AI

Generative AI In Cloud Using AWS, Azure & Google Cloud

This comprehensive 6-month course covers Generative AI fundamentals and cloud-based implementations using AWS, Azure, and Google Cloud platforms. It includes hands-on projects to build, deploy, and fine-tune AI models using cloud services, preparing students for real-world AI applications in cloud environments.

Request Syllabus Back to Courses
Generative AI In Cloud Using AWS, Azure & Google Cloud
Duration4 months
Lessons250
Levelintermediate
ModeLive Online

What you will learn

  • Generative AI Fundamentals
  • AWS Cloud Services
  • AWS Bedrock & SageMaker
  • Azure OpenAI Service
  • Google Cloud Vertex AI
  • Cloud AI Model Deployment
  • Fine-Tuning Foundation Models
  • API Integration with Lambda & API Gateway
  • Building AI-powered Applications in Cloud

Corporate training outcomes

  • Completion certificate
  • Practical assignments and project work
  • Mentor support and progress tracking
  • Custom batch options for teams
  • Yes

Requirements

  • Laptop with good internet
  • Basic knowledge of cloud services (optional but preferred)
  • Passionate about learning
  • No prior experience needed
  • Willing to dedicate time
  • Curious about working with cloud-based AI tools

Curriculum

Generative AI Fundamentals & Foundation Models
  • Introduction to AI Concepts
  • Exploring Generative AI
  • Key Differences Between Discriminative and Generative Models
  • Overview of LLM Architectures
  • Foundation Models in LLMs
  • Deep Dive into Embeddings
  • Measuring Similarity Between Embeddings
Introduction of AWS Cloud & Services for Generative AI
  • Introduction to AWS Cloud Services
  • Steps to Set Up an AWS Account
  • Creating and Managing IAM Users
  • Understanding AWS Regions and Availability Zones
  • AWS Elastic Container Registry Overview
  • Overview of AWS Elastic Cloud Compute (EC2)
  • Getting Started with AWS App Runner
AWS Bedrock
  • Exploring Amazon Bedrock - An Overview
  • Hands-on with Amazon Bedrock Console
  • Architecture of Amazon Bedrock
  • Exploring Bedrock Foundation Models
  • Understanding Bedrock Embeddings
  • Using Amazon Bedrock Chat Playgrounds
  • Amazon Bedrock - A Look at Inference Parameters
  • Pricing and Cost Structure of Amazon Bedrock
AWS Sagemaker
  • Overview of AWS SageMaker
  • Step-by-Step AWS SageMaker Walk-through
  • Exploring AWS SageMaker Studio
  • Hands-on with SageMaker Studio Walk-through
  • Choosing Pre-trained Models with SageMaker
  • Creating SageMaker Endpoints
  • Accessing the SageMaker Console
  • Creating a SageMaker Domain
  • Opening SageMaker Studio
  • Exploring SageMaker JumpStart
  • Deploying Models with AWS SageMaker
AWS Lambda Function
  • Quick Overview of AWS Lambda
  • Lambda Console Walkthrough
  • Lambda Console Walkthrough Continued
  • Lambda Permissions Model
AWS API Gateway
  • Introduction to AWS API Gateway
  • Understanding RESTful APIs
  • Exploring WEBSOCKET APIs
  • Best Practices for Efficient API Development
  • Ensuring Performance at Any Scale
  • Achieving Cost Savings at Scale
  • Easy API Monitoring Techniques
  • Flexible Security Controls in API Management
Enterprice Use case - Text Summarization - Bedrock, API, GW, Lamda
  • Creating AWS Lambda Functions and Upgrading Boto3
  • Writing the AWS Lambda Function to Connect to Bedrock Service - Part 1
  • Writing the AWS Lambda Function to Connect to Bedrock Service - Part 2
  • Creating REST APIs with AWS API Gateway and Lambda Integration
  • Building an End-to-End Application with AWS Lambda and API Gateway
Enterprise Use case - Retrieval-Augmented Generation (RAG)
  • Demo of What We Will Build
  • Overview of Vectors, Embedding, Vector DB, and Use Case Architecture
  • Setting Up the Environment Before Coding
  • Data Ingestion Process
  • Data Transformation and Processing
  • Embedding, Vector Store, and Indexing
  • Hands-on LLM Creation with Context
  • Retrieval QA Techniques
  • Frontend Development and Final Demo
  • End-to-End Demo Implementation
Enterprise Use case - Building Chatbot with Llama2, Langchain & Streamlit
  • Demo Overview of What We Will Build
  • Exploring Vectors, Embedding, Vector DB, and Architecture for the Use Case
  • Preparing the Environment Before Coding
  • Data Ingestion Process
  • Transforming and Processing Data
  • Understanding Embedding, Vector Store, and Indexing
  • Hands-on - Creating LLM with Context
  • Frontend Development and Final Demo
  • Complete End-to-End Demo
Fine Tuning of Foundation Model on Custom data
  • Overview of Fine Tuning Foundation Models
  • Understanding the Architecture of Fine Tuning Foundation Models
  • Exploring Amazon Bedrock's Data Privacy Challenges
  • Hands-On with Fine Tuning Foundation Models
Conclusion - Any Generative AI Use case Identification
  • GenAI Project Lifecycle and Identifying Use Cases
  • Understanding the GenAI Project Lifecycle
