Developing Generative AI applications on AWS

Software Developers interested in leveraging Large Language Models without the need for fine-tuning.

In this course, you will learn how to:

• Describe Generative AI, its alignment with Machine Learning, and its potential risks and benefits.
• Identify the business value derived from Generative AI use cases.
• Explain the steps for planning a Generative AI project.
• Understand the functionality and operations of Amazon Bedrock.
• Describe the typical architecture associated with an Amazon Bedrock solution.
• Implement an Amazon Bedrock demonstration within the AWS Management Console.
• Define Prompt Engineering and apply general best practices when interacting with Foundation Models (FMs).
• Identify basic prompt techniques, including zero-shot and few-shot learning.
• Identify the components of a Generative AI application and how to customize a Foundation Model (FM).
• Describe how to integrate LangChain with Large Language Models (LLMs), prompt templates, chains, chat models, text embedding models, document loaders, retrievers, and agents for Amazon Bedrock.
• Apply concepts to build and test sample use cases leveraging various Amazon Bedrock models, LangChain, and the Retrieval Augmented Generation (RAG) approach.

Module 1: Introduction to Generative AI

• Generative AI concepts
• Benefits, risks, and business value
• Generative AI project planning

Module 2: Amazon Bedrock Fundamentals

• Amazon Bedrock features and capabilities
• Foundation Models
• Bedrock solution architecture
• Amazon Bedrock demonstration

Module 3: Prompt Engineering

• Prompt Engineering fundamentals
• Prompt design best practices
• Zero-shot and few-shot prompting

Module 4: Building Generative AI Applications

• Components of a Generative AI application
• Foundation Model customization
• Application architecture patterns

Module 5: LangChain and Amazon Bedrock

• LangChain integration with Amazon Bedrock
• Prompt templates and chains
• Chat models and embedding models
• Document loaders and retrievers
• Agents and orchestration

Module 6: Retrieval Augmented Generation (RAG)

• RAG concepts
• Building and testing sample use cases
• Implementing Generative AI solutions with Amazon Bedrock and LangChain

Participants should have:

• AWS Technical Essentials (Classroom or Digital).
• Intermediate-level Python proficiency.

• AWS Certified Machine Learning - Specialty