None: The workflow completes successfully when all steps finish
Raises:
Exception: If any required parameters are missing or if the workflow fails
during data loading, retraining, or model update operations
"""
metadata = {
'metadata': {
'schedule_name': input_data['schedule_name'],
'model_name': input_data['model_name'],
'model_id': input_data['model_id'],
'workflow_name': 'minimal_retrain',
}
}
model_name = input_data['model_name']
model_config = input_data.get('model_config', {})
storage_result = await workflow.execute_activity_method(
Activities.load_query_with_minio_offload,
{
**metadata,
'query': input_data['query'],
'datetime_columns': input_data.get('datetime_columns', []),
'model_name': model_name,
},
retry_policy=retry_policy,
start_to_close_timeout=timedelta(seconds=600),
)
storage_payload = MinioDataFramePayload.from_dict(storage_result)
if not storage_payload.has_data():
raise ValueError('No data returned from query')
experiment_response = await workflow.execute_activity_method(
Activities.retrain_model,
{
**metadata,
'data': storage_result,
'model_name': model_name,
'model_config': model_config,
},
retry_policy=retry_policy,
start_to_close_timeout=timedelta(hours=1),
)
if experiment_response['success']:
update_report = await workflow.execute_activity_method(
Activities.update_production_model,
{**metadata, 'model_name': model_name, **experiment_response},
retry_policy=retry_policy,
start_to_close_timeout=timedelta(seconds=60),
)
else:
update_report = {}
report = await workflow.execute_local_activity_method(
Activities.format_retrain_report,
{
**metadata,
'experiment_response': experiment_response,
'model_name': model_name,
'model_id': input_data['model_id'],
'update_report': update_report,
},
retry_policy=retry_policy,
start_to_close_timeout=timedelta(seconds=60),
)
await workflow.execute_activity_method(
Activities.export_data_to_postgres,
{
**metadata,
'data': report,
'schema': input_data['schema'],
'table_name': input_data['table_name'],
},
retry_policy=retry_policy,
start_to_close_timeout=timedelta(seconds=600),
)

View File

@@ -0,0 +1,127 @@
from temporalio import workflow
with workflow.unsafe.imports_passed_through():
from datetime import timedelta
from typing import Any
from sientia_do.temporal.policies import retry_policy
from laborious.activities.activities import Activities
@workflow.defn(name='predictions_batch')
class PredictionsBatch:
"""
Main batch prediction workflow for the Laborious system.
This workflow orchestrates the complete batch prediction process, handling
data loading, configuration management, and workflow delegation. It serves
as the primary entry point for batch prediction operations and ensures
proper data preparation before ML model inference.
The workflow implements a robust data processing pipeline with:
- Custom SQL query execution for data loading
- Comprehensive configuration management
- Data quality filter application
- MLFlow model integration
- Workflow delegation to specialized sub-workflows
Workflow Execution:
1. Data Loading: Executes custom SQL query to load prediction data
2. Configuration Preparation: Sets up prediction parameters and filters
3. Workflow Delegation: Spawns PredictionProcess child workflow
4. Error Handling: Implements comprehensive error handling and retry policies
"""
@workflow.run
async def run(self, input_data: dict[str, Any]):
"""
Execute the batch prediction workflow.
This method orchestrates the complete batch prediction process by:
1. Loading data using the provided custom SQL query
2. Preparing prediction configuration and filters
3. Delegating to the PredictionProcess workflow for ML operations
The method implements comprehensive error handling and ensures all
required parameters are properly configured before proceeding.
