What is Retrieval-Augmented Generation (RAG)?

Поділитися
Вставка
  • Опубліковано 29 січ 2025

КОМЕНТАРІ • 577

  • @xzskywalkersun515
    @xzskywalkersun515 Рік тому +984

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

    • @cosmicscattering5499
      @cosmicscattering5499 Рік тому +8

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

    • @tariqmking
      @tariqmking 10 місяців тому +4

      Yes this was excellently explained, kudos to her.

    • @brianmi40
      @brianmi40 10 місяців тому +20

      Or at least credit for being able to write backwards!

    • @victoriamilhoan512
      @victoriamilhoan512 8 місяців тому +3

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

    • @aguiremedia
      @aguiremedia 8 місяців тому +1

      Why. Chat gpt wrote it

  • @vt1454
    @vt1454 Рік тому +583

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

    • @XEQUTE
      @XEQUTE Рік тому +11

      i think they already do

    • @srinivasreddyt9555
      @srinivasreddyt9555 10 місяців тому +1

      Yes, they have it already. UA-cam.

    • @siddheshpgaikwad
      @siddheshpgaikwad 9 місяців тому +5

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

    • @Hossam_Ahmed_
      @Hossam_Ahmed_ 9 місяців тому

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

    • @CaptPicard81
      @CaptPicard81 9 місяців тому

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

  • @geopopos
    @geopopos 10 місяців тому +106

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

    • @theupsider
      @theupsider Місяць тому +1

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

  • @jordonkash
    @jordonkash 11 місяців тому +92

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

  • @ntoscano01
    @ntoscano01 Рік тому +40

    Very well explained!!! Thank you for your explanation of this. I’m so tired of 45 minute UA-cam 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.

  • @ericadar
    @ericadar Рік тому +109

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

  • @TheAllnun21
    @TheAllnun21 Рік тому +31

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

  • @digvijaysingh6882
    @digvijaysingh6882 7 місяців тому +18

    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

  • @natoreus
    @natoreus 8 місяців тому +25

    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.

  • @ReflectionOcean
    @ReflectionOcean Рік тому +32

    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

  • @aam50
    @aam50 Рік тому +20

    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!

  • @AlexandraSteskal
    @AlexandraSteskal 5 місяців тому +3

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

  • @maruthuk
    @maruthuk Рік тому +22

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

  • @m.kaschi2741
    @m.kaschi2741 Рік тому +8

    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

  • @hamidapremani6151
    @hamidapremani6151 11 місяців тому +2

    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.

  • @Will-lg9ev
    @Will-lg9ev 7 місяців тому +1

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

  • @ghtgillen
    @ghtgillen Рік тому +77

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

    • @jsonbourne8122
      @jsonbourne8122 Рік тому +35

      They flip the video

    • @Paul-rs4gd
      @Paul-rs4gd Рік тому +12

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

    • @aykoch
      @aykoch 8 місяців тому +3

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

    • @7th_CAV_Trooper
      @7th_CAV_Trooper 8 місяців тому +11

      @@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
      @bikrrr 7 місяців тому +1

      ​@@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
    @jyhherng Рік тому +6

    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!

  • @ltkbeast
    @ltkbeast 3 місяці тому +2

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

  • @vikramn2190
    @vikramn2190 Рік тому +47

    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
      @judahb3ar 9 місяців тому

      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
      @PlaytimeEntertainment 9 місяців тому +4

      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
      @velocityra 8 місяців тому

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

  • @AliShakeSpear
    @AliShakeSpear 11 днів тому

    I watched and read so many videos/articles. This explained it so elegantly. Thank you.

  • @kallamamran
    @kallamamran Рік тому +5

    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!

  • @javi_park
    @javi_park Рік тому +73

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

    • @RiaKeenan
      @RiaKeenan Рік тому

      I know, right?!

    • @euseikodak
      @euseikodak Рік тому +10

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

    • @politicallyincorrect1705
      @politicallyincorrect1705 11 місяців тому +1

      Filmed in front of a non-reflective mirror.

    • @TheTomtz
      @TheTomtz 10 місяців тому +2

      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
      @thewallstreetjournal5675 10 місяців тому +1

      Is the board fliped or has she been flipped?

  • @AnjanaSilvaAJ
    @AnjanaSilvaAJ 2 місяці тому +1

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

  • @kingvanessa946
    @kingvanessa946 Рік тому +1

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

  • @indianatlarge
    @indianatlarge Місяць тому +1

    i was distracted by her ability to write lateraly inverted roman script while still thinking and explaining!!! Kudos

  • @redwinsh258
    @redwinsh258 Рік тому +23

    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

  • @shreyjain3344
    @shreyjain3344 5 місяців тому

    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.

