Semantic Search
Search by meaning rather than exact keywords finds 'puppy training' for a query like 'how to teach my dog'.
Semantic search uses embeddings to match queries with documents based on meaning, not literal text overlap. A user can search 'how to make my code faster' and get results about 'optimization techniques' even though no words match.
In practice, hybrid search combining semantic search with traditional keyword search (BM25) and re-ranking outperforms either alone. Most production search systems do this.
Semantic search is the workhorse beneath RAG, recommendation systems, deduplication pipelines, and 'find similar' features. Postgres+pgvector, Elasticsearch, and dedicated vector DBs all support it.