Semantic search: Semantic search finds results based on the meaning of a query rather than exact keyword matches, so a search for 'unpaid invoices' also returns documents about 'overdue bills.' It uses embeddings to compare meaning.
Keyword search looks for the words you typed. Semantic search looks for what you meant. It converts your query into an embedding and returns the documents whose embeddings sit closest to it, which means synonyms, rephrasings, and related ideas all surface even when the exact words are absent.
This is the search you now meet in AI-powered help centers, enterprise knowledge tools, email and document search in modern office suites, and the retrieval step of retrieval-augmented generation. A good system combines both approaches: semantic ranking for meaning plus keyword matching for exact names, part numbers, and codes.
Semantic search still needs good source material. It cannot find an answer that was never written down, and it can confidently surface a passage that is similar in meaning but wrong in detail, like last year's version of a policy. Check dates and sources on anything that will drive a decision.
Example at work
A facilities manager searches the company wiki for 'who approves after-hours HVAC changes' and gets nothing because the policy page says 'temperature setpoint modifications outside business hours require sign-off.' With semantic search enabled, that page is the first result.
Why it matters
Most of the time you lose at work is spent looking for something you know exists. Semantic search is the AI capability that most directly fixes that, and it is the reason 'ask a question in plain English' works across a company's documents.
Related terms
- EmbeddingAn embedding is a list of numbers that represents the meaning of a piece of text, an image, or other content, so that items with similar meaning end up with similar numbers. Embeddings are what let AI systems search by meaning instead of exact words.
- Vector databaseA vector database stores embeddings, the numeric representations of text, images, or other content, and finds the items closest in meaning to a query quickly. It is the storage layer behind semantic search and most document-aware AI assistants.
- Retrieval-augmented generation (RAG)Retrieval-augmented generation (RAG) is a technique in which an AI system first searches a set of documents for relevant passages and then gives those passages to a language model to answer from. It lets an assistant use your own, current information.
- Natural language processing (NLP)Natural language processing (NLP) is the branch of AI focused on understanding and generating human language: reading, classifying, translating, summarizing, and answering questions in ordinary words. Large language models are its current dominant technology.