Quick answer
An embedding is a list of numbers that represents the meaning of text, images or audio. Similar items have similar embeddings, which makes them searchable by meaning.
What it is
An embedding is a vector (a list of numbers) produced by a model. Items with similar meaning have embeddings that are close together in vector space. Embeddings power semantic search, recommendations, clustering and RAG.
Why it matters
Embeddings let you search by meaning, not just keywords. They power the retrieval step in RAG and the recommendations in most modern apps.
How to use it
- Pick an embedding model that fits your domain and language.
- Chunk your content into small, self-contained passages.
- Embed each chunk and store the vectors in a vector database.
- At query time, embed the question and retrieve the closest chunks.
Examples
- A support chatbot retrieves the most relevant help articles using embeddings.
- An e-commerce site recommends products by embedding both products and recent views.