RAG Explained - YouTube 이중 자막

RAG Explained - 이중 자막

So imagine you're a journalist and you want to write an article on a specific topic.

Now you have a pretty good general idea about this topic,

but you'd like to do some more research, so you go to your local library.

Now, this library has thousands of books on multiple different topics, but how do you

know as the journalist which books are Well, you go to the librarian.

Now, the librarian is the expert on what books contain which information in the library.

So our journalist queries the librarian to retrieve books on certain topics, and the librarian produces those books and provides them back to you.

Now, the librarian isn't the expert on writing the article, and the journalist isn't the expert

on finding the most up-to-date and relevant information.

But with the combination of the two, we can get the job done.

Well, this sounds a like the process of RAG, or Retrieval Augmented Generation, where

large language models call on vector databases to provide key sources of data and information to answer questions.

I'm not seeing the connection.

Can you help me understand a little bit better?

Sure.

So we have a user in your scenario.

It's that journalist.

And they have a question.

What types of questions would you want to ask, right?

Maybe can make this more of a business context.

Yeah, so let's say this is a business analyst and let's say they want to ask,

what was revenue in Q1 from customers in the Northeast region?

Right, so that's your prompt.

Okay, so a couple questions on that user.

Does it have to be a person or could it be something else too?

Yeah, so this doesn't necessarily have to be a user.

It could be a bot or it could be another application.

Even the question that we're talking about,

what was our revenue in Q1 from the North You know,

the first part of that question, it's pretty easy for, you know, a general L.N.

to understand, right?

What was our revenue?

But it's that second part in Q1 from customers in the Northeast.

That's not something that L.N.s are trained on, right?

It's very specific to our business and a change.

So we have to treat those separately.

So do we manage that part of the request?

Exactly.

You'll need multiple different sources of data potentially to answer a specific question, right?

Whether maybe a PDF,

or another business application, or maybe some image application, Whatever that question is, we need the appropriate data in order to provide the answer back.

What technology allows us to aggregate that data and use it for our LLM?

Yeah, so we can take this data and we can put it into what we call a vector database.

A vector database is a mathematical representation of structured and unstructured data, similar to what we might see in an array.

Gotcha, and these arrays are better suited or easier to understand for machine learning or generative AI models, versus just that underlying unstructured data.

Exactly.

We query our vector database, right?

And we get back and embedding that includes the relevant data for which we're prompting,

and then we include it back into the original prompt, right?

Yeah, exactly.

That feeds back into the prompt,

and then once we're at this point, we move over to the other side of the equation, which is the large language model.

Gotcha, so that prompt that includes the vector embeddings now are fed into the large

language model, which then produces the output with the answer to our original question with sourced up to date and accurate.

Exactly, and that's a crucial aspect of it.

As new data comes in to this vector database,

where things that are updated back to your relevant question around performance in Q1, as new data comes in, those embeddings are updated.

So when that question's asked a second time,

we have more relevant data in order to provide back to the LLM, which then generates the output and the answer.

Okay, very cool.

So Sean, this sounds a lot like my original analogy there with the librarian and our journalist, right?

So the journalist trusts that the information in the library is accurate.

Now, one of the challenges that I see is when I'm talking to enterprise customers is they're

concerned about deploying this kind of technology into customer-facing business-critical applications.

So if they're building applications,

taking customer orders, processing refunds, they're worried that these kinds of technologies can produce hallucinations or inaccurate results, right, or perpetuate some kind of bias.

What are some things that can be done to help mitigate some of these concerns?

That brings up a great point, Love, right?

Data that comes in on this side,

but also on this side, is incredibly important to the output that we get when we go to make that prompt and get that input.

So it really is true.

Garbage in and garbage out, right?

So we need to make sure we have good data that comes into the vector database.

We need to make sure that data is clean, governed, and managed properly.

Gotcha.

So I'm hearing is that things like governance and data management are, of course, crucial to the data.

the vector database, right?

So making sure that the actual information that's flowing through into the model such as the business results in the sample prompt we talked about is government

and clean, but also crucially on the large language model size.

And we need to make sure that we're not using a large language model that takes a black box approach.

So a where you don't actually know what is the underlying data that went into training it.

You don't know if there's any intellectual property in there.

You don't know if there's inaccuracies in there.

Or you don't know if there are pieces of data that will end up perpetuating bias in your output results.

Right?

So as a business,

and as a business that's trying to manage and upholds their brain reputation,

it's absolutely critical to make sure that we're taking an approach that uses LLMs that are transparent in and we can be 100%

certain that there aren't any inaccuracies or data that's not supposed to be in there to be in there, right?

Yeah, exactly.

It's incredibly important, especially as a brand that we get the right answers.

We've seen the result.

Impact and especially back to our original question around what was our revenue in Q1, right?

We don't want that to be impacted by the results of a question that comes from, you know, the prompts one of our allms.

Exactly, exactly.

So very powerful technology, but it makes me think back to the the library.

Our journalists and librarian, they both trust the data in the books that are in the library.

We have to have that same kind of confidence when we're building out these types of generative AI use cases for business as well.

Exactly love.

So governance, AI, but also data and data management are incredibly important to this process.

번역 언어

번역 언어 선택

비디오 요약 자막 내보내기 구술 평가

더 많은 기능 잠금 해제

Trancy 확장 프로그램을 설치하면 AI 자막, AI 단어 정의, AI 문법 분석, AI 구술 등을 포함한 더 많은 기능을 사용할 수 있습니다.

RAG Explained - 이중 자막

더 많은 기능 잠금 해제

인기 있는 비디오 플랫폼과 호환

시작 준비되셨나요?