What is Retrieval-Augmented Generation (RAG)?

[@xzskywalkersun515]

This lecturer should be given credit for such an amazing explanation.

[@cosmicscattering5499]

I was thinking the same, she explained this so clearly.

[@tariqmking]

Yes this was excellently explained, kudos to her.

[@brianmi40]

Or at least credit for being able to write backwards!

[@victoriamilhoan512]

The connection between a human answering a question in real life vs how LLMs (with or without RAG) do it was so helpful!

[@aguiremedia]

Why. Chat gpt wrote it

[@vt1454]

IBM should start a learning platform. Their videos are so good.

[@XEQUTE]

i think they already do

[@srinivasreddyt9555]

Yes, they have it already. KZbin.

[@siddheshpgaikwad]

Its mirrored video, she wrote naturally and video was mirrored later

[@Hossam_Ahmed_]

They have skill build but not videos at least most of the content

[@CaptPicard81]

They do, I recently attended a week long AI workshop based on an IBM curriculum

[@geopopos]

I love seeing a large company like IBM invest in educating the public with free content! You all rock!

[@theupsider]

Apparently there are scientists in charge who are pushing for such an agenda. Love to see it.

[@ntoscano01]

Very well explained!!! Thank you for your explanation of this. I’m so tired of 45 minute KZbin videos with a college educated professional trying to explain ML topics. If you can’t explain a topic in your own language in 10 minutes or less than you have failed to either understand it yourself or communicate effectively.

[@jordonkash]

4:15 Marina combines the colors of the word prompt to emphasis her point. Nice touch

[@ericadar]

Marina is a talented teacher. This was brief, clear and enjoyable.

[@ReflectionOcean]

1. Understanding the challenges with LLMs - 0:36 2. Introducing Retrieval-Augmented Generation (RAG) to solve LLM issues - 0:18 3. Using RAG to provide accurate, up-to-date information - 1:26 4. Demonstrating how RAG uses a content store to improve responses - 3:02 5. Explaining the three-part prompt in the RAG framework - 4:13 6. Addressing how RAG keeps LLMs current without retraining - 4:38 7. Highlighting the use of primary sources to prevent data hallucination - 5:02 8. Discussing the importance of improving both the retriever and the generative model - 6:01

[@TheAllnun21]

Wow, this is the best beginner's introduction I've seen on RAG!

[@natoreus]

I'm sure it was already said, but this video is the most thorough, simple way I've seen RAG explained on YT hands down. Well done.

[@digvijaysingh6882]

Einstein said, "If you can't explain it simply, you don't understand it well enough." And you explained it beautifuly in most simple and easy to understand way 👏👏. Thank you

[@aam50]

That's a really great explanation of RAG in terms most people will understand. I was also sufficiently fascinated by how the writing on glass was done to go hunt down the answer from other comments!

[@AnjanaSilvaAJ]

This is a fantastic video to learn about RAG in under 7 minutes. Thank you

[@vikramn2190]

I believe the video is slightly inaccurate. As one of the commenters mentioned, the LLM is frozen and the act of interfacing with external sources and vector datastores is not carried out by the LLM. The following is the actual flow: Step 1: User makes a prompt Step 2: Prompt is converted to a vector embedding Step 3: Nearby documents in vector space are selected Step 4: Prompt is sent along with selected documents as context Step 5: LLM responds with given context Please correct me if I'm wrong.

[@judahb3ar]

I’m not sure. Looking at OpenAI documentation on RAG, they have a similar flow as demonstrated in this video. I think the retrieval of external data is considered to be part of the LLM (at least per OpenAI)

[@PlaytimeEntertainment]

I do not think retrieval is part of LLM. LLM is the best model at the end of convergence after training. It can't be modified rather after LLM response you can always use that info for next flow of retrieval

[@velocityra]

Thank you. So many people praising this even though it didn't explain anything that can't be googled in 2 seconds.

[@ltkbeast]

Every time I watch one of these videos I'm amazed at the presenter's skill at writing backwards.

