---
title: "What are embeddings?"
excerpt: "Embeddings turn text into vectors, so 'similar meaning' becomes 'close in space.' They power semantic search and RAG — and cap how good your retrieval can get."
definition: "Embeddings are numeric vectors that represent the meaning of text (or images, code, audio) so that semantically similar items land close together in vector space, enabling similarity search."
date: "2026-07-09"
lastModified: "2026-07-09"
author: "Teo Deleanu"
authorAvatar: "/team/teo.jpg"
tags: ["RAG", "AI Engineering", "Embeddings", "Retrieval"]
keywords:
  - "what are embeddings"
  - "text embeddings explained"
  - "embeddings for semantic search"
---

An embedding is a list of numbers that captures the meaning of a piece of text. Two passages about the same topic produce vectors that sit near each other; unrelated passages sit far apart. That single property — meaning as distance — is what makes semantic search and [RAG](/glossary/retrieval-augmented-generation) possible.

## Why it matters in production

Your embedding model sets the ceiling on retrieval quality. If it maps "cancel my subscription" and "how do I unsubscribe" to distant vectors, no amount of downstream cleverness recovers the match. Everything after retrieval — reranking, prompting, generation — can only work with what the embedding step surfaced.

## The common mistake

Two mistakes recur. First, mixing embedding models: vectors from model A are not comparable to vectors from model B, so re-embedding your whole corpus is mandatory when you switch — a migration people forget to plan for, much like a [model migration](/blog/surviving-a-model-migration). Second, embedding the wrong unit of text. Embed a 5,000-word page as one vector and you get a blurry average that matches everything and retrieves nothing precisely; that is why [chunking](/glossary/chunking) exists.

## How we actually use it

We pick an embedding model, lock it, and treat re-embedding as a deliberate migration event. We embed at chunk granularity, store the vectors in a [vector database](/glossary/vector-database), and validate that "questions we expect to answer" actually retrieve the passages that answer them — measured, not assumed, following the same discipline we describe in [how RAG works in production](/blog/how-rag-works-in-production).