Roman Grebennikov

Is your search cluster stuck in ‘status: red’ due to over-complicated maintenance? Are modern vector databases still falling short in solving your real-world search problems?

Combining BM25, neural embeddings and customer behavior with Learning-to-Rank into an ultimate ranking ensemble, with examples on Amazon ESCI e-commerce search dataset.

Relevancy is subjective. Same items in search results for a “jeans” query may have a completely opposite value for you and me, as we’re different in sizes, shapes, and tastes.

Moving a new ML model from playground to production frequently requires rewriting it in a way mostly focused on latency and stability, which may result in two versions of the same code used for offline model training and online serving.

Operations with Flink state are a common source of performance issues for a typical stateful stream processing application. One tiny mistake can easily make your job to spend most of a precious CPU time in serialization and inflate a checkpoint size to the sky.