What is Retrieval-Augmented Generation (RAG)?
Vložit
- čas přidán 7. 05. 2024
- Try RAG with watsonx → ibm.biz/BdMsRT
Learn more about RAG→ ibm.biz/BdMsRt
Large language models usually give great answers, but because they're limited to the training data used to create the model. Over time they can become incomplete--or worse, generate answers that are just plain wrong. One way of improving the LLM results is called "retrieval-augmented generation" or RAG. In this video, IBM Senior Research Scientist Marina Danilevsky explains the LLM/RAG framework and how this combination delivers two big advantages, namely: the model gets the most up-to-date and trustworthy facts, and you can see where the model got its info, lending more credibility to what it generates.
Get started for free on IBM Cloud → ibm.biz/sign-up-now
Subscribe to see more videos like this in the future → ibm.biz/subscribe-now
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!
IBM should start a learning platform. Their videos are so good.
i think they already do
Yes, they have it already. CZcams.
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
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!
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
4:15 Marina combines the colors of the word prompt to emphasis her point. Nice touch
Very well explained!!! Thank you for your explanation of this. I’m so tired of 45 minute CZcams 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 love seeing a large company like IBM invest in educating the public with free content! You all rock!
Loved the simple example to describe how RAG can be used to augment the responses of LLM models.
The entire video I've been wondering how they made the transparent whiteboard
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?
Wow, this is the best beginner's introduction I've seen on RAG!
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!
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
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
Please keep all these videos coming! They are so easy to understand and straightforward. Muchas gracias!
One of the easiest to understand RAG explanations I've seen - thanks.
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
For me, this is the most easy-to-understand video to explain RAG!
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 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!
Great explanation. Even the pros in the field I have never seen explain like this.
This video is highly underviewed for as informative as it is!
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.
This is the best explanation I have seen so far for RAG! Amazing content!
Great video as always. Thanks for sharing.
Good Explanation of RAG. Thanks for sharing.
I have watched many IBM videos and this is the undoubtedly the best ! I will be searching for your videos now Marina!
Brilliant explanation and illustration. Thanks for your hard work putting this presentation together.
Such an amazing explanation. Thank you ma'am!
Thanks for letting us know about this feature of LLM :)
Great video. Thanks for sharing
Very precise and exact information on RAG in a nutshell. Thank you for saving my time.
Great video, you guys should do one on promising tech industries
perfect explanation understood every bit , no lags kept it very interesting ,amazing job
Pretty simple explanation, thank you
Great, simple, quick explanation
That's what Knowledge graphs are for, to keep LLMs grounded with a reliable source and up-to-date.
Great explanation! The video was very didactic, congratulations!
Marina has done a great job explaining LLM and RAGs in simple terms.
Wow, having a lightbulb moment finally after hearing this mentioned so often. Makes more sense now!
That was excellent, simple, and elegant! Thank you!
Best explanation so far from all the content on internet.
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
very well executed presentation.
i had to think twice about how you can write in reverse but then i RAGed my system 2 :)
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!
Great down the rabbit hole video. Very deep and understandable. IBM academy worthy in my opinion.
Appreciate the succinct explanation. 👍
Super good and clear, well done!
Great explanation with an example. Thank you
Great explanation. Thank you!😊
Fantastic video and explanation. Thank you!
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 :)
Awesome explanation. Love you.
This was such an amazing explanation!
Amazing video, thanks IBM ❤
An amazing explanation that made RAG understandable in about 4:23 minutes!
Very Helpful! Great explanation. thx IBM
Very clear explanation, much respect 🫡
This is so well explained! Thank you 👍🏻✅
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?
Thank you for such a great explanation.
Fantastic explanation, proud to be an IBMer
AWESOME EXPLANATION OF THE CONCEPT RAG
Insightful, please more video like this
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
Great video, excellent explanation!
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?
Beautifully explained....thanks
nice video - great explanation!
Excellent explanation!
Great explanation!
This was explained fantastically.
This is a fantastic lesson video.
This is excellent and I hope IBM does well in this space. We need a reliable, non-hype vendor.
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
Amazing explanation! Thank you:)
wow this was an amazing Explanation ,very easy to understand
*Excellent* explanation, you gave me all the key concepts in one shot.
I gather that the retrieval could be in various forms, for instance a vector database in addition to direct text from internet searches?
a RAG target can be any associated data store (PDF repo, Sharepoint, Google Drive,..) that can be accessed via a query - the LLM has a semantic understanding of the prompt and the queries are the output of the LLM
That's the best video about RAG that I've watched
Excellent ! thank you for sharing this knowledge !
Nicely explained 👍
The explanation was very good 💯.
Thank you Marina, very helpful and informative video. One question I have is; how do you make these videos like this? Being able to on a screen facing the camera, this is great. What's your secret?
Sometimes these are done on transparent "whiteboards" and the video is then flipped horizontally.
czcams.com/video/eVOPDQ5KYso/video.htmlsi=LADnROL0SF33Hg54
See ibm.biz/write-backwards
@@IBMTechnology okay now i get it !!!
IBM should hire left hand writers so it will right handed after flip 😊
Excellent explanation. thx
This is a really good video thank you for sharing this knowledge
Thank you, Marina Danilevsky ....
Thank you for these videos. Makes it much easier to nagivate this new AI-ra of machine learning.
Love this! How is she writing on the glass? Is she writing backward? Or how does that work?
See ibm.biz/write-backwards
Lol, so simple when explained@@IBMTechnology, thanks I can actually pay attention to what she's saying now 😆
thank you. very informative!
How do you built the connector from LLM to external sources? Usually a foundation model is frozen.
Langchain
In it's simplest form, you can just copy paste the external source into the prompt. Python is a way to automate that.
Amazing work. Thanks for sharing this.
very well explained!
the color coding on your whiteboard is really apt here !
thanks for the great explanation
very good and clear explanation
Love the neon markers, also the content of course
Very well explained 🙏🏼👍
Все толково, четко и понятно. Респект автору.
RAG combines the generative power of LLMs with the precision of specialized data search mechanisms, resulting in nuanced and contextually relevant responses.