SIENTIAPDE-1182

Remove deprecated files and configurations

- Deleted coverage.sh, Dockerfile, docker-compose.yml, email.html, input_sample.json, and Makefile as part of the cleanup process.
- Updated README.md to reflect the removal of these components and provide a clearer overview of the project structure and functionality.
- Added module-level docstrings to orchestrator, activities, and workflows for improved documentation and clarity on system architecture.
This commit is contained in:
vitor-aignosi
2025-08-29 16:13:57 -03:00
parent e389bd7c27
commit 3724ea2bc8
25 changed files with 987 additions and 735 deletions

36
.env.example Normal file
View File

@@ -0,0 +1,36 @@
REDIS_HOST="redis-master.redis.svc.cluster.local"
REDIS_PORT="6379"
REDIS_USERNAME="redis_username"
REDIS_PASSWORD="redis_password"
COUCHBASE_CONNECTION_STRING="couchbase://sientia.couchbase.svc.cluster.local"
COUCHBASE_USERNAME="sientia"
COUCHBASE_PASSWORD="sientia"
MONGODB_USERNAME="mongo_username"
MONGODB_PASSWORD="mongo_password"
MONGODB_URL="my-release-mongodb.mongodb.svc.cluster.local:27017"
MONGODB_DATABASE="sientia"
MONGODB_TTL_INDEX_HOURS="1"
EMAIL_SENDER="aignosi@aignosi.com.br"
EMAIL_SENDER_PASSWORD="smtp_password"
EMAIL_SMTP_SERVER="smtp.gmail.com"
EMAIL_SMTP_PORT="587"
POSTGRES_HOST="paradedb-rw.paradedb.svc.cluster.local"
POSTGRES_PORT="5432"
POSTGRES_USER="sientia"
POSTGRES_PASSWORD="sientia"
POSTGRES_DBNAME="sientia"
POSTGRES_MIN_CONNECTIONS="10"
POSTGRES_MAX_CONNECTIONS="40"
LOG_LEVEL="DEBUG"
HTTP_METRICS_PORT="9090"
PROJECT_NAME="sientia-orchestrator"
TEMPORAL_HOST="temporal-frontend.temporal.svc.cluster.local:7233"
TEMPORAL_NAMESPACE="default"
TEMPORAL_SCOUTER_NAMESPACE="scouter"
TEMPORAL_LABORIOUS_NAMESPACE="laborious"

View File

@@ -1,83 +0,0 @@
FROM python:3.11-bookworm
LABEL description="Deploy Mage on ECS"
ARG FEATURE_BRANCH
USER root
SHELL ["/bin/bash", "-o", "pipefail", "-c"]
# Definir Python 3.11 como padrão
ENV PATH="/usr/local/bin/python3.11:$PATH"
RUN update-alternatives --install /usr/bin/python python /usr/local/bin/python3.11 1 && \
update-alternatives --install /usr/bin/python3 python3 /usr/local/bin/python3.11 1 && \
update-alternatives --config python3 <<< '1' && \
update-alternatives --config python <<< '1'
## System Packages
RUN \
curl https://packages.microsoft.com/keys/microsoft.asc | apt-key add - && \
curl https://packages.microsoft.com/config/debian/11/prod.list > /etc/apt/sources.list.d/mssql-release.list && \
apt-get -y update && \
ACCEPT_EULA=Y apt-get -y install --no-install-recommends \
# NFS dependencies
nfs-common \
# odbc dependencies
msodbcsql18 \
unixodbc-dev \
graphviz \
# postgres dependencies
postgresql-client \
# R
r-base && \
apt-get clean && \
rm -rf /var/lib/apt/lists/*
## R Packages
RUN \
R -e "install.packages('pacman', repos='http://cran.us.r-project.org')" && \
R -e "install.packages('renv', repos='http://cran.us.r-project.org')"
## Python Packages
RUN \
pip3 install --no-cache-dir sparkmagic && \
mkdir ~/.sparkmagic && \
curl https://raw.githubusercontent.com/jupyter-incubator/sparkmagic/master/sparkmagic/example_config.json > ~/.sparkmagic/config.json && \
sed -i 's/localhost:8998/host.docker.internal:9999/g' ~/.sparkmagic/config.json && \
jupyter-kernelspec install --user "$(pip3 show sparkmagic | grep Location | cut -d' ' -f2)/sparkmagic/kernels/pysparkkernel"
# Mage integrations and other related packages
RUN \
pip3 install --no-cache-dir "git+https://github.com/wbond/oscrypto.git@d5f3437ed24257895ae1edd9e503cfb352e635a8" && \
pip3 install --no-cache-dir "git+https://github.com/dremio-hub/arrow-flight-client-examples.git#egg=dremio-flight&subdirectory=python/dremio-flight" && \
pip3 install --no-cache-dir "git+https://github.com/mage-ai/singer-python.git#egg=singer-python" && \
pip3 install --no-cache-dir "git+https://github.com/mage-ai/dbt-mysql.git#egg=dbt-mysql" && \
pip3 install --no-cache-dir "git+https://github.com/mage-ai/sqlglot#egg=sqlglot" && \
pip3 install --no-cache-dir faster-fifo && \
if [ -z "$FEATURE_BRANCH" ] || [ "$FEATURE_BRANCH" = "null" ]; then \
pip3 install --no-cache-dir "git+https://github.com/mage-ai/mage-ai.git#egg=mage-integrations&subdirectory=mage_integrations"; \
else \
pip3 install --no-cache-dir "git+https://github.com/mage-ai/mage-ai.git@$FEATURE_BRANCH#egg=mage-integrations&subdirectory=mage_integrations"; \
fi
# Mage
COPY ./mage_ai/server/constants.py /tmp/constants.py
RUN if [ -z "$FEATURE_BRANCH" ] || [ "$FEATURE_BRANCH" = "null" ] ; then \
tag=$(tail -n 1 /tmp/constants.py) && \
VERSION=$(echo "$tag" | tr -d "'") && \
pip3 install --no-cache-dir "mage-ai[all]==$VERSION"; \
else \
pip3 install --no-cache-dir "git+https://github.com/mage-ai/mage-ai.git@$FEATURE_BRANCH#egg=mage-ai[all]"; \
fi
## Startup Script
COPY --chmod=0755 ./scripts/install_other_dependencies.py ./scripts/run_app.sh /app/
ENV MAGE_DATA_DIR="/home/src/mage_data"
ENV PYTHONPATH="${PYTHONPATH}:/home/src"
WORKDIR /home/src
EXPOSE 6789
EXPOSE 7789
# Copia o arquivo requirements.txt para o contêiner
COPY requirements.txt /app/requirements.txt
RUN pip3 install --no-cache-dir -r /app/requirements.txt
CMD ["/bin/sh", "-c", "/app/run_app.sh"]

View File

@@ -1,7 +0,0 @@
VERSION = 1.0.8
name = sientia-laborious
# ENVIRONMENT = production
docker-hub:
@docker build --no-cache -t aignosi.azurecr.io/$(name):$(VERSION) .
@docker push aignosi.azurecr.io/$(name):$(VERSION)

