← Library · Core concept
Embeddings
Embeddings are numerical representations of discrete data like words, images, or even entire documents, transformed into a continuous vector space. In this space, items with similar meanings or characteristics are positioned closer together. This allows AI models to process and understand contextual relationships between different entities.
In plain terms
Embeddings are like a map where similar cities are placed closer to each other, making their relationships visually clear.
Why it matters
They enable AI models to capture semantic meaning and context, crucial for tasks like natural language processing and recommendation systems.
Learn one new AI thing every day.
Daily Deck sends you seven plain-English cards like this every morning. Free.
Start free