Args:
input_data: Complete configuration for the batch prediction
Required keys:
- schedule_name (str): Schedule identifier for the prediction
- model_name (str): Name of the ML model to use
- model_id (int): Unique identifier for the model
- query (str): SQL query for data loading
- schema (dict, optional): Data schema definition
- table_name (str, optional): Target table for predictions
- input_filters (dict, optional): Data quality filters
- mlflow_transform_filters (dict, optional): MLFlow transform filters
- mlflow_predict_filters (dict, optional): MLFlow prediction filters
- model_retention (int, optional): Model retention period in minutes
- path_priority (list[str]): Decision path priority configuration
- opc_output_config (dict, optional): OPC server export configuration
- pi_web_api_output_config (dict, optional): PI Web API export configuration
- datetime_columns (list[str], optional): Columns to treat as datetime
- save_transform (bool, optional): Whether to save transformed data (default: True)
- prediction_store_policy (str, optional): Data retention policy (default: 'lts:1')
Returns:
None: The workflow completes successfully when the child workflow finishes
Raises:
Exception: If any required parameters are missing or if the workflow fails
during data loading or workflow delegation
"""
metadata = {
'metadata': {
'schedule_name': input_data['schedule_name'],
'model_name': input_data['model_name'],
'model_id': input_data['model_id'],
'workflow_name': 'predictions_batch',
}
}
# Load data using custom query with optional MinIO offload for large frames
data = await workflow.execute_activity_method(
Activities.load_query_with_minio_offload,
{
**metadata,
'query': input_data['query'],
'datetime_columns': input_data.get('datetime_columns', []),
'model_name': input_data['model_name'],
},
retry_policy=retry_policy,
start_to_close_timeout=timedelta(seconds=300),
)
# Prepare input for prediction_process workflow
prediction_input = {
'metadata': metadata,
'data': data,
'schema': input_data['schema'],
'table_name': input_data['table_name'],
'transform_table_name': input_data['transform_table_name'],
'model_id': input_data['model_id'],
'model_name': input_data['model_name'],
'input_filters': input_data.get(
'input_filters', {'EMPTY_DATA': {'POLICY': 'STOP', 'CONFIG': {}}}
),
'mlflow_transform_filters': input_data.get(
'mlflow_transform_filters', {'API_ERROR': {'POLICY': 'STOP', 'CONFIG': {}}}
),
'mlflow_predict_filters': input_data.get(
'mlflow_predict_filters', {'API_ERROR': {'POLICY': 'STOP', 'CONFIG': {}}}
),
'model_config': input_data.get('model_config', {}),
'path_priority': input_data.get('path_priority', ['STOP', 'CONTINUE', 'REPEAT']),
'opc_output_config': input_data.get('opc_output_config', {}),
'on_conflict': input_data.get('on_conflict', 'error'),
'pi_web_api_output_config': input_data.get('pi_web_api_output_config', {}),
'prediction_store_policy': input_data.get('prediction_store_policy', 'lts:1'),
'save_transform': input_data.get('save_transform', True),
}
# Execute prediction process workflow
await workflow.execute_child_workflow('subworkflow.prediction_process', prediction_input)

View File

@@ -0,0 +1,95 @@
from temporalio import workflow
with workflow.unsafe.imports_passed_through():
from datetime import timedelta
from typing import Any
from sientia_do.temporal.constants import DATETIME_FORMAT_WITH_TZ
from sientia_do.temporal.policies import retry_policy
from laborious.activities.activities import Activities
@workflow.defn(name='simple_metrics')
class SimpleMetrics:
@workflow.run
async def run(self, input_data: dict[str, Any]):
"""
Execute the simple metrics workflow.
"""
metadata = {
'metadata': {
'model_id': input_data['model_id'],
'model_name': input_data['model_name'],
'workflow_name': 'simple_metrics',
'schedule_name': input_data['schedule_name'],
}
}
model_id = input_data['model_id']
interval_minutes = input_data['interval_minutes']
model_config = input_data['model_config']
target_name = model_config['target']
query = f"""
select p."timestamp", p.prediction, ld.value as "target"
from "{input_data['schema']}"."{input_data['predictions_table_name']}" p
inner join "{input_data['schema']}"."{input_data['data_table_name']}" ld
on p."timestamp" = ld."timestamp"
where
p.model_id = '{model_id}' and
p.prediction is not null and
ld.variable = '{target_name}' and
ld.value is not null and
p."timestamp" >= NOW() - INTERVAL '{interval_minutes} minutes'
order by
p."timestamp" desc;
""" # nosec B608 - values come from internal Temporal workflow config, not user input
target_data = await workflow.execute_activity_method(
Activities.load_custom_query,
{
**metadata,
'query': query,
'datetime_columns': ['timestamp'],
'orient': 'records',
},
retry_policy=retry_policy,
start_to_close_timeout=timedelta(seconds=300),
)
if not target_data:
return
simple_metrics = await workflow.execute_local_activity_method(
Activities.calculate_simple_metrics,
{
**metadata,
'model_id': model_id,
'target_data': target_data,
'metrics': input_data.get('metrics', ['rmse', 'mse', 'mae', 'r2']),
'interval_minutes': interval_minutes,
},
retry_policy=retry_policy,
start_to_close_timeout=timedelta(seconds=300),
)
if not simple_metrics:
return
await workflow.execute_activity_method(
Activities.export_data_to_postgres,
{
**metadata,
'data': simple_metrics,
'schema': input_data['schema'],
'table_name': input_data['target_table_name'],
'timestamp_conversion': {
'column': 'timestamp',
'format': DATETIME_FORMAT_WITH_TZ,
},
},
retry_policy=retry_policy,
start_to_close_timeout=timedelta(seconds=300),
)

View File

@@ -0,0 +1,220 @@
from temporalio import workflow
with workflow.unsafe.imports_passed_through():
from datetime import timedelta
from typing import Any
from sientia_do.temporal.constants import DATETIME_FORMAT_WITH_TZ
from sientia_do.temporal.policies import retry_policy
from laborious.activities.activities import Activities
@workflow.defn(name='subworkflow.format_and_export_prediction')
class FormatAndExportPrediction:
"""
Data formatting and export workflow for prediction results.