  • @GregSolon
    @GregSolon 11 місяців тому

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

  • @444Yielding
    @444Yielding 9 місяців тому +3

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

  • @projectfocrin
    @projectfocrin Рік тому +5

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

  • @HimalayJoriwal
    @HimalayJoriwal 11 місяців тому

    Best explanation so far from all the content on internet.

  • @EmmettYoung
    @EmmettYoung 5 місяців тому

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

  • @evaiintelligence
    @evaiintelligence 9 місяців тому

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

  • @toenytv7946
    @toenytv7946 10 місяців тому +1

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

  • @ivlivs.c3666
    @ivlivs.c3666 7 місяців тому

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

  • @rajeshseptember09
    @rajeshseptember09 7 місяців тому

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

  • @paulaenchina
    @paulaenchina Рік тому +1

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

  • @Aryankingz
    @Aryankingz Рік тому +4

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

  • @AbhishekVerma-jw3jg
    @AbhishekVerma-jw3jg 5 місяців тому

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

  • @sawyerburnett8319
    @sawyerburnett8319 Рік тому +1

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

  • @mohamadhijazi3895
    @mohamadhijazi3895 9 місяців тому

    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?

  • @ReelTaino
    @ReelTaino Рік тому

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

  • @ssr142812
    @ssr142812 7 місяців тому

    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

  • @aakifriaz2388
    @aakifriaz2388 26 днів тому

    Straight to the point explanation that cleared my entire concept. Thanking IBM!

  • @jean-charles-AI
    @jean-charles-AI 6 місяців тому +1

    This explantation is one of the best out there.

  • @Linkky
    @Linkky 2 місяці тому

    Really comprehensive, well explained Marina Danilevsky !

  • @LindsayRichardson-rv2wn
    @LindsayRichardson-rv2wn 5 місяців тому

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

  • @rujmah
    @rujmah 11 місяців тому

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

  • @neotower420
    @neotower420 10 місяців тому

    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
      @neotower420 10 місяців тому

      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.

  • @sarangag
    @sarangag 3 місяці тому

    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?

  • @rockochamp
    @rockochamp Рік тому +1

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

  • @rsu82
    @rsu82 8 місяців тому

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

  • @past_life_project
    @past_life_project Рік тому

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

  • @batumanav
    @batumanav 3 місяці тому

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

  • @janhorak8799
    @janhorak8799 11 місяців тому +34

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

    • @VlogBySKSK
      @VlogBySKSK 9 місяців тому

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

    • @mao-tse-tung
      @mao-tse-tung 9 місяців тому +8

      She was right handed before the mirror effect

    • @Helixur
      @Helixur 8 місяців тому +1

      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
      @vipulsonawane7508 Місяць тому

      @Helixur you got my answer buddy!! Simple

    • @rahul21stcentury
      @rahul21stcentury 19 днів тому

      The video just gets mirrored in in post production , Thats it

  • @neutron417
    @neutron417 Рік тому +2

    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?

  • @rhitikkrishnani510
    @rhitikkrishnani510 5 місяців тому

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

  • @rvssrkrishna2
    @rvssrkrishna2 11 місяців тому

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

  • @paulw4259
    @paulw4259 Місяць тому

    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.

  • @damen238
    @damen238 Місяць тому

    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

    • @charimuvilla8693
      @charimuvilla8693 Місяць тому

      I was bamboozled by this type of video as well. It gets a lot simpler when you realize that all you need to do is mirror the video.

  • @francischacko3627
    @francischacko3627 9 місяців тому

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

  • @ThePoushal
    @ThePoushal 5 днів тому

    Used RAG on Nolan's original interstellar script. Blew my mind with insights.

  • @WallyAlcacio
    @WallyAlcacio 2 місяці тому

    Loved this method of explaining concepts. Thank you!

  • @Jaimin_Bariya
    @Jaimin_Bariya Місяць тому +1

    Hey, JP here again,
    Thank You IBM

  • @prasannakulkarni5664
    @prasannakulkarni5664 9 місяців тому

    the color coding on your whiteboard is really apt here !

