Why RAG

Dive into the world of Retrieval-Augmented Generation (RAG), where we chat with documents like never before!

  • 👀 What’s This Course All About?

    RAG is shaking up the tech scene, letting both individuals and companies develop tools that chat with documents, sparking new levels of productivity that were just a dream before! 📈📚

  • 👩‍💻 Who Should Totally Take This Course?

    SaaS Founders: Go from MVP struggles to having investors and users begging for more! Developers: Turn those brilliant ideas into working prototypes without breaking a sweat! Executives: Imagine analyzing thousands of pages in minutes, not days — be that game-changing leader!

  • 🛠 What Will We Cover?

    We’re mixing theory with hands-on coding! 🖥️💡 Starting with the basics of RAG pipelines, we'll craft a vanilla setup and then leap into advanced techniques that’ll set your applications on fire! 🔥 We will learn using both proprietary and local models for building our RAG system.

Learn The Building Blocks

Level up with re-ranking strategies, query expansion, and more!!!

  • 🚫 What’s Off the Table?

    We’re zooming in on "Chat with PDFs" and similar text docs. No chats with CSVs or databases here – that’s a whole different playground!

  • 🤓 What Do you Need to know?

    All you need is a dash of Python knowledge and a heap of curiosity! We’re using cool tools like LangChain and Streamlit, and while prior knowledge is a plus, it’s not a must.

  • 📚 How’s It All Structured?

    We’re all about the "how" AND the "why". Each topic starts with a deep dive into the theory, followed by coding sessions that build on each other. By the end, you’ll have a RAG pipeline you can call your own! 🌐💬

Why this Course?

Course curriculum

    1. What is RAG? Why we NEED it?

    1. Setting up Virtual Environment

    2. Setting Up API Keys

    1. Deep Dive into RAG Pipeline Structure

    2. Demystifying Embedding Models and Vector Storage

    1. Google Colab Setup

    2. End-to-End RAG Pipeline - Code Time

    3. Loading and Processing PDF Files

    4. How Chunking Works

    5. Focus on Parsing than Chunking

    6. Chunk Size as Function of Text Embedding Models

    7. The Retrieval in RAG

    8. Putting Everything Together - 1st Iteration of RAG

    1. RAG: Advanced Techniques

    2. Improving RAG with Re-ranking for Precise Information Retrieval - Part 1

    3. Re-Ranking with GPT-4, ColBERT, and Cohere

    4. Improving Information Retrieval with Query Expansion using LLMs

    5. Enhancing Search with Hypothetical Documents Embedding Technique

    6. Enhancing Document Retrieval with Ensemble Techniques

    7. Hierarchical Chunking - Exploring the Parent Document Retriever

    1. From Notebook to working Scripts

    2. Creating Streamlit UI App

About this course

  • $199.00
  • 24 lessons
  • 2 hours of video content

Take RAG to the NEXT LEVEL 🚀🚀🚀

Enroll today

Prompt

Prompt Engineering

I am the creator of Prompt Engineering Youtube channel which has over 150k subscribers. I am also the creator and maintainer of localgpt project that has close to 20k stars on github. I have a PhD in Applied Machine Learning and have over 7 years experience of running machine learning teams for startups.