This workflow handles the final stages of the prediction pipeline, including
data formatting, database persistence, OPC server export, and metrics recording.
It implements flexible formatting based on prediction quality and provides
comprehensive export capabilities to multiple destinations.
The workflow supports two main prediction paths:
1. Normal Prediction: Formats and exports successful prediction results
2. Default Prediction: Creates fallback predictions for error conditions
Export Destinations:
- PostgreSQL Database: Persistent storage with timestamp conversion
- PI Web API: Real-time industrial system integration for prediction and confidence values
- OPC Servers: Real-time industrial system integration
- Prometheus Metrics: Performance monitoring and operational visibility
"""
@workflow.run
async def run(self, input_data: dict[str, Any]):
"""
Execute the prediction formatting and export workflow.
This method orchestrates the complete data export process by:
1. Determining the appropriate formatting strategy based on path_flag
2. Formatting prediction data according to quality and requirements
3. Exporting data to PI Web API for real-time industrial access (if configured)
4. Exporting data to OPC servers for real-time industrial access (if configured)
5. Persisting data to PostgreSQL database with comprehensive metadata
6. Recording performance metrics for operational monitoring
The method implements flexible formatting strategies:
- Normal predictions: Full data formatting with confidence scores
- Error predictions: Default formatting with error indicators
- Comprehensive export: Multi-destination data distribution
Args:
input_data: Complete configuration for the export workflow
Required keys:
- metadata (dict): Workflow execution metadata
- path_flag (str | None): Decision path flag for formatting strategy
- None: Normal prediction path with full formatting
- Any other value: Default prediction path for error conditions
- data (dict[str, Any]): Prediction data to format and export
- prediction_confidence (float): Confidence score for the prediction
- timestamp (str): ISO-formatted timestamp for the prediction
- model_id (int): Unique identifier for the ML model
- model_name (str): Name of the ML model
- schema (str): Database schema for data storage
- table_name (str): Target table for data persistence
Optional keys:
- opc_output_config (dict[str, Any]): OPC server export configuration
- pi_web_api_output_config (dict[str, Any]): PI Web API export configuration
Contains endpoint, prediction_tags, and confidence_tags mappings
- transformed_data (dict[str, Any]): Transformed data to export separately
Only processed when path_flag is None
- transform_table_name (str): Target table for transformed data export
Required if transformed_data is provided
- prediction_store_policy (str): Data retention policy (e.g., 'lts:1', 'erl:2')
Required when path_flag is None
- comment (str): Operational comment or error description
Required when path_flag is not None
Returns:
None: The workflow completes successfully when all export operations finish
Note:
When transformed_data is provided and path_flag is None, the workflow will:
1. Format the transformed data using format_transformed_data
2. Export it to a separate table (transform_table_name) asynchronously
3. Wait for both prediction and transformed data exports to complete
"""
metadata = input_data['metadata']
path_flag = input_data['path_flag']
data = input_data['data']
transformed_data = input_data.get('transformed_data', None)
prediction_confidence = input_data['prediction_confidence']
opc_output_config = input_data.get('opc_output_config', None)
pi_web_api_output_config = input_data.get('pi_web_api_output_config', None)
if path_flag is None:
# Normal prediction path: format prediction data with full metadata
prediction = await workflow.execute_local_activity_method(
Activities.format_prediction,
{
**metadata,
'data': data,
'timestamp': input_data['timestamp'],
'model_id': input_data['model_id'],
'prediction_confidence': prediction_confidence,
'prediction_store_policy': input_data['prediction_store_policy'],
'model_name': input_data['model_name'],
},
retry_policy=retry_policy,
start_to_close_timeout=timedelta(seconds=60),
)
