💻
RAG and LLM Bootcamp
  • Welcome to the Bootcamp
    • Course Structure
    • Course Syllabus and Timelines
    • Know your Educators
    • Action Items and Prerequisites
    • Kick-Off Session for the Bootcamp
  • 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: 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
  • 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
  • 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)
    • Using kNN and LSH to Enhance Similarity Search (Bonus Module)
    • Bonus Video: Implementing End-to-End RAG | 1-Hour Session
    • Graded Quiz 2
  • Hands-on Development
    • Prerequisites (Must)
    • Docker Basics
    • Your Hands-on RAG Journey
    • 1 – First RAG Pipeline
      • Building with Open AI
      • How it Works
      • Using 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
  • Final Project + Giveaways
    • Prizes and Giveaways
    • Suggested Tracks for Ideation
    • Sample Projects and Additional Resources
    • Submit Project for Review
Powered by GitBook
On this page
  • Action Items to Consider
  • 1. Let's get you registered
  • 2. Show your support to the GitHub Repositories
  • 3. Join Pathway's Discord Community and Introduce Yourself
  • Prerequisites for a headstart
  1. Welcome to the Bootcamp

Action Items and Prerequisites

PreviousKnow your EducatorsNextKick-Off Session for the Bootcamp

Last updated 11 months ago

To kick off an interactive and engaging learning journey, we've crafted a special exercise to ensure you make the most out of this course. We're thrilled to have you with us and want to guide you through a few simple steps to get started:

Action Items to Consider

1. Let's get you registered

  • First things first, please ensure you're registered via this . It’s the gateway to our adventure together.

  • It might be a good idea to tag along a couple of your learning buddies with whom you can set learning goals for this bootcamp.

  • Feel free to explore the 'Bonus Modules' as and when you come across them within the coursework. They're like the cherry on top – not required for your project or quizzes, but they sure can enrich your foundational understanding of things.

2. Show your support to the GitHub Repositories

  • Visit the and the GitHub repositories and give them your support with a star.

  • Why does this matter? It’s more than just a click; it’s your way of cheering on the project and staying in the loop as things evolve. Got a question? The GitHub issues are your go-to spot.

3. Join and Introduce Yourself

  • Your Action Item: Become part of the vibrant Pathway Discord community, a hub for enthusiasts, creators, and some of the notable changemakers in the field of AI and Data.

  • Make your first post in the #introductions channel.

    • Please note, that the '#introductions' channel on Pathway's Discord is NOT specific to the bootcamps, and it includes some of the finest AI/Data practitioners whom you might want to collaborate with. While introducing yourself, please feel free to skip the bootcamp as many community members might not even understand what you're referring to when you mention bootcamps. :) You can, however, focus on who you are as an engineer or your interests. You can consider sharing about your progress in the field, your background/projects, and what excites you. That's a great way to make a solid first impression – not in Pathway but in any open-source community.

    • We have created an exclusive channel for this bootcamp in the Discord sever, i.e. # bits-goa-bootcamp. Please make sure you're asking all of your bootcamp-specific doubts in the same.

    • Pro Tip: Immersing yourself in any vibrant open-source community not only enriches your learning experience but also opens up opportunities for networking and collaboration.

We're thrilled to have you with us and can't wait to see the contributions and growth you'll bring to this journey. Let's embark on this educational venture together with enthusiasm and curiosity!

For the majority of the bootcamp, these prerequisites aren't necessary. So, if you're an AI product manager or someone who isn't typically hands-on, you'll be just fine. However, as we approach the hands-on development phase towards the end of the bootcamp, these skills will become essential. That's why we're introducing them to you now, allowing you to familiarize yourself with them at your own pace before we dive into the more technical aspects.

  2. Familiarize with Generative AI Tools: Tools like Gemini, Anthropic's Claude 3, Bing Search, or our dear ChatGPT can be invaluable for overcoming obstacles, rephrasing ideas, or basic code debugging. Try to use them a bit in your day-to-day lives.

  3. Explore Docker: Docker simplifies the process of bundling your app and its necessities, making it portable and easy to share. It’s a powerful tool to standardize development environments and sidestep dependency issues – thus making it useful not just for LLM apps but open source development in general. Below are a few resources.

  4. Know what stream data processing is:

Prerequisites for a headstart

Python Proficiency: A foundation in Python 3.11 is crucial. Here are some beginner-level resources to consider: | | .

Beginner Blog on What is Docker:

Basic Tutorial on Dockerfile:

Basic Tutorials on Docker Compose: ,

Blog on using ChatGPT to build an optimized Docker Image:

Gaining a very basic understanding of stream data processing and real-time data can be very beneficial, setting the stage for more advanced project ideas and development strategies even within the realm of LLMs. Here's a to check out for starters.

Prof Abhilash Jindal (CSE Department at IIT Delhi) also took a session to explore the wonderful history beyond stream data processing. You can find their and the recording on DevClub IIT Delhi's YouTube channel.

🚀
🚀
⭐
📚
Google Form
Pathway
LLM App
Templates
Pathway's Discord Community
CodeChef
Microsoft Trainings
Python.org
Here
Here
Part 1 using (Single Container)
Part 2 (using 2 Containers)
3-Minute Read
basic blog
session slides here