💻
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
  • About Pathway
  • Why is Pathway so Fast
  1. Welcome to the Bootcamp

Know your Educators

Our heartfelt thanks go to these amazing folks who have enriched this course with their expertise and insights:

  • Developers' Society at BITS Pilani, K K Birla Goa Campus

  • Adrian Kosowski, CPO at Pathway | Earned PhD at 20 | Former Prof at École Polytechnique and Co-founder of SPOJ | 100+ Research publications

  • Anup Surendran, Head of Product Marketing & Growth at Pathway | Previously Vice President at QuestionPro | Advisor, Texas A&M University

  • Jan Chorowski, CTO at Pathway | PhD in Neural Networks | Co-author with Yoshua Bengio and Geoff Hinton, two of the three Godfathers of AI | Ex – Google Brain, Mila AI

  • Sergey Kulik, Lead Software Research Engineer and Solutions Architect at Pathway | IOI Gold Medalist | Former Head of Service at Yandex

  • Berke Çan Rizai, LLM Research Engineer at Pathway | Former Data Scientist at Getir

  • Mudit Srivastava, Director of Growth at Pathway | Ex - Founding Growth Head at AI Planet

  • Olivier Ruas, Director of Product at Pathway | PhD on kNNs | Ex – Peking University

  • Saksham Goel, DevRel Engineer at Pathway | IIT Delhi Grad, Ex - NTU Singapore

Special acknowledgment goes to:

  • Mike Chambers, Developer Advocate at AWS, for generously allowing the use of his invaluable educational content from the BuildOnAWS YouTube channel. Together with his colleagues, he has also released courses on LLMs through Deeplearning AI, which are definitely worth exploring.

  • Vijay S Agneeswaran, Senior Director and ML Research Leader at Microsoft, for developing and presenting the session on vision transformers that has been integral to one of the bonus modules within this coursework.

  • Łukasz Kaiser, Senior Researcher at Open AI and Co-creator of ChatGPT, TensorFlow, Transformer Architecture, and more. He recently delivered an offline session at a Pathway meetup in San Francisco, which is an important resource within the bootcamp.

  • Jayprasad Hegde, Head of AI and Data Science at NPCI (creator of UPI, IMPS, Rupay, and more). He's a notable figure in the Indian AI landscape and has taken the session on End-to-End Local RAG that is integrated within the RAG module as a bonus resource.

Throughout this bootcamp, we've utilized various resources to enrich your educational journey, making every effort to acknowledge contributions appropriately. Should there be any oversight or missed acknowledgment, we encourage you to contact us.

About Pathway

With main offices in France and Poland, Pathway is a deep-tech startup known for the Pathway framework. It's a Python data processing framework for analytics and AI pipelines over data streams. It’s the ideal solution for real-time processing use cases like streaming ETL or RAG pipelines for unstructured data. Pathway is also the world's fastest data processing engine, supporting unified workflows for batch, streaming data, and LLM applications.

Pathway is the single, fastest integrated data processing layer for real-time intelligence.

  • Mix-and-match: batch, streaming, API calls, including LLMs.

  • Effortless transition from batch to real-time - just like setting a flag in your Spark code.

  • Powered by an extremely efficient and scalable Rust engine, it reduces the cost of any computations.

  • Enabling use cases enterprises crave, making advanced data transformations lightning-fast and easy to implement.

Why is Pathway so Fast

The Pathway engine is built in Rust. We love Rust 🦀. Rust is built for speed, parallel computation, and low-level control over hardware resources. This allows their frameworks to execute maximum optimization for performance and speed.

PreviousCourse Syllabus and TimelinesNextAction Items and Prerequisites

Last updated 10 months ago

We also love Python 🐍 – which is why you can write your data processing code in Python, and Pathway will automagically compile it into a Rust dataflow. In other words, with Pathway, you don’t need to know anything about Rust to enjoy its enormous performance benefits! For now, this is a simple enough starting point (that said, feel free to find more details in this – your first bonus resource 🙂).

ArXiv Paper