HNSW: Hierarchical Navigable Small World

Posted on Mon 05 October 2026 in AI / Machine Learning

What is HNSW?

HNSW (Hierarchical Navigable Small World) — is a graph-based algorithm used for fast approximate nearest neighbor (ANN) search. It is widely used in vector databases and AI applications to quickly find vectors that are most similar to a given query.

When an AI system stores thousands or millions …

Continue reading

Cutting RAG Costs: Do We Really Need to Send the Whole PDF to the LLM?

Posted on Sat 29 August 2026 in AI

The Problem Nobody Talks About Loudly

Retrieval-Augmented Generation — RAG — has quietly become the default way to make LLMs actually useful with real-world documents. You index a PDF, embed the chunks, retrieve the relevant ones at query time, and pass them to the model. It works. People ship it.

But there's …

Continue reading

Ever Wonder How AI "Remembers" Things? Meet FAISS

Posted on Thu 09 July 2026 in AI Engineering

Have You Ever Asked a Chatbot a Question and Been Amazed It Found the Right Answer Instantly?

From thousands of documents, almost instantly — the exact right piece of information. Ever wondered how that actually works under the hood?

The answer often involves a tool called FAISS. It sounds technical, but …

Continue reading

How Your Phone Recognizes Your Face: The Simple Math Behind ArcFace

Posted on Mon 29 June 2026 in AI Engineering

Have You Ever Paused to Wonder How Your Phone Unlocks the Moment You Glance at It?

Not just any face — your face. In dim light. With glasses on. Three years after you set it up.

Behind that everyday magic sits a fascinating idea called ArcFace. Don't let the name fool …

Continue reading