731
README.md
View File

@@ -1,190 +1,655 @@
# SIENTIA DataOps Orchestrator Temporal
## Overview
A high-performance, scalable workflow orchestration system built on Temporal.io for automated pipeline management, notification delivery, and resource coordination. The Orchestrator provides enterprise-grade workflow automation, real-time alerting, and comprehensive monitoring capabilities for the SIENTIA platform.
The SIENTIA DataOps Orchestrator Temporal is a comprehensive workflow orchestration system built on Temporal.io that manages data pipelines, notifications, and system orchestration for the SIENTIA platform. It provides automated scheduling, monitoring, and execution of data processing workflows with integrated alerting and reporting capabilities.
## Features
## Project Goals
### Core Functionality
- **Pipeline Orchestration**: Automated deployment and management of data processing pipelines
- **Real-time Notifications**: Intelligent alert filtering and delivery with TTL management
- **Resource Management**: Dynamic OPC server slot allocation and active ingestor monitoring
- **Schedule Management**: Temporal-based workflow scheduling with automatic retry policies
- **Multi-namespace Support**: Separate workflow queues for scouter and laborious operations
- **Pipeline Orchestration**: Automate the deployment and management of data processing pipelines
- **Notification Management**: Handle real-time alerts and scheduled reports for system events
- **Resource Management**: Manage OPC server slots and data ingestion resources
- **Workflow Automation**: Coordinate complex workflows across multiple services and databases
- **Monitoring & Reporting**: Provide comprehensive logging and metrics for system health
### Advanced Capabilities
- **Incremental Processing**: Timestamp-based data loading to avoid reprocessing
- **Configurable Filtering**: User group-based notification filtering with custom policies
- **Auto-scaling Workers**: Multiple worker instances with task queue isolation
- **Comprehensive Logging**: Structured logging with PostgreSQL audit trails
- **Prometheus Metrics**: Real-time monitoring and alerting integration
## Architecture
The system is built around three main worker queues, each handling specific types of workflows:
The SIENTIA DataOps Orchestrator uses a Temporal-based workflow architecture with clear separation of concerns and robust error handling. The architecture is designed for high availability, scalability, and operational excellence in data pipeline environments.
### 1. Orchestrator Queue (`orchestrator-queue`)
Handles pipeline orchestration and resource management workflows.
### System Overview
### 2. Alerts Queue (`alerts-queue`)
Manages real-time alert notifications and error reporting.
```
┌───────────────────────────────────────────────────────────────────────────────┐
│ Temporal Cluster │
│ ┌─────────────────┐ ┌──────────────────┐ ┌─────────────────────────┐ │
│ │ Main Worker │ │ Temporal Client │ │ Task Queues │ │
│ │ │◄──►│ │◄──►│ │ │
│ │ - Metrics Server│ │ - Namespace Mgmt │ │ - orchestrator-queue │ │
│ │ - Notifications │ │ - Runtime Config │ │ - alerts-queue │ │
│ │ - Lifecycle │ │ - Connection │ │ - reports-queue │ │
│ │ - Health Checks │ │ - Security │ │ - Auto-scaling │ │
│ └─────────────────┘ └──────────────────┘ └─────────────────────────┘ │
└───────────────────────────────────────────────────────────────────────────────┘
┌────────────────────────────────────────────────────────┐
│ Workflow Layer │
│ ┌─────────────────┐ ┌─────────────────────────────┐ │
│ │ Orchestrator │ │ Subworkflows │ │
│ │ │ │ │ │
│ │ - Pipeline Mgmt │ │ - LoadNotificationPackage │ │
│ │ - Resource Mgmt │ │ - ProcessNotifications │ │
│ │ - Schedule Mgmt │ │ - Error Handling │ │
│ └─────────────────┘ └─────────────────────────────┘ │
│ ┌─────────────────┐ ┌─────────────────────────────┐ │
│ │ Alerts │ │ Reports │ │
│ │ │ │ │ │
│ │ - Error Alerts │ │ - Scheduled Reports │ │
│ │ - TTL Filtering │ │ - Summary Generation │ │
│ │ - Group Filtering│ │ - Comprehensive Logging │ │
│ └─────────────────┘ └─────────────────────────────┘ │
└────────────────────────────────────────────────────────┘
┌────────────────────────────────────────────────────────┐
│ Activity Layer │
│ ┌─────────────────┐ ┌─────────────────────────────┐ │
│ │ Temporal Manager│ │ MongoDB Operations │ │
│ │ │ │ │ │
│ │ - Schedule CRUD │ │ - Document Queries │ │
│ │ - Multi-namespace│ │ - Aggregation Pipelines │ │
│ │ - Normalization │ │ - Timestamp Management │ │
│ │ - Error Handling│ │ - TTL Collections │ │
│ └─────────────────┘ └─────────────────────────────┘ │
│ ┌─────────────────┐ ┌─────────────────────────────┐ │
│ │ Slot Manager │ │ Email Services │ │
│ │ │ │ │ │
│ │ - OPC Slots │ │ - HTML Generation │ │
│ │ - Active Ingest │ │ - SMTP Management │ │
│ │ - Redis Ops │ │ - Attachment Handling │ │
│ │ - Cache Mgmt │ │ - Auto Reconnection │ │
│ └─────────────────┘ └─────────────────────────────┘ │
└────────────────────────────────────────────────────────┘
┌────────────────────────────────────────────────────────┐
│ Data Services │
│ ┌─────────────────┐ ┌─────────────────────────────┐ │
│ │ Redis │ │ MongoDB │ │
│ │ │ │ │ │
│ │ - OPC Slots │ │ - Pipeline Configs │ │
│ │ - Timestamps │ │ - Notification Queue │ │
│ │ - Notification │ │ - Receiver Groups │ │
│ │ - Cache TTL │ │ - Orchestrated Schedules │ │
│ └─────────────────┘ └─────────────────────────────┘ │
│ ┌─────────────────┐ ┌─────────────────────────────┐ │
│ │ PostgreSQL │ │ SMTP Services │ │
│ │ │ │ │ │
│ │ - Log Reports │ │ - Email Delivery │ │
│ │ - Audit Trails │ │ - Group Management │ │
│ │ - Metrics Data │ │ - Attachment Support │ │
│ │ - Data Export │ │ - Security & Auth │ │
│ └─────────────────┘ └─────────────────────────────┘ │
└────────────────────────────────────────────────────────┘
┌─────────────────────────────────────────────────────────┐
│ External Systems │
│ ┌─────────────────┐ ┌─────────────────────────────┐ │
│ │ Prometheus │ │ Kubernetes │ │
│ │ │ │ │ │
│ │ - App Metrics │ │ - Container Orchestration │ │
│ │ - Email Metrics │ │ - Health Checks │ │
│ │ - SDK Metrics │ │ - Auto-scaling │ │
│ │ - Alerting │ │ - Resource Management │ │
│ └─────────────────┘ └─────────────────────────────┘ │
└─────────────────────────────────────────────────────────┘
```
### 3. Reports Queue (`reports-queue`)
Handles scheduled reports and data summaries.
### Architecture Principles
## Workflows
#### 1. **Separation of Concerns**
- **Worker Layer**: Manages Temporal workers, task queues, and application lifecycle
- **Workflow Layer**: Orchestrates business logic and process coordination
- **Activity Layer**: Implements specific operations and external system interactions
- **Data Layer**: Handles data persistence, caching, and external service connections
#### 2. **Task Queue Isolation**
- **Orchestrator Queue**: Pipeline and resource management workflows
- **Alerts Queue**: Real-time error notification workflows
- **Reports Queue**: Scheduled reporting and summary workflows
#### 3. **Fault Tolerance & Resilience**
- **Automatic Retry Policies**: Configurable retry strategies for transient failures
- **Graceful Degradation**: System continues operating with reduced functionality
- **Comprehensive Error Handling**: Detailed error reporting and notification integration
- **Connection Management**: Automatic reconnection for SMTP and database services
#### 4. **Scalability & Performance**
- **Horizontal Scaling**: Multiple worker instances for load distribution
- **Connection Pooling**: Optimized database and Redis connections
- **Asynchronous Processing**: Non-blocking operations for improved throughput
- **Resource Optimization**: Intelligent slot allocation and ingestor management
## 🔄 Workflows
### Main Workflows
#### 1. Orchestrator Workflow
**Purpose**: Main orchestration workflow that manages pipeline deployment and resource allocation.
#### 1. Orchestrator Workflow (`orchestrator.py`)
The **Orchestrator** workflow is the main coordination workflow that manages pipeline deployment and resource allocation across the SIENTIA platform.
**Purpose**:
- **Pipeline Management**: Coordinates deployment of scouter and laborious pipelines
- **Resource Allocation**: Manages OPC server slots and active ingestor distribution
- **Schedule Synchronization**: Ensures Temporal schedules match MongoDB configurations
- **Infrastructure Management**: Creates, updates, and deletes workflow schedules
**Execution Flow**:
1. **Configuration Loading**: Retrieves pipeline and OPC server configurations from MongoDB
2. **Resource Assessment**: Loads current OPC slots and active ingestors from Redis
3. **Schedule Processing**: Formats configurations for different workflow types
4. **Deployment Operations**: Creates, updates, or deletes Temporal schedules
5. **Resource Updates**: Updates OPC slots and MongoDB timestamps
6. **Reporting**: Generates comprehensive orchestration reports
**Input Parameters**:
- `schedule_name` (str): Name of the orchestration schedule
- `pipelines_query` (dict): MongoDB query to retrieve pipeline configurations
- `opc_servers_query` (dict): MongoDB query to retrieve OPC server configurations
```json
{
"schedule_name": "hourly_orchestration",
"pipelines_query": {
"collection": "pipelines",
"aggregation": [
{"$match": {"active": true}},
{"$sort": {"updated_at": -1}}
]
},
"opc_servers_query": {
"collection": "opc_servers",
