Live-Online: Developing Generative AI Applications on AWS

The course provides an overview of generative AI, planning a generative AI project, getting started with Amazon Bedrock, the basics of prompt engineering, and architectural patterns for building generative AI applications with Amazon Bedrock and LangChain.
 

1. Introduction to Generative AI - The Art of the Possible

• Overview of ML
• Basics of generative AI
• Use cases of generative AI
• Generative AI in practice
• Risks and benefits

2. Planning a Generative AI Project

• Generative AI fundamentals
• Generative AI in practice
• Generative AI in context
• Steps in planning a generative AI project
• Risks and mitigation

3. Getting Started with Amazon Bedrock

• Introduction to Amazon Bedrock
• Architecture and use cases
• How to use Amazon Bedrock
• Demonstration: Setting up Bedrock access and using Playgrounds

4. Basics of Prompt Engineering

• Foundational model basics
• Basics of prompt engineering
• Basic probing techniques
• Advanced prompt techniques
• Model-specific prompt techniques
• Demonstration: Fine-tuning a simple text prompt
• Handling prompt misuse
• Mitigating biases
• Demonstration: Mitigating image biases

5. Amazon Bedrock Application Components

• Overview of generative AI application components
• Foundation models and the FM interface
• Working with datasets and embeddings
• Demonstration: Word embeddings
• Additional application components
• Retrieval-Augmented Generation (RAG)
• Model fine-tuning
• Securing generative AI applications
• Generative AI application architecture

6. Amazon Bedrock Foundation Models

• Introduction to Amazon Bedrock foundation models
• Using Amazon Bedrock FMs for inference
• Amazon Bedrock methods
• Data privacy and auditability
• Demonstration: Calling the Bedrock model for text generation with zero-shot prompt

7. LangChain

• Optimizing LLM performance
• Using models with LangChain
• Constructing prompts
• Demonstration: Bedrock with LangChain using a prompt that includes context
• Structuring documents with indices
• Storing and retrieving data with memory
• Using chains to sequence components
• Managing external resources with LangChain agents

8. Architectural Patterns

• Introduction to architectural patterns
• Text summarization
• Demonstration: Summarizing text from small files with Anthropic Claude
• Demonstration: Abstract text summarization with Amazon Titan using LangChain
• Question answering
• Demonstration: Using Amazon Bedrock for question answering
• Chatbot
• Demonstration: Conversational interface - Chatbot with AI21 LLM
• Code generation
• Demonstration: Using Amazon Bedrock models for code generation
• LangChain and agents for Amazon Bedrock
• Demonstration: Integrating Amazon Bedrock models with LangChain agents

• Describing generative AI and distinguishing it from machine learning
• Defining the significance of generative AI and explaining its potential risks and benefits
• Identifying the business value of generative AI use cases
• Discussing the technical fundamentals and key terminology for generative AI
• Explaining the steps to plan a generative AI project
• Identifying some risks and mitigation measures when using generative AI
• Understanding how Amazon Bedrock works
• Familiarizing with the basic concepts of Amazon Bedrock
• Recognizing the benefits of Amazon Bedrock
• Listing typical use cases for Amazon Bedrock
• Describing the typical architecture related to an Amazon Bedrock solution
• Understanding the cost structure of Amazon Bedrock
• Implementing a demonstration of Amazon Bedrock in the AWS Management Console
• Defining prompt engineering and applying general best practices when interacting with foundation models (FMs)
• Identifying the basic types of prompt techniques, including zero-shot and few-shot learning
• Applying advanced prompt techniques when necessary for your use case
• Recognizing which prompt techniques are best suited for specific models
• Identifying potential prompt misuse
• Analyzing potential biases in FM responses and developing prompts that mitigate these biases
• Identifying the components of a generative AI application and how to fine-tune an FM
• Describing the Amazon Bedrock foundation models, inference parameters, and key Amazon Bedrock APIs
• Identifying Amazon Web Services (AWS) offerings that help monitor, secure, and manage your Amazon Bedrock applications
• Describing the integration of LangChain with LLMs, prompt templates, chains, chat models, text embedding models, document loaders, retrievers, and agents for Amazon Bedrock
• Describing architectural patterns that you can implement with Amazon Bedrock for building generative AI applications
• Applying the concepts to create and test application examples using various Amazon Bedrock models, LangChain, and the retrieval-augmented generation (RAG) approach

Software developers who want to use LLMs in services and applications.