RAG is just 'full text indexing' on the local data with the ranked results fed into the context window and sent to the LLM along with the question. Every time I see it described as something of a database guy for the last 30 years all I see are new words describing long solved problems.
@rajeshbasnet4454
5 ай бұрын
You mean like how elastic search does indexing ?
@ahmedzouaoui8177
4 ай бұрын
Well new cars have wheels which is a technology that has thousands of years of existence. It does not mean that new cars are 'obsolete' but using an old tech to improve a new one is a great way of doing engineering !
@mahiaravaarava
Ай бұрын
AI algorithms facilitate better decision-making in business by providing actionable insights from data analysis.This enhances strategic planning and operational efficiency.
@finn_the_dog
8 ай бұрын
Great video. Would you make a video the different types of RAGs? Or how to prepare data for a RAG, for example when your document has tables, math formulas, references to images, I haven't seen much content about how to handle diverse data inside a document with RAGs. Cheers
@WhatsAI
8 ай бұрын
Great idea, thank you! Will definitely look into multi modal RAG! :)
@MK-ce7im
6 ай бұрын
I think this is the best video I have seen on this topic. Wanted to ask if we can use RAG offline maybe with Mistral model ?
@WhatsAI
6 ай бұрын
Of course you can host everything locally if you have the capacity! :)
@KEMBL
2 ай бұрын
What happens to the information received from the RAG if the original request already occupies the entire context window?
@WhatsAI
2 ай бұрын
It depends on the code implementation of the system! Most will put in place a system to detect it and summarize or extract key points to make it shorter.
@smritisrinivas7885
3 ай бұрын
Wow. Thanks a lot for this amazing explanation
@PriM-z2k
8 ай бұрын
Now I understood, What is RAG - Retrieval Augmented Generation ,Very Informative Video, Liked your Video 👍
@Parsley1965
7 ай бұрын
Truly excellent video!
@bhanujinaidu
5 ай бұрын
Thanks , very clear excellent explanation
@WhatsAI
5 ай бұрын
Thank you! :)
@JavierTorres-st7gt
3 ай бұрын
How to protect a company's information with this technology?
@sabriboubaker
7 ай бұрын
Great video, straight to the point. Thanks again
@WhatsAI
7 ай бұрын
Thank you Sabri! :)
@rhans6598
7 ай бұрын
Thanks but what's the point of sound effects?
@helainz7198
4 ай бұрын
Et cetera bien sur mon poto
@Plink2120
8 ай бұрын
Vraiment clair et précis merci
@Kama45
4 ай бұрын
Subbed
@martinkrueger937
6 ай бұрын
by any chance do you know which RAG system/framework is giving out the best performance?
@WhatsAI
6 ай бұрын
From our work we like to use llamaindex for many parts and adapt on our own code for more personalized settings!
@chairwood
8 ай бұрын
thx. i enjoyed this video
@WhatsAI
8 ай бұрын
Glad to hear so my friend! 😊
@Mr_Arun_Raj
8 ай бұрын
After integrating with RAG. latency increased....
@WhatsAI
8 ай бұрын
That is for sure! There is some downsides but the latency if very little.
@paulwillisorg
5 ай бұрын
The accent of the speaker is pretty heavy.
@WhatsAI
5 ай бұрын
Hope it’s still easy to understand!
@kunjs
7 ай бұрын
google launched gemini advanced 1.5, a RAG killer 💀
@WhatsAI
7 ай бұрын
A database can be much larger than this context window and much more efficient I believe. It’s unsure how good the models are vs gpt4 yet. Plus, sending millions of tokens for every prompt will be extremely expensive for each request, haha! It’s good for some use cases like sending a full repo once and asking questions but not for working with customers and handling many requests I believe.
Пікірлер: 33