b203b7d22c
Implement workflows for fake data generation, scouter processing, and core scouter operations - Added `FakeData` workflow to generate random data and send it to a Kafka topic. - Implemented `Scouter` workflow to load data from Kafka and trigger the core scouter workflow. - Created `CoreScouter` workflow to process data through quality gates, aggregation, and export to PostgreSQL. - Developed comprehensive unit tests for activities and workflows, ensuring proper functionality and error handling. - Enhanced Redis and Postgres activities with robust testing for data handling and error notifications. - Introduced quality filters for data validation and implemented tests to verify their functionality.
51 lines
1.8 KiB
Python
51 lines
1.8 KiB
Python
from temporalio import workflow
|
|
|
|
with workflow.unsafe.imports_passed_through():
|
|
from scouter.activities.activities import Activities
|
|
from typing import Any
|
|
from datetime import timedelta
|
|
from scouter.utils.policies import retry_policy
|
|
|
|
|
|
@workflow.defn(name="scouter")
|
|
class Scouter:
|
|
@workflow.run
|
|
async def run(self, input_data: dict[str, Any]):
|
|
"""
|
|
Scouter workflow. Loads data from kafka and sends it to the core_scouter
|
|
workflow.
|
|
|
|
Args:
|
|
input_data (dict[str, Any]): The data to process. Contains:
|
|
topic (str): The topic to load data from.
|
|
workflow_name (str): The name of the workflow.
|
|
schedule_name (str): The name of the schedule.
|
|
model_name (str): The name of the model.
|
|
model_id (str): The id of the model.
|
|
trigger_laborious (bool): Whether to trigger laborious.
|
|
filters (dict[str, str]): The filters to apply.
|
|
schema (str): The schema of the table to export data to.
|
|
table_name (str): The name of the table to export data to.
|
|
retention_time (int): The retention time for data in redis in seconds.
|
|
model_tags (dict[str, Any]): The tags of the model. And it's respective configuration.
|
|
"""
|
|
|
|
data = await workflow.execute_activity_method(
|
|
Activities.load_from_kafka,
|
|
{
|
|
'topic': input_data['topic']
|
|
},
|
|
retry_policy=retry_policy,
|
|
start_to_close_timeout=timedelta(seconds=60)
|
|
)
|
|
|
|
if data == {}:
|
|
return
|
|
|
|
input_data['data'] = data
|
|
|
|
await workflow.execute_child_workflow(
|
|
'core_scouter',
|
|
input_data
|
|
)
|