How is it different from Groq api inference service where LPUs are way faster than GPUs for inferencing. NIM is more like hosting hf models inside NVIDIA ecosystem with inferencing facility alongwith.But as groq has also got pretty good models, just for inferencing using groq api will be much wiser option for speed for same kind of models.

Thank you very much

Excellent

❤❤❤❤

Great Tutorial...

Excellent! My comment is: Your updated requirements.txt file is well-suited for an MLOps project. It includes essential libraries for data manipulation, machine learning, visualization, web service creation, and more. BUT, by pinning versions and using a virtual environment, you ensure a reproducible and isolated environment for your project.

most genuine youtuber ever

quite the Quintessential Indian IT KZfaqr, you are good sir.

Thanks Krish. The membership to your channel is worth every penny. You have a great teacher with an amazing products and offering. Keep going strong man!

I don't know for what purpose but everytime I see there is a library called tiktoken imported into the project but it is never used. why is that?

Has anyone faced this issue while creating a new env conda create -n env python=3.9 Channels: - defaults - conda-forge Platform: win-64 Collecting package metadata (repodata.json): done Solving environment: failed PackagesNotFoundError: The following packages are not available from current channels: - packagename1

Also I have another doubt. Why are the similarity search results returning the same results twice. Does that mean there are duplicate entries in the vector database? If so how do you avoid such duplication.

where I can get the notes?? the link to the dashboard in the description is not working

@ exactly 14:40 you have imported something called Concatenate from typing_extensions library (which I think is now deprecated) but I don't see the imported function/Object used anywhere in the code. Can you explain the rationale as to why the import was done? Am I missing something here?

How does modin perform on real-time ML pipeline? It's expected to ingest 10 data points per second

How does modin perform for real-time ML pipeline? It's expected to receive about 10 data points per second

looking forward to this series! Could you go more in-depth into RAG: Re-Ranking ?

Great video! Thanks a ton!

anyway used this lib on ARM mac?

Sir but this is not quite great library for bivariate analysis...

Hey Krish ,Amazing video! Looking forward to seeing many more!

21:44 I suppose there is a chunk of video missing!

Thanks, the enthusiasm with which you teach also carries over to us. 🥰

we can use gradio for this

Listen to krish. He is 100% correct. I am senior DS manager at Meta and conduct many interview where we evaluate basic machine learning concepts because most business problems can be solved by traditional ML and deep learning techniques.

Hi Krish, great videos!! Could you also show us how to create a chatbot using Amazon Q? That would be really helpful. Thanks!

Hi Krish. Thank you very much for the content regarding Gen AI. This has been very helpful. It would be great if you make a video on creating a chatbot using Amazon Q.

Thank u 😊

Standard_scaler( with_mean= False) Use this you wont get that error

Can anyone please tell me coupon code for getting free Complete Machine Learning,NLP Bootcamp MLOPS & Deployment On udemy

Anyone know how can i get free coupon of krish sir udemy courses?

Hello Sir, Hello, could you create a tutorial on fine-tuning vision-language models like LLaVA or Multimodal LLMs like IDEFICS for Visual Question Answering on datasets like VQA-RAD, including evaluation metrics? Please make a full step by step tutorial. Thanks in Advance!

Hello Sir, Hello, could you create a tutorial on fine-tuning vision-language models like LLaVA or IDEFICS for Visual Question Answering on datasets like VQA-RAD using QLoRA, including evaluation metrics? Please make a full step by step tutorial. Thanks in Advance!

Can we use Prompt as a query using Open AI LLM model?? and get answers to it. Any project involving Prompt and Embeddings

in percentile do the numbers have to be in order?

Please anyone here who can help me to remove my error... please share Instagram I'd or something.i will contact you

.env file ...how did you make it... Like you keep original key value in it or the name we given 'open_ai_api_key'

awesome tutorial

This man is the single reason why I am able to learn all that I know till date