From the course: AWS Certified Generative AI Developer - Professional (AIP-C01) Cert Prep
Unlock this course with a free trial
Join today to access over 25,200 courses taught by industry experts.
What is RAG?
From the course: AWS Certified Generative AI Developer - Professional (AIP-C01) Cert Prep
What is RAG?
Imagine asking a chatbot about the latest scientific breakthrough that happened last month, only to receive an apologetic response about its knowledge cutoff date. Or picture a company chatbot confidently giving outdated information about your organization's products. Frustrating, right? So this is where Retrieval Augmented Generation comes in, the technology that's transforming how AI systems access and utilize knowledge. Hence, in this lecture, we'll explore it more to answer what is Retrieval Augmented Generation all about. Retrieval Augmented Generation, or RAG, is an AI framework that integrates an information retrieval component into the generation process of large language models to improve factuality and relevance. The term RAG was coined in a 2020 meta-research paper by Kiela et al. titled Retrieval Augmented Generation for Knowledge-Intensive NLP Task. Unlike LLMs, which are large-language models that depend solely on their pre-trained parameters, RAG systems fetch external…
Download courses and learn on the go
Watch courses on your mobile device without an internet connection. Download courses using your iOS or Android LinkedIn Learning app.
Contents
-
-
(Locked)
What are LLMs?6m 37s
-
(Locked)
What are foundational models?5m 9s
-
(Locked)
What are embeddings?5m 22s
-
(Locked)
What is RAG?5m 17s
-
(Locked)
Sources of ML models2m 38s
-
(Locked)
Components of ML pipeline (overview)3m
-
(Locked)
Model fit2m 42s
-
(Locked)
What is LLM as a judge?5m
-
(Locked)
LLM as a judge on Amazon Bedrock model evaluation3m 57s
-
(Locked)
Feature engineering4m 25s
-
(Locked)
Bias and variance4m 2s
-
(Locked)
Effects of bias and variance3m 17s
-
(Locked)
Batch size, learning rate, and warm-up11m 39s
-
(Locked)
Performance metrics5m 18s
-
(Locked)
Monitoring model performance9m 17s
-
(Locked)
Fine-tuning for specific tasks8m 55s
-
(Locked)
Fine-tuning in practice2m 43s
-
(Locked)
Inference parameters8m 8s
-
(Locked)
Inference parameters in action4m 9s
-
(Locked)
Introduction to hyperparameters5m 47s
-
(Locked)
Epoch count and model accuracy7m 55s
-
(Locked)
Vector databases, embeddings, and RAG explained9m 49s
-
(Locked)
-
-
(Locked)
Amazon Bedrock12m 29s
-
(Locked)
Foundation models in Amazon Bedrock4m 44s
-
(Locked)
Amazon Bedrock playgrounds2m 32s
-
(Locked)
Amazon Bedrock guardrails6m 35s
-
(Locked)
Amazon Bedrock knowledge bases12m 43s
-
(Locked)
Content chunking in Amazon Bedrock knowledge base3m 48s
-
(Locked)
Token management in Amazon Bedrock11m 40s
-
(Locked)
Cost optimization and model selection in Amazon Bedrock3m 29s
-
(Locked)
Provisioned throughput7m 7s
-
(Locked)
Implementing provisioned throughput2m 56s
-
(Locked)
Provisioned throughput model units (MUs) in Amazon Bedrock4m 30s
-
(Locked)
Cross-region inference in Amazon Bedrock5m 50s
-
(Locked)
Reranker model in Amazon Bedrock5m 34s
-
(Locked)
How Amazon Bedrock agents work4m 43s
-
(Locked)
Amazon Bedrock prompt management4m 46s
-
(Locked)
Amazon Bedrock data automation7m 40s
-
(Locked)
Amazon Bedrock flows5m 47s
-
(Locked)
Amazon Bedrock evaluations7m 35s
-
(Locked)
Understanding intelligent prompt routing in Amazon Bedrock6m 39s
-
(Locked)
Safety and governance with Amazon Bedrock guardrails7m 25s
-
(Locked)
-
-
(Locked)
Amazon Bedrock AgentCore overview5m 9s
-
(Locked)
