AI and machine learning
Embedding
- AI and machine learning
Definition
A list of numbers that represents the meaning of a piece of text, image or other content, so similar items sit close together.
Example
The phrases 'late delivery' and 'shipment delay' can have similar numeric representations even though their words differ.
See how it works
- Text or other input
- Embedding model creates a vector
- Compare vectors for similarity
- Retrieve potentially related content
Check your understanding
Common mistake: An embedding is a numerical representation for a particular model and task, not a guaranteed factual interpretation.
Why might embeddings help search?
Show explanation
They can surface related meanings even when the search words differ from the document's words.
For your role
Choose your role to see what this term means in your work.
Why it matters
It lets AI find information by meaning rather than exact words.
Where it is used
AI search tools, chatbots and recommendation systems.