Scribd
Upload
30 views

AI Role Assignment 4

The objective is to develop a simple AI model, create a web service to interact with the model and store results in a database, containerize the components using Docker, deploy with Kubernetes, and document the process. The candidate will develop an image classifier or text analyzer, build a Python or Go web service exposing an API, integrate a MySQL database, and provide setup instructions for reviewers. The comprehensive assignment tests skills in AI modeling, web development, containerization, and cloud deployment without ready-made online solutions.

Uploaded by

shubham.singh2621
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
30 views

AI Role Assignment 4

The objective is to develop a simple AI model, create a web service to interact with the model and store results in a database, containerize the components using Docker, deploy with Kubernetes, and document the process. The candidate will develop an image classifier or text analyzer, build a Python or Go web service exposing an API, integrate a MySQL database, and provide setup instructions for reviewers. The comprehensive assignment tests skills in AI modeling, web development, containerization, and cloud deployment without ready-made online solutions.

Uploaded by

shubham.singh2621
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 2

Assignment: Custom AI Model Deployment Pipeline

Objective: Develop a simple AI model and set up a deployment pipeline using Docker
and Kubernetes. The candidate will also need to create a basic web service (using either
Python or Go Lang) that interacts with the AI model and stores results in a MySQL
database.

Task Details:

1. AI Model Development:
• Develop a simple AI model. This could be a basic image classifier or a text
sentiment analysis model using publicly available datasets (e.g., MNIST for
image classification, IMDB reviews for sentiment analysis).
• The model should be developed in Python using a machine learning
framework of the candidate's choice (e.g., TensorFlow, PyTorch).
2. Web Service Creation:
• Create a web service in Python or Go Lang that serves the AI model. The
service should expose an API endpoint where users can submit data (e.g.,
text snippets mentioned below) and receive the model's predictions
i.e. paraphrased positive version examples below.
• The service should log prediction requests and results in a MySQL
database.
3. Containerization with Docker:
• Containerize the AI model and web service using Docker. This involves
writing a Dockerfile that specifies the environment, dependencies, and
how the application should run.
4. Deployment with Kubernetes:
• Write a Kubernetes deployment configuration to manage the deployment
of the Docker containers. This should include basic configurations for
scaling and managing the application.
5. Documentation:
• Provide a README file explaining how to set up and run the model, web
service, and the Kubernetes deployment. Include any necessary scripts or
commands.
6. Bonus (Optional):
• Implement basic authentication for the API.
• Add a simple front-end interface for interacting with the model.

Submission Requirements:
• Source code for the AI model, web service, Dockerfile, and Kubernetes
configuration files.
• A README file with setup and execution instructions.
• Any scripts or additional resources used in the project.

Evaluation Criteria:

• Correctness and efficiency of the AI model.


• Quality and clarity of the code.
• Functionality of the web service and its interaction with the AI model and MySQL
database.
• Proper use of Docker and Kubernetes for deployment.
• Completeness and clarity of the documentation.

This assignment is comprehensive and tests a wide range of skills relevant to the job
description. It's also unique enough to discourage candidates from finding ready-made
solutions online, as it requires integration of several different technologies and a custom
approach to the problem.

Input Paraphrased (Posi1ve Language) (Just an


Example)
XXXX Text Input Posi1ve Say (And they lived Same input in More Posi1ve / Poem type
happily ever a@er.. ) text.
XXXX Text Input Posi1ve Say (And they lived Same input in More Posi1ve / Poem type
happily ever a@er.. ) text. (With Varia1on)
YYYY Text Input Neutral Say (They were okey Paraphrase conveying same o/p in more
friends but their friendship kept growing with posi1ve way.
1me )

Evaluation Criteria:

Deadline for this assignment is Nov 09. However, if you complete earlier, beRer. Just Ping us in
Dec 10
Linked In As soon as you are done. Also for some reason if you are not able to complete but
have invested significant 1me and reached to certain point by Nov 09, Please send us update.
Dec 10
And we will most likely Jump onto call to discuss based on update.

You might also like