Skip to Content
View all events

Hands-On RAG with AWS

Published by O'Reilly Media, Inc.

Intermediate content levelIntermediate

Build RAG applications with AWS Bedrock and Python

What you’ll learn and how you can apply it

  • Build and deploy RAG AI applications using AWS Bedrock and Python
  • Design and configure semantic search and retrieval workflows
  • Integrate LLMs (Anthropic, Amazon Nova, etc.) for generation in real-world apps
  • Optimize and monitor retrieval/generation for efficiency and cost

Course description

Develop powerful retrieval-augmented generation (RAG) AI applications on AWS using Bedrock and Python. Guided by AWS cloud architect Eduardo Mota, you’ll learn to effectively combine powerful LLMs with targeted information retrieval to create advanced conversational and search agents, building a solid foundation in RAG systems step-by-step.

Throughout the course, you’ll work with real-world scenarios: integrating cutting-edge Bedrock models, leveraging vector databases and OpenSearch, and deploying end-to-end AI workflows. You’ll develop, test, and deploy your own RAG pipelines, exploring best practices for cost optimization, security, and performance on AWS. Interactive exercises will give you hands-on experience building ingestion scripts and search components—and connecting everything to generative models. You’ll come away with a toolbox of code, reusable templates, and the knowledge to build enterprise-grade AI applications.

This live event is for you because...

  • You’re a cloud developer or architect deploying AI solutions.
  • You work with Python and AWS technologies.
  • You want to design performant AI-enabled applications for search, chat, and more.

Prerequisites

  • An AWS account
  • Python 3.x and AWS CLI installed on your machine
  • Bedrock access
  • Basic understanding of Python
  • Experience with AWS cloud platform preferred
  • Familiarity with REST APIs, JSON, or vector databases helpful
  • Verify terminal access for Boto3 calls and notebook use
  • Optional: RAGAS and ChromaDB

Recommended preparation:

Recommended follow-up:

Schedule

The time frames are only estimates and may vary according to how the class is progressing.

RAG fundamentals and AWS Bedrock RAG solutions (40 minutes)

  • Presentation: Introduction to RAG and generative AI
  • Group discussion: Where does RAG help in enterprise apps?
  • Hands-on exercise: Identify RAG components in provided image
  • Q&A

Semantic retrieval and vector search (50 minutes)

  • Presentation: Building semantic search with OpenSearch/vector DB
  • Group discussion: Keyword versus semantic retrieval trade-offs
  • Hands-on exercise: Configure a vector DB and ingest sample docs
  • Q&A
  • Break

Bedrock GenAI integration (50 minutes)

  • Presentation: Using Bedrock for generation; connecting Python to Bedrock APIs
  • Hands-on exercise: Live-coding query and response workflow
  • Q&A
  • Break

Building end-to-end RAG pipeline (70 minutes)

  • Presentation: Integrating retrieval and generation; RAG app design patterns
  • Hands-on exercise: Deploy and test RAG app with sample queries
  • Q&A
  • Break

Cost, security, and advanced templates (30 minutes)

  • Presentation: Monitoring, scaling, and cost optimization; security sample code and checklists
  • Hands-on exercise: Cost comparison
  • Group discussion: Security best practices
  • Q&A

Your Instructor

Eduardo Mota

Eduardo Mota is an accomplished AWS Cloud Architect and Machine Learning Specialist. He holds a Bachelor of Business Administration and multiple Machine Learning certifications, demonstrating his relentless pursuit of knowledge. Eduardo's journey includes pivotal roles at DoiT International and AWS, where his expertise in AWS cloud architecture and optimization strategies significantly impacted operational efficiency and cost savings for multiple organizations. Eduardo's commitment to AWS mastery is underscored by his AWS certifications including Machine Learning and Data Analytics, making him a trusted guide in the realm of cloud innovation and artificial intelligence. Beyond his technical prowess, Eduardo's diverse interests, including photography and biographies, reflect his insatiable curiosity and multidimensional perspective.

Skill covered

Retrieval Augmented Generation (RAG)