What is Embeddings?
Embeddings: Lists of numbers that represent the meaning of text, images, or other data, so similar items sit close together and can be found by similarity search.
An embedding is a vector, a list of hundreds or thousands of numbers, produced by an embedding model to capture the meaning of a piece of content. Texts that mean similar things end up with vectors that are close together, even if they use different words. "How do I get my money back" and "refund process" will land near each other.
Embeddings power semantic search, recommendations, deduplication, clustering, and the retrieval step of RAG. You embed your content once (and again when it changes), store the vectors, and at query time embed the question and find the nearest stored vectors. Embedding models are separate from chat models and much cheaper to run, but you must use the same model for indexing and querying.
Why it matters when you build or buy AI
Embeddings are cheap, but changing embedding models later means re-indexing everything, so pick deliberately. They are also not magic: exact identifiers like SKUs, invoice numbers, and names are often better found with keyword search, which is why good systems combine both. If a vendor proposes pure semantic search for data full of codes and IDs, push back.
Example
A store embeds 150,000 product descriptions so shoppers searching "something warm for hiking" see fleece jackets even though none of them contain that exact phrase.
Related terms
More in AI & LLMs
Book 20 minutes, or send a brief
A former CTO replies. You leave with a written plan and a fixed estimate.
Prefer LinkedIn? Connect with Harish.