[@justsomeguywithasmolmustac9476]

The video is flipped

[@AlexandraSteskal]

I love IBM teachers/trainers, I used to work at IBM and their in-house education quality was AMAZING!

[@maruthuk]

Loved the simple example to describe how RAG can be used to augment the responses of LLM models.

[@hamidapremani6151]

The explanation was spot on! IBM is the go to platform to learn about new technology with their high quality content explained and illustrated with so much simplicity.

[@m.kaschi2741]

Wow, I opened youtube coming from the ibm blog just to leave a comment. Clearly explained, very good example, and well presented as well!! :) Thank you

[@kallamamran]

We also need the models to cross check their own answers with the sources of information before printing out the answer to the user. There is no self control today. Models just say things. "I don't know" is actually a perfectly fine answer sometimes!

[@Jaimin_Bariya]

Hey, JP here again, Thank You IBM

[@ghtgillen]

Your ability to write backwards on the glass is amazing! ;-)

[@jsonbourne8122]

They flip the video

[@Paul-rs4gd]

@@jsonbourne8122 So obvious, but I did not think of it. My idea was way more complicated!

[@aykoch]

They're almost always left-handed as well...

[@7th_CAV_Trooper]

@@aykoch she is right handed. when she writes, the arm moves away from the body. left hand arm would move toward the body. because the video is flipped, it's a bit of a mind trick to see it.

[@bikrrr]

​@@jsonbourne8122 Nice attention to detail as they made sure the outfit was symmetrical without any logos and had a ring on each hand's ring finger, making it harder to tell it was flipped.

[@jyhherng]

this let's me understand why the embeddings used to generate the vectorstore is a different set from the embeddings of the LLM... Thanks, Marina!

[@damen238]

I spent all of the 1st watch talking while a friend watched it aswell trying to figure out is she is a robot because of the backwards writing. Good and fast info the 2nd watch. Great job

[@janhorak8799]

Did all the speakers have to learn how to write in a mirrored way or is this effect reached by some digital trick?

[@VlogBySKSK]

There is a digital mirroring technique which is used to show the content this way...

[@mao-tse-tung]

She was right handed before the mirror effect

[@Helixur]

Writing on a clear glass, camera is behind the glass. It's like standing a glass and lookin at a person in an interrogation room

[@vipulsonawane7508]

@Helixur you got my answer buddy!! Simple

[@Will-lg9ev]

As a salesperson that actually loves tech. This was an awesome explanation and the fact it was visual helped a ton!!!! Thanks

[@javi_park]

hold up - the fact that the board is flipped is the most underrated modern education marvel nobody's talking about

[@RiaKeenan]

I know, right?!

[@euseikodak]

Probably they filmed it in front of a glass board and flipped the video on edition later on

[@politicallyincorrect1705]

Filmed in front of a non-reflective mirror.

[@TheTomtz]

Just simply write on a glass board ,record it from the other side and laterally flip the image! Simple aa that.. and pls dont distract people from the contents being lectured by thinkin about the process behind the rec🤣

[@thewallstreetjournal5675]

Is the board fliped or has she been flipped?

[@paulw4259]

Thanks. Great video. I've had too many conversations where Chatgpt has apparently just made stuff up. I know that's not what happens really, but it seems like it and it still makes untrue statements. I'm glad researchers are working to improve things.

[@kingvanessa946]

For me, this is the most easy-to-understand video to explain RAG!

[@GregSolon]

One of the easiest to understand RAG explanations I've seen - thanks.

[@redwinsh258]

The interesting part is not retrieval from the internet, but retrieval from long term memory, and with a stated objective that builds on such long term memory, and continually gives it "maintenance" so it's efficient and effective to answer. LLMs are awesome because even though there are many challenges ahead, they sort of give us a hint of what's possible, without them it would be hard to have the motivation to follow the road

[@sarangag]

Nicely explained. My questions/doubts? 1. Doesn't this raise questions about the process of building and testing LLMs? 2. In such scenarios will the test and training data used be considered authentic and not "limited and biased"? 3. Is there a process/standard on how often the "primary source data" should be updated?

