Arkhan
Thought dump
Recent posts
Here are things I wrote about as of late.
Information retrieval metrics allow us to diagnose issues in our retriever's performance. In this post, we cover some of these diagnostic patterns.
Self-learning has become more attainable now than ever thanks to AI. Here's how I built a self-learning system that leverages Claude Code.
Order-aware retrieval metrics help quantify how well your retriever orders relevant documents. In this article, we talk about three of these metrics.
The thundering herd problem is a common issue one's system may run into under heavy load. In this post, we discuss what it is and how to solve it.
Information retrieval is a key process in RAG pipelines, which is why it's important to monitor. We start with the fundamentals - recall and precision