learning path

Integrating AWS services with LLMs and other FMs

Advanced
Up to 9h 50m
37
5/5
Enhance your skill setDevelop essential skills for thriving in real-world scenarios.
Stay focused, stay committedBoost your learning journey by enrolling: stay focused, consistent and achieve your goals with ease.
Earn a certificate of completionShow your skills and build your credibility when you include them in your resume and LinkedIn profile.

This course has been designed to cover the different AWS services that allow you to integrate with large language models and other foundation models. The services covered include:

  • Amazon Q - A generative AI-powered chatbot that can be customised to suit your needs as a business
  • Amazon Bedrock - A managed service that allows you to build generative AI applications by accessing a number of different foundation models via APIs
  • Amazon CodeWhisperer - Enabling you to easily and efficiently code your applications with the help of generated code snippets through machine learning


Learning Objectives:

Amazon Q:

  • Understand what Amazon Q is
  • Discover the benefits of leveraging Amazon Q in your enterprise
  • Explore Amazon Q’s different areas of expertise
  • Recognise Amazon Q’s pricing plans and features
  • The various features and use cases
  • How to configure a new Amazon Q web application that connects to business data systems and repositories
  • How to interact with an Amazon Q web application
  • How to control access to Amazon Q within an organization
  • How to use guardrails and chat controls to enhance the quality of end-user interactions with Amazon Q
  • How to configure plugins that interact with third-party services directly from Amazon Q
  • How to work with Amazon Q in the AWS Console and an IDE
  • How to use Amazon Q with Amazon CodeWhisperer
  • How to use Amazon Q with data engineering services
  • How to use Amazon Q with CodeCatalyst

Amazon CodeWhisperer:

  • Learn what CodeWhisperer does and the benefit it provides
  • How to generate code snippets with CodeWhisperer
  • Enable Amazon CodeWhisperer suggestions in the Cloud9 IDE
  • Utilize Amazon CodeWhisperer suggestions to write and deploy a Python function

Amazon Bedrock:

  • What Amazon Bedrock allows you to do
  • The different foundation models supported by Bedrock at the time this lesson was created
  • How you can experiment running inference with Amazon Playgrounds
  • How model evaluations allow you to compare and analyze different model performance and response outputs
  • The different types of model evaluations available and how to configure them
  • The fundamentals of setting up your APIs with Amazon Bedrock
  • Learn how to use Python and the Boto3 SDK to interact with the Bedrock API 
  • Learn how to run single prompt inference using code for both image and text generation 
  • Learn how to switch between Foundation Models using code 
  • Understand the invocation options for the Bedrock Runtime


Feedback

We welcome all feedback and suggestions - please contact us at support@cloudacademy.com if you are unsure about where to start or if you would like help getting started.




Your certificate for this learning path

About the Author

Avatar
Alana Layton, opens in a new tab
Sr. AWS Content Creator
Students
5,566
Courses
43
Learning paths
9

Alana Layton is an experienced technical trainer, technical content developer, and cloud engineer living out of Seattle, Washington. Her career has included teaching about AWS all over the world, creating AWS content that is fun, and working in consulting. She currently holds six AWS certifications. Outside of Cloud Academy, you can find her testing her knowledge in bar trivia, reading, or training for a marathon.

Covered Topics