Very well explained!!! Thank you for your explanation of this. I’m so tired of 45 minute TH-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.
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.
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)
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
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
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
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
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!
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!
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.
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
@@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.
@@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.
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🤣
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?
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.
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.
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?
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?
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 :)
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?
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
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
I have a question, so for these RAG models, is it possible to have them in local? Like download my model and read the data from my computer or so, or is it somethin we have to have in the cloud always running?
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
RAG combines the generative power of LLMs with the precision of specialized data search mechanisms, resulting in nuanced and contextually relevant responses.
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
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.
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?
This lecturer should be given credit for such an amazing explanation.
I was thinking the same, she explained this so clearly.
Yes this was excellently explained, kudos to her.
Or at least credit for being able to write backwards!
The connection between a human answering a question in real life vs how LLMs (with or without RAG) do it was so helpful!
Why. Chat gpt wrote it
IBM should start a learning platform. Their videos are so good.
i think they already do
Yes, they have it already. TH-cam.
Its mirrored video, she wrote naturally and video was mirrored later
They have skill build but not videos at least most of the content
They do, I recently attended a week long AI workshop based on an IBM curriculum
4:15 Marina combines the colors of the word prompt to emphasis her point. Nice touch
I love seeing a large company like IBM invest in educating the public with free content! You all rock!
Very well explained!!! Thank you for your explanation of this. I’m so tired of 45 minute TH-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.
Marina is a talented teacher. This was brief, clear and enjoyable.
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.
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)
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
Thank you. So many people praising this even though it didn't explain anything that can't be googled in 2 seconds.
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
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
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.
Wow, this is the best beginner's introduction I've seen on RAG!
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
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!
Loved the simple example to describe how RAG can be used to augment the responses of LLM models.
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!
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!
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.
I love IBM teachers/trainers, I used to work at IBM and their in-house education quality was AMAZING!
Every time I watch one of these videos I'm amazed at the presenter's skill at writing backwards.
The video is flipped
lecturer did a fantastic job. simple and easy to understand.
As a salesperson that actually loves tech. This was an awesome explanation and the fact it was visual helped a ton!!!! Thanks
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
This video is highly underviewed for as informative as it is!
For me, this is the most easy-to-understand video to explain RAG!
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.
Really comprehensive, well explained Marina Danilevsky !
Marina has done a great job explaining LLM and RAGs in simple terms.
One of the easiest to understand RAG explanations I've seen - thanks.
Thank you for providing a thorough and accessible explanation of RAG!
Your ability to write backwards on the glass is amazing! ;-)
They flip the video
@@jsonbourne8122 So obvious, but I did not think of it. My idea was way more complicated!
They're almost always left-handed as well...
@@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.
@@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.
hold up - the fact that the board is flipped is the most underrated modern education marvel nobody's talking about
I know, right?!
Probably they filmed it in front of a glass board and flipped the video on edition later on
Filmed in front of a non-reflective mirror.
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🤣
Is the board fliped or has she been flipped?
Great explanation. Even the pros in the field I have never seen explain like this.
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?
I have no "Data Science" background. But I completely understood. You simplified this so unbelievably well. Thanks !
This explantation is one of the best out there.
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.
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.
Great down the rabbit hole video. Very deep and understandable. IBM academy worthy in my opinion.
Wow, having a lightbulb moment finally after hearing this mentioned so often. Makes more sense now!
Best explanation so far from all the content on internet.
This was such simple and clear explanation of complex subject. Thanks Marina :)
Amazing explanation. Starting from scratch and gained great perspective on this in a very short time.
That's what Knowledge graphs are for, to keep LLMs grounded with a reliable source and up-to-date.
I really like the analogy from the beginning! It was very smooth explanation! Well done!
Very well explained and it is easily understandable to non AI person as well. Thanks.
The entire video I've been wondering how they made the transparent whiteboard
Very precise and exact information on RAG in a nutshell. Thank you for saving my time.
Did all the speakers have to learn how to write in a mirrored way or is this effect reached by some digital trick?
There is a digital mirroring technique which is used to show the content this way...
She was right handed before the mirror effect
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
This was explained fantastically.
Brilliant explanation and illustration. Thanks for your hard work putting this presentation together.
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?
Great, simple, quick explanation
Thank you, Marina Danilevsky ....
perfect explanation understood every bit , no lags kept it very interesting ,amazing job
Thats one of the best explaination I have got so far ! Thanks a ton !
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?
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?
Great explaination. It's very helpful for my project a GEN Ai intern
very well executed presentation.
i had to think twice about how you can write in reverse but then i RAGed my system 2 :)
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 :)
This is the best explanation I have seen so far for RAG! Amazing content!
Fantastic explanation, proud to be an IBMer
Finally, we got a clear explanation!
Please keep all these videos coming! They are so easy to understand and straightforward. Muchas gracias!
Thanks Marina !!! For that such a simple explanation on such a complex topic !!!
I love how she colored the "om" in "prompt" to visually emphasize that the factual grounding data is now inside the prompt @4:21
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?
You’re an amazing teacher.
An amazing explanation that made RAG understandable in about 4:23 minutes!
That's the best video about RAG that I've watched
good explanation, it's very easy to understand. this video is the first one when I search RAG on TH-cam. great job ;)
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
The ability to write backwards, much less cursive writing backwards, is very impressive!
See ibm.biz/write-backwards
Left hand too!
@@IBMTechnology Thanks .... I was reading comments to check for an answer for that question!
I have watched many IBM videos and this is the undoubtedly the best ! I will be searching for your videos now Marina!
In one 6 minute video, the presenter identifies the largest problem and a practical solution to using Gen AI in the Enterprise 👍
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
Pretty simple explanation, thank you
outstanding explenation and lecturer! Well done!
the color coding on your whiteboard is really apt here !
I have a question, so for these RAG models, is it possible to have them in local? Like download my model and read the data from my computer or so, or is it somethin we have to have in the cloud always running?
That was excellent, simple, and elegant! Thank you!
Exactly what I was trying to understand, great explanation!
Best explanation ever
She's writing in mirror reverse, that is so impressive!
Все толково, четко и понятно. Респект автору.
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
well done, thanks!
that reverse writing made be anxious, but a very smart explanation for RAG!!
This is a great explanation. Thank you
Great explanation with an example. Thank you
AWESOME EXPLANATION OF THE CONCEPT RAG
Very clear explanation, much respect 🫡
Great example using space, which we nerds love.
RAG combines the generative power of LLMs with the precision of specialized data search mechanisms, resulting in nuanced and contextually relevant responses.
Great explanation of RAG. Thank you
Such an amazing explanation. Thank you ma'am!
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
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.
wow this was an amazing Explanation ,very easy to understand
Thank you for such a great explanation.
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?
Yes, I think that's what she also implied.