Nice outline and love your way of delivery 🎉. But honestly speaking your course price is high. You may cosider udemy platform as well to publish your course with a discounted price. Wish you good luck.
Will this course help me understand how to use like for eg using 200k files rather than just using just 1 or 2 pdf examples, which we get on all youtube videos(naive RAG)
The concepts will help you build better RAG systems. The focus is on RAG techniques and algorithms. I do not cover the data pre-processing part since that is going to be application specific but will be critical to any information retrieval system.
I would like to join the course, funny how I wasn't aware of this until now. That being said, the price is quite high for me. I am not a student but the startup I was working for did shut :) hence it's not possible for me to invest 200 bucks....
Thanks, this does sound v tempting and v interesting - congrats on putting this together. It would have been helpful to have had a brief demonstration of the best version of the solution that you have put together. ie does this really work in practice on real research type problems that we encounter, covering hundreds of documents and being able to ask complex questions requiring inputs from multiple documents (as opposed to the typical "who is the president of the US"-type questions that we see on so many other videos of RAG demos). Also, assuming it can do such tasks, what is the average run cost of a typical query, as obviously there are ways of simply cramming the context window with massive chunks of text to the extent that each query costs a fortune). Lastly, kudos for offering to maintain the content over a period as it does seem like the market is changing v quickly in this space.
This is a valid point. I am going to see what I can add there. At the moment, the goal is to cover topics beyond basics and enable the user to build robust applications for retrieval. The course does not cover agentic RAG, something that I a thinking to adding in near future. We do cover reranking techniques that can help you reduce the context that is sent to the LLM hence cost reduction but I think it will be good to add something on the cost of running these LLMs. These are really good points that will help improve the content. It was one of the goals to get feedback and improve it further. Thanks for sharing.
Hi I saw your comment and I was wondering if you could elaborate a little bit. When you say you are interested in ai but not in RAG, can you expand on what type of AI you're interested in.
Thank you for dedicating your time and sharing your knowledge. I'm Brazilian, and I don't speak fluent English, but here I haven't found a course in my language as rich in knowledge as yours.
Interesting, and I am prolly going to drop $ the for this course. The only thng holding me back is..... where are the vector stores. I really like your approach to 'local' for everyone, and tell everyone I know interested in local AI to look at your channel ....... but I don't want to be pointed at 'cloud based' vector stores that use pg-vector plugin extension .....when Postgres is already free, open source, and what the plugin (pg-vector) plugs into. That's the 'decider' for spending $200. Do we get pointed back at something like Pincecone, when postgres running locally overly fits the bill with the very. Same. Technolgy, sans giving our data to Pinecone (ect ilk) and paying them a fee, when I can run the same postgres faster from the Desktop. Are you pointing people (with code) to cloud based vector store, or pointing out the same free version of it on the desktop? It really matters when developing a flow. I'd like an answer to that before spending $200 Other than that, keep doing what you do. It's great.
glad you are finding the content helpful. As for the vectorstore, I use chroma in the course, so everything is local. The goal is to introduce concepts and explain them in a way that everyone can understand. Choice of tools is really a matter of application you are building. Hope you will find the course helpful as well.
@@engineerprompt Right on dude. I just mentioned you to someone earlier and that you 'build' as opposed to some of the other youtubers that will generate kitten images with a $150 million model :) I think 'where and what' is being used for RAG right now is being more looked at. And While I 'DO' respect the ones like you that will still slide paid promos for AI services....... You still have to eat. I get that. Eat well, youj earned it. Chroma is cool. I see fragmentation in this early AI goldrush, and part of this is some of the influencers always trying to wrap a critical componenent like RAG or hosting ...... to do something that can be done locally..... I get it. People have to eat :) But a paid course, is why I asked. I just want to know thats what I am getting. You should 'Udemy' man. Are you doing anything with 'geocoded' embeddings in the future?There's a 'Vector Databasing with DuckDB on Top of PGVector' medium article out there that is pretty interesting.
@@engineerprompt additionally, if I may, when you said 'The goal is to introduce concepts and explain them in a way that everyone can understand'......that last 'Phi' model update, Microsoft said what made the model so great was feeding it cleaner data. Some of the approaches to 'chunking' over simplify how it should be used on different data content types.
First of, thanks for all the great content ! Any plans for a nodejs version of this course ?
thanks, I dont' have nodejs experience but might be able to convert the code with Claude's help :)
let me see what I can do.
Joined already 🎉 just hope that you will keep the content updated with today’s dynamic AI landscape
Great, please let me know if there are questions or suggestions. Will keep adding more updates there.
Nice outline and love your way of delivery 🎉.
But honestly speaking your course price is high.
You may cosider udemy platform as well to publish your course with a discounted price.
Wish you good luck.
