Embedding (AI)

Computers work with numbers, not meaning. Embeddings bridge that gap. When you pass a sentence through an embedding model, you get back a list of numbers (typically 768 to 3072 dimensions) that represents what that sentence means. Similar sentences get similar numbers.

This is what makes semantic search possible. Instead of matching keywords, you compare the embedding of a query against the embeddings of your documents. "Annual revenue" and "yearly income" would match because their embeddings are close together, even though they share no words.

Embedding models are trained on large datasets to learn these representations. OpenAI, Cohere, Google, and open-source projects like Sentence Transformers all provide embedding models. The choice of model affects the quality of your search and retrieval. Better models capture more nuance but may be slower or more expensive to run.

In practice, embeddings are the foundation of any RAG system. Your documents get embedded once and stored in a vector database. Each user query gets embedded at runtime and compared against the stored vectors. The quality of this embedding step directly affects whether the right documents get retrieved.

Beyond search, embeddings are used for clustering (grouping similar documents), classification (categorizing content), anomaly detection (finding outliers), and recommendation systems (suggesting similar items).