Amazon Titan Text Embeddings V2 now available for use with Bedrock Knowledge Bases

Amazon Titan Text Embeddings V2, a new embeddings model in the Amazon Titan family of models, is now available for use with Knowledge Bases for Amazon Bedrock. Using Titan Text Embeddings V2, customers can embed their data into a vector database and use it to retrieve relevant information for tasks such as questions and answers, classification, or personalized recommendations.

Amazon Text Embeddings V2 is optimized for retrieval augmented generation (RAG) and is an efficient model ideal for high accuracy retrieval tasks at different dimensions. The model supports flexible embeddings sizes (1024, 512 , 256) and maintains accuracy at smaller dimension sizes, helping to reduce storage costs without compromising on accuracy. When reducing from 1,024 to 512 dimensions, Titan Text Embeddings V2 retains approximately 99% retrieval accuracy, and when reducing from 1,024 to 256 dimensions, the model maintains 97% accuracy. Additionally, Titan Text Embeddings V2 includes multilingual support for 100+ languages in pre-training as well as unit vector normalization for improving accuracy of measuring vector similarity.