@parth_pm16
Best part of this video: 1. The start of the video clears the thought of why the "Augmented Generation" is required. 2. Drawing while explaining 3. Example during the explanation 4. Pros and Cons 5. Q&A at the end of the video (FunFact: I got all the correct answers) I appreciate making great learning videos! 🙏 Much better than other Tech YouTubers.
@HardcoreFixation
Great video and a fantastic presenter, very clear and helpful - thanks!
@vishalmishra3046
Great job asking questions at the end. Validating what we learned from the video (esp. any new knowledge that we did not know earlier) makes the videos all the more fulfilling.
@ravisinghshare
Very good video. Explains the working of RAG and CAG beautifully and also compared it across 4 parameters.
@emcquesten
You're a great teacher. Thank you for this 🙏🏽
@neelshah1651
Amazing Explanation
@ivozlatanov8084
By far the best and most down-to-earth explanation of these complex concepts
@jeffg4686
CAG + RAG seems like a WINNING combo. WINNERS!!!
@wantstofly86
When speaking about accuracy, I think it's important also to mention that larger context window usually decrease the Model accuracy because it tends to remember mainly the beginning and the end of the context. So with CAG, growing your knowledge DB will impact negatively the accuracy of the LLM model, while with RAG it remains constant. And also there is price that grows with the context windows... In my opinion the only good reason to go with CAG is simplicity of implementation. Building a good RAG system can be quite complex, but CAG is very simple and straight forward. For a MVP or a simple product CAG might do the job.
@markrodnoy
Great video. Loved the game at the end. Thanks!
@scottyb3b7
A downside of leaning on a massive context window is that transformer architectures have a thing called quadratic complexity: every time you double the tokens the resources (like GPUs) can go up 4X. Plus, long context windows tend to forget the middle of their context. So, use the right tools for the right job....one more gotcha, the data that is pulled in for a specific conversation is only germane to THAT 'conversation.' So, other users - and often other conversations by that first user - do not benefit from either RAG or CAG - at least not out of the box. So, the notion of fine-tuning/training the model on the newer/needed data could be on an option. BUT, you then change the core model(s) - and maybe have a library of models and their versioning to manage => more LLMOps.
@--tsatsa--
Just the what I was looking for. Thank you! :)
@NeoStarImpact
Great presentation. I knew the concepts from experience with llms but had no words for it or the exact detail. So this was helpful to put stuff into perspective.
@r.in.shibuya
IBM is lucky to have you Martin!
@SimonBransfieldGarth
You guys always explain things very clearly!
@nopopacz
Best explanation ever. Thank you!
@farhanprine
Absolutely love imagery for describing these flows. Wonderfully broken down into simplified explanations. Love your work. Keep it up!
@emphieishere
Thanks for such an informative yet laconical video!
@Christine_
This is literally the funnest and most engaging video on this topic I have ever seen. And I've only seen one. Im not technical at all by the way!
@saratpoluri