@sivi3883
Best 15 mins of my day! You explained every single component in the code clear and crisp! Excited to check the other videos of yours. Thanks a bunch
@fuba44
UniqueList = list(set(ListWithDuplicates)) to replace those nested for loops. Love your content!
@henkhbit5748
Very informative.👍 Love the umap visualization 2 see the query and the embeddings.
@Pure_Science_and_Technology
Thanks for the video. Perfect timing…. Need this for tomorrow.
@roguesecurity
This channel is a gem 💎
@codewithbrogs3809
This is GREAT!!!
@samyio4256
Youre vids are insanely good. I doubt there is a better ai-prog-tuber
@vegansinnigeunterhaltung
In the images you complain that the similarity search return dots too far away from the Red Cross, the problem imho is the umap projection, maybe it would be different had you calculated the umap projection with the queries included; the projection down from 1024 components to two might loose some important details, so have you manually inspected the allegedly incorrect similarity search results?
@felipecordeiro8531
I don't know the umap library, its very interesting. Good explanation about RAG advanced techniques, sucess for you!
@philgalebach3294
really really good video. best I've seen
@kenchang3456
This video is terrific, I'll give it a try!
@austinpatrick1871
Awesome video. So I glad I found this channel. Long shot question: After testing several chunk/overlaps, my experimentation indicates an optimal chunk_size=1000 and overlap=200. My RAG contains about 10 medical textbooks (~50,000 pages). However, every video I see on RAG nobody uses chunks anywhere near that large. Does it seem improbable that my ideal chunk size is 1,000, or is there likely another variable at play?
@StnImg
Can u please make a video on retrieving data from SQL using SQL agents & Runnable using LCEL. If not possible here, if you can update the same in the udemy course. It helps alot
@micbab-vg2mu
Thank you for the great video:)
@maxlgemeinderat9202
Thank, always nice videos! Do you have a favorite german cross-encoder?
@verybigwoods
How much computation resource (specifically GPU) required in running this cross encoder model?
@andreypetrunin5702
Спасибо!!
@vinaychitturi5183
Thanks for the video.. But while genering queries using llm_chain.invoke(query), facing exception related to output parser. OutputParserException: Invalid json output:
@erenbagc9164
What's the best way to evaluate this RAG?
@MaazBhatti-g8t