Teach on Udemy

Turn what you know into an opportunity and reach millions around the world.

Learn More

Your cart is empty.

Keep shopping

Amazon Bedrock - The Complete Guide to AWS Generative AI

Name: Amazon Bedrock - The Complete Guide to AWS Generative AI
Rating: 4.7 (1577 reviews)

Learn to Deploy Scalable, Reliable, and Secure Generative AI Apps Using AWS and Amazon Bedrock (Python and TypeScript)

Created byAlex Dan • 300K+ Students

Last updated 8/2026

English

German [Auto],English [Auto],

What you'll learn

Understand the fundamentals of Generative AI, including its applications, algorithms, and potential impact across various industries.
Gain familiarity with the AWS ecosystem, including core services such as EC2, S3, Lambda, and more, essential for deploying and managing Generative AI apps
Learn about Amazon Bedrock Managed Service, its features and capabilities
Step-by-step guidance on creating the necessary infrastructure to support Generative AI workloads.
Develop Generative AI apps backed by AWS with your preferred programming language (Python or TypeScript))
Easily develop RAG apps with Bedrock Knowledge bases
Integrate LangChain with Amazon Bedrock (Python and TypeScript code examples)

Course content

17 sections • 102 lectures • 9h 23m total length

How to take this course2:29
Course roadmap covering Bedrock setup, text and image models, embeddings, vector databases, RAG applications, Bedrock knowledge bases, custom models, and AWS CDK/Terraform infrastructure-as-code sections.
Udemy tips3:35
Udemy platform guidance covering playback speed, GitHub diff code resources, Python vs TypeScript lecture selection, Q&A usage, and course review timing.
Tools setup2:12
Required tools for the course: AWS account with Bedrock access, VS Code editor, Python, and Node.js installation for following Python or TypeScript code examples.

Section intro0:39
Overview of Amazon Bedrock fundamentals covering supported foundation models, the Bedrock console, and Python and TypeScript SDK access setup for building applications.
What is Amazon Bedrock?4:19
Amazon Bedrock definition covering serverless and provisioned model access, foundation model providers Amazon, Anthropic, Cohere, and Meta, and text, image, and embedding use cases.
Hands on: Bedrock console overview8:32
Bedrock console walkthrough covering the model catalog, region-based model availability, Anthropic Claude Haiku access request, and playground testing with system prompts, temperature, top P, and max tokens.
AWS configure - CLI access8:55
IAM user creation for CLI access, AWS access key generation, AWS CLI installation, and aws configure setup for calling Bedrock APIs from a local machine.
Bedrock API - Boto3 - Python7:43
Boto3 SDK installation in a Python virtual environment, bedrock client setup, and list_foundation_models and get_foundation_model API calls for Amazon Bedrock.
Bedrock API - JS SDK - TypeScript8:30
AWS SDK for JavaScript v3 setup with @aws-sdk/client-bedrock, TypeScript configuration, and ListFoundationModelsCommand and GetFoundationModelCommand usage.
Optional - VSCode debug7:24
VS Code debugger configuration for Python and TypeScript Bedrock projects using launch.json, the Python debugger, and the tsx debug recipe for Node.js.
Course source code0:05

Section intro1:02
Overview of Amazon Bedrock text model access, inference parameters, and Converse API and Invoke API usage in Python and TypeScript.
Amazon Bedrock text models intro4:17
Amazon Nova and Titan text model pricing and access via the Bedrock model catalog, plus the difference between the model-specific Invoke API and the unified Converse API.
Understanding tokens6:30
Token concepts for Bedrock text models covering max token limits per model, the OpenAI tokenizer, and token-based pricing calculations for input and output.
Text models parameters6:33
Inference parameters for Bedrock text models including temperature, top P nucleus sampling, stop sequences, and camelCase vs snake_case naming across Titan, Llama, and Anthropic models.
Converse and Invoke API - Python7:29
Boto3 implementation of the Invoke API with Meta Llama 3 and the Converse API with Amazon Nova Lite, including system prompts, in Python.
Converse and Invoke API - TypeScript9:02
AWS SDK client-bedrock-runtime implementation of InvokeModelCommand with Llama 3 and ConverseCommand with Amazon Nova Lite in TypeScript.
Prompt engineering3:37
Prompt engineering fundamentals covering prompt context, reference text, and task instructions for summarization using the Amazon Bedrock Converse API.
Multi turn conversation - Python6:55
Multi-turn chatbot implementation with Boto3 and the Converse API, message history arrays, user and assistant roles, and system prompts in Python.
Multi turn conversation - TypeScript8:16
Multi-turn chatbot implementation using the AWS SDK Converse API, a Node.js stdin listener, conversation history array, and system prompts in TypeScript.
Shortcut for advanced text app0:06

Section intro3:05
Overview of Amazon Bedrock Guardrails covering content safety, PII filtering, denied topics, and compliance controls between users and AI models or agents.
LAB: Bedrock Guardrails6:31
Bedrock Guardrails console setup with content filters, prompt attack protection, denied topics, word filters, and PII filtering, tested against Claude models in the playground.
Bedrock SDK calls with Guardrails3:16
Guardrail ID and version attachment to the Converse API guardrailConfig parameter for enforcing content filtering in Bedrock SDK calls.

