Introduction to Bedrock

Amazon Bedrock is a fully managed serviceA fully managed service is a service in which AWS takes care of all underlying infrastructure, maintenance, scaling, updates, and administrative tasks and allows users to focus solely on their applications. that simplifies the process of building and scaling generative AI applications. It provides access to pretrained foundational models (FMs) from various AI providers like Cohere, Anthropic, Stability AI, and Amazon’s own Titan models. Bedrock allows us to use these models for tasks such as natural language processing (NLP), image generation, text summarization, and more without having the need to manage the underlying infrastructure.

Amazon Bedrock is designed to be highly customizable. It allows us to fine-tune models, integrate them into existing applications, and scale them as needed. It manages machine learning models and infrastructure, allowing developers to focus on building AI-powered applications.

In this section, we will learn about Amazon Bedrock’s main features, foundational models, and how to fine-tune and evaluate foundational models. We’ll also learn about retrieval-augmented generation (RAG) and how to implement it using Bedrock.