Doug Turnbull

Various strategies of Elasticsearch benchmarked w/ NDCG stats

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

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

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

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

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

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

A revelation has occured to me. Don