Embeddings
Numerical representations of text that capture meaning, allowing AI to measure similarity between words, sentences, or documents.
An embedding is a list of numbers (a vector) that represents the meaning of a piece of text. Two pieces of text with similar meanings will have vectors that are close together in this numeric space, even if they use different words. "How do I deploy my app?" and "Steps to launch to production" would have similar embeddings.
Embeddings power semantic search, recommendations, and RAG systems. Instead of matching exact keywords, you convert both the query and your documents into embeddings, then find the closest matches. This captures intent, not just word overlap.
Building with embeddings involves: choosing an embedding model (OpenAI's text-embedding-3, Cohere, or open-source alternatives), converting your content into vectors, storing them in a vector database (Pinecone, Weaviate, pgvector), and querying by similarity at runtime.