Writing

Notes on backend engineering, distributed systems, databases and AI.

28
Nov
Street photograph by Stalin Pereira

Kafka vs. NATS: Why Your Team Is Probably Better Off With the Underdog

Challenging the default enterprise choice of Kafka by arguing that for most modern, real-time applications, NATS provides a simpler, more performant, and cost-effective solution without the operational overhead.
1 min read
24
Nov
A hand planting a seedling in sand

Stop Paying for OpenAI: How to Self-Host an Enterprise-Grade RAG on Your Laptop with Ollama

Build a fully local RAG pipeline with Ollama, open embedding models, and Chroma: working Python for ingestion, retrieval, and a FastAPI service, plus the tuning, security, and cost trade-offs that decide whether self-hosting is right for you.
9 min read
24
Nov
Street photograph by Stalin Pereira

Ditch the Cloud: Why Every AI Engineer Needs to Master Ollama for Local LLM Development

Advocating for the underappreciated power and simplicity of local LLMs using Ollama as a superior alternative to cloud-based APIs for development, iteration speed, and data privacy.
1 min read
23
Nov
Street photograph by Stalin Pereira

A Practical Guide to Implementing Semantic Search with Vector Databases (e.g., Pinecone, Milvus)

Beyond Keywords: Why Vector Databases Are the Real Future of Semantic Search, Not Your Old Fuzzy Search Hacks
1 min read