Semantic search
Also called vector search, search by meaning
Search that matches meaning rather than exact words, so "cheap flights to Rome" can find a page that only says "low-cost fares to Italy".
Classic search looks for the words you typed. Semantic search looks for what you meant. It turns your query and every document into embeddings, lists of numbers that capture meaning, and returns the documents whose numbers sit closest to your query's.
That's why it copes with synonyms, paraphrases and vague memories, and why it's the usual first step when a chatbot answers from your own files: find the passages that relate to the question, then hand them to the model. Many systems combine both kinds, using meaning to catch paraphrases and exact matching to catch names and numbers.
For example
Searching your notes for "when I complained about the boiler" and finding the one titled "Heating engineer, third visit" is search by meaning.
Put it to use
Where you'll meet semantic search in ChatGPT, Gemini and Claude, how to use it there, and the mix-up most people make.
Daily Bytes Plus is in the Android app.