DSG IIT Roorkee Bootcamp
  • Start Here: Welcome to the Bootcamp
    • Course Structure
    • Course Syllabus and Timelines
    • Know your Educators
    • Action Items and Prerequisites
    • Kick-Off Session for the Bootcamp
  • Module 1: Basics of LLMs
    • What is Generative AI?
    • What is a Large Language Model?
    • Advantages and Applications of LLMs
    • Bonus Resource: Multimodal LLMs and Google Gemini
  • Module 2: Word Vectors, Simplified
    • What is a Word Vector?
    • Word Vector Relationships
    • Role of Context in LLMs
    • Transforming Vectors into LLM Responses
    • Bonus: Overview of the Transformer Architecture
      • Attention Mechanism
      • Multi-Head Attention and Transformer Architecture
      • Vision Transformers (ViTs)
    • Bonus: Future of LLMs? | By Transformer Co-inventor
    • Graded Quiz 1
  • Module 3: Prompt Engineering and Token Limits
    • What is Prompt Engineering
    • Prompt Engineering and In-context Learning
    • For Starters: Best Practices
    • Navigating Token Limits
    • Hallucinations in LLMs
    • Prompt Engineering Excercise (Ungraded)
      • Story for the Excercise: The eSports Enigma
      • Your Task fror the Module
  • Module 4: RAG and LLM Architecture
    • What is Retrieval Augmented Generation (RAG)?
    • Primer to RAG: Pre-trained and Fine-Tuned LLMs
    • In-context Learning
    • High-level LLM Architecture Components for In-context Learning
    • Diving Deeper: LLM Architecture Components
    • Basic RAG Architecture with Key Components
    • RAG versus Fine-Tuning and Prompt Engineering
    • Versatility and Efficiency in RAG
    • Key Benefits of using RAG in an Enterprise/Production Setup
    • Hands-on Demo: Performing Similarity Search in Vectors (Bonus Module)
      • Implementation of RAG for Production Use Cases
    • Using kNN and LSH to Enhance Similarity Search (Bonus Module)
    • Bonus Video: Implementing End-to-End RAG | 1-Hour Session
    • Graded Quiz 2
  • Module 5: Hands-on Development
    • Build Your Own AI Slide Search Pipeline
    • Prerequisites (Must)
    • Docker Basics
    • Your Hands-on RAG Journey
    • 1 – First RAG Pipeline
      • Building with Open AI
      • How it Works
      • RAG with Gemini and other Open AI Alternatives
      • RAG with Open Source and Running "Examples"
    • 2 – Amazon Discounts App
      • How the Project Works
      • Building the App
    • 3 – Private RAG with Mistral, Ollama and Pathway
      • Building a Private RAG project
      • (Bonus) Adaptive RAG Overview
    • 4 – Realtime RAG with LlamaIndex/LangChain and Pathway
      • Understand the Basics
      • Implementation with LlamaIndex and LangChain
    • Cloud Deployment Basics
  • Module 6: Project Tracks and Submission
    • Prizes and Giveaways
    • Suggested Tracks for Ideation
    • Sample Projects and Additional Resources
    • Submit Project for Review
Powered by GitBook
On this page
  • Local vs. Cloud Deployment
  • Benefits of Cloud Deployment
  1. Module 5: Hands-on Development

Cloud Deployment Basics

PreviousImplementation with LlamaIndex and LangChainNextModule 6: Project Tracks and Submission

Last updated 7 months ago

Cool. If you've understood Private RAG and how you can get an application up and running on your system. But what if you want to deploy it to the cloud?

Cloud computing has become a key solution for hosting, managing, and scaling applications. A significant part of this is the public cloud — a service model where cloud infrastructure is provided by third-party vendors like Amazon Web Services (AWS), Google Cloud Platform (GCP), and Microsoft Azure. These platforms offer flexible compute, storage, and networking resources over the internet, allowing developers to deploy applications without needing to maintain physical servers.

Cloud deployment refers to the process of moving applications, services, and workloads to cloud environments, where they can be accessed globally and scaled efficiently. This approach simplifies resource management, enables rapid scaling, and improves overall application availability.

A key part of modern cloud deployment is serverless container services such as AWS Fargate and Azure Container Instances (ACI). These services allow developers to run containerized applications without managing the underlying servers. Containers are lightweight, self-contained environments that include everything an application needs to run. Serverless container services handle tasks like scaling and orchestration, freeing developers to focus on their application code rather than managing infrastructure.

Local vs. Cloud Deployment

When running applications locally, all resources — such as computing power, storage, and networking — are limited by your own physical hardware. This makes scaling and ensuring availability more difficult, as hardware limitations and maintenance issues (like server failures or network outages) can disrupt service. In contrast, running in the cloud removes these limitations by leveraging a cloud provider’s infrastructure, which is scalable, redundant, and globally accessible. In the cloud, applications can dynamically adjust resources based on demand and remain available regardless of local hardware issues, offering a more reliable and flexible deployment environment.

Benefits of Cloud Deployment

Deploying to the cloud offers several key benefits:

  1. Scalability: Cloud platforms automatically scale resources based on demand, ensuring optimal performance without over-provisioning.

  2. Cost Efficiency: You only pay for the resources you use, helping reduce costs compared to traditional infrastructure.

  3. Global Availability: Public clouds offer a network of data centers worldwide, allowing for faster, localized services.

  4. High Availability: Built-in redundancy and fault tolerance ensure reliable service even during hardware failures.

  5. Developer Focus: Serverless container services like AWS Fargate simplify infrastructure management, allowing developers to focus on building applications.

Next, we’ll explore how to deploy applications on three major cloud platforms: AWS, GCP, and Azure. The following sections will provide detailed tutorials for each:

By following these tutorials, you'll gain practical experience with cloud deployment across these platforms.

Deploying to AWS
Deploying to GCP
Deploying to Azure