CF

RAG: Beyond Basics

2h 40m 48s
English
Paid

RAG: Beyond Basics is a 27-lesson 2 hours 40 minutes self-paced course by Prompt Engineering. Explore the cutting-edge world of Retrieval-Augmented Generation (RAG) in this comprehensive course designed to deepen your understanding of both the practical and theoretical aspects of RAG.

Course facts

Lessons
27
Duration
2 hours 40 minutes
Level
All levels
Language
English
Updated
Instructor
Prompt Engineering
Price
Premium

Explore the cutting-edge world of Retrieval-Augmented Generation (RAG) in this comprehensive course designed to deepen your understanding of both the practical and theoretical aspects of RAG. You will master not only the techniques but also the underlying principles that make these methods effective. Additionally, you will gain the skills to develop dependable "chat with documents" applications, leveraging the latest advancements in Large Language Models (LLMs) and advanced RAG methodologies.

Course Overview

This program progresses from building a basic pipeline to delving into advanced strategies like re-ranking and query expansion. You will also learn to work with a variety of models, including commercial and local ones. The curriculum effectively blends theoretical knowledge with hands-on programming experience using Python. You will become adept at utilizing tools such as LangChain and Streamlit, which are pivotal in the RAG landscape.

Who Should Enroll?

The course is tailored for developers, SaaS product founders, and managers who are eager to swiftly harness the potential of large volumes of textual data. By the course's conclusion, participants will not only have constructed their own fully functioning RAG pipeline but also gained a profound comprehension of strategies necessary to elevate application performance significantly.

What You Will Learn

  • Understand the core principles and workings of Retrieval-Augmented Generation (RAG).
  • Develop "chat with documents" applications using state-of-the-art LLMs.
  • Build and enhance a RAG pipeline with hands-on Python programming.
  • Apply advanced techniques, such as re-ranking and query expansion.
  • Utilize essential tools like LangChain and Streamlit for RAG applications.

Who teaches RAG: Beyond Basics? Prompt Engineering

Prompt Engineering thumbnail

Prompt Engineering is the YouTube channel and paid-course brand of an AI engineer focused on practical RAG (Retrieval-Augmented Generation) implementations and the broader applied LLM toolchain.

The CourseFlix listing carries RAG — Beyond Basics — a deep treatment of production RAG systems covering chunking strategies, embedding choice, vector-store selection, reranking, and the eval craft that separates working RAG from RAG that hallucinates.

Material is paid and aimed at engineers building production RAG pipelines on top of LLM APIs and vector databases. For the broader RAG / AI App Building track on CourseFlix, see the RAG category page.

What lessons are included in RAG: Beyond Basics?

This is a demo lesson (10:00 remaining)

You can watch up to 10 minutes for free. Subscribe to unlock all 27 lessons in this course and access 10,000+ hours of premium content across all courses.

View Pricing
0:00
/
#1: What is RAG? Why we NEED it?
All Course Lessons (27)
#Lesson TitleDurationAccess
1
What is RAG? Why we NEED it? Demo
04:59
2
Setting up Virtual Environment
04:04
3
Setting Up API Keys
03:52
4
Deep Dive into RAG Pipeline Structure
04:01
5
Demystifying Embedding Models and Vector Storage
06:18
6
Google Colab Setup
03:10
7
End-to-End RAG Pipeline - Code Time
02:11
8
Loading and Processing PDF Files
02:36
9
How Chunking Works
06:49
10
Focus on Parsing than Chunking
02:07
11
Chunk Size as Function of Text Embedding Models
05:28
12
The Retrieval in RAG
04:38
13
Putting Everything Together - 1st Iteration of RAG
05:13
14
RAG: Advanced Techniques
01:13
15
Improving RAG with Re-ranking for Precise Information Retrieval - Part 1
06:41
16
Re-Ranking with GPT-4, ColBERT, and Cohere
07:32
17
Improving Information Retrieval with Query Expansion using LLMs
08:14
18
Enhancing Search with Hypothetical Documents Embedding Technique
08:02
19
Enhancing Document Retrieval with Ensemble Techniques
06:55
20
Hierarchical Chunking - Exploring the Parent Document Retriever
08:25
21
From Notebook to working Scripts
12:05
22
Creating Streamlit UI App
05:02
23
Private and local Chat with PDFs
04:43
24
The Recap
03:58
25
Contextual Retrieval - Adding Context to Your Chunks
09:31
26
Contextual Retrieval - Implementation
09:26
27
Multimodal RAG - Working with Images and Tables
13:35
Unlock unlimited learning

Get instant access to all 26 lessons in this course, plus thousands of other premium courses. One subscription, unlimited knowledge.

Learn more about subscription

What courses are similar to RAG: Beyond Basics?

Frequently asked questions

What prerequisites do I need before enrolling in this RAG course?
Before enrolling in this course, you should have a solid understanding of Python programming, as the course involves significant hands-on programming experience. Familiarity with basic machine learning concepts and tools, such as embedding models and vector storage, will also be beneficial. The course does not cover these foundational topics but rather assumes you have prior knowledge.
What will I build during the course?
Throughout the course, you will construct a fully functioning Retrieval-Augmented Generation (RAG) pipeline. This includes setting up a virtual environment, configuring API keys, and working through the end-to-end RAG pipeline. You'll move from parsing and chunking text data to implementing advanced techniques like re-ranking and query expansion, ultimately developing a 'chat with documents' application using tools like LangChain and Streamlit.
Who is the target audience for this course?
The course is designed for developers, SaaS product founders, and managers who want to quickly leverage large volumes of textual data. It is particularly beneficial for those looking to enhance application performance through advanced RAG methodologies and the latest advancements in Large Language Models (LLMs).
How does this course compare to other RAG courses in terms of depth and scope?
This course goes beyond basic RAG concepts, diving into advanced strategies like re-ranking with GPT-4 and query expansion using LLMs. It covers both commercial and local models, ensuring comprehensive exposure to different techniques. The curriculum balances theoretical knowledge with hands-on programming, providing a deeper understanding of RAG than introductory courses.
What specific tools and platforms will I use in this course?
You will utilize several tools and platforms throughout the course, including Python for programming, LangChain for managing RAG pipelines, and Streamlit for creating UI apps. The course also involves setting up environments in Google Colab and working with advanced techniques such as re-ranking using GPT-4, ColBERT, and Cohere.
What topics are not covered in this course?
The course does not cover basic machine learning or Python programming concepts, assuming that participants already possess this knowledge. Additionally, it does not delve into the development of foundational embedding models or vector storage solutions, focusing instead on their application within RAG frameworks.
What is the expected time commitment for completing the course?
The course consists of 27 lessons, with additional time needed for practical exercises and project development. While the exact runtime isn't specified, participants should be prepared to invest a significant amount of time into both learning the material and applying it through hands-on programming tasks to fully grasp the advanced strategies taught.