Embedding playground

What are embeddings?

Embeddings are numerical vectors that represent the meaning of text in a vector space. Similar texts have embeddings that are close to each other, which enables search, recommendations, clustering, and other operations based on similarity.

What is cosine similarity?

Cosine similarity is a metric that measures how similar two vectors are by comparing the angle between them (the normalized dot product). The value typically ranges from -1 to 1, where a higher value means the vectors (and therefore the texts) are more similar. Learn more:Wikipedia — Cosine similarity.