BentoML Tutorial: Build Production Grade AI Applications

[@krishnaik06]

Connect me on instagram is case of any queries instagram.com/krishnaik06

[@tohidmalik1131]

0:15 0:15

[@Technogamecoc]

sir can you solve this doubt of me " In different industries, do we typically have to construct models and neural networks from the ground up using Python, or is it more common to utilize existing prebuilt models and frameworks like 'Yolov8,' 'keras,' 'tensorflow,' and 'Theano' "

[@jugeshprajapati9437]

why you don't use conda install instead of pip install ?

[@moondevonyt]

just finished watching your deep dive on Bento ml, and gotta say, your delivery and walkthrough are on point it's clear you're pretty passionate about ML Ops and helping your followers understand the nuances that said, while Bento ml does simplify the deployment process and is pretty awesome, there's still a big learning curve for someone new to ML Ops Integrating it into existing pipelines might not be as seamless for everyone still, mad props for spotlighting such a tool. keep it up!

[@None-wi9us]

Sir, i know you on twitter (X), is that you?

[@amrirasyidi]

I watched many of your videos, it really helpful to have this kind of practical hands-on tutorial. Another great video! Just a tip, you can type "cmd" in the powershell terminal to switch it to cmd mode (easier than clicking the terminal option).

[@PavanKumar-om8nk]

Thank you, so this is like the japanese bento box!

[@oscartandi8703]

Sir bentoml build is taking infinite time for its execution, rest everything works perfectly fine can you please help me with the best possible solution !

[@LoonyPlays]

❤❤❤❤❤❤❤

[@Technogamecoc]

In different industries, do we typically have to construct models and neural networks from the ground up using Python, or is it more common to utilize existing prebuilt models and frameworks like 'Yolov8,' 'keras,' 'tensorflow,' and 'Theano'?

[@ishanpandey5917]

as per what i know in most of the cases we fine tune the existing models in regards of yolo we can say transfer learning but there might be special problem statement for which we may have to work from scratch

[@machinelearning3518]

is new content going to come up on your one neuron platform. can you please clarify the progress of that platform in future or is it discontinued?

[@sharanreddy-m4p]

do video on LLM and Gen AI

[@milanbeherazyx]

Hi Krish, I was thinking, could we create a project using BentoML, Langchain, and Falcon180b or 40b or 7b? Something like a voice chat bot. We could train it on a substantial amount of data and then use it to generate responses. For instance, we could ask it to create a pair plot or a bar chart, and it would generate and display it for us. This could be a fascinating end-to-end project. What do you think about this idea?

[@MrKB_SSJ2]

Starting to work on it. Thanks :)

[@AnilDumbre-k3s]

Great Sir! 👌

[@rodriguekalach5502]

hello @krishnaik what about the DVC ?

[@krishnaik06]

already uploaded a video :)

[@techandprogramming4688]

Would you be able to create a comprehensive end-to-end project on feature stores for ML?

[@saranya417]

Can you do tutorials on quantum ML

[@ggopi767]

can we use it for ocr?

[@sharanreddy-m4p]

cant 't we use hugging face to deploy ?

[@albela7434]

VH= very helpfull

[@sheikhmuhammadsaqib3387]

Dear sir , can we use bentoml in Jupiter?? Please guide us in this regrad

[@sayrevillatlorew4636]

i want to build serach retrival AI where shoud i do

[@gauravfamily2209]

Great. Please create end to end Airflow with ML pipeline. Thank you.

[@abhijeetghosh3340]

it has been an hour and still the bentoml build step has not completed Krish sir. can you comment, why is that and how to solve it? should I just wait or should I abandon and start again? my computer is pretty fast and I am following exactly what you are doing here trying to implement the same step.

[@nirajbava799]

Sir I have already trained model so how I use it with bentoml

[@adelorton727]

could you please do a vdeo about zenML ?

[@mikiallen7733]

Am not getting the point still sir , is this just a more sophisticated tool to create python-written APIs (mainly to be consumed by technically savvy audience ) or rather to generate an end user or client-facing app (mainly to be consumed by others who are not software developers or programmers) ? merci

[@beytullahyayla7401]

Hi, i had an error : File "C:\Users\Beytullah\anaconda3\envs\bentoml\lib\site-packages\bentoml\_internal\bento\bento.py", line 539, in from_yaml_file yaml_content["tag"] = Tag(yaml_content["name"], yaml_content["version"]) KeyError: 'name' Here is my yaml file : service: "service:mnist_service" labels: owner: Valerio stage: dev include: - "*.py" python: packages: - tensorflow - numpy

[@nileshmaharjan9534]

Have you found a solution for this?

[@beytullahyayla7401]

@@nileshmaharjan9534 unfortunaltely, havent found a solutiın yet

[@Whatever20237]

I think Wandb does exactly this but I guess the only issues is that it's paid...

[@krishnaik06]

I prefer open source :)

[@Whatever20237]

@@krishnaik06 agreed! The best part is you can open the box and view the code! Learning a lot from your videos...

[@MamunKhan-px2vb]

Hi

[@progamer0256]

bentoml build taking too much time, i feel like it is freeze

[@sayrevillatlorew4636]

2nd comment

[@ZibaFact]

Instead of uploading videos nowadays, take some break and customize you videos and make playlists, so that every one can access without disgusted. Structured your channel proper by handling the playlists