Lab 3: What Are Embeddings?

See how text becomes numbers — and how those numbers capture meaning.

🔢

The Solution Foundation: Text → Math

An embedding model converts any text into a list of numbers (a vector). Similar meanings produce similar vectors. This is what makes semantic search possible.

Section 1: Text → Vector

Type any text and watch it become a 1536-dimensional vector.

Section 2: How Similar Are Two Sentences?

Enter two sentences and see a cosine similarity score (0 = unrelated, 1 = identical meaning).

Try these revealing pairs

Takeaway: Embeddings turn text into vectors where similar meanings cluster together in space. Cosine similarity measures the angle between two vectors — a small angle means similar meaning. This is the mathematical engine behind semantic search in Lab 2, and behind RAG retrieval in Lab 5.