Hands-On AI: RAG using LlamaIndex

Focused View

Harpreet Sahota

6:25:45

0 View

01 - Introduction

01 - Overcome the limitations of LLMs with RAG.mp4

00:52

02 - Limitations of LLMs.mp4

04:07

03 - Use cases for retrieval-augmented generation (RAG).mp4

05:55

02 - 1. Getting Started

01 - Using GitHub Codespaces.mp4

02:59

02 - Setting up your environment.mp4

09:55

03 - Choosing an LLM and embeddings provider.mp4

08:11

04 - Setting up LLM accounts.mp4

03:31

05 - Choosing a vector database.mp4

05:22

06 - Setting up a Qdrant account.mp4

04:14

07 - Downloading our data.mp4

04:49

03 - 2. Fundamental Concepts in LlamaIndex

01 - How LlamaIndex is organized.mp4

06:11

02 - Using LLMs.mp4

08:48

03 - Loading data.mp4

11:52

04 - Indexing.mp4

08:11

05 - Storing and retrieving.mp4

08:55

06 - Querying.mp4

09:08

07 - Agents.mp4

06:14

04 - 3. Introduction to RAG

01 - Components of a RAG system.mp4

06:25

02 - Ingestion pipeline.mp4

06:11

03 - Query pipeline.mp4

10:34

04 - Prompt engineering for RAG.mp4

08:44

05 - Data preparation for RAG.mp4

18:38

06 - Putting it all together.mp4

07:40

07 - Drawbacks of Naive RAG.mp4

04:47

05 - 4. RAG Evaluation

01 - Introduction to RAG evaluation.mp4

05:53

02 - Evaluation metrics.mp4

08:16

03 - How to create an evaluation set.mp4

11:23

06 - 5. Advanced RAG Pre-Retrieval and Indexing Techniques

01 - How we can improve on Naive RAG.mp4

04:24

02 - Optimizing chunk size.mp4

25:59

03 - Small to big retrieval.mp4

15:12

04 - Semantic chunking.mp4

11:45

05 - Metadata extraction.mp4

12:14

06 - Document summary index.mp4

10:00

07 - Query transformation.mp4

08:47

07 - 6. Advanced RAG Post-Retrieval and Other Techniques

01 - Node post-processing.mp4

15:35

02 - Re-ranking.mp4

04:33

03 - FLARE.mp4

08:44

04 - Prompt compression.mp4

05:57

05 - Self-correcting.mp4

13:15

08 - 7. Modular RAG

01 - Hybrid retrieval.mp4

14:32

02 - Agentic RAG.mp4

14:48

03 - Ensemble retrieval.mp4

05:51

04 - Ensemble query engine.mp4

06:20

09 - Conclusion

01 - LlamaIndex evaluation.mp4

01:56

02 - Comparative analysis of retrieval-augmented generation techniques.mp4

08:08

Description

This course offers a deep dive into the principles and applications of retrieval-augmented generation (RAG), with a focus on the innovative LlamaIndex system. Explore how RAG enhances machine learning models by integrating external knowledge sources for more informed and accurate outputs. Instructor Harpreet Sahota covers the architecture of retrieval systems, the mechanics of indexing vast datasets, and the integration of LlamaIndex with AI models.

Gain an understanding of the theoretical underpinnings of RAG, practical skills in building and deploying LlamaIndex, and review a critical analysis of RAG applications in various industries. Topics range from the basics of data retrieval and indexing to advanced techniques in enhancing generative models with external data. By the end of the course, you’ll be prepared to design, implement, and evaluate RAG systems, positioning them at the cutting edge of AI technology implementation.

More details

User Reviews

Rating

average 0

Total votes0

Focused display

Artificial Intelligence

Harpreet Sahota

Instructor's Courses

Linkedin Learning

View courses Linkedin Learning

LinkedIn Learning is an American online learning provider. It provides video courses taught by industry experts in software, creative, and business skills. It is a subsidiary of LinkedIn. All the courses on LinkedIn fall into four categories: Business, Creative, Technology and Certifications. It was founded in 1995 by Lynda Weinman as Lynda.com before being acquired by LinkedIn in 2015. Microsoft acquired LinkedIn in December 2016.