Overview
Developing Generative AI Applications on AWS is a two-day advanced course designed for software developers interested in leveraging large language models without fine-tuning. This course provides an in-depth understanding of generative AI, project planning, prompt engineering, and building generative AI applications using Amazon Bedrock and LangChain.
Objectives
By the end of this course, leaner will be able to:
- Describe generative AI and its alignment with machine learning.
- Identify business value and use cases for generative AI.
- Plan a generative AI project, understanding its steps, risks, and mitigations.
- Implement and demonstrate Amazon Bedrock in the AWS Management Console.
- Apply advanced prompt engineering techniques to specific models and use cases.
Prerequisites
- AWS Technical Essentials.
- Intermediate-level proficiency in Python.
- Basic understanding of machine learning concepts.
- Familiarity with cloud computing fundamentals.
- Previous experience with AWS services.
Course Outline
- Overview of application components, RAG, and model fine-tuning
- Securing generative AI applications
- Demonstration: Word embeddings
- Introduction, inference methods, data protection, and auditability
- Demonstration: Zero-shot text generation
- Integrating AWS and LangChain
- Optimizing LLM performance and constructing prompts
- Demonstration: Bedrock with LangChain using contextual prompts
- Text summarization, question answering, chatbots, and code generation
- Demonstration: Various generative AI applications with Amazon Bedrock and LangChain