RAG & knowledge

Semantic search

Searching by meaning instead of keywords. Powered by embeddings and vector databases.

also known as: vector search

In depth

Semantic search returns results that mean the same thing as the query, even if they share no words. The user query is embedded, the database finds nearby vectors, the closest documents are returned. Better than keyword search for natural-language questions, worse for exact matches (product codes, specific names) where keyword search wins.

Related concepts

EmbeddingA fixed-size numeric vector that represents the semantic meaning of a piece of text.Vector databaseA database optimised for storing and querying high-dimensional vectors, typically for similarity search.Hybrid searchCombining vector similarity with keyword matching to get the best of both.

Newsletter

Get the next post in your inbox.

Engineering notes from the Digitorn team. No marketing, no launch announcements, no "10 prompts that will change your life". Just the things we write that we'd want to read.

More in RAG & knowledge

Chunking/glossary/chunking Embedding/glossary/embedding Hybrid search/glossary/hybrid-search Knowledge base/glossary/knowledge-base RAG/glossary/rag Re-ranking/glossary/rerank