BentoML Tutorial: Build Production Grade AI Applications
ฝัง
- เผยแพร่เมื่อ 29 ก.ค. 2024
- BentoML is a framework for building reliable, scalable, and cost-efficient AI applications. It comes with everything you need for model serving, application packaging, and production deployment.
TimeStamp
00:00:00 What is BentoML
00:04:40 BentoML Implementation
00:15:12 Model Serving Using BentoML
00:19:22 Model Api Demo Using Swagger
00:24:21 Building Bentos
-------------------------------------------------------------------------------------------------------------
Support me by joining membership so that I can upload these kind of videos
/ @krishnaik06
------------------------------------------------------------------------------------------------------------------------------
►Data Science Projects:
• Now you Can Crack Any ...
►Learn In One Tutorials
Statistics in 6 hours: • Complete Statistics Fo...
Machine Learning In 6 Hours: • Complete Machine Learn...
Deep Learning 5 hours : • Deep Learning Indepth ...
►Learn In a Week Playlist
Statistics: • Live Day 1- Introducti...
Machine Learning : • Announcing 7 Days Live...
Deep Learning: • 5 Days Live Deep Learn...
NLP : • Announcing NLP Live co...
►Detailed Playlist:
Python Detailed Playlist: • Complete Road Map To B...
Python playlit in Hindi: • Tutorial 1- Python Ove...
Stats For Data Science In Hindi : • Starter Roadmap For Le...
Machine Learning In English : • Complete Road Map To B...
Machine Learning In Hindi : • Introduction To Machin...
Complete Deep Learning: • Why Deep Learning Is B...
Connect me on instagram is case of any queries
instagram.com/krishnaik06
0:15 0:15
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' "
why you don't use conda install instead of pip install ?
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).
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!
Thank you, so this is like the japanese bento box!
Great Sir! 👌
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'?
Would you be able to create a comprehensive end-to-end project on feature stores for ML?
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 !
VH= very helpfull
can we use it for ocr?
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?
Great. Please create end to end Airflow with ML pipeline. Thank you.
Dear sir , can we use bentoml in Jupiter?? Please guide us in this regrad
i want to build serach retrival AI where shoud i do
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.
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
❤❤❤❤❤❤❤
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?
Starting to work on it. Thanks :)
do video on LLM and Gen AI
Sir I have already trained model so how I use it with bentoml
cant 't we use hugging face to deploy ?
Can you do tutorials on quantum ML
hello @krishnaik what about the DVC ?
already uploaded a video :)
could you please do a vdeo about zenML ?
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
Have you found a solution for this?
@@nileshmaharjan9534 unfortunaltely, havent found a solutiın yet
2nd comment
Hi
I think Wandb does exactly this but I guess the only issues is that it's paid...
I prefer open source :)
@@krishnaik06 agreed! The best part is you can open the box and view the code! Learning a lot from your videos...
bentoml build taking too much time, i feel like it is freeze
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