How to Choose the Right Search Model for RAG Using Retrieval Metrics
Use evaluation — not hype — to match your embedding or search approach to how users actually query
Jul 3, 202610 min read90
Command Palette
Search for a command to run...
Latest articles
The hidden cost of RAG: our vector database is not the bottleneck
The real bottlenecks in AI product search — and where retrieval-augmented generation (RAG) actually gets slow, expensive, and wrong. I watched a team burn three weeks picking a vector database once. P
Jun 27, 202610 min read127
What AI Engineers Can Learn From OpenSearch's Move to gRPC
Why a search engine changing its transport protocol quietly became one of the most important infrastructure decisions for RAG and vector workloads in 2025 Let's start with a number that deserves more
Jun 20, 20269 min read207
Lambda vs. EKS for AI Orchestration at Scale
What I learned building production AI for over a million e-commerce users Building a proof-of-concept AI workflow is straightforward. Building one that serves over a million users, survives traffic s
Jun 13, 20268 min read218