RAGAS - Evaluate your LangChain RAG Pipelines

No video

RAGAS - Evaluate your LangChain RAG Pipelines

Рет қаралды 7,710

Coding Crash Courses

Күн бұрын

Пікірлер: 30

@mosheragomaa5544 2 ай бұрын

So simple, helpful and clear! Very interesting. Thanks for the video

@seallyolme 4 ай бұрын

This is awesome! Great and clear video :)

@M10n8 5 ай бұрын

Excellent timing ;-) Thanks for video

@user-we3qo9kj4q 5 ай бұрын

Bro is on fire this month!

@codingcrashcourses8533 5 ай бұрын

You guys give me so many requests on topics 😀

@user-we3qo9kj4q 5 ай бұрын

@@codingcrashcourses8533 i was, i am and i will support you till the end. Ur videos helped my sooooooooooo much.

@maxlgemeinderat9202 5 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

@codingcrashcourses8533 5 ай бұрын

yes, it´s still far away from perfect, but good that frameworks like these are developed

@nguyenquynghia9755 2 ай бұрын

I switched to using RecursiveCharacterTextSplitter, but my context relevance is still low. Do you know why?

@Challseus 5 ай бұрын

Another banger! :)

@robertputneydrake 5 ай бұрын

Nice, Meister! Machste irgendwann das Thema Code RAG ggf. mit Knowledge-Graphen?

@codingcrashcourses8533 5 ай бұрын

Currently no plans on working with knowledge graphs, since I don´t have experience with these. But maybe in the future :)

@mohammed333suliman 2 ай бұрын

Great video , thank you

@codingcrashcourses8533 2 ай бұрын

thank you for your comment :)

@alexandershevchenko4167 5 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

@codingcrashcourses8533 5 ай бұрын

Maybe in a few weeks

@andreypetrunin5702 5 ай бұрын

Огромное спасибо за видео!!

@GenerativeAI-Guru 5 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

@codingcrashcourses8533 5 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-Guru 5 ай бұрын

@@codingcrashcourses8533 thanks

@maxlgemeinderat9202 5 ай бұрын

you could also calculate the RAGAS score which is the mean across all metrics

@doggydoggy578 16 күн бұрын

Does this need an open ai key ? i have zero in my account

@codingcrashcourses8533 16 күн бұрын

@@doggydoggy578 yes

@doggydoggy578 16 күн бұрын

@@codingcrashcourses8533 did you mention this in this video ? i think it's super important

@doggydoggy578 8 күн бұрын

@@codingcrashcourses8533 very nice, not at all an important detail to conveniently leave out

@fire17102 5 ай бұрын

It's there an ai pipeline to auto optimize the rag quality? Seems like the obvious next step... Great video 🙏👍

@codingcrashcourses8533 5 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.

@fire17102 5 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