Developing Generative AI Solutions on AWS

This course is designed to introduce generative artificial intelligence (AI) to software developers interested in using large language models (LLMs) without fine-tuning. The course provides an overview of generative AI, planning a generative AI project, getting started with Amazon Bedrock, the foundations of prompt engineering, and the architecture patterns to build generative AI applications using Amazon Bedrock and LangChain.  Developing Generative AI Solutions on AWS Benefits Training Prerequisites AWS Technical Essentials Intermediate-level proficiency in Python  Gen AI Solutions on AWS Training Outline Module 1: Introduction to Generative AI Art of the Possible Overview of ML   Basics of generative AI   Generative AI use cases   Generative AI in practice   Risks and benefits Module 2: Planning a Generative AI Project Generative AI fundamentals Generative AI in practice Generative AI context Steps in planning a generative AI project Risks and mitigation Module 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 Module 4: Foundations of Prompt Engineering Basics of foundation models Fundamentals of Prompt Engineering Basic prompt techniques Advanced prompt techniques Model-specific prompt techniques Demonstration Finetuning a basic text prompt Addressing prompt misuses Mitigating bias Demonstration Image bias mitigation Module 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 finetuning   Securing generative AI applications   Generative AI application architecture Module 6: Amazon Bedrock Foundation Models Introduction to Amazon Bedrock foundation models   Using Amazon Bedrock FMs for inference   Amazon Bedrock methods   Data protection and auditability   Demonstration Invoke Bedrock model for text generation using zeroshot prompt Module 7: LangChain Optimizing LLM performance   Using models with LangChain   Constructing prompts  Demonstration Bedrock with LangChain using a prompt that includes context   Structuring documents with indexes   Storing and retrieving data with memory   Using chains to sequence components   Managing external resources with LangChain agents Module 8: Architecture Patterns Introduction to architecture patterns   Text summarization   Demonstration Text summarization of small files with Anthropic Claude   Demonstration Abstractive 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