Amazon Bedrock AgentCore code interpreter and browser tools8m 37s
-
(Locked)
Amazon Bedrock AgentCore gateway overview6m 43s
-
(Locked)
Amazon Bedrock AgentCore memory overview9m 7s
-
(Locked)
Amazon Bedrock AgentCore runtime overview6m 29s
-
(Locked)
Amazon Bedrock AgentCore identity overview6m 40s
-
(Locked)
Amazon Bedrock AgentCore observability overview6m 31s
-
(Locked)
What is AWS Agent Squad2m 55s
-
(Locked)
What is AWS Strands Agents2m 45s
-
(Locked)
Human-in-the-loop (HITL) validation patterns1m 52s
-
(Locked)
-
-
(Locked)
Generative AI observability overview7m 57s
-
(Locked)
Introduction to security scoping matrix1m 56s
-
(Locked)
Generative AI security scoping matrix4m 54s
-
(Locked)
Security discipline: Resilience4m 51s
-
(Locked)
Security discipline: Risk management5m 33s
-
(Locked)
Security discipline: Legal and privacy5m 12s
-
(Locked)
Security discipline: Controls6m 53s
-
(Locked)
Security discipline: Governance and compliance3m 24s
-
(Locked)
Understanding consumer app scope2m 35s
-
(Locked)
Understanding enterprise app scope3m 1s
-
(Locked)
Understanding model context protocol5m 24s
-
(Locked)
Understanding self-trained models scope2m 24s
-
(Locked)
Understanding fined-tuned models scope3m 5s
-
(Locked)
Validating compliance and scope1m 55s
-
(Locked)
-
-
(Locked)
What is agentic AI?7m 12s
-
(Locked)
Introduction to prompt engineering4m
-
(Locked)
Types of prompts and techniques5m 3s
-
(Locked)
What is prompt caching4m 57s
-
(Locked)
Chain of thought prompting7m 5s
-
(Locked)
What are tokens in AI?5m 18s
-
(Locked)
Tokens and prompts in generative AI9m 16s
-
(Locked)
How tokenization works, from sentences to subwords8m
-
(Locked)
AWS Neuron for Gen AI3m 44s
-
(Locked)
What is Langchain?10m 36s
-
(Locked)
What is Langraph ?4m 38s
-
(Locked)
What is Langsmith?3m 56s
-
(Locked)
Generative AI application builder on AWS5m 37s
-
(Locked)
-
-
(Locked)
AWS services categories5m 18s
-
(Locked)
AWS machine learning services overview16m 41s
-
(Locked)
AWS compute services overview10m 44s
-
(Locked)
AWS deployment services overview14m 25s
-
(Locked)
AWS security services overview12m 56s
-
(Locked)
AWS application integration services overview10m 9s
-
(Locked)
AWS storage services overview17m 32s
-
(Locked)
AWS database services overview11m 51s
-
(Locked)
AWS networking and content delivery services overview13m 54s
-
(Locked)
AWS management and governance services overview9m 50s
-
(Locked)
AWS transfer and migration services overview9m 33s
-
(Locked)
AWS monitoring services overview6m 6s
-
(Locked)
AWS audit and compliance services overview3m 22s
-
(Locked)
AWS analytics services overview22m 32s
-
(Locked)
AWS identity services overview4m 32s
-
(Locked)
AWS container services overview6m 4s
-
(Locked)
-
-
(Locked)
Amazon Comprehend with hands-on labs7m 17s
-
(Locked)
Amazon Rekognition9m 47s
-
(Locked)
Amazon Augmented AI (A2I) overview2m 56s
-
(Locked)
Amazon Augmented AI (A2I) with hands-on labs7m 52s
-
(Locked)
Amazon Lex with hands-on labs10m 23s
-
(Locked)
Amazon Transcribe with hands-on labs7m 37s
-
(Locked)
Amazon Translate with hands-on labs7m 9s
-
(Locked)
Amazon Polly hands-on lab5m 8s
-
(Locked)
Amazon Textract7m 43s
-
(Locked)
Amazon Nova8m 22s
-
(Locked)
Amazon Q4m 9s
-
(Locked)
Getting started with Amazon Q developer7m 1s
-
(Locked)
Getting started with Amazon Q business9m 57s
-
(Locked)
Building a custom Amazon Q business web experience5m 27s
-
(Locked)
Amazon Quick Suite: your agentic AI teammate5m 22s
-
(Locked)
AWS vector search across services5m
-
(Locked)
-
-
(Locked)
Amazon SageMaker Jumpstart9m 36s
-
(Locked)
Amazon SageMaker feature store4m 51s