# Optionally format and export transformed data to separate table
if transformed_data is not None:
transformed = await workflow.execute_local_activity_method(
Activities.format_transformed_data,
{
**metadata,
'data': transformed_data,
'model_id': input_data['model_id'],
'model_name': input_data['model_name'],
},
retry_policy=retry_policy,
start_to_close_timeout=timedelta(seconds=60),
)
write_transformed_handler = workflow.start_activity_method(
Activities.export_payload_to_postgres,
{
**metadata,
'schema': input_data['schema'],
'table_name': input_data['transform_table_name'],
'data': transformed,
'timestamp_conversion': {
'column': 'timestamp',
'format': DATETIME_FORMAT_WITH_TZ,
},
},
retry_policy=retry_policy,
start_to_close_timeout=timedelta(seconds=60),
)
else:
write_transformed_handler = None
else:
# Error path: create default prediction with error indicators
prediction = await workflow.execute_local_activity_method(
Activities.format_default_prediction,
{
**metadata,
'timestamp': input_data['timestamp'],
'model_id': input_data['model_id'],
'prediction_confidence': prediction_confidence,
'comment': input_data['comment'],
},
retry_policy=retry_policy,
start_to_close_timeout=timedelta(seconds=60),
)
write_transformed_handler = None
opc_metrics: dict[str, dict[str, float | None]] = {}
# write to pi web api
if pi_web_api_output_config:
prediction = await workflow.execute_activity_method(
Activities.write_pi_web_api_data,
{
'pi_web_api_output_config': pi_web_api_output_config,
'data': prediction,
**metadata,
},
retry_policy=retry_policy,
start_to_close_timeout=timedelta(seconds=60),
)
# write to opc
if opc_output_config:
prediction, opc_metrics = await workflow.execute_activity_method(
Activities.write_opc_data,
{
'opc_output_config': opc_output_config,
'data': prediction,
**metadata,
},
retry_policy=retry_policy,
start_to_close_timeout=timedelta(seconds=60),
)
# write to postgres
await workflow.execute_activity_method(
Activities.export_data_to_postgres,
{
**metadata,
'schema': input_data['schema'],
'table_name': input_data['table_name'],
'data': prediction,
'timestamp_conversion': {'column': 'timestamp', 'format': DATETIME_FORMAT_WITH_TZ},
'on_conflict': input_data.get('on_conflict', 'error'),
'unique_columns': ['model_id', 'timestamp'],
},
retry_policy=retry_policy,
start_to_close_timeout=timedelta(seconds=180),
)
if write_transformed_handler is not None:
await write_transformed_handler
await workflow.execute_activity_method(
Activities.write_metrics,
{
**metadata,
'prediction': prediction,
'opc_metrics': opc_metrics,
},
retry_policy=retry_policy,
start_to_close_timeout=timedelta(seconds=60),
)

View File

@@ -0,0 +1,346 @@
from temporalio import workflow
with workflow.unsafe.imports_passed_through():
from datetime import timedelta
from typing import Any
from sientia_do.temporal.policies import retry_policy
from laborious.activities.activities import Activities
@workflow.defn(name='subworkflow.prediction_process')
class PredictionProcess:
"""
Core prediction processing workflow for the Laborious system.
This workflow implements the complete ML model inference pipeline, handling
data quality validation, MLFlow model interactions, and prediction processing.
It serves as the central orchestrator for all prediction operations and ensures
data quality throughout the entire process.
The workflow implements a robust data processing pipeline with:
- Data quality validation using configurable filters
- MLFlow model transformation and prediction
- Response validation and quality assurance
- Flexible decision path handling
- Comprehensive error handling and retry policies
Workflow Execution:
1. Timestamp Retrieval: Gets last processed timestamp for incremental processing
2. Input Data Gate: Applies data quality filters
3. Path Decision: Determines processing path based on filter results
4. MLFlow Transform: Requests data transformation using MLFlow models
5. Response Validation: Filters transform responses for quality assurance
6. MLFlow Prediction: Executes prediction using transformed data
7. Content Validation: Filters prediction responses for final quality check
8. Export Delegation: Delegates to FormatAndExportPrediction workflow
"""
@workflow.run
async def run(self, input_data: dict[str, Any]):
"""
Execute the prediction process workflow.
