TextEmbeddingAda002

text-embedding-ada-002 is more performant version of the initial ada embedding model. But it's an older model compared to TextEmbeddingAda3Small and TextEmbeddingAda3Large.

Fast, cheap, good for many general tasks

Outputs: 1536-dimensional vectors Max input tokens: 8191 Released: Dec 2022

Embeddings are a numerical representation of text that can be used to measure the relatedness between two pieces of text. Embeddings are useful for search, clustering, recommendations, anomaly detection, and classification tasks.

See also