-
(Locked)
SageMaker Data Wrangler5m 59s
-
(Locked)
SageMaker Clarify7m 40s
-
(Locked)
Amazon SageMaker role manager5m 3s
-
(Locked)
SageMaker model cards10m 37s
-
(Locked)
SageMaker model registry9m 33s
-
(Locked)
SageMaker model endpoints7m 55s
-
(Locked)
Amazon SageMaker inference recommender5m 55s
-
(Locked)
Understanding model drift in machine learning7m 27s
-
(Locked)
Amazon SageMaker HyperPod7m 7s
-
(Locked)
Amazon SageMaker Canvas5m 2s
-
(Locked)
Amazon SageMaker catalog4m 45s
-
(Locked)
Amazon SageMaker Ground Truth7m 18s
-
(Locked)
Amazon SageMaker endpoints6m 56s
-
(Locked)
-
-
(Locked)
Amazon EC2 overview5m 11s
-
(Locked)
Instance types8m 6s
-
(Locked)
Amazon Machine Image (AMI)7m 29s
-
(Locked)
Instance user data2m 31s
-
(Locked)
Instance metadata6m 13s
-
(Locked)
Amazon EC2 networking14m 20s
-
(Locked)
Amazon EC2 network security16m 12s
-
(Locked)
Hands-on lab: Vertically scaling an Amazon EC2 instance8m 13s
-
(Locked)
Hands-on lab: Using EC2 Instance Connect to connect to your instance5m 23s
-
(Locked)
Hands-on lab: Setting up a web server on an EC2 instance5m 52s
-
(Locked)
Hands-on lab: Connecting the domain name to the EC2 instance using Elastic IP9m 58s
-
(Locked)
-
-
(Locked)
IAM overview8m 13s
-
(Locked)
IAM identities9m
-
(Locked)
AWS IAM Identity Center8m 5s
-
(Locked)
IAM access analyzer3m 38s
-
(Locked)
IAM policy types7m 42s
-
(Locked)
IAM policy basics9m 14s
-
(Locked)
IAM policy evaluation logic9m 8s
-
(Locked)
AWS Audit Manager6m 51s
-
(Locked)
AWS Key Management Service (KMS) overview6m 58s
-
(Locked)
AWS Secrets Manager3m 53s
-
(Locked)
What is AWS Firewall Manager2m 47s
-
(Locked)
AWS Resource Access Manager6m 13s
-
(Locked)
AWS Security Hub6m 13s
-
(Locked)
Amazon Macie hands-on6m 54s
-
(Locked)
Amazon Fraud Detector13m 25s
-
(Locked)
Amazon CodeGuru Security1m 38s
-
(Locked)
Amazon CodeGuru Profiler1m 30s
-
(Locked)
Amazon CodeGuru Reviewer2m 2s
-
(Locked)
Open Cybersecurity Schema Framework (OCSF) in Security Lake4m 5s
-
(Locked)
Amazon Security Lake1m 59s
-
(Locked)
AWS Shield5m 23s
-
(Locked)
Amazon Inspector4m 3s
-
(Locked)
-
-
(Locked)
Systems Manager Parameter Store5m 44s
-
(Locked)
Systems Manager AppConfig6m 21s
-
(Locked)
Systems Manager Automation8m 8s
-
(Locked)
Systems Manager Run Command7m 18s
-
(Locked)
Systems Manager Change Manager5m 5s
-
(Locked)
Systems Manager Patch Manager6m 48s
-
(Locked)
Hands-on lab: AWS Systems Manager Parameter Store10m 2s
-
(Locked)
-
-
(Locked)
CloudFormation overview4m 58s
-
(Locked)
Anatomy of a CloudFormation template9m 2s
-
(Locked)
CloudFormation helper scripts3m 59s
-
(Locked)
DependsOn and WaitCondition2m 43s
-
(Locked)
CloudFormation: StackSets6m 4s
-
(Locked)
CloudFormation: Nested stacks3m 52s
-
(Locked)
CloudFormation: Custom resource4m 56s
-
(Locked)
AWS CloudFormation Guard2m 47s
-
(Locked)
-
-
(Locked)
Amazon RDS overview10m 58s
-
(Locked)
Amazon RDS read replica13m
-
(Locked)
Amazon RDS multi-AZ deployments11m 5s
-
(Locked)
Amazon RDS events notification6m 17s
-
(Locked)
Amazon RDS proxy3m 49s
-
(Locked)
Amazon Aurora overview7m 10s
-
(Locked)
Amazon DynamoDB overview14m 30s
-
(Locked)
Amazon DynamoDB core components7m 32s
-
(Locked)
Amazon MemoryDB7m 10s
-
(Locked)
-
-
(Locked)
Amazon S3 overview9m 22s
-
(Locked)
Understanding Amazon S3 Storage Lens4m 14s
-
(Locked)
Amazon S3 storage classes12m 41s
-
(Locked)
Amazon S3 storage class: Standard1m 46s
-
(Locked)
Amazon S3 storage class: One zone-IA2m 31s
-
(Locked)
Amazon S3 storage class: Standard-IA2m 28s
-
(Locked)
Amazon S3 storage class: Intelligent-tiering2m 33s
-
(Locked)