  • Approach for Identifying GenAI Use Cases
  • Tools, Techniques, and Productionizing GenAI Projects
Azure Cloud Introduction and basics
  • Introduction to Azure Cloud Services
  • Creating an Azure Account
  • Creating Resources for Your Project in Azure
  • Understanding Azure Regions and Availability Zones
  • Why Choose Pay-as-you-go Service in Azure
Azure OpenAI Service
  • Introduction to Azure OpenAI Service
  • Setting Up Your Azure OpenAI Service Account
  • Understanding System Message Framework and Templates
  • Deploying a Model on Your Own Azure Server
  • Chatting with Your Model using Completion API
  • Using Function Calling with Azure OpenAI
  • Chat Completions API with Tokens, Temperature, and Other Parameters
  • Using Dall-E, GPT-4, and GPT-4v Models
  • Deploying a Web App (Chat Engine) with Your Own Data on Azure Cloud
Prompt Engineering
  • Introduction to Prompt Engineering
  • Different Templates for Prompting
  • The Core Elements of a Good Prompt
  • Which Context Should You Add?
  • Zero-Shot Prompting
  • One- & Few-Shot Prompting
  • Prompt Chaining
  • Super Prompts Like CAN & DAN
Fine Tuning of Foundation Model on Custom data
  • Choosing the Right Foundation Model from Azure OpenAI
  • Fine Tuning of Foundation Model - Overview
  • Fine Tuning of Foundation Model - Architecture
  • Fine Tuning of Foundation Models - Hands On
  • Identifying the Right Parameters for Fine-Tuning
  • PEFT (Parameter Efficient Fine-Tuning)
  • Data Compliance & Data Privacy Challenges
Enterprise Use case - Retrieval-Augmented Generation (RAG)
  • Demo of What We Will Build
  • Overview of Vectors, Embedding, Vector DB
  • Architecture for the Use Case
  • Environment Setup Before Coding
  • Data Ingestion in RAG
  • Data Transforming in RAG
  • Embedding, Vector Store, Index & Reranking
  • Retrieval QA
  • LLM Creation + Context
  • Frontend and Final Demo
Enterprise Use case - Building Chatbot with GPT 4, Langchain & Streamlit
  • Demo of What We Will Build
  • Overview of Vectors, Embedding, Vector DB
  • Architecture for the Use Case
  • Environment Setup Before Coding
  • Data Ingestion
  • Data Transformation & Preprocessing
  • Embedding, Vector Store & Index
  • Hands-on - LLM Creation + Context
  • Frontend and Final Demo
  • LLMOps Pipeline
Conclusion - Any Generative AI Use case Identification
  • GenAI Project Lifecycle and Use Case Identification
  • Overview of GenAI Project Lifecycle
  • GenAI - Use Case Identification Approach
  • Implementation Tools, Techniques & Productionisation
GCP Basics & Introduction to Vertex AI
  • What is Vertex AI?
  • Google Cloud Regions & Zones
  • Foundation Google Models
  • Prompt Engineering Best Practices
  • Google Cloud Overview
  • Vertex AI installation
  • Google Cloud setup for production
  • Vertex AI Overview
  • Vertex AI Model Garden
  • Google AI Studio Introduction
  • Benefits of Google NLP API
Google NLP API
  • Demo of Google NLP API
  • Key features in Google NLP API
  • Entity analysis and extraction
  • Sentiment analysis using google NLP API
  • Content classification using google NLP API
  • Multi language assistant using google NLP API
  • Pricing of NLP API
Gemini Models with Vertex AI and Google AI Studio
  • What is Google Gemini?
  • Google Gemini: Playing with Gemini
  • Gemini 1.5 Pro (Preview only)
  • Gemini 1.0 Pro
  • Gemini 1.0 Pro Vision
  • Gemini Embeddings
  • Advanced Information Retrieval with Gemini
  • Creative and Expressive Capabilities
  • Advanced Coding Capabilities
  • Google Gemini Limitations
Google Cloud Vertex AI Studio
  • Working with Codey (Palm 2) model
  • Working with Text Chat prompt
  • Generate Code, Unit test with Code Chat Bison model
  • Translate text with Translation LLM
  • Summarization (Use case of language model)
  • Classification (Use case of language model)
  • Vision Model
  • Speech to Text & Text to Speech
  • Multimodal Prompts
Enterprise Use case - Retrieval-Augmented Generation (RAG)
  • Demo of what we will Build
  • Overview of Vectors, Embedding, Vector DB and
  • Architecture for the Use Case
  • Environment Setup before coding
  • Data Load
  • Data Transform
  • Embedding, Vector Store & Index
  • Hands-on - LLM Creation + Context
  • Retrieval QA
  • Frontend and Final Demo
  • End to End Demo
Enterprise Use case - Building Chatbot with Gemini pro , Langchain & Streamlit
  • Demo of what we will Build
  • Overview of Vectors, Embedding, Vector DB and
  • Architecture for the Use Case
  • Environment Setup before coding
  • Data Load
  • Data Transform
  • Embedding, Vector Store & Index
  • Hands-on - LLM Creation + Context
  • Frontend and Final Demo
  • End to End Demo
Conclusion - Any Generative AI Use case Identification
  • GenAI Project Lifecycle and Use Case Identification
  • Overview of GenAI Project Lifecycle
  • GenAI - Use Case Identification Approach
  • Implementation Tools, Technique & Productionisation