This method orchestrates the complete prediction processing pipeline by:
1. Retrieving the last processed timestamp for incremental processing
2. Applying data quality filters to validate input data
3. Executing MLFlow model transformation and prediction
4. Validating all responses for quality assurance
5. Delegating to export workflow for data persistence
The method implements comprehensive error handling and ensures all
data quality requirements are met before proceeding with ML operations.
Args:
input_data: Complete configuration for the prediction process
Required keys:
- metadata (dict): Workflow execution metadata
- data (dict): Input data for prediction processing
- schema (dict): Data schema definition
- table_name (str): Target table for predictions
- model_id (str): ML model identifier
- model_name (str): ML model name
- input_filters (dict): Data quality filters
- mlflow_transform_filters (dict): MLFlow transform filters
- mlflow_predict_filters (dict): MLFlow prediction filters
- model_retention (int): Model retention period in minutes
- path_priority (list[str]): Decision path priority configuration
- opc_output_config (dict, optional): OPC server export configuration
- pi_web_api_output_config (dict, optional): PI Web API export configuration
- save_transform (bool, optional): Whether to save transformed data (default: True)
- prediction_store_policy (str, optional): Data retention policy (default: 'lts:1')
Returns:
None: The workflow completes successfully when export workflow finishes
Raises:
Exception: If any required parameters are missing or if the workflow fails
during data processing, MLFlow operations, or workflow delegation
"""
metadata = input_data['metadata']
data = input_data['data']
model_id = input_data['model_id']
model_name = input_data['model_name']
model_config = input_data.get('model_config', {})
save_transform = input_data.get('save_transform', True)
try:
await self._run_prediction_pipeline(
input_data,
metadata,
data,
model_id,
model_name,
model_config,
save_transform,
)
await workflow.execute_activity_method(
Activities.cleanup_minio_objects_expired,
{**metadata, 'data': data},
retry_policy=retry_policy,
start_to_close_timeout=timedelta(minutes=5),
)
except Exception as e:
await workflow.execute_activity_method(
Activities.cleanup_minio_objects_expired,
{**metadata, 'data': data},
retry_policy=retry_policy,
start_to_close_timeout=timedelta(minutes=5),
)
raise e
async def _run_prediction_pipeline(
self,
input_data: dict[str, Any],
metadata: dict[str, Any],
data: dict[str, Any],
model_id: str,
model_name: str,
model_config: dict[str, Any],
save_transform: bool,
) -> None:
last_timestamp = data['last_timestamp']
# Apply input data quality gates
gate_input = {
**metadata,
'filters': input_data['input_filters'],
'data': data,
'path_priority': input_data['path_priority'],
}
path_flag, confidence, comment = await workflow.execute_local_activity_method(
Activities.input_gate,
gate_input,
retry_policy=retry_policy,
start_to_close_timeout=timedelta(minutes=1),
)
# Handle path decision based on filter results
if await self.path_flag_handler(
data, path_flag, input_data, confidence, last_timestamp, comment
):
return
# Request MLFlow model transformation
transformed_data = await workflow.execute_activity_method(
Activities.request_transform,
{**metadata, 'data': data, 'model_name': model_name, 'model_config': model_config},
retry_policy=retry_policy,
start_to_close_timeout=timedelta(minutes=5),
)
# Validate MLFlow transform response
path_flag, confidence, comment = await workflow.execute_local_activity_method(
Activities.mlflow_response_gate,
{
**metadata,
'filters': input_data['mlflow_transform_filters'],
'data': transformed_data,
'type': 'transform',
'path_priority': input_data['path_priority'],
},
retry_policy=retry_policy,
start_to_close_timeout=timedelta(minutes=1),
)
# Handle path decision based on transform validation
if await self.path_flag_handler(
data, path_flag, input_data, confidence, last_timestamp, comment
):
return
path_flag, confidence, comment = await workflow.execute_local_activity_method(
Activities.mlflow_content_gate,
{
**metadata,
'filters': input_data['mlflow_transform_filters'],
'data': transformed_data,
'type': 'transform',
'path_priority': input_data['path_priority'],
},
retry_policy=retry_policy,
start_to_close_timeout=timedelta(minutes=1),
)
if await self.path_flag_handler(
data, path_flag, input_data, confidence, last_timestamp, comment
):
return
predicted_data = await workflow.execute_activity_method(
