Hands on Gen AI with AWS and Anthropic Book by Ngesa Marvin, First Edition

Companion Jupyter notebooks for the book

This repository contains Jupyter notebooks implementing the code samples found in the book # Hands on Gen AI with AWS and Anthropic by Ngesa Marvin, First Edition.

For readability, these notebooks only contain runnable code blocks and section titles, and omit everything else in the book: text paragraphs, figures, and pseudocode. If you want to be able to follow what's going on, I recommend reading the notebooks side by side with your copy of the book.

Table of contents

• Chapter 1: Prompt Engineering Techniques with Claude
  • Part 1: A Gentle intoroduction to Prompt Engineering Techniques with Claude
  • Part 2: Advanced Prompt Engineering Techniques with Claude
  • Part 3: Papers

A systematic overview of prompting techniques, organizing methods and strategies to help you effectively communicate with LLMs.

• Chapter 2: RAG Architectures / Embeddings and Vector Stores

  • Part 1: Naive RAG
  • Part 2: Retrieve And Rerank
  • Part 3: Multi-Modal RAG
  • Part 4: Graph RAG
  • Part 5: Hybrid RAG
  • Part 6: Agentic RAG - Router
  • Part 7: Agentic RAG - Multi Agent RAG
  • Part 8: Papers

• Chapter 3: Agentic Design Patterns - Reflection Workflows

  • Part 1: Papers

• Chapter 4: Agentic Design Patterns - Planning Workflows. Building Effective Agents

  • Part 1: Agentic Design Patterns - Planning Workflows with ReACT
  • Part 2: Agentic Design Patterns - Planning Workflows with ReWOO
  • Part 3: Papers

• Chapter 5: gentic Design Patterns - Automatic Reasoning and ToolUse (ART) Workflows

  • Part 3: Papers

• Chapter 6: Multi AI Agent Systems

  • Part 1: Multi AI Agent Systems with crewAI
  • Part 2: Multi AI Agent Systems with LangGraph
  • Part 3: Multi AI Agent Systems with Swarm
  • Part 4: Multi AI Agent Systems with AutoGen
  • Part 5: Papers

• Chapter 7: Security, Privacy and Risks

  • Part 1: Prompt Injections
  • Part 2: Jailbreaks
  • Part 3: Papers

• Chapter 8: Jailbreaks and Guardrails

  • Part 1: Guardrails
  • Part 2: Bedrock Guardrails
  • Part 3: NeMo Guardrails Guardrails
  • Part 4: Papers

• Chapter 9: Iteration, Evaluation, and Observability

  • Part 1: Evaluation and Feedback Loops
  • Part 2: Observability and Debugging

• Chapter 10: Scaling Gen AI Platform from infrastructure to deployment

  • Part 1: Adapting LLMs for Domain-Specific and Real-World Tasks
  • Part 2: Scaling and Productionizing LLM-Powered Platforms

• Chapter 13: Best practices for the real world

• Chapter 14: Conclusions