Section intro0:49
Overview of Bedrock image generation covering model parameters and Python and TypeScript SDK usage for Stability AI and Titan image models.
Image models intro3:37
Bedrock image model catalog covering Amazon Titan and Stability AI providers, model access requests, and per-resolution pricing for image generation.
Stability AI parameters3:49
Stability AI image model parameters including aspect ratio, output format, seed, negative prompt, and a style preset workaround via inline prompt text.
Stability AI images - Python and TypeScript3:08
Stable Image Core model invocation via the Bedrock SDK in Python and TypeScript, with base64 image decoding from the response body.
Titan model image generation3:35
Amazon Titan Image Generator text-to-image task type, negative text parameter, and image generation config with height, width, and CFG scale in Python and TypeScript.
Titan model image editing3:59
Titan Image Generator inpainting task type with the mask prompt parameter for editing existing images using Python and TypeScript.
Shortcut for advanced image generation app0:03

Section intro1:03
Overview of embeddings and vector databases covering Amazon Bedrock embedding models for text and image similarity search.
Embeddings and Similarity6:58
Embedding vectors, dot product and cosine similarity calculations, and the Amazon Titan Embed Text v1 and Titan Embed Image v1 models explained.
Embedding models - Python and TypeScript3:11
Amazon Titan Embeddings G1 Text model invocation for generating 1536-dimension text embeddings in Python and TypeScript.
Text embeddings - Python4:45
Cosine similarity comparison across a list of text facts using Titan Embed Text v1 embeddings to find the most relevant match in Python.
Text embeddings - TypeScript4:16
Cosine similarity ranking of text embeddings generated with Titan Embed Text v1 to find the most relevant fact using TypeScript.
Image embeddings - Python5:20
Amazon Titan Embed Image model used to compare image similarity via base64 encoding and cosine similarity for a lightweight image search engine in Python.
Image embeddings - TypeScript6:25
Titan Embed Image v1 model invocation and cosine similarity comparison for building an image search application in TypeScript.
Vector databases4:07
Vector database concepts covering Pinecone, Chroma, Redis, pgvector, Amazon OpenSearch, Aurora PostgreSQL, and DocumentDB, plus the embedding storage and query workflow.

Section intro2:27
Overview of building a local RAG application with LangChain and Amazon Bedrock, covering hardcoded text data and PDF document question answering.
Langchain intro2:09
LangChain framework overview for LLM applications covering chains, agents, vector database integrations, and abstractions for Amazon Bedrock applications.
Langchain - updated imports notice0:30
First Chain - Python5:40
LangChain Bedrock LLM wrapper, ChatPromptTemplate with system and human messages, and a basic chain pipeline using Boto3 in Python.
First Chain - TypeScript5:37
LangChain Bedrock model wrapper, ChatPromptTemplate construction, and prompt-to-model chain piping using the AWS SDK in TypeScript.
What is a RAG app?3:16
Retrieval augmented generation architecture covering document chunking, embedding models, vector database storage, and the query retrieval workflow.
Basic RAG app - Python7:15
FAISS in-memory vector store, Bedrock embeddings, a retriever, and a ChatPromptTemplate chain for question answering over hardcoded text data in Python.
Basic RAG app - TypeScript7:20
MemoryVectorStore, Bedrock embeddings, a retriever with a k parameter, and a prompt template chain for RAG question answering in TypeScript.
Document app - Python7:10
PyPDFLoader document ingestion, RecursiveCharacterTextSplitter chunking, a FAISS vector store, and retriever-based question answering over a PDF in Python.
Document app - TypeScript6:54
PDF loading with a PDF loader, RecursiveCharacterTextSplitter chunking, MemoryVectorStore, and retriever-based question answering over a PDF document in TypeScript.
Shortcut for bedrock knowledge base app0:03

Section intro2:07
Overview of building a text summarization API using Amazon Bedrock, API Gateway, Lambda, and IAM.
Project architecture3:18
Text summarization API architecture covering API Gateway POST requests, Lambda, Bedrock text model integration, and IAM role permissions.
Summary Lambda - Python8:41
Boto3 Lambda handler invoking Amazon Titan Text Express for text summarization, parsing the API Gateway event body and query string parameters in Python.
Summary Lambda test - Python5:25
AWS Lambda console deployment of the Python summary function, handler configuration, timeout increase, bedrock:InvokeModel IAM permission, and test event execution.
Summary Lambda - TypeScript8:56
Lambda handler using client-bedrock-runtime InvokeModelCommand with Amazon Titan Text Express for text summarization via an API Gateway proxy event in TypeScript.
Summary Lambda test - TypeScript6:15
AWS Lambda console deployment of the compiled TypeScript summary function, handler and timeout configuration, IAM bedrock permissions, and a test event.
ApiGateway and Lambda integration5:04
API Gateway REST API resource, POST method, and Lambda proxy integration setup for exposing the summary Lambda as a web service.
IAC: Summary api - CDK Python9:32
AWS CDK Python stack defining a Lambda function, an IAM bedrock:InvokeModel policy, and an API Gateway REST API with cdk synth and deploy.
IAC: Summary api - CDK TypeScript9:10
AWS CDK TypeScript stack with a NodejsFunction Lambda, a bedrock invoke IAM policy, and API Gateway integration deployed via CDK.