"filters": {"active": true}
}
}
```
**What it does**:
- Retrieves pipeline configurations from MongoDB
- Loads current OPC server slots and active ingestors from Redis
- Processes schedules and creates slot configurations
- Deploys schedules to Temporal server (scouter and laborious namespaces)
- Updates OPC slots in Redis
- Generates orchestration reports
#### 2. Alerts Workflow (`alerts.py`)
#### 2. Alerts Workflow
**Purpose**: Sends real-time error alerts to configured user groups.
The **Alerts** workflow processes and sends real-time error notifications to configured user groups with intelligent filtering and duplicate prevention.
**Purpose**:
- **Error Alerting**: Immediate notification of ERROR-level events
- **TTL Management**: Prevents alert spam using configurable time-to-live settings
- **Group Filtering**: Sends alerts only to relevant user groups
- **Persistent Monitoring**: Tracks and escalates persistent issues
**Execution Flow**:
1. **Notification Loading**: Retrieves ERROR-level notifications from MongoDB
2. **Timestamp Filtering**: Applies incremental processing using Redis timestamps
3. **Group Filtering**: Filters notifications by user group configurations
4. **TTL Processing**: Checks notification cache to prevent duplicate alerts
5. **Email Generation**: Creates HTML email content for each group
6. **Delivery & Logging**: Sends emails and logs results to PostgreSQL
**Input Parameters**:
- `schedule_name` (str): Name of the alert schedule
- `notification_ttl` (int): Time period before considering notifications persistent
- `sent_ttl` (int): Time to live for sent notification cache
```json
{
"schedule_name": "error_alerts",
"notification_ttl": 3600,
"sent_ttl": 7200
}
```
**What it does**:
- Filters notifications by ERROR level
- Loads notification packages from MongoDB
- Applies user group filtering and notification TTL rules
- Sends HTML email alerts
- Stores notification logs in PostgreSQL
- Caches sent notifications to prevent duplicates
#### 3. Reports Workflow (`reports.py`)
#### 3. Reports Workflow
**Purpose**: Sends scheduled reports to configured user groups.
The **Reports** workflow generates and sends scheduled comprehensive reports to configured user groups.
**Input Parameters**:
- `schedule_name` (str): Name of the report schedule
**Purpose**:
- **Scheduled Reporting**: Regular summary reports of system activity
- **Comprehensive Coverage**: Includes all notification levels (not just errors)
- **Group Management**: Customizable reports per user group
- **Audit Trail**: Complete logging of report delivery
**What it does**:
- Loads all notifications (any level) from MongoDB
- Applies user group filtering
- Generates HTML report emails
- Stores report logs in PostgreSQL
**Execution Flow**:
1. **Data Collection**: Loads all notifications from MongoDB (any level)
2. **Timestamp Processing**: Uses incremental loading with Redis timestamps
3. **Group Processing**: Applies user group filtering for report customization
4. **Report Generation**: Creates HTML reports with comprehensive summaries
5. **Distribution**: Sends reports to configured recipients
6. **Audit Logging**: Records delivery status in PostgreSQL
### Subworkflows
#### 1. Load Notification Package
**Purpose**: Loads notification data and configuration from various sources.
#### 1. Load Notification Package (`load_notification_package.py`)
**Purpose**: Centralized notification data loading and configuration management for both alerts and reports workflows.
**Key Features**:
- **Incremental Processing**: Uses Redis timestamps for efficient data loading
- **Configuration Management**: Loads active receiver group configurations
- **Data Validation**: Ensures complete data packages before processing
- **Timestamp Management**: Updates last processed timestamps
**Input Parameters**:
- `metadata` (dict): Workflow metadata
- `mail_type` (str): Type of mail (Alerts/Reports)
- `base_data_filter` (dict): Base filters for data retrieval
```json
{
"metadata": {"workflow_name": "alerts", "schedule_name": "error_alerts"},
"mail_type": "Alerts",
"base_data_filter": {"level": "ERROR"}
}
```
**Returns**:
- `last_timestamp` (str): Last processed timestamp
- `notification_package` (list): Package of notifications to process
- `sending_configs` (list): Email sending configurations
- `last_timestamp` (str | None): Last processed timestamp
- `notification_package` (list[dict]): Retrieved notifications
- `sending_configs` (list[dict]): Active receiver group configurations
#### 2. Process Notifications
**Purpose**: Processes notifications and sends emails with logging.
#### 2. Process Notifications (`process_notifications.py`)
**Purpose**: Handles email generation, delivery, and audit logging for notification workflows.
**Key Features**:
- **HTML Generation**: Creates formatted email content for each receiver group
- **Email Delivery**: Sends emails with attachment support and error handling
- **Audit Logging**: Records delivery status and metrics in PostgreSQL
- **Error Recovery**: Handles SMTP failures with detailed error reporting
**Input Parameters**:
- `metadata` (dict): Workflow metadata
- `mail_type` (str): Type of mail being sent
- `schema` (str): Database schema name
- `table_name` (str): Database table name
- `notification_package` (list): Notifications to process
```json
{
"metadata": {"workflow_name": "alerts", "schedule_name": "error_alerts"},
"mail_type": "Alerts",
"schema": "sientia_data",
"table_name": "log_report",
"notification_package": {
"group_name": "admin_team",
"members": ["admin@example.com"],
"notifications": [...]
}
}
```
**Returns**:
- `log_report` (dict): Report of processed notifications
- `log_report` (list[dict]): Detailed delivery status for each notification
## Environment Variables
### Key Components
### Database Connections
#### **Worker (`orchestrator/worker/worker.py`)**
- **Purpose**: Main application orchestrator managing Temporal workers and task queues
- **Responsibilities**:
- Temporal client initialization and connection management
- Worker lifecycle management and graceful shutdown
- Task queue configuration (orchestrator, alerts, reports)
- Prometheus metrics server initialization
- Notification handler setup and configuration
- **Key Features**:
- Multi-queue worker management with automatic scaling
- Health check endpoints for Kubernetes liveness/readiness probes
- Graceful shutdown with cleanup procedures
- Comprehensive error handling and metrics collection
#### Redis Configuration
- `REDIS_HOST`: Redis server hostname (default: localhost)
- `REDIS_PORT`: Redis server port (default: 6379)
- `REDIS_USERNAME`: Redis username (default: default)
- `REDIS_PASSWORD`: Redis password (from secret)
#### **Activities (`orchestrator/activities/`)**
- **Activities**: Main activity orchestrator combining all operations
- **TemporalManager**: Temporal schedule CRUD operations across namespaces
- **SlotManager**: Redis-based OPC slot and cache management
- **MongoDB**: Document operations, aggregations, and TTL management
- **Email**: SMTP operations with HTML generation and attachment support
- **Formatters**: Configuration processing and slot distribution algorithms
#### MongoDB Configuration
- `MONGODB_USERNAME`: MongoDB username (default: root)
- `MONGODB_PASSWORD`: MongoDB password
- `MONGODB_URL`: MongoDB server URL (default: localhost:27017)
- `MONGODB_DATABASE`: Database name (default: sientia)
- `MONGODB_TTL_INDEX_HOURS`: TTL index duration in hours (default: 1)
#### **Utilities (`orchestrator/utils/`)**
- **Connectors Configuration**: Database and service configuration management
- **Email Builder**: HTML email template generation and formatting
- **Orchestrator Functions**: Pipeline configuration transformation utilities
- **Converters**: Data type conversion and validation utilities
#### PostgreSQL Configuration
- `POSTGRES_HOST`: PostgreSQL server hostname
- `POSTGRES_PORT`: PostgreSQL server 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: 10)
- `POSTGRES_MAX_CONNECTIONS`: Maximum connection pool size (default: 40)
## 📋 Prerequisites
#### Couchbase Configuration
- `COUCHBASE_CONNECTION_STRING`: Couchbase server connection string
- `COUCHBASE_USERNAME`: Couchbase username (default: sientia)
- `COUCHBASE_PASSWORD`: Couchbase password (default: sientia)
- Python 3.11+
- Temporal server/cluster
- Redis server
- MongoDB server
- PostgreSQL database
- SMTP server access
### Email Configuration
- `EMAIL_SENDER`: Sender email address
- `EMAIL_SENDER_PASSWORD`: App password for SMTP authentication
- `EMAIL_SMTP_SERVER`: SMTP server hostname (default: smtp.gmail.com)
- `EMAIL_SMTP_PORT`: SMTP server port (default: 587)
**Note**: External dependencies must be available either through:
- Kubernetes cluster deployment
- Docker Compose setup
- Cloud-managed services
- Local installations
### Temporal Configuration
- `TEMPORAL_HOST`: Temporal server hostname and port
- `TEMPORAL_NAMESPACE`: Default Temporal namespace (default: default)
- `TEMPORAL_SCOUTER_NAMESPACE`: Scouter workflow namespace (default: scouter)
- `TEMPORAL_LABORIOUS_NAMESPACE`: Laborious workflow namespace (default: laborious)
## 🚀 Installation
### Application Configuration
- `LOG_LEVEL`: Logging level (default: DEBUG)
- `HTTP_METRICS_PORT`: Prometheus metrics port (default: 9090)
- `PROJECT_NAME`: Project identifier (default: sientia-orchestrator)
- `POD_ID`: Kubernetes pod identifier for metrics
