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
  • Module Release Timelines and the Coursework:
  • Note:
  • What are Bonus Sections/Resources?
  1. Start Here: Welcome to the Bootcamp

Course Syllabus and Timelines

PreviousCourse StructureNextKnow your Educators

Last updated 8 months ago

By the end of this course, you will:

  • Be proficient in developing LLM-based applications for production applications from day 0.

  • Have a clear understanding of LLM architecture and pipeline.

  • Be able to perform prompt engineering to use generative AI tools such as ChatGPT.

  • Create an open-source project on a real-time stream of data or static data.

Module Release Timelines and the Coursework:

Module
Topics
Module
Topics
Module
Topics
Module
Topics
Module
Topics
Module
Topics
Module
Topics

Note:

  • Once the problem statements and the hands-on development module are released on the 5th September 2024, the project submissions will remain open till the 11th September 2024, 11:59 pm CEST.

  • There'll be weekly sessions to help you cover the curriculum. They'll be scheduled on Thursdays. If there's a dedicated live session beyond this, then you'll be notified beforehand.

What are Bonus Sections/Resources?

Throughout the bootcamp, you'll see some modules or links labeled as bonus resources. These are not compulsory for building a project by the end of the bootcamp or attempting the quizzes.

Nonetheless, they are relevant resources that could enhance your understanding, although they might require additional prerequisites. Depending on your starting point and the pace you're progressing through the bootcamp, you can explore or park these bonus materials.

1 – Basics of LLMs

  • What is generative AI and how it's different

  • Understanding LLMs

  • Advantages and Common Industry Applications

  • Bonus section: Google Gemini and Multimodal LLMs

--- When to learn: 21 August

2 – Word Vectors

  • What are word vectors and word-vector relationships?

  • Role of context

  • Transforming vectors in LLM responses

  • Overview of Transformers Architecture

  • Bonus Resource: Transformers Architecture, Self-attention, Multi-head attention, and Vision Transformers

  • Bonus Resource: Talk on Future of LLMs by the Co-Creator of ChatGPT, Łukasz Kaiser

--- When to learn: 21-25 Aug

Quiz Releasing on: 25 Aug (Revised)

3 – Prompt Engineering

  • Introduction and in-context learning

  • Best practices to follow: Few Shot Prompting and more

  • Token Limits

  • Prompt Engineering Exercise (Ungraded)

--

When to learn: 25-27 Aug

Refresher Module

  • Overview of learnings so far sent over registered email address.

  • Release of bootcamp keynote session(s).

--

Will be sent via email to registered email IDs on 28th August

4 – RAG and LLM Architecture

  • Introduction to RAG

  • LLM Architecture Used by Enterprises

  • RAG vs Fine-Tuning and Prompt Engineering

  • Key Benefits of RAG for Realtime Applications

  • Bonus: Similarity Search for Efficient Information Retrieval

  • Bonus: Use of LSH + kNN and Incremental Indexing

  • Bonus: Forgetting in LLMs and Stream Data Processing (archived live interactions)

-- When to learn: 28-31 Aug Quiz Releasing on: 28 Aug

5 – Hands-on Development of Realtime LLM ApplicationsQu

  • Installing Dependencies and Pre-requisites

  • Building a Dropbox RAG App using open-source

  • Building Realtime Discounted Products Fetcher for Amazon Users

  • Building RAG applications with local models

  • Leveraging Pathway with LlamaIndex/Langchain (Bonus)

  • Problem Statements for Projects

  • Project Submission

-- When to learn: 1-5 Sept

6 – Project Development: Tracks and Submission

  • Problem Statements Release for the Projects

  • Window for Sharing/Reviewing Project Ideas via Discord Channel

  • Online Office Hours

  • Projects Submission

  • Project Feedback (after the submissions deadline)

--

Module Yet to Be Released. Releasing 5th Sept

<>

Link to register