Doug Turnbull

Kicking the tires of jev for a very basic query understanding task

What you should be thinking of as you consider search + retrieval roles

My biased search expert perspective on where new AI teams run into expensive and unfortunate mistakes

For vector search buyers, pay attention to how graphs get updated.

A useful pattern for LLM classification at scale is to let it hallucinate plausible, fake entities.

Sure its not fancy, but you might save operational headaches by just brute-forcing vector search for a small enough corpus

A week of wector wevents - vector retrieval, hybrid search, combining the dense and lexical.

Let's walk through basics of using PCA to reduce dimensionality of embeddings