Monitor embedding drift for LLMs deployed from Amazon SageMaker JumpStart
AWS Machine Learning
FEBRUARY 2, 2024
One of the most useful application patterns for generative AI workloads is Retrieval Augmented Generation (RAG). Embeddings capture the information content in bodies of text, allowing natural language processing (NLP) models to work with language in a numeric form. Are the questions users are asking changing over time?
Let's personalize your content