More on Full Stack Data Science👇 👉Series Playlist: th-cam.com/play/PLz-ep5RbHosWmAt-AMK0MBgh3GeSvbCmL.html 💻Example Code: github.com/ShawhinT/TH-cam-Blog/tree/main/full-stack-data-science/ml-engineering
One of the best aspects of AWS Elastic Cloud is how seamlessly everything comes together, whether you're using FastAPI or Docker. It's all integrated beautifully.
This is fantastic stuff as I’m pulling out my hair on this same step. You have the right idea for the next video, but I think the next one after that is making the chat interface publicly accessible
Great suggestion Brian! There are several ways one can do this. The simplest and cheapest would be hosting it via HuggingFace Spaces: huggingface.co/spaces/launch However, for this specific use case the most practical option would be to embed it into my Squarespace website. I'll need to do some more digging to see the best way to do that.
@@ShawhinTalebi The streamlit cloud has been my go-to so far. I am toying with creating a react front end template but would like to see what others are doing
Hi! Great video! Thanks for sharing with us! Do you have any recommendation on what to study next to learn more about these topics or to go deeper in it?
I want to know why you didnt consider importing the sentence transfromer using model.pretrained() instead. Was it causing issues in launching the server. I am trying to do a similar thing with a RAG model and it is giving me issues such that the server keeps on loading.
My understanding of a POST request is it will pass input data to a backend data store. I don't think that helps much in generating a prediction from a model. For that, GET makes more sense.
Good question. This should be similar to the Gradio example shown 25:54. This blog post might be helpful: blog.streamlit.io/create-a-search-engine-with-streamlit-and-google-sheets/
Hi Shaw! Tysm for this tutorial, I'm learning a lot of cool stuff thanks to you I have a question : can you access directly your web interface (made from gradio) directly in a google tab and notwith a jupyter notebook ? I'm thinking if you have your security group, it should work if the saas is deployed on AWS, without having to do much more stuff. Maybe i'm mssing something
Glad it was helpful! I don't know what a Google tab is, but you can definitely deploy the UI as an app. Basically you'd create another container (on AWS of the like) to run the gradio (i.e. uvicorn) app and have it talk to the search API container.
Hey Shaw! what a beautiful content. I followed all the steps from ML APP from scratch till deployment but at last moment, I don;t have AWS free tier account as they still ask to enter the debit card details for having free access, so can you please tell me another way round to cope up with this ?
Glad you liked it! You could try deploying to railway (railway.app/). I just used them for a project and don't think I needed to input credit card info.
i have been following this video, and everything went perfectly fine, until the container deployment on AWS (i think because I am working with an LLM and therefore i need GPU) what should i do in this situation?
Great tutorial... Im still not able to connect to the API unfortunately (This site can’t be reached,refused to connect.) even though I followed the network config steps you explained...
To confirm, you added inbound rules in the VPC dashboard to allow all incoming traffic from your IP? Does the IP listed in the inbound rules match yours?
that was an awesome video, I have a task for one click ml model deployment on aws, azure and GCP, like one click on aws and other click on azure. CAn u please guide me shortly the roadmap...!
Thank you Shaw for making so many amazing videos. quick question from this video.. where exactly are you making a connection between your dockerhub and AWS ECS? Is it where you mention the url of the image? what if someone has a similar image name (shawhint/yt-search-demo) or that's not possible? Sorry if its a dumb question 😐
![Automating Data Pipelines with Python & GitHub Actions [Code Walkthrough]](http://i.ytimg.com/vi/wJ794jLP2Tw/mqdefault.jpg)
![Automating Data Pipelines with Python & GitHub Actions [Code Walkthrough]](/img/tr.png)
More on Full Stack Data Science👇
👉Series Playlist: th-cam.com/play/PLz-ep5RbHosWmAt-AMK0MBgh3GeSvbCmL.html
💻Example Code: github.com/ShawhinT/TH-cam-Blog/tree/main/full-stack-data-science/ml-engineering
One of the best aspects of AWS Elastic Cloud is how seamlessly everything comes together, whether you're using FastAPI or Docker. It's all integrated beautifully.
This is such a great video, no nonsense straight to the point!
Your detail explanations gained my subscription.
Thanks a lot for sharing.
One of the best video available. on the internet for deployment.
Glad it was helpful :)
you rock it men...The thing I was searching for days...
Hey Shawn, videos on FastAPI and Docker from you would be great.
Thanks for the suggestion! I'll add it to my queue :)
This was so simplified. thank you Shawhin
Super detailed explanation, thank you!
It was amazing ...love this type of content❤
I like your video, it deserves much more views
Fantastic video. Thank you for this!
great video ! very informative . Thanks a lot :)
This is fantastic stuff as I’m pulling out my hair on this same step.