### Local Development Setup
### Kafka Configuration
- `KAFKA_BOOTSTRAP_SERVERS`: Kafka bootstrap servers
1. **Clone the repository**
```bash
git clone <repository-url>
cd sientia-dataops-orchestrator_temporal
```
## Deployment
2. **Create virtual environment**
```bash
python3.11 -m venv venv
source ./venv/bin/activate
```
The system is designed for Kubernetes deployment using Helm charts with:
- Health checks and readiness probes
- Prometheus metrics endpoint
- ServiceMonitor integration for Prometheus Operator
- Configurable resource limits and scaling
- SSH key management for Git operations
3. **Install dependencies**
```bash
pip install -r requirements.txt
```
## Usage
4. **Configure environment variables**
```bash
# Set required environment variables for services
export TEMPORAL_HOST=localhost:7233
export REDIS_HOST=localhost
export MONGODB_URL=localhost:27017
export POSTGRES_HOST=localhost
# ... additional configuration
```
Workflows can be triggered via Temporal client calls with appropriate input parameters. The system automatically handles:
- Pipeline configuration retrieval
- Resource allocation
- Schedule deployment
- Notification processing
- Email delivery
- Logging and monitoring
## 📦 How to Run
## Monitoring
### Running the Orchestrator Application
The system exposes Prometheus metrics at `/metrics` endpoint including:
- Application status (up/down)
- Email sent counts
- Workflow execution metrics
- Custom business metrics
Use the provided script to run the application locally:
All operations are logged with structured metadata for debugging and auditing purposes.
```bash
# Make script executable (first time only)
chmod +x run_local.sh
# PR shortcut
# Run the application
./run_local.sh
```
git log origin/main..HEAD --no-merges > git_log
The script will:
- Activate the virtual environment
- Load environment variables from `.env`
- Start the orchestrator worker application
### Running Tests and Coverage
Use the provided script to run tests with coverage:
```bash
# Make script executable (first time only)
chmod +x run_coverage.sh
# Run tests with coverage
./run_coverage.sh
```
Prompt:
Write a summary of PR changes in markdown. Be objective and direct. Write to file
### Manual Application Execution
For manual execution without scripts:
```bash
# Activate virtual environment
source ./venv/bin/activate
# Start the orchestrator worker
python -m orchestrator.worker.worker
```
## ⚙️ Configuration
### Environment Variables
| Variable | Description | Default | Required |
|----------|-------------|---------|----------|
| `TEMPORAL_HOST` | Temporal server address | `localhost:7233` | Yes |
| `TEMPORAL_NAMESPACE` | Default Temporal namespace | `default` | No |
| `TEMPORAL_SCOUTER_NAMESPACE` | Scouter workflow namespace | `scouter` | No |
| `TEMPORAL_LABORIOUS_NAMESPACE` | Laborious workflow namespace | `laborious` | No |
| `REDIS_HOST` | Redis server hostname | `localhost` | Yes |
| `REDIS_PORT` | Redis server port | `6379` | Yes |
| `REDIS_USERNAME` | Redis username | `default` | Yes |
| `REDIS_PASSWORD` | Redis password | - | Yes |
| `MONGODB_URL` | MongoDB server URL | `localhost:27017` | Yes |
| `MONGODB_USERNAME` | MongoDB username | `root` | Yes |
| `MONGODB_PASSWORD` | MongoDB password | - | Yes |
| `MONGODB_DATABASE_NAME` | MongoDB database name | `sientia` | Yes |
| `POSTGRES_HOST` | PostgreSQL hostname | `localhost` | Yes |
| `POSTGRES_PORT` | PostgreSQL port | `5432` | Yes |
| `POSTGRES_USER` | PostgreSQL username | `sientia` | Yes |
| `POSTGRES_PASSWORD` | PostgreSQL password | - | Yes |
| `POSTGRES_DBNAME` | PostgreSQL database | `sientia` | Yes |
| `EMAIL_SENDER` | Sender email address | - | Yes |
| `EMAIL_SENDER_PASSWORD` | SMTP password | - | Yes |
| `EMAIL_SMTP_SERVER` | SMTP server | `smtp.gmail.com` | No |
| `EMAIL_SMTP_PORT` | SMTP port | `587` | No |
| `HTTP_METRICS_PORT` | Prometheus metrics port | `9090` | No |
| `HTTP_SDK_METRICS_PORT` | Temporal SDK metrics port | `9091` | No |
### Workflow Configuration
Temporal input configuration sample:
#### Orchestrator Workflow
```json
{
"schedule_name": "orchestrator-test",
"pipelines_query": {
"collection": "pipelines",
"aggregation": [
{
"$lookup": {
"from": "models",
"localField": "model_id",
"foreignField": "id",
"as": "model_docs"
}
},
{
"$match": {
"active": True
}
},
{
"$addFields": {
"models": {
"$arrayElemAt": [
"$model_docs",
0
]
}
}
},
{
"$match": {
"models.active": True
}
},
{
"$project": {
"model_docs": 0
}
}
]
},
"opc_servers_query": {
"collection": "opc-servers",
"filters": {
}
}
}
```
#### Alerts Workflow
```json
{
"schedule_name": "alerts",
"notification_ttl": 5*60,
"sent_ttl": 10*60
}
```
#### Reports Workflow
```json
{
"schedule_name": "reports",
}
```
## 📊 Monitoring and Metrics
The Orchestrator system exposes comprehensive Prometheus metrics:
### Application Metrics
- `app_up`: Application health status (1=healthy, 0=unhealthy)
- `email_sent_count`: Email delivery operation count by group
### Workflow Metrics
- Schedule creation, update, and deletion success rates
- Notification processing times and error rates
- Resource allocation and slot management metrics
### Database Metrics
- MongoDB query performance and connection health
- Redis operation counts and response times
- PostgreSQL export operations and audit log metrics
## 🧪 Testing
### Test Structure
```
tests/
├── orchestrator/ # Orchestrator workflow tests
├── activities/ # Activity implementation tests
├── utils/ # Utility function tests
└── integration/ # End-to-end workflow tests
```
### Test Execution
```bash
# Install test dependencies
pip install pytest pytest-cov pytest-asyncio
# Run tests with coverage
pytest --cov=orchestrator --cov-report=html
# Run specific test modules
pytest tests/activities/test_mongo_db.py
pytest tests/workflows/test_orchestrator.py
```
## 🔧 Development
### Project Structure
```
orchestrator/
├── activities/ # Temporal activity implementations
│ ├── activities.py # Main activities orchestrator
│ ├── temporal_manager.py # Temporal schedule operations
│ ├── slot_manager.py # Redis slot management
│ ├── mongo_db.py # MongoDB operations
│ ├── email.py # Email service operations
│ └── formatters.py # Configuration formatting
├── workflows/ # Temporal workflow definitions
│ ├── orchestrator.py # Main orchestration workflow
│ ├── alerts.py # Error alert workflow
│ ├── reports.py # Scheduled report workflow
│ └── subworkflows/ # Sub-workflow implementations
├── worker/ # Worker implementation
│ └── worker.py # Main worker orchestrator
├── utils/ # Utility functions
│ ├── connectors_config.py # Database configuration
│ ├── email_builder.py # Email template generation
│ └── orchestrator_functions.py # Pipeline utilities
└── metrics.py # Prometheus metrics definitions
```
### Adding New Features
1. **Follow Temporal patterns** for new workflows and activities
2. **Add comprehensive docstrings** for all public methods
3. **Include Prometheus metrics** for monitoring
4. **Add unit tests** for new functionality
5. **Update this README** with new features and configuration
## 🐛 Troubleshooting
### Common Issues
1. **Temporal Connection Failures**
- Verify Temporal server is running and accessible
- Check namespace configuration and permissions
- Review server logs for connection issues
2. **Database Connection Issues**
- Verify all database services are running
- Check connection credentials and network access
- Ensure proper connection pool configuration
3. **Email Delivery Failures**
- Verify SMTP server configuration and credentials
- Check email sender permissions and authentication
- Review email delivery logs for specific errors
4. **Workflow Execution Failures**
- Review activity error logs and notifications
- Check MongoDB collection configurations
- Verify input data format and required fields
### Debug Mode
Enable debug logging by setting the log level:
```bash
export LOG_LEVEL=DEBUG
```
## ⚡ Performance Tuning
### Key Parameters
- **Worker Concurrency**: Configure worker task limits in Temporal client
- **Connection Pools**: Optimize database connection pool sizes
- **Redis TTL**: Adjust cache TTL settings based on requirements
- **Batch Sizes**: Configure notification processing batch sizes
### Scaling Considerations
- **Horizontal Scaling**: Deploy multiple worker instances
- **Task Queue Distribution**: Use dedicated queues for different workflows
- **Database Performance**: Optimize indexes and connection pooling
- **Memory Management**: Monitor and configure appropriate resource limits
## 🤝 Contributing
1. Fork the repository
2. Create a feature branch
3. Make your changes with comprehensive testing
4. Update documentation and docstrings
5. Submit a pull request
### Code Quality Standards
- Follow PEP 8 style guidelines
- Include comprehensive docstrings for all public methods
- Maintain test coverage above 80%
- Use type hints where appropriate
- Follow Temporal.io best practices
## 📄 License
This project is licensed under the terms specified in the LICENSE file.
## 🆘 Support
For support and questions:
- Check the troubleshooting section above
- Review the metrics and logs for error patterns
- Open an issue in the project repository
- Contact the development team
---
**Note**: The SIENTIA DataOps Orchestrator is designed for production use in enterprise data environments. Ensure proper security configuration and network isolation for production deployments.

