Data & retrieval
Semantic Search
Search that finds results by meaning rather than exact keyword matches — so "car" finds results about "automobile" too.
01 ——
In plain English
Semantic search understands the intent and meaning behind a query rather than looking for exact word matches. It uses embeddings to represent both the query and documents as vectors, then finds the documents whose vectors are closest to the query vector.
Keyword search vs semantic search:
- Keyword: searching "dog training tips" only finds pages with those exact words
- Semantic: also finds pages about "teaching your puppy commands" or "canine obedience"
Why it matters for AI tools: Most AI-powered search, knowledge bases, and RAG systems use semantic search under the hood. It's why you can ask a question in plain English and get relevant results even if the source document uses different words.
02 ——
Related terms
Embeddings
A way of converting text (or images) into lists of numbers so an AI can measure how similar two pieces of content are.
Vector Database
A database optimised for storing and searching embeddings (numerical representations of text or images) by similarity.
RAG
Retrieval-Augmented Generation — a technique that gives an AI model access to external documents before it answers, so it can cite real, up-to-date sources.
Natural Language Processing
The branch of AI focused on understanding, generating, and working with human language — covering everything from spell-check to ChatGPT.
Back to glossaryLast reviewed May 2026