How to Improve LLMs with RAG (Overview + Python Code)

In this video, I give a beginner-friendly introduction to retrieval augmented generation (RAG) and show how to use it to improve a fine-tuned model from a previous video in this LLM series.

Resources

--

Socials

The Data Entrepreneurs

Support ❤️

Intro - 0:00
Background - 0:53
2 Limitations - 1:45
What is RAG? - 2:51
How RAG works - 5:03
Text Embeddings + Retrieval - 5:35
Creating Knowledge Base - 7:37
Example Code: Improving YouTube Comment Responder with RAG - 9:34
What's next? - 20:58

[ShawhinTalebi]

Check out more videos in this series 👇


--

Resources

[saadowain]

Thank you Talebi. No one explains the subject like you

[ifycadeau]

This is so helpful! Thanks Shaw, you never miss!

[jagtapjaidip]

very nice. thank you for explaining in details.

[firespark]

Awesome video, thanks! I'm wondering if instead of using top_k documents/batches one could define a threshold/distance for the used batches?

[zahrahameed]

Thankyou so much. Becoming a fan of yours!
Please do a video on Rag with llamaIndex + llama3 if it's free and not paid.

[nistelbergerkurt]

great video as always 👍
does a reranker improve the quality of the output for a RAG approach? like that we could take the output directly from the reranker, right? or what is your experience with reranker?

[Pythonology]

Happy Nowruz, kheyli khoob! Question: how would you propose to evaluate a document on the basis of certain guidelines? I mean, to see how far it complies with the guidelines or regulations for writing a certain document. Is RAG any good? shall we just embed the guidelines in the prompt right before the writing? or shall we store the guidelines as a separate document and do RAG? Or ...?

[candidlyvivian]

Hey Shaw, thanks so much for such a helpful video.
I''d love to seek your advice on something :)

Currently we are using OpenAI to build out a bunch of insights that will be refreshed using business data (i.e. X users land on your page, Y make a purchase)
Right now we are doing a lot of data preparation and feeding in the specific numbers into the user/system prompt before passing to OpenAI but have had issues with consistency of output and incorrect numbers.

Would you recommend a fine-tuning approach for this? Or RAG? Or would the context itself be small enough to fit into the "context window" given it's a very small dataset we are adding to the prompt.
Thanks in advance 🙂

[TheLordSocke]

Nice Video, any ideas for doing this on PowerPoints? Want to build a kind of knowledge base from previous projects but the grafics are a problem. Even GPT4V is not always interpreting them correctly. 😢

[edsleite]

Hi Talebi. Thanks for all you show us. But one question : I did your code with mine database, without the fine tuning and it works, very quickly answers but poor contents. That is the point of fine tuning make better answers ?

[vamsitharunkumarsunku]

So we get top 3 similar chunks from RAG right, We are adding 3 chunks to prompt template?

[halle]

Any recommendations or experience on which embeddings database to use?

[TheRcfrias]

Rag is great for semi-static or static content as knowledge base, but which path do you use for dynamic, time-relevant data like current sales from a database?

[jjen]

hello, do you have a video showing how to make a datasett and upload it to huggind face?

[CppExpedition]

what do you mean with 'not to scale?' isn't the book at the size of the earth?

[JavierTorres-stgt]

How to protect a company's information with this technology?

[yameen]

Vector retrieval is quite shite. Trust me. To improve accuracy of retrieval, you need to use multiple methods.