💪
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
  • 1. Exploring Frontiers of LLMs | Recorded Interaction with Jan Chorowski at IIT Bombay
  • 2. Understanding Real-time Use Cases | Recorded Interaction with Adrian Kosowski on ML & AI Podcast

Bonus Resource: Recorded Interactions from the Archives

PreviousHow to Run 'Examples'NextBootcamp Keynote Session on Vision Transformers

Last updated 1 year ago

As a part of this bootcamp at IIT Guwahati, we will be announcing our live sessions soon.

In the meantime, we have curated a selection of valuable resources from Pathway's Archives to broaden your learning horizon.

1. Exploring Frontiers of LLMs | Recorded Interaction with Jan Chorowski at IIT Bombay

  • Session Overview:

    • Participants: Anup Surendran (Growth Head at Pathway) and Jan Chorowski (CTO at Pathway).

    • Jan's Background: An AI reference figure with a PhD in Neural Networks. Jan has a rich history of co-authoring papers with AI luminaries like Yoshua Bengio and Geoff Hinton and has worked with Microsoft Research, Google Brain, and MILA AI, boasting over 10,000 Google Scholar citations.

  • Session Highlights:

    • Evolution of LLMs: Insights into the development and practical applications of Large Language Models.

    • Operational Challenges: Discussion on the challenges faced by LLMs in real-world scenarios.

    • Learning to Forget: Exploring this crucial concept in LLM development.

    • Real-Time Relevance: Delving into how LLMs adapt and remain pertinent in dynamic environments.

    • Interactive Q&A: Audience-driven discussion on various aspects of LLMs, including document versioning.

2. Understanding Real-time Use Cases | Recorded Interaction with Adrian Kosowski on ML & AI Podcast

  • Session Overview:

    • Adrian's Background: A distinguished figure in the realm of competitive programming. He previously co-founded Spoj.com, a platform used by millions of developers. Adrian earned his PhD at 20 and has since accrued over 15 years of research experience across disciplines, contributing to over 100 publications.

  • Session Highlights:

    • Reactive Data Processing: Gain a deep understanding of real-time data processing nuances.

    • Stream vs. Batch Processing: Explore the differences and practical applications.

    • Transformers in Data Engineering: The role of transformers in managing and streaming data.

    • ML Innovations for Startups: Discover emerging machine learning tools and approaches beneficial for startups.

Don't miss these illuminating Fireside Chats that offer unique perspectives on the fast-evolving domains of Large Language Models and Real-time Data Processing. These sessions provide valuable insights into the wonderful world of AI and machine learning.

Participants: Jon Krohn (Chief Data Scientist at Nebula | ) and Adrian Kosowski (CPO at Pathway | ).

Stay tuned for more updates as we gear up to announce the live interactions for this exciting bootcamp. It's our ambition to announce them to you as soon as possible.

😊
GitHub
Google Scholar