[@shreyjain3344]

The explanation is good and easy to understand for a student like me who is new to this topic it gives me a clear idea of what RAG is.

[@projectfocrin]

Great explanation. Even the pros in the field I have never seen explain like this.

[@ReelTaino]

Please keep all these videos coming! They are so easy to understand and straightforward. Muchas gracias!

[@neotower420]

tokens as a [word] is what I'm working on right now (solo, self learning LLM techniques), this video helped me realize how the model doesn't know what it's outputting obviously, but AI-AI is different, so building tokens that have dimensional vectors that process in a separate model, can be used for explainable AI.

[@neotower420]

meaning a separate model processes the response itself, meta, it's for building evolution learning. AI-AI machine learning, you need a way to configure in between the iterations.

[@paulaenchina]

This is the best explanation I have seen so far for RAG! Amazing content!

[@evaiintelligence]

Marina has done a great job explaining LLM and RAGs in simple terms.

[@444Yielding]

This video is highly underviewed for as informative as it is!

[@ivlivs.c3666]

lecturer did a fantastic job. simple and easy to understand.

[@ssr142812]

I have few questions here @ (1) When I prompt and it is not present in context store, shall I get generated text from LLM? 2. when I prompt and a match with embeddings of context store, shall I get content generated from both LLM and Context store? 3. How to enforce RAG framework in Langchain? Appreciate answers

[@toenytv7946]

Great down the rabbit hole video. Very deep and understandable. IBM academy worthy in my opinion.

[@rajeshseptember09]

I have no "Data Science" background. But I completely understood. You simplified this so unbelievably well. Thanks !

[@LindsayRichardson-rv2wn]

Thank you for providing a thorough and accessible explanation of RAG!

[@EmmettYoung]

I really like the analogy from the beginning! It was very smooth explanation! Well done!

[@past_life_project]

I have watched many IBM videos and this is the undoubtedly the best ! I will be searching for your videos now Marina!

[@AbhishekVerma-jw3jg]

This was such simple and clear explanation of complex subject. Thanks Marina :)

[@Linkky]

Really comprehensive, well explained Marina Danilevsky !

[@HimalayJoriwal]

Best explanation so far from all the content on internet.

[@Aryankingz]

That's what Knowledge graphs are for, to keep LLMs grounded with a reliable source and up-to-date.

[@sawyerburnett8319]

Wow, having a lightbulb moment finally after hearing this mentioned so often. Makes more sense now!

[@jean-charles-AI]

This explantation is one of the best out there.

[@batumanav]

Amazing explanation. Starting from scratch and gained great perspective on this in a very short time.

[@rujmah]

Brilliant explanation and illustration. Thanks for your hard work putting this presentation together.

[@rsu82]

good explanation, it's very easy to understand. this video is the first one when I search RAG on KZbin. great job ;)

[@vipulsonawane7508]

Wow, simple neat and clear explanation!!!

[@rvssrkrishna2]

Very precise and exact information on RAG in a nutshell. Thank you for saving my time.

[@rhitikkrishnani510]

Thats one of the best explaination I have got so far ! Thanks a ton !

[@WallyAlcacio]

Loved this method of explaining concepts. Thank you!

[@francischacko3627]

perfect explanation understood every bit , no lags kept it very interesting ,amazing job

[@xdevs23]

The entire video I've been wondering how they made the transparent whiteboard

[@rockochamp]

very well executed presentation. i had to think twice about how you can write in reverse but then i RAGed my system 2 :)

[@AntenorTeixeira]

That's the best video about RAG that I've watched

[@sudhakarveeraraghavan5832]

Very well explained and it is easily understandable to non AI person as well. Thanks.

[@mzimmerman1988]

well done, thanks!

[@Bikashics]

Thanks Marina !!! For that such a simple explanation on such a complex topic !!!

