Amazon Bedrock
Bedrock’s role in AWS, model invocation, RAG, inference parameters and model customization.
Complete guide to Amazon Bedrock: architecture, model invocation, RAG, inference parameters, and model customization.
Challenges: multiple subscriptions, multiple API keys, different prompt formats, variable response structures, multiple billing.
Definition: Amazon Bedrock is a fully managed generative AI service by AWS. It provides secure access to leading foundation models through a unified set of APIs.
Sign in to read this course
A free account unlocks all 514 courses. 20 are readable without one.
What's inside
9 sections- 1 Table of Contents
- 2 Amazon Bedrock's Role in AWS Architectures
- 3 Request-Response Flow for Model Invocation
- 4 Architectural Patterns for Bedrock Use Cases
- 5 Retrieval-Augmented Generation (RAG)
- 6 Choosing the Right Foundation Model
- 7 Configuring Inference Parameters
- 8 Model Customization and Fine-Tuning
- 9 Code Examples
More AWS AI & Machine Learning courses
View all 4AWS Machine Learning and AI Fundamentals
How machines learn, the ML process and the key AWS AI and ML services with boto3 examples.
Amazon SageMaker
Train, evaluate and deploy models on Amazon SageMaker through a worked absenteeism-analysis case.
AWS ML Engineer Associate (MLA-C01): Deployment & Orchestration
Select deployment infrastructure, script it and orchestrate ML CI/CD pipelines for the MLA-C01 exam.
Interested in this course?
Contact us to book it or get a custom training plan for your team.