View File

@@ -1 +0,0 @@
pytest --cov=orchestrator --cov-report=html && xdg-open htmlcov/index.html

View File

@@ -1,148 +0,0 @@
version: '3.8'
services:
postgres:
image: postgres:15
container_name: postgres
environment:
POSTGRES_USER: sientia
POSTGRES_PASSWORD: sientia
POSTGRES_DB: sientia
ports:
- "5432:5432"
volumes:
- ./postgres_data:/var/lib/postgresql/data
networks:
- sientia-network
couchbase:
image: couchbase/server:7.2.0
container_name: couchbase
ports:
- "8091:8091" # Admin UI and REST API
- "8092:8092" # Query Service (N1QL)
- "8093:8093" # Index Service
- "8094:8094" # Search Service
- "11210:11210" # Data Service (KV)
- "18091:18091" # Analytics Service (if enabled)
environment:
CB_CLUSTER_USERNAME: sientia
CB_CLUSTER_PASSWORD: sientia
CB_CLUSTER_RAMSIZE: 256
CB_CLUSTER_INDEX_RAMSIZE: 256
volumes:
- ./couchbase_data:/opt/couchbase/var
networks:
- sientia-network
healthcheck:
test: ["CMD-SHELL", "curl -f http://localhost:8091/pools/default || exit 1"]
interval: 10s
timeout: 10s
retries: 5
redis:
image: redis:7-alpine # Using a lightweight Redis image
container_name: redis
ports:
- "6379:6379"
volumes:
- ./redis_data:/data # Persist Redis data
networks:
- sientia-network
redis-commander:
image: rediscommander/redis-commander:latest
container_name: redis-commander
environment:
REDIS_HOSTS: local:redis:6379 # Connects to the 'redis' service within the Docker network
ports:
- "8081:8081" # Access the Redis Commander UI on this port
depends_on:
- redis # Ensures Redis starts before Redis Commander
networks:
- sientia-network
kafka:
image: bitnami/kafka:3.7 # Using a specific Kafka version for stability
container_name: kafka
ports:
- "9092:9092" # For clients connecting from the host machine or outside Docker network
environment:
# KRaft (Kafka Raft without Zookeeper) settings
KAFKA_CFG_NODE_ID: '0'
KAFKA_CFG_PROCESS_ROLES: 'broker,controller'
KAFKA_CFG_CONTROLLER_LISTENER_NAMES: 'CONTROLLER'
# Listeners: <PROTOCOL>://<HOST/IP>:<PORT>
# PLAINTEXT_EXTERNAL for host access, INTERNAL for container-to-container communication
KAFKA_CFG_LISTENERS: 'PLAINTEXT_EXTERNAL://0.0.0.0:9092,INTERNAL://0.0.0.0:19092,CONTROLLER://0.0.0.0:9093'
# Advertised Listeners: How clients (including Kafka-UI) will connect
KAFKA_CFG_ADVERTISED_LISTENERS: 'PLAINTEXT_EXTERNAL://localhost:9092,INTERNAL://kafka:19092'
KAFKA_CFG_LISTENER_SECURITY_PROTOCOL_MAP: 'CONTROLLER:PLAINTEXT,PLAINTEXT_EXTERNAL:PLAINTEXT,INTERNAL:PLAINTEXT'
KAFKA_CFG_INTER_BROKER_LISTENER_NAME: 'INTERNAL'
KAFKA_CFG_CONTROLLER_QUORUM_VOTERS: '0@kafka:9093' # Node 0 is at kafka:9093 for controller comms
# Single node cluster settings (important for KRaft single node)
KAFKA_CFG_OFFSETS_TOPIC_REPLICATION_FACTOR: '1'
KAFKA_CFG_TRANSACTION_STATE_LOG_REPLICATION_FACTOR: '1'
KAFKA_CFG_TRANSACTION_STATE_LOG_MIN_ISR: '1'
KAFKA_CFG_DEFAULT_REPLICATION_FACTOR: '1' # For auto-created topics
KAFKA_CFG_NUM_PARTITIONS: '1' # Default partitions for auto-created topics
KAFKA_CFG_AUTO_CREATE_TOPICS_ENABLE: 'true' # Convenient for development
volumes:
- kafka_data:/bitnami/kafka # Bitnami Kafka data directory
networks:
- sientia-network
healthcheck:
# Checks if Kafka is ready by trying to list topics using the internal listener
test: ["CMD-SHELL", "/opt/bitnami/kafka/bin/kafka-topics.sh --bootstrap-server kafka:19092 --list > /dev/null || exit 1"]
interval: 30s
timeout: 10s
retries: 5
kafka-ui:
image: provectuslabs/kafka-ui:latest
container_name: kafka-ui
ports:
- "8082:8080" # Kafka UI will be accessible on host's port 8082
environment:
KAFKA_CLUSTERS_0_NAME: sientia-local-kafka
KAFKA_CLUSTERS_0_BOOTSTRAPSERVERS: kafka:19092 # Connects to Kafka's internal listener
# DYNAMIC_CONFIG_ENABLED: 'true' # Optional: To allow config changes through UI
depends_on:
kafka: # Ensures Kafka starts and is healthy before Kafka UI
condition: service_healthy
networks:
- sientia-network
mongodb:
image: mongo:7.0
container_name: mongodb
ports:
- "27017:27017"
environment:
MONGO_INITDB_ROOT_USERNAME: sientia
MONGO_INITDB_ROOT_PASSWORD: sientia
volumes:
- mongodb_data:/data/db
networks:
- sientia-network
networks:
sientia-network:
driver: bridge
volumes:
postgres_data:
driver: local
couchbase_data:
driver: local
redis_data:
driver: local
kafka_data:
driver: local
mongodb_data:
driver: local

