How RAG Turns AI Chatbots Into Something Practical

Retrieval augmented generation, a current popular method to utilize LLMs to retrieve from a database instead of putting everything in a context window. But how does it work? Today I will walk through the most basic idea of RAG and the current meta of how RAG is used, and what it is composed of.

some papers

This video is supported by the kind Patrons & YouTube Members:
🙏Andrew Lescelius, alex j, Chris LeDoux, Alex Maurice, Miguilim, Deagan, FiFaŁ, Robert Zawiasa, Owen Ingraham, Tanaro, Daddy Wen, Tony Jimenez, Panther Modern, Jake Disco, Demilson Quintao, Penumbraa, Shuhong Chen, Hongbo Men, happi nyuu nyaa, Carol Lo, Mose Sakashita, Miguel, Bandera, Gennaro Schiano, gunwoo, Ravid Freedman, Mert Seftali, Mrityunjay, Richárd Nagyfi, Timo Steiner, Henrik G Sundt, projectAnthony, Brigham Hall, Kyle Hudson, Kalila, Jef Come, Jvari Williams, Tien Tien, BIll Mangrum, owned, Janne Kytölä, SO, Richárd Nagyfi, Hector, Drexon, Claxvii 177th, Inferencer, Michael Brenner, Akkusativ, Oleg Wock, FantomBloth, Thipok Tham, Clayton Ford

[Music] massobeats - glisten
[Video Editor] @Askejm

[Steamrick]

Lifetime for $130? Your sponsor is banking on LLMs getting cheaper real hard.

[nicejungle]

Couldn't agree more on usefulness of chatbots.
RAG is awesome features.
But with the growing size of context window for recent LLM (Mistral-NeMo has a window of 128k tokens for example), RAG isn't that useful now.
It greatly depends of the size of your knowledge database

[HanzDavid]

I dont think LLMs are going to replace RAG. RAGs are going to be a long term solution for context retrieval. Even if the context window is large enough for processing thousends of books, it would still be expensive and the LLM looses precission with growing input. The LLM should be able to focus on its specific task and not be overlorded with lots of expensive context. I wouldn't also call it a "hacky" way, its just another type of database.

[Laszer]

LLMs are like cars, if it stands in the middle of the deep forest we can point at it and laugh at how it's stupid and how it's better to just walk through the forest.

RAG and tools (as in tool-calling for llms) are the infrastructure comparable to roads. Many people don't realize that once the "car" gets on the proper "road", it is all of sudden very efficient at what it does.

We don't faster cars (e.g. GPT-5), infrastructure is all we need right now.

[SperkSan]

Your thumbnail reminds me of The Code Report

[kocokan]

Describing all these AI news and papers for casual mortals takes significant efforts

[juriaan]

at this point we are creating diffrent parts of a brain. this is littrally how our brain works. amazing! keep up the content you now alot about the topic and i can really find out what is the latest hot news

[vladimirtchuiev]

The "what is this pokemon" of a transformer is brilliant, saved for future references.

[Neomadra]

Ngl, this lifetime access deal is sus af

[l.halawani]

You turn AI science into proper entertainment.
Couldn't be more digestible! Thanks for that!

[RyanClark-gryb]

Esstally RAG helps LLMs have data access to whatever contextualized information you have at hand, and helps it bring more meaningful data out of it cheaper and faster.

[ghaith]

Thank you for the high quality information, you have no idea how much headache and time you saved me

[andydataguy]

Its so simple! Thanks for breaking it down like this 💜

[st.dantry]

This channel is a circejerk for people who already know enough about the topic to not need these videos. I'm a reasonably smart layman with an interest in AI and could learn nothing from this video. Too much jargon. It's the reason why this channel has so few subscribers. It should have millions, but the information is not packaged into easily understandable bits.

[StephenRayner]

You didn’t talk about the best chuck size / overlap

[aykutakguen]

I think the future of llms will be a system where an llm primarily traverses a rag like systems and uses thag to build rules, it keeps building rules until all requirements are fullfilled and then sends back the result. Models like these would be poor ceratives but insanly factual and logistically strong

[clapclapapp]

So, indexing is what search engines do, right?

[KoZM]

Can you share the link for the Knowledge-Nexus RAG example you used for GraphRAG?

[deepmodel-qb]

7:47 "what sets STINK BUDDY apart..."

[marshallodom]

I wish I could use AI to do something productive with out having to learn rocket surgery. This sounds interesting but way beyond a layman's understanding of chat AIs.