What is an Embedding?

What is an embedding?

An embedding is a list of numbers, typically a few hundred to a few thousand values, that a model produces to represent an input. The numbers themselves are not human-readable, but their geometry is meaningful: inputs with similar content are mapped to nearby vectors, and unrelated inputs land far apart. That single property is what makes embeddings so useful, because once similarity is a distance, it can be computed at scale.

Almost any data can be embedded, including images, text, audio, video, point clouds, and robot trajectories, which is why embeddings have become the common currency of modern AI systems.

Key takeaways

An embedding is a learned vector representation of an input.
Similar inputs map to nearby vectors, making similarity computable.
Embeddings power search, clustering, deduplication, and curation.

How it works

An embedding model, often a neural network trained with contrastive or self-supervised objectives, transforms each input into a fixed-length vector. Distances between vectors, such as cosine similarity, quantify how alike two inputs are. Collections of embeddings can then be indexed for fast search, projected to 2D for visualization, or clustered to reveal a dataset's structure.

Why it matters

Embeddings are the foundation of semantic search, recommendation, near-duplicate detection, anomaly detection, and data curation. For visual and physical AI teams, they turn overwhelming datasets into something navigable: instead of scrolling through millions of samples, you can search by meaning, group by similarity, and surface the rare cases that matter.

Frequently asked questions

What is the difference between an embedding and a feature?

Embeddings are the modern, learned form of features. The terms are often used interchangeably, though embedding usually implies a dense vector from a neural network.

How long is an embedding vector?

Typically between a few hundred and a few thousand dimensions, depending on the model. Longer is not automatically better.

Jesse Mostipak is the SEO and Content Manager at Voxel51, where the work is helping humans find and trust what the brand knows, and teaching the Google knowledge graph and the LLMs answering on their behalf to do the same. That question, how knowledge gets built inside a system, is one Jesse has been chasing for years. Earlier versions of it ran through a New York City high school science classroom, data science and machine learning, and developer relations at Kaggle, Posit (formerly RStudio), and Baseten. The answer doesn't change much depending on whether the learner is a teenager, a software engineer, or a knowledge graph. Jesse holds a Master's in Education from CUNY Hunter College. LinkedIn

Embedding

Building visual or physical AI? 
Let's talk.