From the course: AI Pricing and ROI: A Technical Breakdown

Unlock the full course today

Join today to access over 25,200 courses taught by industry experts.

Estimating cost for a RAG solution: What is RAG?

Estimating cost for a RAG solution: What is RAG?

From the course: AI Pricing and ROI: A Technical Breakdown

Start my 1-month free trial Buy for my team

Estimating cost for a RAG solution: What is RAG?

“

- [Instructor] Now that we know the basics of GenAI, let's implement a more complex app. Today we will talk about Retrieval Augmented Generation, or RAG. This techniques provides a large-language model context to generate an answer. Breaking it down, retrieval means get the context, augment means add the context to the LLM prompt, and generated means respond to the prompt. Let's take a look at an example. I'm here in ChatGPT, and I can ask, "Why is the sky blue?" So let's type that out, and hit Enter. You can see here we got a response. Generally it looks pretty good. Now, in a more complex case, we might want some domain-specific information. Let's say we trust information on Wikipedia. And right here I have some information on why the sky is blue. So I'm going to go ahead and copy it. Let's open up a new ChatGPT tab. Now what I'm going to do is I'm going to write out a prompt that uses this information. So let's…

Contents