gitea_admin/sientia-dataops-laborious_temporal
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

SIENTIAPDE-1712

Browse Source 
Update dependencies and refactor input filter handling for consistency

- Updated sientia-dataops-library dependency version from 1.10.3 to 1.10.4 in requirements.txt.
- Refactored input filter handling in the Gates class to read policy and config keys in a case-insensitive manner.
- Updated test cases to ensure consistency in filter key naming conventions across various scenarios.
This commit is contained in:
vitor-aignosi
2026-03-23 14:45:21 -03:00
parent f22cc49b93
commit 503d9aa485
24 changed files with 331 additions and 234 deletions
Download Patch File Download Diff File Expand all files Collapse all files

44
laborious/activities/gates.py
View File

@@ -118,6 +118,22 @@ class Gates(MinioManager):
def __del__(self):
self.close()
@staticmethod
def _read_filter_entry(config: dict[str, Any]) -> tuple[str, dict[str, Any]]:
"""
Read filter policy/config keys in a case-insensitive way.
Args:
config (dict[str, Any]): Filter configuration dictionary.
Return:
tuple[str, dict[str, Any]]: Parsed policy and config payload.
"""
normalized = {str(key).upper(): value for key, value in config.items()}
policy = normalized['POLICY']
filter_config = normalized.get('CONFIG', {})
return policy, filter_config
@activity.defn(name='input_gate')
async def input_gate(self, input_data: dict[str, Any]) -> tuple[str | None, int, str]:
"""
@@ -171,10 +187,11 @@ class Gates(MinioManager):
if fil not in input_filter_functions:
self.error(f'Filter {fil} not found', metadata)
continue
policy, filter_config = self._read_filter_entry(config)
try:
if input_filter_functions[fil](data, config['config']):
if input_filter_functions[fil](data, filter_config):
self.debug(f'Data not passed the input filter {fil}:{config}', metadata)
filter_output.append(config['policy'])
filter_output.append(policy)
except Exception as e:
trace = traceback.format_exc()
await self.send_notification_async(
@@ -235,8 +252,10 @@ class Gates(MinioManager):
self.info('Performing mlflow response gate...', metadata)
raw_data = input_data['data']
filters = input_data['filters']
self.debug(f'Input data: \n {create_sample_dict(raw_data, max_items=5, max_depth=5)}', metadata)
self.debug(
f'Input data: \n {create_sample_dict(raw_data, max_items=5, max_depth=5)}', metadata
)
self.debug(f'Filters: {filters}', metadata)
payload = MinioDataFramePayload.from_dict(raw_data)
@@ -254,17 +273,18 @@ class Gates(MinioManager):
for fil, config in filters.items():
if fil not in mlflow_response_filter_functions:
continue
policy, filter_config = self._read_filter_entry(config)
try:
if mlflow_response_filter_functions[fil](status, config):
filter_output.append(config['policy'])
comments.append(status['message'])
if mlflow_response_filter_functions[fil](status, filter_config):
filter_output.append(policy)
comments.append(status.get('message', 'Unknown MLFlow API error'))
await self.send_notification_async(
metadata=metadata,
notification_id=f'{gate_type.upper()}_GATE_RESPONSE_FILTER__{fil}',
message=data['content']['message'],
message=status.get('message', 'Unknown MLFlow API error'),
block='mlflow_gate',
level=NotificationLevel.ERROR,
attachment_content=data['content']['traceback'],
attachment_content=status.get('traceback'),
)
except Exception as e:
trace = traceback.format_exc()
@@ -341,9 +361,10 @@ class Gates(MinioManager):
for fil, config in filters.items():
if fil not in mlflow_content_filter_functions:
continue
policy, filter_config = self._read_filter_entry(config)
try:
if mlflow_content_filter_functions[fil](data, config):
filter_output.append(config['policy'])
if mlflow_content_filter_functions[fil](data, filter_config):
filter_output.append(policy)
await self.send_notification_async(
metadata=metadata,
notification_id=f'{gate_type.upper()}_GATE_CONTENT_FILTER__{fil}',
@@ -703,7 +724,6 @@ class Gates(MinioManager):
self.info(f'Writing metrics for model {metadata["model_name"]}', metadata)
core_tags = {
'pod_id': self.pod_id,
'runtime': self.runtime,