View File

@@ -1,267 +0,0 @@
<!DOCTYPE html>
<html lang="pt-BR">
<head>
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>SIENTIA™ Report</title>
<style>
body { font-family: Arial, sans-serif; margin: 0; padding: 20px; }
h1, h2 { color: #333; }
table { width: 100%; border-collapse: collapse; margin-top: 20px; }
th, td { border: 1px solid #ddd; padding: 8px; text-align: left; }
th { background-color: #f4f4f4; }
</style>
</head>
<body>
<h1>SIENTIA™ Alerts</h1>
<h3>Errors detected:</h3>
<h4>Model: <span>ipsum et</span></h4>
<table>
<thead>
<tr>
<th>Notification ID</th>
<th>Schedule</th>
<th>Block</th>
<th>Timestamp</th>
<th>Message</th>
</tr>
</thead>
<tbody>
<tr>
<td>TAG_node34:tag_8_LISTENNING_STOPPED</td>
<td>adipiscing_eiusmod_do</td>
<td>dolor_labore_consectetur_ipsum</td>
<td>2025-07-29 14:39:52.952316+00:00</td>
<td>sed elit dolore incididunt incididunt aliqua</td>
</tr>
</tbody>
</table>
<h4>Model: <span>incididunt et do</span></h4>
<table>
<thead>
<tr>
<th>Notification ID</th>
<th>Schedule</th>
<th>Block</th>
<th>Timestamp</th>
<th>Message</th>
</tr>
</thead>
<tbody>
<tr>
<td>OPC_LISTENNING_STOPPED__server_5</td>
<td>eiusmod_adipiscing_dolore_ipsum_incididunt_incididunt</td>
<td>aliqua_dolore</td>
<td>2025-07-29 14:39:52.952579+00:00</td>
<td>dolor elit do ipsum consectetur amet ut do amet et</td>
</tr>
</tbody>
</table>
<h4>Model: <span>magna adipiscing aliqua</span></h4>
<table>
<thead>
<tr>
<th>Notification ID</th>
<th>Schedule</th>
<th>Block</th>
<th>Timestamp</th>
<th>Message</th>
</tr>
</thead>
<tbody>
<tr>
<td>REPORT_PARTITION_MANAGER</td>
<td>do_dolore_ut_amet</td>
<td>et_eiusmod</td>
<td>2025-07-29 14:39:52.952688+00:00</td>
<td>incididunt lorem eiusmod do et ipsum et ut</td>
</tr>
</tbody>
</table>
<h3>Warnings detected:</h3>
<h4>Model: <span>adipiscing magna lorem</span></h4>
<table>
<thead>
<tr>
<th>Notification ID</th>
<th>Schedule</th>
<th>Block</th>
<th>Timestamp</th>
<th>Message</th>
</tr>
</thead>
<tbody>
<tr>
<td>REPORT_PARTITION_MANAGER</td>
<td>ipsum_et_incididunt_do</td>
<td>ut_sed_incididunt</td>
<td>2025-07-29 14:39:52.952121+00:00</td>
<td>aliqua tempor aliqua sit ipsum amet elit ipsum</td>
</tr>
</tbody>
</table>
<h4>Model: <span>sed amet adipiscing incididunt</span></h4>
<table>
<thead>
<tr>
<th>Notification ID</th>
<th>Schedule</th>
<th>Block</th>
<th>Timestamp</th>
<th>Message</th>
</tr>
</thead>
<tbody>
<tr>
<td>ALIQUA_SIT_INCIDIDUNT_EIUSMOD</td>
<td>consectetur_dolore_sit_sed_sed</td>
<td>dolore_ipsum</td>
<td>2025-07-29 14:39:52.952259+00:00</td>
<td>do aliqua ut incididunt consectetur consectetur sed et labore</td>
</tr>
</tbody>
</table>
<h4>Model: <span>ipsum ipsum amet tempor</span></h4>
<table>
<thead>
<tr>
<th>Notification ID</th>
<th>Schedule</th>
<th>Block</th>
<th>Timestamp</th>
<th>Message</th>
</tr>
</thead>
<tbody>
<tr>
<td>OPC_LISTENNING_STOPPED__server_6</td>
<td>sit_labore_sed_dolor_et_elit</td>
<td>dolor_do_magna_et</td>
<td>2025-07-29 14:39:52.952376+00:00</td>
<td>magna consectetur do et dolor aliqua</td>
</tr>
</tbody>
</table>
<h4>Model: <span>sed ut</span></h4>
<table>
<thead>
<tr>
<th>Notification ID</th>
<th>Schedule</th>
<th>Block</th>
<th>Timestamp</th>
<th>Message</th>
</tr>
</thead>
<tbody>
<tr>
<td>REPORT_PARTITION_MANAGER</td>
<td>elit_et_ipsum_dolore</td>
<td>sed_ipsum</td>
<td>2025-07-29 14:39:52.952426+00:00</td>
<td>elit dolor dolore dolor eiusmod</td>
</tr>
</tbody>
</table>
<h4>Model: <span>eiusmod labore</span></h4>
<table>
<thead>
<tr>
<th>Notification ID</th>
<th>Schedule</th>
<th>Block</th>
<th>Timestamp</th>
<th>Message</th>
</tr>
</thead>
<tbody>
<tr>
<td>OPC_CONNECTION_RETRY__server_3</td>
<td>dolor_ut_dolor_sit_adipiscing_incididunt</td>
<td>sit_tempor_dolore</td>
<td>2025-07-29 14:39:52.952483+00:00</td>
<td>ipsum consectetur magna elit dolore</td>
</tr>
</tbody>
</table>
<h4>Model: <span>do dolor tempor amet</span></h4>
<table>
<thead>
<tr>
<th>Notification ID</th>
<th>Schedule</th>
<th>Block</th>
<th>Timestamp</th>
<th>Message</th>
</tr>
</thead>
<tbody>
<tr>
<td>REPORT_PARTITION_MANAGER</td>
<td>sed_sit_do_tempor_ut</td>
<td>eiusmod_adipiscing</td>
<td>2025-07-29 14:39:52.952637+00:00</td>
<td>incididunt do do adipiscing dolore ut ut elit sit labore</td>
</tr>
</tbody>
</table>
<h3>Infos detected:</h3>
<h4>Model: <span>sed consectetur ut</span></h4>
<table>
<thead>
<tr>
<th>Notification ID</th>
<th>Schedule</th>
<th>Block</th>
<th>Timestamp</th>
<th>Message</th>
</tr>
</thead>
<tbody>
<tr>
<td>TEMPOR_DO_DOLOR_TEMPOR_DOLOR</td>
<td>elit_tempor_dolore_consectetur_dolore_adipiscing</td>
<td>magna_labore_lorem</td>
<td>2025-07-29 14:39:52.952199+00:00</td>
<td>et et adipiscing lorem magna eiusmod labore do</td>
</tr>
</tbody>
</table>
</body>
</html>

View File

@@ -1,37 +0,0 @@
[
{
"schedule_name": "orchestrator-test",
"pipelines_query": "SELECT pipelines.*, models FROM `pipelines` JOIN `models` ON KEYS pipelines.model_id;",
"opc_servers_query": "select META().id, opc_servers.* from `opc_servers`;"
},
{
"schedule_name": "orchestrator-test",
"pipelines_query": {
"collection": "pipelines",
"aggregation": [
{
"$lookup": {
"from": "models",
"localField": "model_id",
"foreignField": "id",
"as": "model_docs"
}
},
{
"$addFields": {
"models": { "$arrayElemAt": ["$model_docs", 0] }
}
},
{
"$project": {
"model_docs": 0
}
}
]
},
"opc_servers_query": {
"collection": "opc-servers",
"filters": {}
}
}
]

View File

@@ -0,0 +1,15 @@
"""
SIENTIA DataOps Orchestrator Temporal.
A high-performance, scalable workflow orchestration system built on Temporal.io
for automated pipeline management, notification delivery, and resource coordination.
The orchestrator provides enterprise-grade workflow automation, real-time alerting,
and comprehensive monitoring capabilities for the SIENTIA platform.
Modules:
activities: Temporal activity implementations for database, email, and resource operations
workflows: Temporal workflow definitions for orchestration, alerts, and reports
worker: Main worker implementation and application lifecycle management
utils: Utility functions for configuration, email building, and data conversion
metrics: Prometheus metrics definitions for monitoring and observability
"""

