Embeddings
noun · AI technique · element 90 of 117
Numbers that capture what a piece of text means, so software can find related content by meaning rather than matching words.
My levelProficientComfortable in production. I ship with it without supervision.
- Projects
- 2
- Family
- AI and agents
What is Embeddings?
An embedding model turns text into a list of numbers, a vector, so that texts with similar meaning end up close together. Comparing vectors powers semantic search, related content, clustering and retrieval for AI assistants.
It is how a site can answer a question with the page that means the same thing, even when it uses different words.
How I use Embeddings
I use embeddings to merge near-duplicate questions and cluster the rest, and to find the right passages in a site's own content before a model answers. In my open framework for AI on WordPress, AI Workbench Hub grounds every job that way.