Technical Infrastructure
Production infrastructure that powers the things I design and build. I use a wide variety of tools, systems and custom built models that adapt specifically to what YOU need.
Technology Stack
System Architecture
A modular production stack: gateway at the edge, services in the middle, knowledge and storage beneath. The specifics change per project—the structure stays consistent.
Receives all external traffic, routes to internal services, enforces global policies, and handles TLS. First line of defense and traffic control.
Stateless services handling REST/GraphQL APIs, real-time channels, and async workers. Message queues decouple workloads for resilience.
150+ workflows orchestrate data movement, scheduled tasks, and event-driven automations. 8.5K daily executions coordinate the entire stack.
Privacy-first AI with local Ollama models and 2.8M vector embeddings. Semantic search, code generation, and intelligent automation—all running in-house.
Multi-model persistence: PostgreSQL for transactions, Neo4j for relationships, Redis for sub-millisecond reads. Purpose-built for each data pattern.
End-to-end observability with Prometheus metrics, Grafana dashboards, and real-time alerting. Security policies enforced at every layer.
All services communicate via internal Docker network with automatic service discovery. Prometheus monitors health metrics, Grafana visualizes performance, and automated backups run daily.
AI Infrastructure
Privacy-first AI architecture. All models run locally via Ollama—no data leaves your infrastructure. Cloud APIs (OpenAI, Claude) used only for non-sensitive workloads.
# Model routing logic
if task.sensitive_data:
model = "llama3.1:8b" # Local only
elif task.requires_code:
model = "deepseek-coder:6.7b"
elif task.context_length > 10000:
model = "claude-3.5-sonnet"
else:
model = "mistral:7b" # Fast default
Vector Database
Weaviate vector database with 2.8M+ embeddings enables sub-100ms semantic search across millions of entities. Hybrid search combines vector similarity with keyword filtering for precision.
Embedding Pipeline: Documents chunked to 512 tokens → Voyage AI embeddings → Weaviate index → Redis cache hot queries. Nuculair uses this for instant profile context retrieval across 300+ data sources.
Hybrid Search: Vector similarity (cosine distance) + BM25 keyword matching + metadata filters. Weighted fusion algorithm combines scores for optimal relevance ranking.
Workflow Orchestration
150+ n8n workflows handle data ingestion, processing, and delivery. 8,500+ daily executions power OSINT aggregation, security scanning, and AI model orchestration.