Kathleen DeRusso
Principal Software Engineer I
Kathleen is a software engineer at Elastic working on search and search relevance.
All about those chunks, ’bout those chunks, and snippets!
Exploring chunking and snippet extraction for LLMs, highlighting enhancements for identifying the most relevant chunks and snippets to send to models such as rerankers and LLMs.
Semantic text is all that and a bag of (BBQ) chips! With configurable chunking settings and index options
Semantic text search is now customizable, with support for customizable chunking settings and index options to customize vector quantization, making semantic_text more powerful for expert use cases.
Elasticsesarch semantic search, leveled up: now with native match, knn and sparse_vector support
Semantic text search becomes even more powerful, with native support for match, knn and sparse_vector queries. This allows us to keep the simplicity of the semantic query while offering the flexibility of the Elasticsearch query DSL.
Query rules retriever: ensuring business rules work seamlessly with semantic search
Harness the power of Elasticsearch query rules combined with semantic search and rerankeras.
Looking back: Elastic's vector search improvements in Elasticsearch & Lucene
Looking back at Elastic's vector search innovations in Elasticsearch and Lucene.
Elasticsearch query rules are now generally available
Introducing the general availability of query rules
The sparse vector query: Searching sparse vectors with inference or precomputed query vectors
Learn about the Elasticsearch sparse vector query, how it works, and how to effectively use it.
Search relevance tuning: Balancing keyword and semantic search
This blog offers practical strategies for tuning search relevance that can be complementary to semantic search.
