What are embeddings in AI?

An embedding model turns a sentence into a vector: hundreds or thousands of numbers. What makes it useful is the distance between vectors: "how do I change my password" and "I forgot my login" end up close even though they share no words, while "empanada recipe" ends up far away.

That powers search by meaning (rather than exact words), recommendations and grouping similar texts. The vectors are stored in a vector database so they can be found fast.

They are the piece that makes RAG work: embedding closeness is how you find which parts of your documents relate to the question.

Related terms

• RAG (retrieval-augmented generation): RAG is a technique that finds relevant information in your documents and hands it to the model along with the question, so it answers with real, current data.
• LLM (large language model): An LLM (large language model) is an AI model trained on huge amounts of text to predict the next token. It is the engine behind ChatGPT, Claude and Gemini.
• Neural network: A neural network is a model made of layers of simple connected units, with weights that are adjusted during training. It is the basis of deep learning and of LLMs.