Amazon Titan Embeddings G1 - Text models - Amazon Bedrock

Amazon Titan Embeddings G1 - Text models

Amazon Titan Embeddings text models include Amazon Titan Embeddings G1 - Text G1.

Text embeddings represent meaningful vector representations of unstructured text such as documents, paragraphs, and sentences. You input a body of text and the output is a (1 x n) vector. You can use embedding vectors for a wide variety of applications.

The Amazon Titan Embeddings G1 - Text model (amazon.titan-embed-text-v1). The Amazon Titan Embeddings G1 - Text – Text v1.2 can intake up to 8k tokens and outputs a vector of 1,536 dimensions. The model also works in 25+ different languages. The model is optimized for text retrieval tasks, but can also perform additional tasks, such as semantic similarity and clustering. Amazon Titan Embeddings G1 - Text – Text v1.2 also supports long documents, however, for retrieval tasks it is recommended to segment documents into logical segments (such as paragraphs or sections). In line with our recommendation.

Note

Titan Embeddings G1 - Text model doesn't support inference parameters such as maxTokenCount or topP.

To use the text or image embeddings models, use the Invoke Model API operation with amazon.titan-embed-text-v1 or amazon.titan-embed-image-v1 as the model Id and retrieve the embedding object in the response.

To see Jupyter notebook examples:

  1. Sign in to the Amazon Bedrock console at https://console.aws.amazon.com/bedrock/home.

  2. From the left-side menu, choose Base models.

  3. Scroll down and select the Amazon Titan Embeddings G1 - Text model

  4. In the Amazon Titan Embeddings G1 - Text tab (depending on which model you chose), select View example notebook to see example notebooks for embeddings.

For more information on preparing your dataset for multimodal training, see Preparing your dataset.