View File

@@ -0,0 +1,12 @@
"""
Temporal activity implementations for the orchestrator.
This package contains all Temporal activity classes that implement
specific operations for the orchestration workflows including:
- Database operations (MongoDB, PostgreSQL, Redis)
- Email services and notification delivery
- Temporal schedule and resource management
- Configuration formatting and slot distribution
- Data validation and processing
"""

View File

@@ -16,6 +16,23 @@ with workflow.unsafe.imports_passed_through():
class Activities( # Couchbase,
TemporalManager, SlotManager, Formatters, MongoDB, Email,
Postgres):
"""
Central activities orchestrator for Temporal workflow operations.
This class combines multiple activity components including temporal management,
slot management, data formatting, MongoDB operations, email services, and
PostgreSQL operations. It provides a unified interface for all activity
operations required by the orchestration workflows.
Args:
temporal_config (dict[str, Any]): Temporal server configuration
redis_config (dict[str, Any]): Redis server configuration
mongodb_config (dict[str, Any]): MongoDB connection configuration
email_config (dict[str, Any]): Email service configuration
postgres_config (dict[str, Any]): PostgreSQL database configuration
logger (Logger): Application logger instance
notification_handler (NotificationHandler): Notification management handler
"""
def __init__(self,
temporal_config: dict[str, Any],
@@ -83,7 +100,11 @@ class Activities( # Couchbase,
def shutdown(self):
"""
Shutdown the MongoDB connection and clean up resources.
Shutdown all connections and clean up resources.
This method gracefully shuts down all database connections, email
services, and other resources to ensure proper cleanup when the
application terminates.
"""
MongoDB.shutdown(self)
Postgres.close(self)

View File

@@ -15,6 +15,25 @@ with workflow.unsafe.imports_passed_through():
class Couchbase(BaseActivity):
"""
Couchbase database operations activity (currently unused).
This class provides Couchbase database connectivity and query operations
for Temporal workflows. It handles connection management, query execution,
and error reporting with automatic connection lifecycle management.
Args:
connection_string (str): Couchbase cluster connection string
username (str): Couchbase authentication username
password (str): Couchbase authentication password
logger (Logger): Application logger instance
notification_handler (NotificationHandler): Notification management handler
Note:
This class is currently commented out in the main Activities class
but maintained for potential future use.
"""
def __init__(self, connection_string: str, username: str,
password: str, logger: Logger,
notification_handler: NotificationHandler):

View File

@@ -19,6 +19,22 @@ with workflow.unsafe.imports_passed_through():
class Email(BaseActivity):
"""
Email service activity for sending workflow notifications.
This class provides email sending capabilities including HTML email
generation, attachment handling, and SMTP connection management with
automatic reconnection for workflow notification delivery.
Args:
sender_email (str): Email address for sending messages
sender_password (str): SMTP authentication password
smtp_server (str): SMTP server hostname
smtp_port (int): SMTP server port number
logger (Logger): Application logger instance
notification_handler (NotificationHandler): Notification management handler
"""
def __init__(self, sender_email: str, sender_password: str,
smtp_server: str, smtp_port: int,
logger: Logger, notification_handler: NotificationHandler):
@@ -51,10 +67,24 @@ class Email(BaseActivity):
@activity.defn(name="build_email_html")
async def build_email_html(self, input_data: dict[str, Any]) -> dict[str, Any]:
"""
Builds the email html for each receiver group.
input_data:
- receiver_groups (dict): The receiver groups.
- mail_type (str): The mail type.
Build HTML email content for configured receiver groups.
This activity generates HTML email content for each receiver group
based on notification data and mail type. It processes notification
data through the email builder to create formatted HTML messages.
Args:
input_data (dict[str, Any]): Activity input parameters.
Required fields:
- metadata (dict[str, Any]): Workflow execution metadata
- receiver_groups (dict[str, Any]): Receiver group configurations with notifications
- mail_type (str): Type of email (Alerts/Reports)
Returns:
dict[str, Any]: Updated receiver groups with generated HTML content
Raises:
Exception: If HTML generation fails
"""
metadata = input_data['metadata']
receiver_groups = input_data['receiver_groups']
@@ -147,10 +177,24 @@ class Email(BaseActivity):
@activity.defn(name="send_email")
async def send_email(self, input_data: dict[str, Any]) -> dict[str, Any]:
"""
Sends an email to the receivers of each group.
input_data:
- receiver_groups (dict): The receiver groups.
- mail_type (str): The mail type.
Send email notifications to configured receiver groups.
This activity sends HTML emails with attachments to all configured
receiver groups. It handles SMTP connection management, attachment
processing, and error reporting with automatic reconnection support.
Args:
input_data (dict[str, Any]): Activity input parameters.
Required fields:
- metadata (dict[str, Any]): Workflow execution metadata
- receiver_groups (dict[str, Any]): Receiver groups with HTML content
- mail_type (str): Type of email being sent (Alerts/Reports)
Returns:
dict[str, Any]: Updated receiver groups with sending status
Raises:
Exception: If email sending fails for all groups
"""
metadata = input_data['metadata']
receiver_groups = input_data['receiver_groups']

View File

@@ -22,6 +22,21 @@ topic_separator = "\n ========== \n"
class Formatters(BaseActivity):
"""
Schedule and slot configuration formatting activity.
This class provides formatting operations for schedules and OPC slots,
converting pipeline configurations into Temporal-compatible formats
and managing slot distribution across active ingestors for optimal
resource utilization.
Args:
scouter_namespace (str): Scouter workflow namespace
laborious_namespace (str): Laborious workflow namespace
logger (Logger): Application logger instance
notification_handler (NotificationHandler): Notification management handler
"""
def __init__(self,
scouter_namespace: str,
laborious_namespace: str,

View File

@@ -41,6 +41,22 @@ def clear_mongo_id(docs: list) -> list:
class MongoDB(BaseActivity):
"""
MongoDB operations activity for Temporal workflows.
This class provides MongoDB database operations including document
querying, aggregation, timestamp management, and collection management
with TTL indexes. It handles all MongoDB interactions required by
the orchestration system.
Args:
connection_string (str): MongoDB connection string
database_name (str): Target database name
ttl_index_seconds (int): TTL index duration in seconds
logger (Logger): Application logger instance
notification_handler (NotificationHandler): Notification management handler
"""
def __init__(self, connection_string: str, database_name: str, ttl_index_seconds: int,
logger: Logger,
notification_handler: NotificationHandler):
@@ -415,14 +431,25 @@ class MongoDB(BaseActivity):
@activity.defn(name="load_latest_data")
async def load_latest_data(self, input_data: dict[str, Any]) -> list[dict[str, Any]]:
"""
Loads the latest data from MongoDB.
input_data:
- metadata (dict): The metadata of the workflow.
- collection_name (str): The name of the collection to load data from.
- last_data_timestamp (str): The timestamp of the last data to load.
- base_data_filter (dict): The base data filter to apply to the query.
returns:
- data (list[dict]): The data loaded from MongoDB.
Load the latest data from MongoDB collection since a specified timestamp.
This activity retrieves data from a MongoDB collection, optionally
filtering by timestamp to enable incremental data processing. It
handles connection management and provides comprehensive error reporting.
Args:
input_data (dict[str, Any]): Activity input parameters.
Required fields:
- metadata (dict[str, Any]): Workflow execution metadata
- collection_name (str): Name of the MongoDB collection
- last_data_timestamp (str | None): Last processed timestamp for filtering
- base_data_filter (dict[str, Any]): Base query filter conditions
Returns:
list[dict[str, Any]]: Retrieved data, or empty list if no data found
Raises:
Exception: If MongoDB operation fails
"""
metadata = input_data['metadata']
collection_name = input_data['collection_name']

View File

@@ -15,6 +15,22 @@ with workflow.unsafe.imports_passed_through():
class SlotManager(Redis):
"""
Redis-based OPC slot management activity.
This class manages OPC server slots and notification processing through
Redis operations. It provides functionality for loading, updating, and
deleting OPC slots, managing active ingestors, and handling notification
caching with timestamp management.
Args:
host (str): Redis server hostname
port (int): Redis server port number
username (str): Redis authentication username
password (str): Redis authentication password
logger (Logger): Application logger instance
notification_handler (NotificationHandler): Notification management handler
"""
def __init__(self, host: str, port: int,
username: str, password: str,

