Embedding
A list of numbers that captures what a passage means, so AI can match it to questions worded differently.
In plain English
Embeddings let machines compare meaning instead of exact words. A page about “fixing a leaky faucet” can match a question about a “dripping tap” because their embeddings are close.
In practice
A question about “AC blowing warm air” finds a page titled “Why your air conditioner isn’t cooling”.
Related terms
How AI reads the webPro Semantic search Search that matches meaning and intent, not just the exact words typed. In practice, and related terms → Content & structurePro Passage A short section of a page that AI tools can pull out and use on its own. In practice, and related terms → How AI reads the webPro Retrieval-augmented generationRAG Fetching relevant documents first, then writing an answer from them. It is how most AI search works. In practice, and related terms →