Embedding Models

How embeddings work, which models pair well with Claude, and how to choose by task and cost.

What You Will Learn

• What an embedding is: dense vector representation of text
• Embedding model options: OpenAI, Cohere, open-source (bge, e5, nomic)
• Choosing by task: general vs domain-specific embeddings
• Dimensionality and storage implications
• Re-embedding: when to update your index after a model change