I am working on RAG systems for my master thesis. Thank you for this video. really thank you!
@codingcrashcourses853325 күн бұрын
You´re welcome. On my channel I have more RAG videos and I also offer an Advanced RAG course on Udemy :)
@mosheragomaa55445 ай бұрын
So simple, helpful and clear! Very interesting. Thanks for the video
@M10n87 ай бұрын
Excellent timing ;-) Thanks for video
@MMO-g2w7 ай бұрын
Bro is on fire this month!
@codingcrashcourses85337 ай бұрын
You guys give me so many requests on topics 😀
@MMO-g2w7 ай бұрын
@@codingcrashcourses8533 i was, i am and i will support you till the end. Ur videos helped my sooooooooooo much.
@Challseus7 ай бұрын
Another banger! :)
@andreypetrunin57027 ай бұрын
Огромное спасибо за видео!!
@maxlgemeinderat92027 ай бұрын
Nice one! Also a big fan of RAGAS, however there are still many bugs that come with RAGAS, especially when trying to evaluate with local llms
@codingcrashcourses85337 ай бұрын
yes, it´s still far away from perfect, but good that frameworks like these are developed
@mohammed333suliman5 ай бұрын
Great video , thank you
@codingcrashcourses85335 ай бұрын
thank you for your comment :)
@robertputneydrake7 ай бұрын
Nice, Meister! Machste irgendwann das Thema Code RAG ggf. mit Knowledge-Graphen?
@codingcrashcourses85337 ай бұрын
Currently no plans on working with knowledge graphs, since I don´t have experience with these. But maybe in the future :)
@alexandershevchenko41677 ай бұрын
Thank you for the video! Yeah, It will be really intereseting to know how to perform RAGAS in CI/CD pipline. Can you record video for this one please? Will be really helpful
@codingcrashcourses85337 ай бұрын
Maybe in a few weeks
@GenerativeAI-Guru7 ай бұрын
I was waiting for this thank you so much, is it possible to add how to evaluate accuracy using F1 scoring or other methods
@codingcrashcourses85337 ай бұрын
Not out of the box, F1 scores can be easily caculated with pandas (to_pandas) like this: F1 = 2*precision*recall/(precision+recall)
@GenerativeAI-Guru7 ай бұрын
@@codingcrashcourses8533 thanks
@maxlgemeinderat92027 ай бұрын
you could also calculate the RAGAS score which is the mean across all metrics
@kumarrajaakula9064Ай бұрын
I want to know one thing that even the ground truth is generated by an LLM, how can we determine whether it is correct for a particular query?
@codingcrashcourses8533Ай бұрын
You probably want to create your own dataset for that. I also dont want the llm to define a ground truth
@nguyenquynghia97554 ай бұрын
I switched to using RecursiveCharacterTextSplitter, but my context relevance is still low. Do you know why?
@fire171027 ай бұрын
It's there an ai pipeline to auto optimize the rag quality? Seems like the obvious next step... Great video 🙏👍
@codingcrashcourses85337 ай бұрын
You probably would have to build something like that on your own, since there are so many ways how a pipeline could look like. You could also work on your prompt and so on.
@fire171027 ай бұрын
@@codingcrashcourses8533 I'd always want to manually make changes I think are best, but I'd still like to see a full matrix of hyperperameters to remove alot of the guess work. Chunk size for example. More over I'd like to benchmark everything and add scoring functions. For example a score for fact checking - see Lucidate's last video. And also IndyDevDan last video battle royal of models, I suggested to combine it with something like you do with rag params and what I suggest for full pipeline benchmark with ai suggested optimization
@doggydoggy5782 ай бұрын
Does this need an open ai key ? i have zero in my account
@codingcrashcourses85332 ай бұрын
@@doggydoggy578 yes
@doggydoggy5782 ай бұрын
@@codingcrashcourses8533 did you mention this in this video ? i think it's super important
@doggydoggy5782 ай бұрын
@@codingcrashcourses8533 very nice, not at all an important detail to conveniently leave out