You have the right idea for the next video, but I think the next one after that is making the chat interface publicly accessible
Great suggestion Brian! There are several ways one can do this. The simplest and cheapest would be hosting it via HuggingFace Spaces: huggingface.co/spaces/launch
However, for this specific use case the most practical option would be to embed it into my Squarespace website. I'll need to do some more digging to see the best way to do that.
@@ShawhinTalebi The streamlit cloud has been my go-to so far. I am toying with creating a react front end template but would like to see what others are doing
Amazing video...really helped alot.
Hi! Great video! Thanks for sharing with us! Do you have any recommendation on what to study next to learn more about these topics or to go deeper in it?
Happy to give recs. What's your end goal?
I want to know why you didnt consider importing the sentence transfromer using model.pretrained() instead. Was it causing issues in launching the server. I am trying to do a similar thing with a RAG model and it is giving me issues such that the server keeps on loading.
You can do this too! The one hiccup is the first inference will take while since the model will need to download from the internet.
@@ShawhinTalebi Thanks for replying back. Appreciate it!
Is it possible to predict by using API with POST ?
My understanding of a POST request is it will pass input data to a backend data store. I don't think that helps much in generating a prediction from a model. For that, GET makes more sense.
Excellent video!! Hey just one small question, the API and the model combinedly are dockerized before hosting on AWS right ?
Yes! The model lives in the Docker container,
Thank you so much, such videos are really very helpful
Glad to hear :)
how can we integrate streamlit to make the UI to get input and send to model and display the output here ?
Good question. This should be similar to the Gradio example shown 25:54.
This blog post might be helpful: blog.streamlit.io/create-a-search-engine-with-streamlit-and-google-sheets/
Hi Shaw!
Tysm for this tutorial, I'm learning a lot of cool stuff thanks to you
I have a question : can you access directly your web interface (made from gradio) directly in a google tab and notwith a jupyter notebook ?
I'm thinking if you have your security group, it should work if the saas is deployed on AWS, without having to do much more stuff. Maybe i'm mssing something
Glad it was helpful! I don't know what a Google tab is, but you can definitely deploy the UI as an app. Basically you'd create another container (on AWS of the like) to run the gradio (i.e. uvicorn) app and have it talk to the search API container.
This is such a great video, Is it normal for the image to be 6.91gb in size? Why is yours so much smaller?
That might be happening because your are creating a multi-platform image?
@@ShawhinTalebi I followed all the steps in the video; it might be because I use debian gnu/Linux .
well done , Thanks !
Hey Shaw!
what a beautiful content. I followed all the steps from ML APP from scratch till deployment but at last moment, I don;t have AWS free tier account as they still ask to enter the debit card details for having free access, so can you please tell me another way round to cope up with this ?
Glad you liked it! You could try deploying to railway (railway.app/). I just used them for a project and don't think I needed to input credit card info.
i have been following this video, and everything went perfectly fine, until the container deployment on AWS (i think because I am working with an LLM and therefore i need GPU)
what should i do in this situation?
Self-hosting LLMs can get tricky. I'd recommend using an API like OpenAI, TogetherAI, or the like if possible.
@@ShawhinTalebi the problem is that I have my own fine-tuned LLM on huggingface, i cannot use another one
where does K8S fit in in this pipeline?
Good question. In my experience, Kubernetes is rarely used in DS/ML, so I wouldn't worry learning it if your just getting started.
Great tutorial... Im still not able to connect to the API unfortunately (This site can’t be reached,refused to connect.) even though I followed the network config steps you explained...
To confirm, you added inbound rules in the VPC dashboard to allow all incoming traffic from your IP?
Does the IP listed in the inbound rules match yours?
Thank you!
can you add this for RAG chatbot through langchain plzzz
That's a cool idea! I've been thinking of a few product idea which may align with this. Hopefully I can cover this in 2025 :)
Bro create a video for handling post and get request and multiple endpoints using fast api dockerize and ECR and aws lambda functions
Great suggestion. I'll add that to my list!
that was an awesome video, I have a task for one click ml model deployment on aws, azure and GCP, like one click on aws and other click on azure. CAn u please guide me shortly the roadmap...!
Thanks for your comment. Sorry I'm not sure what you mean by "one click ml model deployment". Could you share more details?
GOATED
Thank you Shaw for making so many amazing videos. quick question from this video.. where exactly are you making a connection between your dockerhub and AWS ECS? Is it where you mention the url of the image? what if someone has a similar image name (shawhint/yt-search-demo) or that's not possible? Sorry if its a dumb question 😐
Good question! Yes, exactly. No one will have a similar image name because the first part will be your unique DockerHub username.