Skip to main content

AI21

AI21 Studio’s Embeddings model provides dense vector representations of text. The model takes a segment of text and returns a vector representation produced by our model.

The embedding vectors encode semantic information about the text they represent. This can be used as a basis for various use cases including RAG (retrieval augmented generation), semantic search, clustering and classification.

Requisites​

To use AI21 models, you need to have an AI21 API key. You can get one by signing up at AI21's website.

Required credentials:

  • AI21_API_KEY: Your AI21 API key.

Supported Models:​

AI21 Embedding​

  • Model schema id: ai21/ai21_embedding

Properties:

  • Embedding size: 1024
  • Input token limit: 400
  • Max batch size: 200