View File

@@ -19,6 +19,22 @@ with workflow.unsafe.imports_passed_through():
class TemporalManager(BaseActivity):
"""
Temporal workflow and schedule management activity.
This class manages Temporal schedules across multiple namespaces,
providing operations for schedule creation, updates, deletion, and
normalization. It handles connections to both scouter and laborious
namespaces for comprehensive workflow orchestration.
Args:
host (str): Temporal server host address
scouter_namespace (str): Scouter workflow namespace
laborious_namespace (str): Laborious workflow namespace
logger (Logger): Application logger instance
notification_handler (NotificationHandler): Notification management handler
"""
def __init__(self, host: str, scouter_namespace: str, laborious_namespace: str,
logger: Logger, notification_handler: NotificationHandler):

View File

@@ -1,3 +1,11 @@
"""
Prometheus metrics definitions for the orchestrator application.
This module defines all Prometheus metrics used for monitoring the
orchestrator system including application health, email delivery,
and workflow execution metrics.
"""
from prometheus_client import Gauge, Counter
APP_UP = Gauge(

View File

@@ -1,6 +1,23 @@
def parse_frequency(frequency: str) -> int:
"""
Parse frequency string to seconds
Parse frequency string into seconds for Temporal schedule intervals.
This function converts human-readable frequency strings into seconds
for use in Temporal schedule configurations. Supports seconds, minutes,
hours, and days notation.
Args:
frequency (str): Frequency string with suffix:
- 's' for seconds (e.g., '30s')
- 'm' for minutes (e.g., '5m')
- 'h' for hours (e.g., '2h')
- 'd' for days (e.g., '1d')
Returns:
int: Frequency converted to seconds
Raises:
ValueError: If frequency format is invalid
"""
if frequency.endswith("s"):
return int(frequency[:-1])

View File

@@ -6,6 +6,18 @@ import re
class EmailBuilder:
"""
HTML email template builder for notification emails.
This class handles the generation of HTML email content from notification
data using Jinja2 templates. It supports different email types (alerts,
reports) and notification levels (ERROR, WARNING, INFO) with customizable
templates and parameter replacement.
Args:
logger (Logger): Application logger instance for error reporting
"""
def __init__(self, logger: Logger):
self.logger = logger

View File

@@ -0,0 +1,11 @@
"""
Temporal workflow definitions for the orchestrator.
This package contains all Temporal workflow classes that define
the business logic and coordination patterns for:
- Main orchestration workflow for pipeline and resource management
- Alert workflows for real-time error notification delivery
- Report workflows for scheduled notification summaries
- Subworkflows for notification loading and processing
"""

View File

@@ -9,16 +9,37 @@ with workflow.unsafe.imports_passed_through():
@workflow.defn(name="orchestrator")
class Orchestrator:
"""
Main orchestrator workflow for pipeline and resource management.
This workflow coordinates pipeline deployment and OPC server slot
management by retrieving configurations from MongoDB and Redis,
processing schedules, and deploying them to the Temporal server
and Redis infrastructure.
"""
@workflow.run
async def run(self, input_data: dict[str, Any]):
"""
Orchestrates the pipeline and slot management. Gets configuration from MongoDB and Redis,
creates the configuration and deploys the schedules and slots in the Temporal server and
Redis server.
input_data:
- schedule_name (str): The name of the schedule.
- pipelines_query (dict): The query to get the pipelines.
- opc_servers_query (dict): The query to get the OPC servers.
Execute the orchestration workflow for pipeline and slot management.
This workflow retrieves pipeline configurations and OPC server data,
processes schedules and slot configurations, and deploys them to
the appropriate services. It handles creation, updates, and deletion
of schedules and slots based on current system state.
Args:
input_data (dict[str, Any]): Workflow input parameters.
Required fields:
- schedule_name (str): Name of the orchestration schedule
- pipelines_query (dict[str, Any]): MongoDB query for pipeline configurations
- opc_servers_query (dict[str, Any]): MongoDB query for OPC server data
Returns:
None: Workflow completes without return value
Raises:
Exception: If orchestration operations fail
"""
input_data['workflow_name'] = 'orchestrator'

View File

@@ -9,20 +9,34 @@ with workflow.unsafe.imports_passed_through():
@workflow.defn(name="reports")
class Reports:
"""
Reports workflow for sending scheduled notification summaries.
This workflow processes and sends scheduled reports to configured
user groups. It loads notification data from MongoDB, filters it
by receiver group configurations, and sends formatted HTML reports
via email.
"""
@workflow.run
async def run(self, input_data: dict[str, Any]):
"""
Workflow to send reports to the users
Execute the reports workflow for scheduled notification delivery.
This workflow loads all notifications from the notification queue,
applies receiver group filtering, and sends comprehensive HTML
reports to configured user groups.
Args:
input_data (dict[str, Any]): Input data. It contains the following keys:
- schedule_name: str - Name of the schedule
input_data (dict[str, Any]): Workflow input parameters.
Required fields:
- schedule_name (str): Name of the report schedule
Returns:
None
None: Workflow completes without return value
Raises:
Exception: If the workflow fails
Exception: If report generation or delivery fails
"""
metadata = {
'metadata': {

View File

@@ -9,20 +9,39 @@ with workflow.unsafe.imports_passed_through():
@workflow.defn(name="load_notification_package")
class LoadNotificationPackage:
"""
Subworkflow for loading notification data and configuration.
This subworkflow retrieves notification packages from MongoDB and
loads receiver group configurations. It handles timestamp-based
filtering for incremental data processing and manages the data
required for notification workflows.
"""
@workflow.run
async def run(self, input_data: dict[str, Any]):
"""
Loads the notification package from the MongoDB collection "notification_queue"
and the sending configs from the MongoDB collection "receiver_groups".
Load notification package and sending configurations.
input_data:
- metadata (dict): The metadata of the workflow.
This subworkflow loads notifications from the MongoDB notification
queue using timestamp-based filtering and retrieves active receiver
group configurations. It updates the last processed timestamp in Redis.
returns:
- last_timestamp (str): The last timestamp of the notification package.
- notification_package (list[dict]): The notification package.
- sending_configs (list[dict]): The sending configs.
- mail_type (str): The mail type.
Args:
input_data (dict[str, Any]): Workflow input parameters.
Required fields:
- metadata (dict[str, Any]): Workflow execution metadata
- mail_type (str): Type of mail (Alerts/Reports)
- base_data_filter (dict[str, Any]): Base filter for notification query
Returns:
dict[str, Any]: Package containing:
- last_timestamp (str | None): Last processed timestamp
- notification_package (list[dict]): Retrieved notifications
- sending_configs (list[dict]): Active receiver group configurations
Raises:
Exception: If data loading fails
"""
metadata = input_data['metadata']

View File

@@ -10,30 +10,37 @@ with workflow.unsafe.imports_passed_through():
@workflow.defn(name="process_notifications")
class ProcessNotifications:
"""
Subworkflow for processing and sending notification emails.
This subworkflow handles the email delivery process including HTML
generation, email sending, and logging to PostgreSQL. It processes
receiver groups and generates delivery reports for monitoring.
"""
@workflow.run
async def run(self, input_data: dict[str, Any]) -> dict[str, Any]:
"""
Processes the notifications. Builds the report html for each group and each model,
sends the report html to the receivers of each group, stores the sending log in the
postgres database "log_report", and returns the log report to the caller.
Process notifications and send emails to configured receiver groups.
input_data:
- metadata (dict): The metadata of the workflow.
- mail_type (str): The mail type.
- schema (str): The schema of the table.
- table_name (str): The name of the table.
- notification_package (list[dict]): The notification package. the format of each
notification package is:
{
'group_name' (str)
'group_members' (list[str])
'notifications' (dict)
{
'model_name' (dict[str, list[dict]])
}
}
returns:
- log_report (dict)
This subworkflow builds HTML email content, sends emails to all
receiver groups, and logs the delivery results to PostgreSQL for
monitoring and audit purposes.
Args:
input_data (dict[str, Any]): Workflow input parameters.
Required fields:
- metadata (dict[str, Any]): Workflow execution metadata
- mail_type (str): Type of email being sent
- schema (str): PostgreSQL schema name for logging
- table_name (str): PostgreSQL table name for logging
- notification_package (dict[str, Any]): Receiver groups with notifications
Returns:
dict[str, Any]: Log report of email delivery results
Raises:
Exception: If notification processing fails
"""
metadata = input_data["metadata"]