Your cart is empty.
Keep shopping
Build an Enterprise RAG System on AWS with Generative AI
Hot & New
New
25 students
Build an Enterprise RAG System on AWS with Generative AI
Build enterprise RAG with Bedrock, Textract, Lambda, S3 Vectors, event-driven architecture, and AI-assisted development.
Created byDinesh Sharma
Last updated 10/2026
English
What you'll learn
- Build an end-to-end enterprise RAG system on AWS that transforms documents into searchable knowledge and grounded AI answers.
- Design a serverless, event-driven AI architecture using Amazon Bedrock, Amazon Textract, AWS Lambda, Amazon S3, DynamoDB, API Gateway, and S3 Vectors.
- Build the RAG knowledge journey with enrichment, chunking, embeddings, vector search, retrieval, and grounded generation.
- Use AI-assisted development to turn business requirements and architecture into code, AWS configuration, testing, and validation.
- Build event-driven AWS workflows that process documents asynchronously and safely.
- Create grounded AI answers by retrieving relevant knowledge from enterprise documents.
Explore related topics
Course content
17 sections • 130 lectures • 8h 37m total length
Requirements
- Curiosity about Generative AI, RAG, and building real-world AI systems.
- An AWS account for completing the hands-on exercises. AWS usage charges may apply.
- No prior AWS or cloud computing experience is required.
- No prior Python programming experience is required. We use an AI-assisted development approach throughout the course.
- A computer with internet access and permission to use the course tools, including a REST client, curl, and Python where required.
Description
This course contains the use of artificial intelligence.
Move beyond RAG concepts and build a complete enterprise AI system on AWS.
In this hands-on course, you will build FinInsight, an end-to-end Retrieval-Augmented Generation (RAG) system that transforms financial documents into searchable knowledge and grounded AI answers.
Prior Knowledge
No prior Cloud or AWS experience required.
No prior Python programming experience required.
No prior API testing or curl experience required.
We will work through what you need step by step.
What You Will Build
Instead of learning AWS and Generative AI services in isolation, you will see how they work together as part of a real application architecture.
Starting with a PDF document, you will build the workflow step by step: secure document intake, asynchronous text extraction, Generative AI analysis, customer matching, human confirmation, document archiving, knowledge enrichment, chunking, vector embeddings, vector indexing, semantic retrieval, grounded answer generation, and a conversational chat experience.
Along the way, you will work with services including Amazon Bedrock, Amazon Textract, AWS Lambda, Amazon S3, Amazon DynamoDB, Amazon API Gateway, Amazon EventBridge, and Amazon S3 Vectors.
You will also learn an AI-assisted development approach that connects business requirements to architecture, plain-English flows, Mermaid diagrams, implementation prompts, AI-generated Python code, AWS configuration, testing, and validation.
By the end of the course, you won't just understand how RAG works—you will understand how the surrounding cloud architecture turns RAG into a complete enterprise AI system.
You will learn not just what to build, but why each architectural decision matters.
Who this course is for:
- AI beginners and enthusiasts who want to understand Generative AI and RAG by building a complete working application.
- Business and product professionals who want to understand how an AI idea becomes a real-world enterprise solution.
- Developers who want hands-on experience building RAG workflows with AWS services, Generative AI, vector search, and AI-assisted development.
- Solution and enterprise architects who want to understand how AI, cloud services, data, APIs, security, and event-driven architecture come together in an enterprise AI system.