Setting Up Your Self-Hosted AI Stack - Part 3: From Receipts to Structured Data with Vision Language Models and n8n
Feb 3 · 21 min read · It's Been a While Sorry for being away for so long. I've been head-down strengthening my software engineering foundation—consuming rather than producing. After a while, I started feeling this pull to balance things out by building again. I just finis...
Join discussion
Observability 3.0 AI-Powered APM = Claude (cloud-based) / Ollama (self-hosted) + MCP Server + n8n + Prometheus, Grafana, Loki, Tempo, OpenTelemetry
Dec 20, 2025 · 11 min read · In today’s cloud-based world, observability is no longer just about collecting logs, metrics, and traces. We can take observability to the next level with AI-powered Application Performance Monitoring (APM). Tools like Claude (cloud-based AI) and Oll...
Join discussion
Setting Up Your Self-Hosted AI Stack - Part 2: Document Processing and RAG with Apache Tika and Qdrant Vector Database
Aug 10, 2025 · 15 min read · What we're building today We're adding document processing capabilities to the foundation from Part 1. This extends your chat interface to work with your files and documents. Two key additions make th
FAFMI and 1 more commented
Setting Up Your Self-Hosted AI Stack - Part 1: Building the foundation with Open WebUI, Ollama, and Postgres
Aug 3, 2025 · 11 min read · What we're building today By the end of this post, you'll have a fully operational chat interface connected to the LLM of your choice, running completely locally. No external APIs, no data leaving you
Join discussion