Data & retrieval
Embeddings
A way of converting text (or images) into lists of numbers so an AI can measure how similar two pieces of content are.
01 ——
In plain English
Embeddings are numerical representations of text. An embedding model reads a word, sentence, or document and outputs a list of hundreds or thousands of numbers — called a vector — that captures its meaning.
The key property: similar meanings produce similar vectors. "Dog" and "puppy" end up close together in this number space; "dog" and "democracy" end up far apart.
What they're used for:
- Semantic search — find documents by meaning, not just exact keywords
- Recommendations — surface similar articles or products
- RAG — retrieve relevant context before sending a query to an LLM
- Clustering — group similar pieces of content automatically
02 ——
Related terms
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.
Vector Database
A database optimised for storing and searching embeddings (numerical representations of text or images) by similarity.
Semantic Search
Search that finds results by meaning rather than exact keyword matches — so "car" finds results about "automobile" too.
Neural Network
A computing system inspired by the brain, made up of layers of connected "neurons" that learn patterns from data — the building block of modern AI.
Back to glossaryLast reviewed May 2026