Method
Vector / semantic search
Similarity search over embeddings stored in a vector index.
32 cases from 25 companies apply Vector / semantic search. 3 were checked in an online A/B test; 13 report results in production.
Typical tasks: Answer questions over data, Retrieve and rank from millions of items, Rank search results, Build an assistant over internal docs and 10 more. Companies: Databricks, Pinterest, Netflix, LY Corporation, Rabota.ru, Wildberries and 19 more. Often combined with: RAG, LLM-as-a-judge, Text-to-SQL, BM25, MCP and 66 more.