Same price is very much high
Exactly. The course is awesome and very useful. However, the price is too high for me. I really wish for a discount.
thank you for kind words. If the price is too high, email me and let's see what we can do :)
Will this course help me understand how to use like for eg using 200k files rather than just using just 1 or 2 pdf examples, which we get on all youtube videos(naive RAG)
The concepts will help you build better RAG systems. The focus is on RAG techniques and algorithms. I do not cover the data pre-processing part since that is going to be application specific but will be critical to any information retrieval system.
Just enrolled...happy that i did.... Half way through already.....
Awesome, let me know if you have any questions or things that I can improve on!.
I really want to take this course, but as a student, it's quite expensive.
Email me
I would like to join the course, funny how I wasn't aware of this until now. That being said, the price is quite high for me. I am not a student but the startup I was working for did shut :) hence it's not possible for me to invest 200 bucks....
email me, would love to help here.
@@engineerprompt what’s your email id
I would love to buy the course. I'll be paying by Indian credit card. Can I get a discount?
@@ajaytaneja111 I haven’t received his email yet :(
@@ajaytaneja111 please email me
Thanks, this does sound v tempting and v interesting - congrats on putting this together.
It would have been helpful to have had a brief demonstration of the best version of the solution that you have put together. ie does this really work in practice on real research type problems that we encounter, covering hundreds of documents and being able to ask complex questions requiring inputs from multiple documents (as opposed to the typical "who is the president of the US"-type questions that we see on so many other videos of RAG demos).
Also, assuming it can do such tasks, what is the average run cost of a typical query, as obviously there are ways of simply cramming the context window with massive chunks of text to the extent that each query costs a fortune).
Lastly, kudos for offering to maintain the content over a period as it does seem like the market is changing v quickly in this space.
This is a valid point. I am going to see what I can add there. At the moment, the goal is to cover topics beyond basics and enable the user to build robust applications for retrieval. The course does not cover agentic RAG, something that I a thinking to adding in near future.
We do cover reranking techniques that can help you reduce the context that is sent to the LLM hence cost reduction but I think it will be good to add something on the cost of running these LLMs. These are really good points that will help improve the content. It was one of the goals to get feedback and improve it further. Thanks for sharing.
Will you add this to Udemy?
No plans for that at the moment. Might do that later depending on if there is interest.
Good luck i would like to learn about AI but not RAG maybe next course :)
Hi I saw your comment and I was wondering if you could elaborate a little bit. When you say you are interested in ai but not in RAG, can you expand on what type of AI you're interested in.
Would be interested in what specific topics related to AI you are thinking about?
Thank you for dedicating your time and sharing your knowledge. I'm Brazilian, and I don't speak fluent English, but here I haven't found a course in my language as rich in knowledge as yours.
glad you found this helpful.
You misspelled "Annoucement".
Good catch, thanks for pointing it out
He Mervin, when do will you make a course about memgpt and oobabooga, connecting silly tavern ;)
Not sure who Mervin is :D
@@engineerprompt haha sorry.... wrong channel :)
Interesting, and I am prolly going to drop $ the for this course. The only thng holding me back is..... where are the vector stores. I really like your approach to 'local' for everyone, and tell everyone I know interested in local AI to look at your channel ....... but I don't want to be pointed at 'cloud based' vector stores that use pg-vector plugin extension .....when Postgres is already free, open source, and what the plugin (pg-vector) plugs into.
That's the 'decider' for spending $200. Do we get pointed back at something like Pincecone, when postgres running locally overly fits the bill with the very. Same. Technolgy, sans giving our data to Pinecone (ect ilk) and paying them a fee, when I can run the same postgres faster from the Desktop.
Are you pointing people (with code) to cloud based vector store, or pointing out the same free version of it on the desktop? It really matters when developing a flow. I'd like an answer to that before spending $200
Other than that, keep doing what you do. It's great.
glad you are finding the content helpful. As for the vectorstore, I use chroma in the course, so everything is local.
The goal is to introduce concepts and explain them in a way that everyone can understand. Choice of tools is really a matter of application you are building. Hope you will find the course helpful as well.
@@engineerprompt Right on dude. I just mentioned you to someone earlier and that you 'build' as opposed to some of the other youtubers that will generate kitten images with a $150 million model :)
I think 'where and what' is being used for RAG right now is being more looked at. And While I 'DO' respect the ones like you that will still slide paid promos for AI services....... You still have to eat. I get that. Eat well, youj earned it.
Chroma is cool. I see fragmentation in this early AI goldrush, and part of this is some of the influencers always trying to wrap a critical componenent like RAG or hosting ...... to do something that can be done locally..... I get it. People have to eat :)
But a paid course, is why I asked. I just want to know thats what I am getting. You should 'Udemy' man.
Are you doing anything with 'geocoded' embeddings in the future?There's a 'Vector Databasing with DuckDB on Top of PGVector' medium article out there that is pretty interesting.
@@engineerprompt additionally, if I may, when you said 'The goal is to introduce concepts and explain them in a way that everyone can understand'......that last 'Phi' model update, Microsoft said what made the model so great was feeding it cleaner data.
Some of the approaches to 'chunking' over simplify how it should be used on different data content types.