  • @Anubis2828
    @Anubis2828 10 місяців тому

    Great, simple, quick explanation

  • @xdevs23
    @xdevs23 10 місяців тому +8

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

  • @AntenorTeixeira
    @AntenorTeixeira Рік тому

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

  • @MraM23
    @MraM23 Рік тому

    Great lessons! Nice of you to step out 🙃 and make such engaging and educative content This is a very useful in helping us in critical thinking. Thank you for sharing this video. 👍
    Current ai models may impose neurotypical norms and expectations based on current data trained on . 🤔
    Curious to see more on how IBM approach the challenges and limitations of Ai

  • @Kekko400D
    @Kekko400D 11 місяців тому

    Fantastic explanation, proud to be an IBMer

  • @RickOShay
    @RickOShay 8 місяців тому +1

    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?

  • @vipulsonawane7508
    @vipulsonawane7508 Місяць тому

    Wow, simple neat and clear explanation!!!

  • @JonCoulter-u1y
    @JonCoulter-u1y Рік тому +16

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

    • @IBMTechnology
      @IBMTechnology  Рік тому +9

      See ibm.biz/write-backwards

    • @jsonbourne8122
      @jsonbourne8122 Рік тому

      Left hand too!

    • @NishanSaliya
      @NishanSaliya Рік тому

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

  • @JasonVonHolmes
    @JasonVonHolmes 10 місяців тому

    This was explained fantastically.

  • @Bikashics
    @Bikashics 6 місяців тому

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

  • @rafa1rafa
    @rafa1rafa Рік тому +2

    Great explanation! The video was very didactic, congratulations!

  • @gbluemink
    @gbluemink Рік тому +1

    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 :)

  • @sonjoysengupto
    @sonjoysengupto Місяць тому

    Excellent tutorial on RAG, thanks a lot!

  • @AIPretendingToBeHuman
    @AIPretendingToBeHuman 3 місяці тому

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

  • @sudhakarveeraraghavan5832
    @sudhakarveeraraghavan5832 9 місяців тому

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

  • @stanislavzayarsky
    @stanislavzayarsky Рік тому

    Finally, we got a clear explanation!

  • @bhaskarmothali
    @bhaskarmothali 7 місяців тому

    Exactly what I was trying to understand, great explanation!

  • @peterciank
    @peterciank 5 місяців тому

    outstanding explenation and lecturer! Well done!

  • @bdouglas
    @bdouglas 9 місяців тому

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

  • @ravirajasekharuni
    @ravirajasekharuni 6 місяців тому +1

    Outstanding explanation. Its very easy to underatand. I like the way the video is made with presenter writing to the blackboard . I want to know what SOFTWARE/TOOL is used to make this video/presentation. Its really cool.

  • @limitlessrari1
    @limitlessrari1 7 місяців тому

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

  • @mengyu-iv8wn
    @mengyu-iv8wn 9 місяців тому +1

    Hi, thanks for your share and I have a question regarding the RAG framework. Is the content of the answers solely retrieved from documents, or does the LLM integrate the retrieved content with its own knowledge before providing a response?

  • @VishalSharma-gp6dm
    @VishalSharma-gp6dm 10 місяців тому

    that reverse writing made be anxious, but a very smart explanation for RAG!!

  • @aniket_mishr
    @aniket_mishr 9 місяців тому

    The explanation was very good 💯.

  • @mikezooper
    @mikezooper 7 місяців тому

    You’re an amazing teacher.

  • @AravindBadrinath
    @AravindBadrinath Рік тому +4

    Very well explained.❤
    But what happens if RAG and LLM trained data has conflict. in this case LLM knows answer as Jupiter and rag content store is saying answer is Saturn. Is it that RAG always gets higher weightage?

    • @Famaash
      @Famaash Рік тому

      Yes, I think that's what she also implied.

  • @lewi594
    @lewi594 Рік тому +2

    This is brilliant and concise, helped make sense of a complex subject..
    Can this be implemented in a small environment with limited computing? Such that the retriever only has access to a closed data source

  • @ashwinkumar675
    @ashwinkumar675 9 місяців тому

    This is so well explained! Thank you 👍🏻✅

  • @khalidelgazzar
    @khalidelgazzar Рік тому +2

    Great explanation. Thank you!😊

  • @lauther_27
    @lauther_27 Рік тому +1

    Amazing video, thanks IBM ❤

  • @alexiojunior7867
    @alexiojunior7867 9 місяців тому

    wow this was an amazing Explanation ,very easy to understand

  • @421sap
    @421sap Рік тому

    Thank you, Marina Danilevsky ....

  • @vnaykmar7
    @vnaykmar7 Рік тому +2

    Such an amazing explanation. Thank you ma'am!

  • @yeezhihao
    @yeezhihao Рік тому +1

    Can someone help me explain why we are better off pulling from an updater content store vs retrain the model with the content store data?