Prompt Engineering vs RAG vs Fine-tuning: The $100 Billion Vertical AI Showdown

Thanks! Share it with your friends!

You disliked this video. Thanks for the feedback!

Added 2 months ago by admin

15 Views

There’s so much that Generative AI Large Language Models can do, but domain-specific niche use cases often need a bit more tweaking to have a stronger value proposition for the target users. In this video we discuss the different approaches, from Prompt Engineering to Retrieval Augmented Generation (RAG) and Fine-tuning and we discuss the pros and cons of each method.

Follow AWS Developers!
???? Instagram: https://www.instagram.com/awsdevelopers/?hl=en
???? X: https://x.com/awsdevelopers
???? LinkedIn: https://www.linkedin.com/showcase/aws-developers/
???? Twitch: https://twitch.tv/aws

Follow Basil Fateen!
???? LinkedIn: https://www.linkedin.com/in/basilfateen

00:00 - 00:35 Intro
00:35 - 01:15 What is Vertical AI
01:15 - 02:15 How to Build Vertical AI
02:15 - 04:01 Prompt Engineering
04:01 - 04:41 Retrieval Augmented Generation (RAG)
04:41 - 05:22 Fine-tuning
05:22 - 06:15 Amazon Q to prepare datasets
06:15 - 06:50 Comparing the methods
06:50 - 08:29 A comprehensive example

#promptengineering #retrievalaugmentedgeneration #finetuning