5
laborious/activities/mlflow.py
View File

@@ -1,7 +1,5 @@
from temporalio import activity, workflow
with workflow.unsafe.imports_passed_through():
import traceback
from typing import Any
@@ -20,8 +18,9 @@ with workflow.unsafe.imports_passed_through():
now,
)
from sientia_do.utils.formatters import create_sample_dict
from laborious.utils.repository.minio_manager import MinioManager
from laborious.utils.models.minio_dataframe_payload import MinioDataFramePayload
from laborious.utils.repository.minio_manager import MinioManager
from laborious.utils.repository.model_repository import MLFlowRepository

4
laborious/metrics.py
View File

@@ -25,9 +25,7 @@ Metric Labels:
"""
from prometheus_client import Counter, Gauge, Histogram
from sientia_do.observability.metrics import (
CORE_LABELS
)
from sientia_do.observability.metrics import CORE_LABELS
# Application health metric
APP_UP = Gauge(

3
laborious/utils/models/minio_dataframe_payload.py
View File

@@ -162,7 +162,7 @@ class MinioDataFramePayload:
"""
Return True if the payload has some data internally or in MinIO.
"""
return (self.data is not None and not self.data != {}) or self.object_key is not None
return (self.data is not None and self.data != {}) or self.object_key is not None
@classmethod
async def from_dataframe(
@@ -200,7 +200,6 @@ class MinioDataFramePayload:
data=None, last_timestamp=now().strftime(DATETIME_FORMAT_WITH_TZ), status=status
)
if last_timestamp is None:
last_timestamp = max(dataframe['timestamp'].values.tolist())

5
laborious/worker/worker.py
View File

@@ -219,20 +219,21 @@ async def main():
logger.custom_info('Workers started successfully', metadata)
exit_code = 0
try:
# This will run the workers and wait for them to complete.
# If an exception occurs in any of the worker handlers, it will be propagated here.
await asyncio.gather(*handlers)
except BaseException as e: # NOSONAR
logger.custom_error(f'An unhandled exception occurred: {e}', metadata)
exit_code = 1
finally:
if notification_handler:
notification_handler.shutdown()
if activities:
await activities.shutdown()
# Exit with a non-zero status code to indicate failure to Kubernetes
metrics.APP_UP.labels(pod_id=POD_ID).set(0) # Mark app as DOWN
sys.exit(1)
sys.exit(exit_code)
def start_prometheus_server():

4
laborious/workflows/drift.py
View File

@@ -46,7 +46,7 @@ class Drift:
ORDER BY timestamp ASC
""" # nosec B608 - values come from internal Temporal workflow config, not user input
target_data_handler = workflow.start_local_activity_method(
target_data_handler = workflow.start_activity_method(
Activities.load_custom_query,
{
**metadata,
@@ -58,7 +58,7 @@ class Drift:
start_to_close_timeout=timedelta(seconds=300),
)
reference_data_handler = workflow.start_local_activity_method(
reference_data_handler = workflow.start_activity_method(
Activities.get_reference_data,
{**metadata, 'model_name': input_data['model_name']},
retry_policy=retry_policy,

4
laborious/workflows/minimal_retrain.py
View File

@@ -7,6 +7,7 @@ with workflow.unsafe.imports_passed_through():
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')
@@ -84,7 +85,8 @@ class MinimalRetrain:
start_to_close_timeout=timedelta(seconds=600),
)
if not storage_result.has_data():
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(

8
laborious/workflows/predictions_batch.py
View File

@@ -105,12 +105,14 @@ class PredictionsBatch:
'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'}}),
'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'}}
'mlflow_transform_filters', {'API_ERROR': {'POLICY': 'STOP', 'CONFIG': {}}}
),
'mlflow_predict_filters': input_data.get(
'mlflow_predict_filters', {'API_ERROR': {'POLICY': 'STOP'}}
'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']),

2
laborious/workflows/simple_metrics.py
View File

@@ -47,7 +47,7 @@ class SimpleMetrics:
p."timestamp" desc;
""" # nosec B608 - values come from internal Temporal workflow config, not user input
target_data = await workflow.execute_local_activity_method(
target_data = await workflow.execute_activity_method(
Activities.load_custom_query,
{
**metadata,

2
laborious/workflows/sub_workflows/prediction_process.py
View File

@@ -7,7 +7,6 @@ with workflow.unsafe.imports_passed_through():
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='subworkflow.prediction_process')
@@ -112,7 +111,6 @@ class PredictionProcess:
start_to_close_timeout=timedelta(minutes=5),
)
raise e
async def _run_prediction_pipeline(
self,