Eldric Cluster Architecture

Complete reference for distributed AI infrastructure with database connectivity

v3.0.4

Global Cluster Layout

Enterprise Multi-Region Deployment
Eldric Distributed AI Cluster Global Controller Primary - Port 8880 EU-WEST Region Controller Secondary Router 8881 Worker Ollama Worker vLLM Data PostgreSQL PostgreSQL EU Analytics DB US-EAST Region Controller Secondary Router 8881 Worker TGI Worker Triton Data MySQL MySQL US App DB APAC Region Controller Secondary Router 8881 Worker llama.cpp Data DB2 IBM DB2 z/OS Mainframe - DRDA Edge Layer - CDN / Gateway Edge Server Europe CDN Edge Server Americas CDN Edge Server Asia CDN API Gateway Load Balancer - SSL External Clients (Web Apps, Mobile, CLI, API Consumers) HTTPS / REST API / WebSocket Legend Controller (8880) Router (8881) AI Worker (8890) Data Worker (8895) Edge

Node Types

Controller

Port 8880

Cluster orchestration and management. Handles node registration, job scheduling, license validation, and provides the management dashboard.

Tiers: Primary, Secondary, Tertiary

Binary: eldric-multiapi

Router

Port 8881

Intelligent request routing with AI-powered decisions. Routes requests to appropriate workers based on content, model requirements, and load.

Features: Theme detection, model specialization, load balancing, streaming support

Binaries:

  • eldric-routerd - Dedicated router daemon (recommended)
  • eldric-multiapi --router - Router mode in controller

AI Worker

Port 8890

Handles AI inference requests via multiple backends: Ollama, vLLM, TGI, llama.cpp, Triton, TensorFlow Serving.

Tiers: Core (GPU), Standard, Edge

Binary: eldric-workerd

Data Worker

Port 8895

Database connectivity for AI workers. Connection pooling with health checks. Supports PostgreSQL, MySQL, SQLite, IBM DB2.

Features: Connection pooling, schema discovery, parameterized queries

Binary: eldric-datad

Edge Server

Port 8080

Edge/CDN gateway for caching, SSL termination, and request optimization at the network edge.

Features: Caching, compression, geo-routing

Binary: eldric-edge

Deployment Scenarios

1. Development Setup

Single machine for local development and testing

localhost Your Machine Controller :8880 Worker Ollama :8890 Data SQLite :8895 dev.db SQLite

2. Production Multi-Region

Global deployment with regional controllers

Global Primary US-WEST EU-WEST APAC Secondary Secondary Secondary vLLM Data TGI Data Triton Data PostgreSQL MySQL DB2

3. Enterprise Mainframe

IBM z/OS DB2 connectivity via DRDA

Eldric Cluster Controller :8880 Worker AI Inference Data DB2 CLI mainframe db2 DRDA :446 SSL IBM z/OS DB2 DSN1 / DSN1LOC VSAM IMS DB Pool: 5-50 conn

4. Knowledge Routing

AI-powered theme detection and model selection

Request "medical Q" AI Router Theme Detection medical legal code general Medical Worker meditron:70b Legal Worker saul:7b Code Worker codellama:34b General Worker llama3.1:70b AI selects optimal model

Use Cases

Enterprise AI Analytics Platform

User Query
→
Edge/CDN
→
Router
Theme Detection
→
AI Worker
SQL Generation
→
Data Worker
Query DB
→
AI Worker
Analyze Results

Multi-Database RAG Pipeline

Combine data from multiple enterprise databases for AI-powered analysis:

# AI Worker queries multiple data sources 1. Query PostgreSQL for customer data 2. Query MySQL for transaction history 3. Query DB2 z/OS for mainframe records 4. AI synthesizes all data into unified response

Real-time Business Intelligence

Dashboard Request
→
Controller API
→
Data Workers
→
DB Cluster
→
AI Summary

Quick Reference

Start a Complete Cluster

# 1. Controller (management) ./eldric-multiapi -p 8880 # 2. Router - Option A: Dedicated daemon (recommended) ./eldric-routerd -p 8881 -c http://localhost:8880 --ai-routing # 2. Router - Option B: Controller router mode ./eldric-multiapi --router -p 8881 -c http://localhost:8880 # 3. AI Workers (inference) ./eldric-workerd -p 8890 -c http://localhost:8880 # 4. Data Workers (databases) ./eldric-datad -p 8895 -c http://localhost:8880 # 5. Edge Server (CDN/gateway) ./eldric-edge -p 8080 -c http://localhost:8880

Health Checks

curl http://localhost:8880/health # Controller curl http://localhost:8881/health # Router curl http://localhost:8890/health # Worker curl http://localhost:8895/health # Data Worker

Port Reference

Component Default Port Protocol Purpose
Controller 8880 HTTP/REST Cluster API, Dashboard, Node Registration
Router 8881 HTTP/REST Request Routing, Load Balancing
AI Worker 8890 HTTP/REST LLM Inference, Tool Execution
Data Worker 8895 HTTP/REST Database Queries, Schema Discovery
Edge Server 8080 HTTP/HTTPS CDN, SSL Termination, Caching

Reserved Ports (Inference Backends)

Backend Port Notes
Ollama11434Local LLM runtime
vLLM8000OpenAI-compatible API
TGI8080HuggingFace Text Generation
llama.cpp8081Native GGUF serving
Triton8000-8002NVIDIA multi-framework
TensorFlow Serving8501TensorFlow models