Wow, this was so easy to follow. I was working on a classical NLP problem and the wifey suggested using LLMs into it. Hadn't worked with Ollama before this and your introduction to it brought me up to speed on it so darn quickly. Great work!

Hello Sir,i am btech 1st year cse student from tier 3 college.what should i do from 1st year should i learn machine .i have learnt 2 programming language.i am not getting clear roadmap.everyone is telling learn AI .Very confused

Bro it's just a installation video not a review video

You are the best!!!!

Thanks a lot

Thank you sir. Works smoothly and wonderful explanation.

it's crazy how hard is it to turn this stupid thing on. like they advertise this so much with their cuda cores while it takes ages to find best combination of versions. this is ridiculous

Hi, I followed your series from video 1, but I noticed that there seems to be a missing part between videos 6 and 7. After completing video 6, there is a sudden disconnect in video 7 regarding the creation of the DistilBERT model and for other files. If a part was missed by mistake, please upload it.

ResponseError: model "llama3.2:1b" not found, try pulling it first same is pulled..but getting error.

Thank you so much, I wasted a few weeks trying to solve this problem. 🥰

I was trying to install cuda and cudnn correctly for 2 days. And just your video worked thank you ❤

I'm grateful for your valuable work

Hi, I'd like to scrape a search page of LinkedIn, getting the link and the city of shown profiles. Is it possible?

Build Your Own Chatbot with Langchain, Ollama & LLAMA 3.2 | Local LLM Tutorial

Sir is there any library to process tables differently from the pdf if i use this method the retrieval of text inforamation is working properly but the tables are getting messed up and not able to retrieve the information that is stored in the table from the pdfs? For a semi-structured data a pdf that contains(text and tables both)?

Hi sir I have huge pdf for my project if I take the chunk size to be 1000 then the total chunks are close to 1000 for that ids = vector_store.add documents is taking a lot of time the maximum size is for chunks character is 8192 correct so is it okay if I increase my chunk size and decrease the chunk overlap? Or is there another way to reduce the time it took almost 10 to 15 minutes

Thankyou sir I had tight deadline of 3 days and I was panicking but your video helped me a lot and now I have successful rag implemnetation.

Is designing websites for clients using Streamlite the right thing to do? With Streamlit I can create hotel reservations or doctor appointment systems or whatever But I can't build this project with Django and Flask because it's hard and time consuming Do you think using Streamlite instead of Django and Flask is the right thing to do? Please give your opinion

Can you please help make a tutorial on how to load the model?

Thanks a ton!

Excuse me, how voltage amplitude of NE555 increase?

Thank you

Very well explained neatly. Great job :)

No more indian people speaking in english PLSSSSSSSSSSSSSSSSSSS

Thank you soo much for the method i spent all the night looking how to install it

Excellent work on RAG, Laxmi Kant! . Completed in one-go without any single bug.

Sir g lots of love from whole Pakistan

Thank you for the instructions. Would the picture in PDF be read by the LLM or not?

can you use langfuse which is free alternative to langsmith

dude, what a great video! With all the information, you somehow made it easy to follow. Bravo sir!

bro you are the best

THANK YOUUUUUU !!!!!!!!!!!!!!

I have a laptop of 8gb ram and entry level gtx graphics card. will i able to run llama3.2 ?? @KGPTalkie

Bro it's great video.. I have couple of questions... 1. Why you are not using requirement.txt to install all depending library? 2. Is this Ec2 instance is free or do we need to pay some amount?

This is one of the best video Available on Yt wrt to RAG, headsoff to you bro.. The way you described is absolutely great... It would be great if you add chapter, that would be more helpful for audience... At the end I want to say big thank you.. And also your channel is underrated... Continue this great work bro ❤

good work and explanation

Thanks for this Tutorial, It was nicely explained and given with functional simple code.

There are 2 types/format of experience section in linkedin profile. How can we make a code to extract both type of section by if esle condition

Thanks in advance for this, simple and works!

The goal of scraping is to automate the task of processing the data and save it somewhere in a clean way (Nice JSON), but your method requires to go and get ID and Class for each profile which is exactly the opposite of scraping, just do copy and paste then! I found weird that you said to do that only on your account in the beginning, but those kesy are changing all the time, which makes your tutorial useless for automation but good to understand beautiful soup. The moment where it is really obvious is at 36:45. Now, if you have built a better code or video, please share. Good Luck

how to resolve ptxas.exe not found error while running DL models?

using rotate proxy ?

great job than you!

Thank you very much

Thank you sooooo much.

Great video!. I made a classification model similar to this one. But I have a question related. Suppose you have on your training data, how many people have voted for a movie to be action or comedy, and you would like to use this information also to train your model. Your label vector for the example was [1, 0, 0, 1, 0] where one is the class active for the comment. Now you will have [240, 0, 0, 42, 0]. Can you use this instead of a classification problem to be a multi-label regression where your model will output the number of votes for a given movie category? Can this be done? I just wondering how to use the additional information. Thanks for any comment on this. Best.

@KGPTalkie Hello, Are you available for a brief discussion about optimizing your Udemy course SEO? My goal is to help boost your course visibility and position it on Udemy’s top pages. I look forward to hearing from you soon. Best regards, Messi

Just an overall for those who in future will plan to use this lesson to write similar code without paying for udemy course - you won't be able without this script "scripts.llm import ask_llm" on 12:50 it is useless. (I WAS WRONG IN THIS COMMENT, SEE BELOW )

Please how do I get a 120Hz output frequency?

Really huge work, thank you! Also have problem finding "from scripts.llm import ask_llm" could you please give a link