Our RAG live course is coming up soon, and as a way of giving back to our amazing community, we're offering you 15% off. Just use this link: maven.com/angelina-yang/mastering-rag-systems-a-hands-on-guide-to-production-ready-ai?promoCode=TwoSetAI We'd love to see you there! 🎉 In the course, you'll have the chance to connect directly with Professor Mehdi (just like I do 😉 in the videos), and you can even ask him your questions 1:1. Bring your real work projects, and during our office hours, we'll help you tackle your day-to-day challenges. This course is for: 01 👇 𝗔𝗜 𝗘𝗻𝗴𝗶𝗻𝗲𝗲𝗿𝘀 & 𝗗𝗲𝘃𝗲𝗹𝗼𝗽𝗲𝗿𝘀: For AI engineers/developers looking to master production-ready RAG systems combining search with AI models. 02 👇 𝗗𝗮𝘁𝗮 𝗦𝗰𝗶𝗲𝗻𝘁𝗶𝘀𝘁𝘀: Ideal for data scientists seeking to expand into AI by learning hands-on RAG techniques for real-world applications. 03 👇 𝗧𝗲𝗰𝗵 𝗟𝗲𝗮𝗱𝘀 & 𝗣𝗿𝗼𝗱𝘂𝗰𝘁 𝗠𝗮𝗻𝗮𝗴𝗲𝗿𝘀: Perfect for tech leads/product managers wanting to guide teams in building and deploying scalable RAG systems
Amazing video! A followup question: regarding the judge who decide 0 or 1, what if the judge is incorrect? Any methods about how can we make this role robust enough? Thx!
Great question! Your judge should be really capable i.e. GPT4o or specialized LLM models for this task. However, even they could potentially make mistakes. Even if judge does miss, what is the worst that can happen? it does an online search and use it to answer the question. So nothing bad will happen. That said, You must evaluate your judge decisions and improve it if necessary!
Yay, thanks for putting this forward. I would love to do the course but my time is very chopped up and I wouldn't have time to dedicate to a cohort and deal with strict time bound deliverables. But I would happily buy in and follow the material as time permits. Is that possible?
@@kenchang3456 welcome welcome! We got similar feedbacks so we will roll out a shorter and more dedicated to pain point solving version, perhaps just 1 weekend of your time
as an end user, my personal ambition is to build an agentic rag system capable of digesting a full library upon a theme, so maybe a little library can be 10 books from 200 to 500 pages each one. Right now I understand the logic you are exposing, I'm very far from achieving this, but will persevere. as far as I understand my agent has to answer only using my curated library, I'm thinking about other functions it can solve. thanks for your work. this is going very fast, or too slow depending how you look at it. do you need feedback from end users like me? do you build a community to achieve feed backs between coders and needers? thanks again.
@@TwoSetAI I will identify function needs I believe agents have to deal whith to achieve this goal and come back to you, the logic of the system must obey end user's needs, so the logic should be how can it helps to provide what users needs : learning and integrating knowledge into their life. so if learning is one of the keys, I really can't answer how to structure an agent logic in just one message, neither a single brainstorming session can resolve this as it has been studied and structured in deep dive books before, but we can't have access to the accurate bookstore at any moment, can we? ( ideally ), what I need is to identify functions to fulfill the needs. and curating a library also depends of the need maybe, I don't know yet. Thanks for answering and for your work.
Our RAG live course is coming up soon, and as a way of giving back to our amazing community, we're offering you 15% off. Just use this link: maven.com/angelina-yang/mastering-rag-systems-a-hands-on-guide-to-production-ready-ai?promoCode=TwoSetAI
We'd love to see you there! 🎉
In the course, you'll have the chance to connect directly with Professor Mehdi (just like I do 😉 in the videos), and you can even ask him your questions 1:1. Bring your real work projects, and during our office hours, we'll help you tackle your day-to-day challenges.
This course is for:
01 👇
𝗔𝗜 𝗘𝗻𝗴𝗶𝗻𝗲𝗲𝗿𝘀 & 𝗗𝗲𝘃𝗲𝗹𝗼𝗽𝗲𝗿𝘀: For AI engineers/developers looking to master production-ready RAG systems combining search with AI models.
02 👇
𝗗𝗮𝘁𝗮 𝗦𝗰𝗶𝗲𝗻𝘁𝗶𝘀𝘁𝘀: Ideal for data scientists seeking to expand into AI by learning hands-on RAG techniques for real-world applications.
03 👇
𝗧𝗲𝗰𝗵 𝗟𝗲𝗮𝗱𝘀 & 𝗣𝗿𝗼𝗱𝘂𝗰𝘁 𝗠𝗮𝗻𝗮𝗴𝗲𝗿𝘀: Perfect for tech leads/product managers wanting to guide teams in building and deploying scalable RAG systems
Really, well explained. Thanks Sir !!
Glad you found it helpful!
Awesome video! I learned a lot, thank you.
We’re glad you liked it!
Awesome video as usual. Can't wait to do the course.
The course is already out. here's the link:
maven.com/angelina-yang/mastering-rag-systems-a-hands-on-guide-to-production-ready-ai
Amazing video! A followup question: regarding the judge who decide 0 or 1, what if the judge is incorrect? Any methods about how can we make this role robust enough? Thx!
Great question! Your judge should be really capable i.e. GPT4o or specialized LLM models for this task. However, even they could potentially make mistakes. Even if judge does miss, what is the worst that can happen? it does an online search and use it to answer the question. So nothing bad will happen. That said, You must evaluate your judge decisions and improve it if necessary!
Yay, thanks for putting this forward. I would love to do the course but my time is very chopped up and I wouldn't have time to dedicate to a cohort and deal with strict time bound deliverables. But I would happily buy in and follow the material as time permits. Is that possible?
@@kenchang3456 welcome welcome! We got similar feedbacks so we will roll out a shorter and more dedicated to pain point solving version, perhaps just 1 weekend of your time
as an end user, my personal ambition is to build an agentic rag system capable of digesting a full library upon a theme, so maybe a little library can be 10 books from 200 to 500 pages each one. Right now I understand the logic you are exposing, I'm very far from achieving this, but will persevere. as far as I understand my agent has to answer only using my curated library, I'm thinking about other functions it can solve. thanks for your work. this is going very fast, or too slow depending how you look at it. do you need feedback from end users like me? do you build a community to achieve feed backs between coders and needers? thanks again.
@@airebreton yes happy to chat. Please leave a message any time or email me at angelina@oscr.tech. Thanks!
@@TwoSetAI I will identify function needs I believe agents have to deal whith to achieve this goal and come back to you, the logic of the system must obey end user's needs, so the logic should be how can it helps to provide what users needs : learning and integrating knowledge into their life. so if learning is one of the keys, I really can't answer how to structure an agent logic in just one message, neither a single brainstorming session can resolve this as it has been studied and structured in deep dive books before, but we can't have access to the accurate bookstore at any moment, can we? ( ideally ), what I need is to identify functions to fulfill the needs. and curating a library also depends of the need maybe, I don't know yet. Thanks for answering and for your work.
Excellent tutorial , and in very informative and simple language, can you please share the code with us.
Thank you! Here's the code: github.com/mallahyari/twosetai/blob/main/13_agentic_rag.ipynb
Its in the video description now!
Excellent explanation thx ! :)
Thanks for sharing great explanation on Agentic AI
Amazing video
this kind of teacher we need rather who teach abscration plz make more video on complex topics with is man tq
Thanks for your feedback! Glad you enjoyed the video.