Introducing DS1

DS1 is the world's fastest text embedding API, delivering sub-20ms p99 latency and billions of tokens per hour on CPU infrastructure.

Embedding models transform text into dense numerical vectors (embeddings) that capture semantic meaning. These embeddings enable efficient semantic search and Retrieval-Augmented Generation (RAG), making them essential for building domain-specific AI applications.

DS1 processes your documents through a streamlined endpoint and returns their embeddings with industry-leading speed. Designed as a modular component, DS1 integrates seamlessly with vector stores, LLM providers, and other AI pipeline elements.

Currently, DS1 is available as a SageMaker Model Package, enabling straightforward deployment and scalability within the AWS ecosystem.