In semantic search, both the query and the documents are converted into embeddings and compared in vector space. Results are ranked by how close they are in meaning, not whether they contain identical words. This way, a search for cheap car also finds texts about affordable vehicles. Semantic search is the foundation of modern search systems and a core component of RAG.
Semantic Search
Semantic search finds content by its meaning rather than exact keywords. It returns relevant results even when the query uses different words than the target document.