[@AIPretendingToBeHuman]

In one 6 minute video, the presenter identifies the largest problem and a practical solution to using Gen AI in the Enterprise 👍

[@rafa1rafa]

Great explanation! The video was very didactic, congratulations!

[@JonCoulter-u1y]

The ability to write backwards, much less cursive writing backwards, is very impressive!

[@IBMTechnology]

See ibm.biz/write-backwards

[@jsonbourne8122]

Left hand too!

[@NishanSaliya]

@@IBMTechnology Thanks .... I was reading comments to check for an answer for that question!

[@josejaimefelixgarciagarcia8884]

I love how she colored the "om" in "prompt" to visually emphasize that the factual grounding data is now inside the prompt @4:21

[@Kekko400D]

Fantastic explanation, proud to be an IBMer

[@stanislavzayarsky]

Finally, we got a clear explanation!

[@bhaskarmothali]

Exactly what I was trying to understand, great explanation!

[@peterciank]

outstanding explenation and lecturer! Well done!

[@Anubis2828]

Great, simple, quick explanation

[@ZHOUQin]

chatGPT: an answer. Google: an answer. IBM: hmm...how about combining the two, and give it a fancy name?

[@mohamadhijazi3895]

The video is short and consice yet the delivery is very elegant. She might be the best instructor that have teached me. Any idea how the video was created?

[@bdouglas]

That was excellent, simple, and elegant! Thank you!

[@limitlessrari1]

Great explaination. It's very helpful for my project a GEN Ai intern

[@TimDegraye]

She's writing in mirror reverse, that is so impressive!

[@RickOShay]

Less Helium! How does this system resolve conflicting answers from the datastore and generative process? Does the datastore answer always take precedence - and if so - is there a logic or reasoning layer that checks how reliable and up-to-date the datastore is and its reliability index?

[@gbluemink]

So the question I have here is when I have an answer from my LLM but not the Rag data, what is the response to the user? "I don't know" or the LLM response that may be out of date or without a reliable source? Looks like a question for an LLM :)

[@JasonVonHolmes]

This was explained fantastically.

[@vnaykmar7]

Such an amazing explanation. Thank you ma'am!

[@davidtindell950]

MOST OF US WOULD prefer a 'qualified answer' rather than a not-so-useful 'I DON'T KNOW' ! BTW: There were 9 planets, but now there are 8 and soon there may be 10 !

[@alexiojunior7867]

wow this was an amazing Explanation ,very easy to understand

[@zuzukouzina-original]

Very clear explanation, much respect 🫡

[@preciousrose2715]

This was such an amazing explanation!

[@PaulGrew-wl7mh]

An amazing explanation that made RAG understandable in about 4:23 minutes!

[@SharieffMansour]

Fantastic video and explanation. Thank you!

[@mikezooper]

You’re an amazing teacher.

[@421sap]

Thank you, Marina Danilevsky ....

[@neutron417]

From which corpus/database are the documents retrieved from? Are they up-to date? and how does it know the best documents to select from a given set?

[@laurentpastorelli1354]

Super good and clear, well done!

[@prasannakulkarni5664]

the color coding on your whiteboard is really apt here !

[@kunalsoni7681]

Thanks for letting us know about this feature of LLM :)

[@lauther_27]

Amazing video, thanks IBM ❤

[@geasderlinasdwsxcdeasd]

I have no idea. I think maybe I should do it and wondering and maybe I should go an d stay here and try something back in the past life. there is totally no need to bring so many stuff with me everyday. you know I could study like everyday. so why not just give me some place and sometimes go to the bed while sometimes didn't? that's sounds like a good great idea. the only question or problem is to be focus and be calm. be vibrant. to change your environment consistently. you will know and figure the thing out one day not soon but I hope I could keep going and doing it. wonderful spirit

[@khalidelgazzar]

Great explanation. Thank you!😊

[@oklahomaguy23]

Great explanation of RAG. Thank you

[@mrhassell]

RAG combines the generative power of LLMs with the precision of specialized data search mechanisms, resulting in nuanced and contextually relevant responses.