SIENTIAPDE-1171

Update dependencies and enhance ML model retraining functionality

- Updated sientia-dataops-library version in requirements.txt from 1.3.3 to 1.3.4.
- Incremented image tag in values.yaml from 0.2.4 to 0.2.5 and added a new environment variable MONGODB_TTL_INDEX_HOURS.
- Introduced new methods in MLFlowRepository for model retraining and production model updates, including error handling and logging.
- Added retrain_model and update_production_model activities in mlflow.py to support model management workflows.
- Modified MongoDB connection settings in connectors_config.py for improved security and configuration flexibility.

laborious/workflows/minimal_retrain.py

@@ -0,0 +1,93 @@
+from temporalio import workflow
+
+with workflow.unsafe.imports_passed_through():
+    from laborious.activities.activities import Activities
+    from typing import Any
+    from sientia_do.temporal.utils.policies import retry_policy
+    from datetime import timedelta
+
+
+@workflow.defn(name="minimal_retrain")
+class MinimalRetrain():
+    @workflow.run
+    async def run(self, input_data: dict[str, Any]):
+        """
+        This workflow runs a minimal retrain of a model.
+
+        The workflow executes in four steps:
+        1. Loads the data from the database
+        2. Formats the data and perform the retrain
+        3. Updates the production model
+        4. Saves a model
+
+        Args:
+            - input_data (dict[str, Any]): The input data for the workflow.
+                - schedule_name (str): The name of the schedule.
+                - model_name (str): The name of the model.
+                - model_id (int): The id of the model.
+                - query (str): The SQL query to be executed to load data.
+                - schema (dict, optional): The schema to store the report.
+                - table_name (str, optional): The name of the table to store report.
+
+        Returns:
+            None
+
+        Raises:
+            Exception: If any of the required parameters are missing or if the workflow fails.
+        """
+
+        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']
+
+        data = await workflow.execute_local_activity_method(
+            Activities.load_custom_query,
+            {
+                **metadata,
+                'query': input_data['query'],
+            },
+            retry_policy=retry_policy,
+            start_to_close_timeout=timedelta(seconds=60)
+        )
+
+        experiment_response = await workflow.execute_activity_method(
+            Activities.retrain_model,
+            {
+                **metadata,
+                'data': data,
+                'model_name': model_name
+            },
+            retry_policy=retry_policy,
+            start_to_close_timeout=timedelta(seconds=60)
+        )
+
+        report = await workflow.execute_activity_method(
+            Activities.update_production_model,
+            {
+                **metadata,
+                'model_name': model_name,
+                'model_id': input_data['model_id'],
+                **experiment_response
+            },
+            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=60)
+        )