Activities.request_predict,
{
**metadata,
'data': transformed_data,
'model_name': model_name,
'model_config': model_config,
},
retry_policy=retry_policy,
start_to_close_timeout=timedelta(minutes=5),
)
# Validate MLFlow prediction response
path_flag, confidence, comment = await workflow.execute_local_activity_method(
Activities.mlflow_response_gate,
{
**metadata,
'filters': input_data['mlflow_predict_filters'],
'data': predicted_data,
'type': 'predict',
'path_priority': input_data['path_priority'],
},
retry_policy=retry_policy,
start_to_close_timeout=timedelta(minutes=1),
)
# Handle path decision based on prediction validation
if await self.path_flag_handler(
data, path_flag, input_data, confidence, last_timestamp, comment
):
return
# Delegate to export workflow for data persistence
await workflow.execute_child_workflow(
'subworkflow.format_and_export_prediction',
{
'metadata': metadata,
'on_conflict': input_data.get('on_conflict', 'error'),
'path_flag': path_flag,
'data': predicted_data,
'transformed_data': transformed_data if save_transform else None,
'prediction_confidence': confidence,
'timestamp': last_timestamp,
'model_id': model_id,
'model_name': model_name,
'model_config': model_config,
'opc_output_config': input_data['opc_output_config'],
'pi_web_api_output_config': input_data['pi_web_api_output_config'],
'schema': input_data['schema'],
'table_name': input_data['table_name'],
'transform_table_name': input_data['transform_table_name'],
'comment': comment,
'prediction_store_policy': input_data['prediction_store_policy'],
},
)
async def path_flag_handler(
self,
data: dict[str, Any],
path_flag: str | None,
input_data: dict,
confidence: int,
last_timestamp: str,
comment: str,
) -> bool:
"""
Handle path decisions based on filter results and confidence levels.
This method determines the appropriate action based on the path flag
returned by data quality filters. It can stop processing, continue,
or repeat operations based on the configured path priority.
Args:
data: Input data for processing
path_flag: Path decision from filter (STOP, CONTINUE, REPEAT)
input_data: Complete workflow input configuration including:
- metadata (dict): Workflow execution metadata
- schema (str): Database schema
- table_name (str): Target table for predictions
- transform_table_name (str): Target table for transformed data
- model_id (str): ML model identifier
- model_name (str): ML model name
- model_config (dict, optional): Model configuration
- opc_output_config (dict, optional): OPC server export configuration
- pi_web_api_output_config (dict, optional): PI Web API export configuration
- prediction_store_policy (str, optional): Data retention policy
confidence: Confidence level from filter validation
last_timestamp: Last processed timestamp
comment: Additional information about the filter result
Returns:
bool: True if processing should stop, False to continue
Path Handling:
- STOP: Terminates workflow execution
- CONTINUE: Delegates to FormatAndExportPrediction workflow with current data
- REPEAT: Repeats last prediction if available
"""
metadata = input_data['metadata']
schema = input_data['schema']
table_name = input_data['table_name']
transform_table_name = input_data['transform_table_name']
model_id = input_data['model_id']
model_name = input_data['model_name']
model_config = input_data.get('model_config', {})
path_flag = path_flag.upper() if path_flag else ''
if path_flag == 'STOP':
# Stop processing and exit workflow
return True
elif path_flag == 'REPEAT':
# Repeat last prediction if available
await workflow.execute_activity_method(
Activities.repeat_last_prediction,
{
**metadata,
'schema': schema,
'table_name': table_name,
'model': model_id,
'last_timestamp': last_timestamp,
},
retry_policy=retry_policy,
start_to_close_timeout=timedelta(minutes=1),
)
return True
elif path_flag == 'CONTINUE':
# call write workflow
await workflow.execute_child_workflow(
'subworkflow.format_and_export_prediction',
{
'metadata': metadata,
'path_flag': path_flag,
'data': data,
'prediction_confidence': confidence,
'timestamp': last_timestamp,
'model_id': model_id,
'model_name': model_name,
'model_config': model_config,
'schema': schema,
'table_name': table_name,
'transform_table_name': transform_table_name,
'comment': comment,
'opc_output_config': input_data['opc_output_config'],
'pi_web_api_output_config': input_data['pi_web_api_output_config'],
'prediction_store_policy': input_data['prediction_store_policy'],
'on_conflict': input_data.get('on_conflict', 'error'),
},
)
return True
return False