Articles

Long-form writing on software engineering, systems design, and building things.

How I Built a RAG System in Rails Using Nomic Embeddings and OpenAI

RAG doesn’t have to mean heavyweight infrastructure. In this post, I show how I wired up a lean Retrieval-Augmented Generation pipeline inside a Rails app using Nomic for embeddings, PgVector for search, and OpenAI for generation. The result is a flexible system: open-source at the embedding layer, powerful where it counts, and simple enough to extend without vendor lock-in.

Autocomplete at Scale - How Tries and Partitioning Can Unlock Blazing-Fast Search in Ruby on Rails

Scalable autocomplete functionality achieving sub-millisecond response times with millions of records employs trie data structures and advanced partitioning strategies in Ruby on Rails. Performance optimization techniques include memory management, database partitioning patterns, and efficient prefix-based search algorithms.