Amazon S3 storage class: Glacier instant retrieval2m 19s
-
(Locked)
Amazon S3 storage class: Glacier flexible retrieval2m 33s
-
(Locked)
Transform data with Amazon S3 object lambda7m 39s
-
(Locked)
Vector management with Amazon S3 vectors10m 4s
-
(Locked)
Exploring the Amazon S3 console7m 32s
-
(Locked)
Creating an Amazon S37m 48s
-
(Locked)
Uploading and downloading objects in Amazon S35m 1s
-
(Locked)
Tabular data management in S3 with table buckets6m
-
(Locked)
-
-
(Locked)
AWS Glue overview6m 6s
-
(Locked)
AWS Glue for beginners5m 51s
-
(Locked)
Data cleaning with AWS Glue DataBrew6m 21s
-
(Locked)
Building visual ETL jobs with AWS Glue Studio5m 5s
-
(Locked)
Getting started with AWS Glue crawler7m 59s
-
(Locked)
AWS Glue connections: Centralize your data source management6m 16s
-
(Locked)
Bulletproof your streaming data with AWS Glue schema registry6m 32s
-
(Locked)
AWS Glue job bookmarks explained4m 58s
-
(Locked)
Automate data discovery with AWS Glue classifiers5m 21s
-
(Locked)
Improve data with AWS Glue data quality6m 4s
-
(Locked)
Automate pipelines with AWS Glue triggers7m 20s
-
(Locked)
-
-
(Locked)
What is the AWS Well-Architected Framework?9m 18s
-
(Locked)
The pillars of the AWS Well-Architected Framework12m 31s
-
(Locked)
Introduction to AWS Well-Architected lenses3m 3s
-
(Locked)
AWS WA Tool step 1: define workload5m 18s
-
(Locked)
AWS WA Tool step 2: conduct architectural review5m 12s
-
(Locked)
AWS WA Tool step 3: apply best practices3m 10s
-
(Locked)
AWS Well-Architected Tool custom lens for your ML workloads6m 25s
-
(Locked)
AWS Well-Architected Tool for generative AI: Your blueprint for success5m 59s
-
(Locked)
-
-
(Locked)
Route 53 simple routing: Connect your domain in minutes4m 39s
-
(Locked)
Route 53 multivalue answer routing: Simple load distribution with health checks4m 59s
-
(Locked)
Route 53 weighted routing: Split your traffic like a pro5m 53s
-
(Locked)
Route 53 failover routing: Automatic disaster recovery5m 55s
-
(Locked)
Route 53 latency routing: Send users to the fastest server7m 12s
-
(Locked)
Route 53 geolocation routing: Direct traffic by user location6m 10s
-
(Locked)
Route 53 geoproximity routing: Route by location with bias control4m 50s
-
(Locked)
Route 53 IP-based routing: Route traffic by specific IP ranges6m 4s
-
(Locked)
-
-
(Locked)
What is routing?4m 20s
-
(Locked)
Monitoring your AWS bill with AWS Budgets notification5m 5s
-
(Locked)
Creating a billing alarm with Amazon CloudWatch to monitor AWS charges6m 40s
-
(Locked)
Amazon OpenSearch Service4m 22s
-
(Locked)
Accessing the Amazon EC2 instance using SSH5m 34s
-
(Locked)
Connecting the domain name to the Amazon EC2 instance using Elastic IP9m 58s
-
(Locked)
AWS Amplify overview3m 13s
-
(Locked)
AWS Cost Explorer overview5m 14s
-
(Locked)
AWS CloudShell5m 40s
-
(Locked)
AWS AppSync2m 44s
-
(Locked)
AWS DataSync5m 32s
-
(Locked)
What is AWS Lake Formation?2m 32s
-
(Locked)
Amazon API Gateway5m 1s
-
(Locked)
-
-
(Locked)
Extracting text from unstructured documents using Bedrock and Textract (hands-on lab)5m 30s
-
(Locked)
Amazon Bedrock Serverless + Claude Haiku hands-on lab5m 47s
-
(Locked)
Integrating generative AI into business workflows8m 5s
-
(Locked)
Economic and business implications of gen-AI solutions7m 4s
-
(Locked)
AWS Data Transfer Terminal: Drive your data to the cloud7m 28s
-
(Locked)
AWS Service Catalog: Governance made simple8m 10s
-
(Locked)
Amazon S3 + Amazon Q business hands-on lab6m 47s
-
(Locked)
Building a custom Amazon Q business web experience hands-on lab5m 27s
-
(Locked)
Building a cost-aware RAG application with Amazon Bedrock27m 10s
-
(Locked)