Amazon SageMaker

Amazon SageMaker is a fully managed service that brings together a broad set of tools to enable high-performance, low-cost machine learning (ML) for any use case. With SageMaker, you can build, train and deploy ML models at scale— all in one integrated development environment (IDE). SageMaker supports governance requirements with simplified access control and transparency over your ML projects. Amazon SageMaker offers access to hundreds of pretrained models, including publicly available foundational models (FMs), and you can build your own FMs with purpose-built tools to fine-tune, experiment, retrain, and deploy FMs.

Amazon SageMaker and Pinecone can be used together for high-performance, scalable, and reliable retrieval augmented generation (RAG) use cases. The integration uses Amazon SageMaker to compute and host models for large language Models (LLMs), and uses Pinecone as the knowledge base that keeps the LLMs up-to-date with the latest information, reducing the likelihood of hallucinations.

​

Related articles

• Mitigate hallucinations through Retrieval Augmented Generation using Pinecone vector database & Llama-2 from Amazon SageMaker JumpStart