Chevron Left
Back to Introduction to Retrieval Augmented Generation (RAG)

Learner Reviews & Feedback for Introduction to Retrieval Augmented Generation (RAG) by Duke University

4.0
stars
14 ratings

About the Course

In this 2-hour project-based course, you will learn how to import data into Pandas, create embeddings with SentenceTransformers, and build a retrieval augmented generation (RAG) system with your data, Qdrant, and an LLM like Llamafile or OpenAI. This hands-on course will teach you to build an end-to-end RAG system with your own data using open source tools for a powerful generative AI application....

Top reviews

ST

Oct 6, 2024

The guided project helped me understand RAG and its application in a concise and accurate manner. The project code was very helpful in understanding the workflow of implementing RAG with LLMS.

JC

May 16, 2024

Good Exercise for introduction RAG by LLM and VectorDB

Filter by:

1 - 5 of 5 Reviews for Introduction to Retrieval Augmented Generation (RAG)

By Lorin R

•

Aug 19, 2024

Needs testing on Windows. Final project didn't provide a cloud option and I could not get it to work locally. Probably a much better experience on Macs supporting Cuda.

By Valerio V

•

Aug 23, 2024

The videos do not provide any information about what a vector DB is and how it works (e.g. the architecture), same for RAG and LLM. The project is extremely trivial and, personally, I won't put it into my personal repo because it won't add any value to it (possibly the opposite though).

By Teig L

•

May 18, 2024

The introduction to the lab was good, but the goals could have been more specific. I would have liked more time spent on some of the concepts that the final questions were about, though that may be in a different course.

By Suhas T

•

Oct 7, 2024

The guided project helped me understand RAG and its application in a concise and accurate manner. The project code was very helpful in understanding the workflow of implementing RAG with LLMS.

By Johnson c

•

May 17, 2024

Good Exercise for introduction RAG by LLM and VectorDB