Home icon

NeMo Retriever Llama 3.2 text embedding and reranking NVIDIA NIM microservices now available in Amazon SageMaker JumpStart

Machine Learning Blog



AWS and NVIDIA have announced the availability of NeMo Retriever Llama 3.2 text embedding and reranking NVIDIA NIM microservices in Amazon SageMaker JumpStart, offering powerful multilingual AI capabilities for enterprise search and retrieval systems.

  • Two new microservices are now available: text embedding and text reranking NIM
  • Supports 26 languages with document support up to 8,192 tokens
  • Reduces data storage footprint by 35-fold through dynamic embedding sizing
  • Enables deployment through SageMaker Studio or programmatically via SDK
  • Supports real-time and batch inference for various use cases

These models are particularly valuable for enterprise knowledge bases, customer support systems, and multilingual content recommendation engines, providing efficient and accurate semantic search capabilities across diverse languages.



Go to article

The AWS News Feed is currently looking for gold sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.

Related articles

Feb 24
2026
Amazon SageMaker AI now hosts NVIDIA Evo-2 NIM microservices
Jun 4
2026
NVIDIA Nemotron 3 Ultra now available on Amazon SageMaker JumpStart
Dec 17
2024
Llama 3.3 70B now available in Amazon SageMaker JumpStart
Dec 4
2024
Amazon Bedrock Marketplace now includes NVIDIA models: Introducing NVIDIA Nemotron-4 NIM microservices

The AWS News Feed is currently looking for silver sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.