Section intro2:15
Overview of building an image generation API using Amazon Bedrock, API Gateway, Lambda, and S3 with signed URL responses.
Project architecture2:40
Image generation API architecture covering API Gateway, Lambda, the Bedrock text-to-image model, S3 storage, and signed URL generation.
Image Lambda - Python7:47
Boto3 Lambda handler invoking Amazon Titan Image Generator, saving base64 images to S3, and generating pre-signed URLs in Python.
Lambda Test - Python8:17
AWS Lambda console deployment of the image generation function, bedrock and S3 IAM permissions, timeout configuration, and test event execution.
Image Lambda - TypeScript8:36
client-bedrock-runtime and client-s3 Lambda handler for Titan Image Generator invocation, S3 PutObjectCommand, and getSignedUrl generation in TypeScript.
Lambda Test - TypeScript8:49
AWS Lambda console deployment of the TypeScript image function, bedrock and S3 IAM policy configuration, and test event execution.
ApiGateway and Lambda integration6:03
API Gateway REST API POST method with Lambda proxy integration for exposing the image generation Lambda as a web service.
IAC: Image api - CDK Python13:53
AWS CDK Python stack with an S3 bucket, a Lambda function, a bedrock IAM policy, and API Gateway for the image generation API.
IAC: Image api - CDK TS11:42
AWS CDK TypeScript stack using NodejsFunction, esbuild bundling, an S3 bucket grant, and API Gateway for the image generation API.

Requirements

Basic Knowledge of Machine Learning and AI
Proficiency in at least one programming language commonly used in AI and data science, such as Python
Basic understanding of AWS services and infrastructure is recommended, including familiarity with services like EC2, S3, Lambda, IAM, and VPC.
Basic programming knowledge - Python or TypeScript

Description

Unleash the Power of Generative AI on AWS with This Comprehensive Course!

Welcome to Amazon Bedrock - The Ultimate Guide to AWS Generative AI – your gateway to mastering the fusion of cutting-edge AI technology and the unparalleled scalability of Amazon Web Services (AWS).

In this course, you'll dive deep into the world of Generative AI, harnessing its potential to create innovative solutions across diverse domains. Whether you're a seasoned data scientist, a visionary entrepreneur, or a curious developer, this course is your ticket to unlocking limitless possibilities.

Key Highlights:

Hands-On Practice: Dive right into real-world scenarios with practical exercises using Python's boto3, JavaScript SDKs, and TypeScript, coupled with VSCode debugging for seamless development.
Text and Image Models: Explore the magic of text generation with chatbots, delve into image generation with state-of-the-art models, and master embedding techniques for vector databases.
Advanced Applications: From LangChain to RAG apps and document processing, you'll explore a wide array of advanced applications, empowering you to tackle complex challenges with confidence.
Amazon Bedrock Mastery: Get up close and personal with Amazon Bedrock – the game-changer for deploying scalable, reliable, and secure Generative AI applications on AWS. Practice sections ensure you're well-versed with Bedrock, ready to tackle any project.

Key topics covered in this course include:

Amazon Bedrock introduction and setup for console and CLI access
Code examples with Python and TypeScript
Integration between Bedrock and LagChain
Building an Amazon Bedrock chat bot with history
Building Image APIs backed by Amazon Bedrock
Learn all about the essence of AI: embeddings with Bedrock
Build state of the art RAG app with Bedrock Knowledge bases
Fine tune models and create your custom models.

Why Choose This Course?

Expert Guidance: Learn from industry experts with years of experience in AI and AWS.
Practical Approach: Gain hands-on experience with guided exercises and real-world case studies.

Don't miss out on this opportunity to become a trailblazer in the world of AI innovation! Enroll now and embark on your journey to becoming a Generative AI expert with Amazon Bedrock and AWS.

Go beyond the theory and learn from active instructors, aligned with today's programming demands!

Let's revolutionize the future together!

Who this course is for:

Professionals keen on expanding their skill set in AI and machine learning, particularly in the domain of Generative AI
Developers aiming to explore the intersection of AI and cloud computing
Researchers and academics interested in exploring practical applications of Generative AI
IT professionals responsible for managing cloud infrastructure and ensuring its security and scalability

Amazon Bedrock - The Complete Guide to AWS Generative AI

What you'll learn

Explore related topics

Course content

Course Introduction3 lectures • 8min

Introduction to Amazon Bedrock8 lectures • 46min

Working with text models10 lectures • 54min

Amazon Bedrock Guardrails3 lectures • 13min

Amazon Bedrock Image models7 lectures • 19min

Amazon Bedrock embedding models8 lectures • 36min

Halfway discussion1 lecture • 2min

Project RAG app (local)11 lectures • 48min

Practice: Text API9 lectures • 58min

Practice: Image API9 lectures • 1hr 10min

Requirements

Description

Who this course is for: