AI Services
AI Services Server Configuration
This document details the server configuration for the AI Services suite, providing a guide for new system administrators and engineers deploying and maintaining these crucial components. The AI Services provide backend processing for various features across the wiki, including [Semantic MediaWiki] enhancements, [abuse filtering], and [content translation]. Understanding the underlying infrastructure is key to optimal performance and stability. This configuration is current as of MediaWiki 1.40.
Overview
The AI Services are hosted on a dedicated cluster of servers, separated from the core wiki infrastructure to isolate resource contention. This cluster utilizes a combination of high-performance CPUs, substantial RAM, and fast storage to handle the computationally intensive tasks associated with AI processing. The services themselves are containerized using [Docker] and orchestrated with [Kubernetes] for scalability and resilience. Monitoring is carried out via [Prometheus] and visualized using [Grafana]. Access to the AI Services cluster is restricted to authorized personnel only, utilizing [SSH keys] and multi-factor authentication. Regular [backups] are performed to ensure data recovery in case of failure. All services are designed to be stateless, allowing for easy scaling and replacement of individual instances.
Hardware Specifications
The AI Services cluster consists of five dedicated servers, each with the following specifications:
| Component | Specification |
|---|---|
| CPU | 2 x Intel Xeon Gold 6248R (24 cores/48 threads per CPU) |
| RAM | 256 GB DDR4 ECC Registered 2933MHz |
| Storage | 2 x 4TB NVMe SSD (RAID 1) for OS and application data |
| Network | 2 x 100 Gigabit Ethernet |
| Power Supply | 2 x 1600W Redundant Power Supplies |
These specifications are chosen to provide sufficient processing power and memory for the AI models used. The NVMe SSDs ensure fast data access, critical for minimizing latency. The redundant power supplies offer high availability. [Network configuration] is handled by our dedicated networking team.
Software Stack
The software stack is built around a core of Linux, Docker, and Kubernetes. Here's a breakdown:
| Software | Version |
|---|---|
| Operating System | Ubuntu Server 22.04 LTS |
| Containerization | Docker 20.10 |
| Orchestration | Kubernetes 1.25 |
| Monitoring | Prometheus 2.40, Grafana 9.0 |
| Logging | Elasticsearch 8.5, Logstash 8.5, Kibana 8.5 (the [ELK stack]) |
| Programming Languages | Python 3.9, C++ |
This stack allows for efficient deployment, scaling, and monitoring of the AI Services. The ELK stack provides centralized logging for troubleshooting and auditing. [Security updates] are applied regularly to all components.
Service Breakdown
The AI Services cluster hosts several key services, each responsible for a specific AI-powered feature.
| Service Name | Description | Scalability |
|---|---|---|
| Semantic Analysis Service | Processes text to extract meaning and relationships for [Semantic MediaWiki]. | Horizontal (up to 10 replicas) |
| Abuse Filter Service | Evaluates edits against predefined rules to detect and prevent vandalism and spam. | Horizontal (up to 5 replicas) |
| Content Translation Service | Provides machine translation capabilities for [Translation extensions]. | Horizontal (up to 8 replicas) |
| Sentiment Analysis Service | Analyzes the sentiment of text content to identify potentially problematic contributions. | Horizontal (up to 3 replicas) |
| Image Recognition Service | Identifies objects and content within uploaded images, used for [category suggestions]. | Horizontal (up to 4 replicas) |
Each service is deployed as a separate Kubernetes deployment, allowing for independent scaling and updates. [Resource limits] are configured for each service to prevent resource exhaustion. [Load balancing] is handled by Kubernetes services.
Access and Security
Access to the AI Services cluster is strictly controlled. Only authorized personnel with approved [SSH keys] and enabled [multi-factor authentication] are granted access. Network access is limited to specific IP ranges. All communication between services is encrypted using [TLS]. Regular security audits are conducted to identify and address potential vulnerabilities. [Firewall rules] are configured to restrict inbound and outbound traffic.
