@oziomaochin

Engineers Don't Want to Search Logs. They Want to Know What Broke.

3d ago · 12 min read · It's 7 pm on a Friday and production is on fire. Your weekend is off to a great start. Obviously. Your Payment service is throwing errors and your company is losing revenue. You open your log tool, fi

Semantic Search Is an Architecture Problem — Not an Embedding Problem

Apr 11 · 14 min read · Most semantic search systems don’t fail at the embedding layer. They fail at the architecture layer. When I started building a semantic search API with Spring Boot and pgvector, I expected the hard pa

Building a Semantic Search API with Spring Boot and pgvector — Part 4: The Service Layer.

Apr 5 · 11 min read · This is Part 4 of a series building a production-ready semantic search API with Java, Spring Boot, and pgvector. Part 1 covered the architecture. Part 2 defined the schema. Part 3 handled the embeddi

Why Most Developers Reach for a Vector Database Too Soon.

Mar 28 · 12 min read · The feature request sounded simple: type question, get the right internal doc back. A few hundred documents. Support notes and wiki pages, nothing exotic. The kind of thing that should take a week, ma

Building a Semantic Search API with Spring Boot and pgvector - Part 3: The Embedding Layer.

Mar 20 · 11 min read · Most semantic search tutorials treat embeddings as a single line of code — call the API, get a vector, store it. In practice, this is the part of the system where the most subtle bugs live. Not the ki