Author
-
Semantic Similarity with Focused Selectivity
Why does semantic search need selectivity? Up until now, we’ve viewed a vector embedding as a complete, stand-alone entity – focused entirely on the meaning it encodes. While this enables semantic search, often with…
-
Vector Search Performance: The Rise of Recall
Introducing vector search (KNN), with its distance-based similarity scoring, into the existing Search paradigm necessitated a shift in how we thought about “relevant” results and how to measure them. Text based indexes use tf-idf…