What distance metrics does Pinecone support?

Pinecone supports three distance metrics: cosine similarity, Euclidean distance, and dot product. The metric is chosen at index creation and cannot be changed later. Cosine is the default for text embeddings because it compares angle regardless of magnitude, dot product is faster when vectors are normalized and often used for recommendation, and Euclidean is used for some image and biology embeddings where raw magnitude matters. Most modern embedding models expect either cosine or dot product, so choose based on the model's documentation.