Chevron Left
Back to Retrieval Augmented Generation (RAG)

Learner Reviews & Feedback for Retrieval Augmented Generation (RAG) by DeepLearning.AI

4.8
stars
131 ratings

About the Course

Retrieval Augmented Generation (RAG) improves large language model (LLM) responses by retrieving relevant data from knowledge bases—often private, recent, or domain-specific—and using it to generate more accurate, grounded answers. In this course, you’ll learn how to build RAG systems that connect LLMs to external data sources. You’ll explore core components like retrievers, vector databases, and language models, and apply key techniques at both the component and system level. Through hands-on work with real production tools, you’ll gain the skills to design, refine, and evaluate reliable RAG pipelines—and adapt to new methods as the field advances. Across five modules, you'll complete hands-on programming assignments that guide you through building each core part of a RAG system, from simple prototypes to production-ready components. Through hands-on labs, you’ll: - Build your first RAG system by writing retrieval and prompt augmentation functions and passing structured input into an LLM. - Implement and compare retrieval methods like semantic search, BM25, and Reciprocal Rank Fusion to see how each impacts LLM responses. - Scale your RAG system using Weaviate and a real news dataset—chunking, indexing, and retrieving documents with a vector database. - Develop a domain-specific chatbot for a fictional clothing store that answers FAQs and provides product suggestions based on a custom dataset. - Improve chatbot reliability by handling real-world challenges like dynamic pricing and logging user interactions for monitoring and debugging. - Develop a domain-specific chatbot using open-source LLMs hosted by Together AI for a fictional clothing store that answers FAQs and provides product suggestions based on a custom dataset. You’ll apply your skills using real-world data from domains like media, healthcare, and e-commerce. By the end of the course, you’ll combine everything you’ve learned to implement a fully functional, more advanced RAG system tailored to your project’s needs....

Top reviews

P

Aug 15, 2025

The content is excellent, and Zain explains everything with calm clarity and a well-structured approach.

RS

Aug 14, 2025

I learnt quite a bit about LLMs, vector databases, RAG and various terms associated with this space. I came out better informed and hopefully learn more and implement these things in my projects

Filter by:

26 - 36 of 36 Reviews for Retrieval Augmented Generation (RAG)

By Sebastian R

•

Aug 6, 2025

Amazing course on RAG systems at production scale.

By Michel W

•

Sep 25, 2025

Excellent approach for RAG including LLM use

By Gonzalo Á F

•

Oct 4, 2025

I learned a lot about real RAG systems

By Rajesh I

•

Aug 25, 2025

Gave good understanding on RAG.

By Omar

•

Aug 29, 2025

What a GRATE course to have !!

By Yue.Zhao

•

Oct 26, 2025

very useful, Thank you!

By aqadadeh

•

Oct 6, 2025

Very Good

By Santiago S

•

Oct 4, 2025

The instructor and lessons were excellent. It is also a highly relevant course for today's software engineers. However, I think more attention should be put to the Jupyter Notebook tasks. One had a bug that prevented correct grading (which affected my course final grade), and another had a bug that made impossible to do one part of the assignment. One even had factually incorrect information. Even with this challenges, I am happy I took this course. I did learn a lot and it was a very rewarding and productive use of my time.

By Siddartha K

•

Sep 1, 2025

explains the key concepts very well. code examples are also good to build on the concepts

By Vicente F M

•

Oct 23, 2025

I’m really enjoying the course so far, but I think it would greatly benefit from a section explaining how to set up a local environment on Windows to run the Python notebooks. Many of us following the course would appreciate clear instructions for configuring a local setup to practice and experiment more effectively. Thank you for considering this suggestion! Best regards,

By Alon T

•

Aug 11, 2025

Overly technical, lacks conceptual grounding in generative models.