Files
sientia-dataops-laborious-l…/laborious/utils/connectors_config.py
vitor-aignosi 7512963e19 SIENTIAPDE-1231
Enhance MinIO integration and update environment configurations

- Added MinIO configuration parameters to .env.example and values.yaml for improved storage management.
- Updated requirements.txt to include necessary libraries for MinIO support.
- Refactored Activities class to utilize Storage for MinIO interactions.
- Enhanced MLFlow class to integrate MinIO for data retrieval during model retraining.
- Introduced build_minio_config function to streamline MinIO configuration setup.
- Updated minimal_retrain workflow to support data storage in MinIO.
2025-10-07 16:56:16 -03:00

153 lines
6.1 KiB
Python

from os import getenv
import json
from typing import Dict, Any
def build_postgres_config() -> Dict[str, Any]:
"""
Build PostgreSQL database configuration from environment variables.
This function constructs a PostgreSQL configuration dictionary from
environment variables with sensible defaults for local development.
It handles connection pool configuration and security parameters.
Environment Variables:
POSTGRES_HOST: Database hostname (default: localhost)
POSTGRES_PORT: Database port (default: 5432)
POSTGRES_USER: Database username (default: sientia)
POSTGRES_PASSWORD: Database password (default: sientia)
POSTGRES_DBNAME: Database name (default: sientia)
POSTGRES_MIN_CONNECTIONS: Minimum connection pool size (default: 5)
POSTGRES_MAX_CONNECTIONS: Maximum connection pool size (default: 20)
Returns:
dict: PostgreSQL configuration dictionary with all required parameters
"""
return {
'host': getenv('POSTGRES_HOST', 'localhost'),
'port': int(getenv('POSTGRES_PORT', '5432')),
'user': getenv('POSTGRES_USER', 'sientia'),
'password': getenv('POSTGRES_PASSWORD', 'sientia'),
'dbname': getenv('POSTGRES_DBNAME', 'sientia'),
'min_connections': int(getenv('POSTGRES_MIN_CONNECTIONS', '5')),
'max_connections': int(getenv('POSTGRES_MAX_CONNECTIONS', '20'))
}
def build_mlflow_config() -> Dict[str, Any]:
"""
Build MLFlow server configuration from environment variables.
This function constructs an MLFlow configuration dictionary from
environment variables with sensible defaults for local development.
It handles server connection and authentication parameters.
Environment Variables:
MLFLOW_HOST: MLFlow server hostname (default: http://localhost)
MLFLOW_PORT: MLFlow server port (default: 5080)
MLFLOW_USERNAME: MLFlow username (default: aignosi)
MLFLOW_PASSWORD: MLFlow password (default: aignosi)
Returns:
dict: MLFlow configuration dictionary with all required parameters
"""
return {
'host': getenv('MLFLOW_HOST', 'http://localhost'),
'port': int(getenv('MLFLOW_PORT', '5080')),
'username': getenv('MLFLOW_USERNAME', 'aignosi'),
'password': getenv('MLFLOW_PASSWORD', 'aignosi')
}
def build_opc_config() -> Dict[str, Any]:
"""
Build OPC server configuration from environment variables.
This function constructs an OPC server configuration dictionary from
environment variables. It supports both single server and multi-server
configurations with flexible parameter handling.
Environment Variables:
OPC_CONFIG: JSON string containing multiple OPC server configurations
OPC_ID: OPC server ID (fallback, default: 1)
OPC_URL: Single OPC server URL (fallback, default: opc.tcp://localhost:4840)
OPC_SERVER_URI: Single OPC server URI (fallback, default: opc.tcp://localhost:4840)
OPC_CERT_PATH: Client certificate path (fallback, default: None)
OPC_PRIVATE_KEY_PATH: Client private key path (fallback, default: None)
OPC_SERVER_CERT_PATH: Server certificate path (fallback, default: None)
OPC_RECONNECTION_INTERVAL: Reconnection interval in seconds (fallback, default: 120)
Returns:
dict: OPC server configuration dictionary
"""
opc_raw = getenv('OPC_CONFIG', None)
if opc_raw:
return json.loads(opc_raw)
return {
getenv('OPC_ID', '1'): {
'id': getenv('OPC_ID', '1'),
'url': getenv('OPC_URL', 'opc.tcp://localhost:4840'),
'server_uri': getenv('OPC_SERVER_URI', 'opc.tcp://localhost:4840'),
'cert_path': getenv('OPC_CERT_PATH', None),
'private_key_path': getenv('OPC_PRIVATE_KEY_PATH', None),
'server_cert_path': getenv('OPC_SERVER_CERT_PATH', None),
'reconnection_interval': int(getenv('OPC_RECONNECTION_INTERVAL', '120'))
}
}
def build_mongodb_config() -> Dict[str, Any]:
"""
Build MongoDB configuration from environment variables.
This function constructs a MongoDB configuration dictionary from
environment variables with sensible defaults for local development.
It handles connection string and database name configuration.
Environment Variables:
MONGODB_USERNAME: MongoDB username (default: root)
MONGODB_PASSWORD: MongoDB password (default: wKZDbMNU1c)
MONGODB_URL: MongoDB connection URI (default: localhost:27018)
MONGODB_DATABASE_NAME: MongoDB database name (default: sientia)
MONGODB_TTL_INDEX_HOURS: TTL index duration in hours (default: 1)
Returns:
dict: MongoDB configuration dictionary with connection parameters
"""
username = getenv('MONGODB_USERNAME', 'root')
password = getenv('MONGODB_PASSWORD', 'wKZDbMNU1c')
uri = getenv('MONGODB_URL', 'localhost:27018')
connection_string = f'mongodb://{username}:{password}@{uri}'
return {
'connection_string': connection_string,
'database_name': getenv('MONGODB_DATABASE_NAME', 'sientia'),
'ttl_index_seconds': int(getenv('MONGODB_TTL_INDEX_HOURS', '1')) * 3600
}
def build_minio_config() -> Dict[str, Any]:
"""
Build MinIO (S3-compatible) configuration from environment variables.
Environment Variables:
MINIO_ENDPOINT: MinIO endpoint including scheme (default: http://localhost:9000)
MINIO_ACCESS_KEY: Access key (default: minioadmin)
MINIO_SECRET_KEY: Secret key (default: minioadmin)
MINIO_REGION: Region name for S3 client (default: us-east-1)
MINIO_BUCKET_DEFAULT: Default bucket for uploads (default: laborious)
Returns:
dict: MinIO configuration dictionary
"""
return {
'endpoint_url': getenv('MINIO_ENDPOINT_URL', 'http://localhost:9000'),
'access_key': getenv('MINIO_ACCESS_KEY', 'minioadmin'),
'secret_key': getenv('MINIO_SECRET_KEY', 'minioadmin'),
'region_name': getenv('MINIO_REGION_NAME', 'us-east-1'),
'default_bucket': getenv('MINIO_DEFAULT_BUCKET', 'laborious')
}