Files
sientia-dataops-model-manager/model_manager/activities/activities.py
Bruno Domingues dfc190c818 SIENTIAPDE-1243: Refactor and enhance model manager activities and workflows
This commit includes several changes:

- Reorganized imports and class inheritance in activities.py, gates.py and mlflow.py for better readability and maintainability.
- Improved error handling and logging in gates.py and mlflow.py.
- Added input validation and filtering in gates.py to ensure data quality.
- Enhanced prediction formatting and storage policy management in gates.py.
- Updated metrics.py to use consistent naming conventions and labels.
- Refactored connectors_config.py to use type hints and improve code clarity.
- Updated conditional and MLFlow filters for better data quality checks.
- Improved model repository logic for retraining and updating models.
- Enhanced worker.py to include SDK metrics and improved error handling.
- Refactored workflows for better modularity and error handling.
- Updated tests to reflect the changes and improve test coverage.
2025-10-01 17:28:57 -03:00

96 lines
3.7 KiB
Python

from temporalio import workflow
with workflow.unsafe.imports_passed_through():
from typing import Any
from sientia_do.notifications.handlers import CoreNotificationHandler as NotificationHandler
from sientia_do.observability.logger import Logger
from sientia_do.temporal.activities.postgres import Postgres
from model_manager.activities.gates import Gates
from model_manager.activities.mlflow import MLFlow
class Activities(Postgres, MLFlow, Gates):
"""
Main activities orchestrator for the Model Manager system.
This class combines functionality from multiple activity classes to provide
a unified interface for all workflow operations. It manages database connections,
MLFlow model interactions, and data quality validation.
The class implements multiple inheritance to combine specialized functionality:
- Postgres: Database operations and data persistence
- MLFlow: Model inference and transformation operations
- Gates: Data quality validation and filtering mechanisms
Attributes:
postgres_config (dict): PostgreSQL connection configuration
mlflow_config (dict): MLFlow server configuration
logger (Logger): Logging and observability instance
notification_handler (NotificationHandler): Notification management instance
"""
def __init__(
self,
postgres_config: dict[str, Any],
mlflow_config: dict[str, Any],
logger: Logger,
notification_handler: NotificationHandler,
):
"""
Initialize the Activities orchestrator with all required configurations.
This constructor initializes all parent classes with their respective
configurations and sets up the foundation for all activity operations.
Args:
postgres_config: PostgreSQL connection configuration dictionary
Required keys: host, port, user, password, dbname, min_connections, max_connections
mlflow_config: MLFlow server configuration dictionary
Required keys: host, port, username, password
logger: Logger instance for observability and debugging
notification_handler: Notification handler for alerts and monitoring
Raises:
Exception: If any parent class initialization fails
"""
# Initialize parent classes
Postgres.__init__(
self,
host=postgres_config['host'],
port=postgres_config['port'],
user=postgres_config['user'],
password=postgres_config['password'],
dbname=postgres_config['dbname'],
min_connections=postgres_config['min_connections'],
max_connections=postgres_config['max_connections'],
logger=logger,
notification_handler=notification_handler,
)
MLFlow.__init__(
self,
mlflow_host=mlflow_config['host'],
mlflow_port=mlflow_config['port'],
mlflow_username=mlflow_config['username'],
mlflow_password=mlflow_config['password'],
logger=logger,
notification_handler=notification_handler,
)
Gates.__init__(self, logger=logger, notification_handler=notification_handler)
async def shutdown(self):
"""
Gracefully shutdown all activities and clean up resources.
This method ensures proper cleanup of all resources including:
- PostgreSQL connection pools
- Any other resources that need explicit cleanup
The method should be called before the application terminates to ensure
proper resource cleanup and prevent resource leaks.
"""
Postgres.close(self)