Future Considerations
Future enhancements to the AI Services infrastructure include:
- Integration with a dedicated [GPU cluster] for more demanding AI tasks.
- Implementation of a [model registry] for managing and versioning AI models.
- Exploration of [serverless computing] options for specific services.
- Enhanced monitoring and alerting capabilities.
- Improved [disaster recovery] procedures.
This documentation provides a starting point for understanding the AI Services server configuration. Please consult the [internal documentation wiki] for more detailed information and specific configuration details. Refer to the [Kubernetes documentation] for detailed information on managing deployments and services. [Contact the DevOps team] for any assistance or questions.
Semantic MediaWiki
Abuse filtering
Content translation
Docker
Kubernetes
Prometheus
Grafana
SSH keys
Backups
Network configuration
Security updates
ELK stack
Translation extensions
Resource limits
Load balancing
Multi-factor authentication
TLS
Firewall rules
GPU cluster
Model registry
Serverless computing
Disaster recovery
Internal documentation wiki
Kubernetes documentation
Contact the DevOps team
Intel-Based Server Configurations
| Configuration | Specifications | Benchmark |
|---|---|---|
| Core i7-6700K/7700 Server | 64 GB DDR4, NVMe SSD 2 x 512 GB | CPU Benchmark: 8046 |
| Core i7-8700 Server | 64 GB DDR4, NVMe SSD 2x1 TB | CPU Benchmark: 13124 |
| Core i9-9900K Server | 128 GB DDR4, NVMe SSD 2 x 1 TB | CPU Benchmark: 49969 |
| Core i9-13900 Server (64GB) | 64 GB RAM, 2x2 TB NVMe SSD | |
| Core i9-13900 Server (128GB) | 128 GB RAM, 2x2 TB NVMe SSD | |
| Core i5-13500 Server (64GB) | 64 GB RAM, 2x500 GB NVMe SSD | |
| Core i5-13500 Server (128GB) | 128 GB RAM, 2x500 GB NVMe SSD | |
| Core i5-13500 Workstation | 64 GB DDR5 RAM, 2 NVMe SSD, NVIDIA RTX 4000 |
AMD-Based Server Configurations
| Configuration | Specifications | Benchmark |
|---|---|---|
| Ryzen 5 3600 Server | 64 GB RAM, 2x480 GB NVMe | CPU Benchmark: 17849 |
| Ryzen 7 7700 Server | 64 GB DDR5 RAM, 2x1 TB NVMe | CPU Benchmark: 35224 |
| Ryzen 9 5950X Server | 128 GB RAM, 2x4 TB NVMe | CPU Benchmark: 46045 |
| Ryzen 9 7950X Server | 128 GB DDR5 ECC, 2x2 TB NVMe | CPU Benchmark: 63561 |
| EPYC 7502P Server (128GB/1TB) | 128 GB RAM, 1 TB NVMe | CPU Benchmark: 48021 |
| EPYC 7502P Server (128GB/2TB) | 128 GB RAM, 2 TB NVMe | CPU Benchmark: 48021 |
| EPYC 7502P Server (128GB/4TB) | 128 GB RAM, 2x2 TB NVMe | CPU Benchmark: 48021 |
| EPYC 7502P Server (256GB/1TB) | 256 GB RAM, 1 TB NVMe | CPU Benchmark: 48021 |
| EPYC 7502P Server (256GB/4TB) | 256 GB RAM, 2x2 TB NVMe | CPU Benchmark: 48021 |
| EPYC 9454P Server | 256 GB RAM, 2x2 TB NVMe |
Order Your Dedicated Server
Configure and order your ideal server configuration
Need Assistance?
- Telegram: @powervps Servers at a discounted price
⚠️ *Note: All benchmark scores are approximate and may vary based on configuration. Server availability subject to stock.* ⚠️