📘
Winter LLM Bootcamp
  • Welcome to the course. Bienvenue!
    • Course Structure
    • Course Syllabus and Timelines
    • Know your Educators
    • Action Items and Prerequisites
    • Bootcamp Kick-Off Session
  • 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
  • Word Vectors, Simplified!
    • What is a Word Vector
    • Word Vector Relationships
    • Role of Context in LLMs
    • Transforming Vectors into LLM Responses
    • Bonus Section: Overview of the Transformers Architecture
      • Attention Mechanism
      • Multi-Head Attention and Transformers Architecture
      • Vision Transformers
    • Graded Quiz 1
  • Prompt Engineering and Token Limits
    • What is Prompt Engineering
    • Prompt Engineering and In-context Learning
    • Best Practices to Follow
    • Token Limits and Hallucinations
    • Prompt Engineering Excercise (Ungraded)
      • Story for the Excercise: The eSports Enigma
      • Your Task for the Module
  • Retrieval Augmented Generation (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/LLM Architecture Diagram with Key Steps
    • RAG versus Fine-Tuning and Prompt Engineering
    • Versatility and Efficiency in RAG
    • Understanding Key Benefits of Using RAG in Enterprises
    • Hands-on Demo: Performing Similarity Search in Vectors (Bonus Module)
    • Using kNN and LSH to Enhance Similarity Search (Bonus Module)
    • Graded Quiz 2
  • Hands-on Development
    • Prerequisites
    • Dropbox Retrieval App
      • Understanding Docker
      • Building the Dockerized App
      • Retrofitting our Dropbox app
    • Amazon Discounts App
      • How the project works
      • Repository Walkthrough
    • How to Run 'Examples'
    • Bonus Section: Real-time RAG with LlamaIndex and Pathway
  • Bonus Resource: Recorded Interactions from the Archives
  • Final Project + Giveaways
    • Prizes and Giveaways
    • Suggested Tracks for Ideation
    • Form for Submission
Powered by GitBook
On this page
  • Course Format
  • Course Timelines
  • Course Completion Criteria and Prizes

Was this helpful?

  1. Welcome to the course. Bienvenue!

Course Structure

PreviousWelcome to the course. Bienvenue!NextCourse Syllabus and Timelines

Last updated 1 year ago

Was this helpful?

The instructors of this course are seasoned professionals with rich academic and applied research backgrounds. However, the curriculum of this course goes beyond conventional AI studies to prioritize the development of real-time Retrieval Augmented Generation (RAG) applications – a foundational technique needed by companies trying to leverage Generative AI. This focus tackles two prevalent industry hurdles that even experienced professionals find intricate: the application of Generative AI in actual production environments and the crafting of real-time solutions for industry use cases.

By the end of this program, you will have not only acquired the knowledge to create impactful, open-source LLM applications using RAG and live data streams but also completed a significant personal project. This opportunity allows students to dive deep into and excel in a technically demanding yet immensely rewarding emerging technological field.

Course Format

The introductory segment of this course has been made available since February 7th, 2024. Registration remains open for the first 2-3 weeks, providing ample time to catch up with the initial, more straightforward modules. This approach ensures you're well-prepared before diving into a relatively complex RAG-specific and hands-on development modules.

  • Please note that there will be a pause in the release of new course modules from February 12th to February 25th. This break coincides with the mid-semester exams at IIT Kanpur and IIT (BHU) Varanasi, allowing students a week to prepare, followed by the exams themselves.

  • Suppose you're not participating in these exams. In that case, this period offers a valuable opportunity to begin brainstorming potential project ideas to tackle during or following the boot camp, enhancing the learning experience.

  • Additionally, this time can be well spent getting acquainted with technologies like Docker. While Docker may not directly relate to RAG or LLMs, its understanding is invaluable for open-source development, helping to sidestep unforeseen issues.

To successfully complete the bootcamp, you must finish all quizzes by the established deadlines and submit your final project. You have the option to work on the project either solo or in a team of two. If you decide to team up closer to the project submission, choose a partner with skills that complement yours, though you are equally encouraged to take on this challenge by yourself. In cases with a team of two, the prizes mentioned below will be awarded to both members.

Your project should involve creating and sharing an innovative GitHub project that utilizes the open-source RAG frameworks discussed in the coursework to tackle real-world challenges. More detailed criteria for bootcamp completion and eligibility for the top 9 teams will be announced as the project submission deadline approaches.

Rewards for Completing the Bootcamp:

  • For All Completers: Certificates, T-shirts, and swag will be given to you upon course completion.

  • For the Top 9 Teams: You will receive XBOX controllers, phone camera lenses, and JBL waterproof speakers as special prizes. The top projects will also be featured on Pathway's official blog, becoming a valuable credential in your professional journey.

A Piece of Advice

For those new to creating real-world AI applications, be ready to face challenges in selecting problems, integrating data, and applying foundational LLM knowledge. Engaging early is crucial to navigate these challenges successfully.

In brief – it's primarily recorded. Designed with a blend of learning styles in mind, the course predominantly features pre-recorded lectures, enabling you to progress at their convenience. Moreover, interactive live sessions will be scheduled, and registered attendees () will be informed beforehand. Thus, please ensure you've registered with an email address you access regularly and use for receiving calendar invites.

Course Timelines

Note: Module-specific released dates are specified after mentioning the ahead.

Course Completion Criteria and Prizes

🗓️
🎮
form link
course curriculum
💻