Scribd
Upload
17 views4 pages

Hands-On Lab - CU

This document outlines the prerequisites for attending the Agentic AI hands-on lab, including the need for Ubuntu 22.04 or later, Visual Studio Code, and Python 3.10 or later. Participants must also have an active Azure for Students subscription and deploy the Azure OpenAI Service, along with access to the GPT-4o model. