💪
3 Week Bootcamp: Building Realtime LLM Application
  • Introduction
    • Timelines and Structure
    • Course Syllabus
    • Meet your Instructors
    • Action Items
  • Basics of LLM
    • What is Generative AI?
    • What is a Large Language Model?
    • Advantages and Applications of Large Language Models
    • Bonus Resource: Multimodal LLMs and Google Gemini
  • Word Vectors Simplified
    • What is a Word Vector
    • Word Vector Relationships
    • Role of Context in LLMs
    • Transforming Vectors into LLM Responses
      • Neural Networks and Transformers (Bonus Module)
      • Attention and Transformers (Bonus Module)
      • Multi-Head Attention, Transformers Architecture, and Further Reads (Bonus Module)
    • Graded Quiz 1
  • Prompt Engineering
    • What is Prompt Engineering
    • Prompt Engineering and In-context Learning
    • Best Practices to Follow in Prompt Engineering
    • Token Limits in Prompts
    • Ungraded Prompt Engineering Excercise
      • Story for the Excercise: The eSports Enigma
      • Your Task
  • Retrieval Augmented Generation 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
    • LLM Architecture Diagram and Various Steps
    • RAG versus Fine-Tuning and Prompt Engineering
    • Versatility and Efficiency in Retrieval-Augmented Generation (RAG)
    • Key Benefits of RAG for Enterprise-Grade LLM Applications
    • Similarity Search in Vectors (Bonus Module)
    • Using kNN and LSH to Enhance Similarity Search in Vector Embeddings (Bonus Module)
    • Graded Quiz 2
  • Hands-on Development
    • Prerequisites
    • Dropbox Retrieval App in 15 Minutes
      • Building the app without Dockerization
      • Understanding Docker
      • Building the Dockerized App
    • Amazon Discounts App
      • How the Project Works
      • Repository Walkthrough
    • How to Run 'Examples'
  • Bonus Resource: Recorded Interactions from the Archives
  • Bootcamp Keynote Session on Vision Transformers
  • Final Project + Giveaways
    • Prizes and Giveaways
    • Tracks for Submission
    • Final Submission
Powered by GitBook
On this page
  • Course Structure: Live or Recorded?
  • Introductory Session Recording (Optional)
  • Bootcamp Completion and Rewards
  • Registration and Timelines
  1. Introduction

Timelines and Structure

PreviousIntroductionNextCourse Syllabus

Last updated 1 year ago

While most educators of this coursework are professionals with extensive backgrounds in professional and academic research, the focus of this course extends beyond traditional AI research. A key aspect of this course is its emphasis on building real-time Retrieval Augmented Generation (RAG) applications. This approach addresses two significant challenges in the industry that even skilled professionals find complex: leveraging Generative AI in production and developing real-time solutions.

Upon completing the course, you will not only gain insights into creating real-world, open-source LLM applications using RAG and real-time data but also develop a meaningful project of your own. This presents a unique chance to delve into and master a technically challenging yet highly rewarding upcoming field of technology.

Course Structure: Live or Recorded?

This format balances self-paced learning with the dynamism of real-time interactions, ensuring a comprehensive educational experience without disrupting your professional or personal commitments.

Introductory Session Recording (Optional)

If you couldn't attend the kick-off session of the bootcamp live, you have the option to watch the 30-minute recorded interaction below.

However, reading the course introduction is highly recommended. If you prefer, you can first read the course introduction and then return to the kick-off session's video if you have any questions or need further clarification.

Bootcamp Completion and Rewards

To complete the bootcamp, you must complete all the quizzes within the specific deadlines and complete the project.

For the course's project, you will create and publish a novel GitHub project, utilizing open-source RAG frameworks to tackle real-world challenges. Criteria for bootcamp completion and eligibility for the top 9 prizes will be detailed as we progress towards project submission.

However, it's worth noting that successful completion comes with its share of exciting rewards:

  • All graduates receive Certificates, T-shirts, and swag.

  • Top 9 graduates win XBOX controllers, phone camera lenses, and JBL waterproof speakers.

Registration and Timelines

The 3-week bootcamp is structured as follows:

  • First 1-1.5 weeks: Focus on learning prerequisites and building a solid foundation.

  • Final 2 weeks: Dedicated to hands-on development.

The modules will be released gradually.

A Word of Advice

If this is your first foray into building a real-world AI application, be prepared for challenges in problem selection, data integration, and leveraging foundational LLM knowledge. Early engagement is key to overcoming these hurdles.

Short answer – mostly recorded. The course is crafted with a hybrid learning approach in mind. Most content is provided via recorded sessions, offering the flexibility to learn at your own pace. Additionally, if and when there will be interactive live sessions, will receive timely notifications.

Register soon at ; the deadline is December 13, 2023.

registered participants
https://lu.ma/llm23-guwahati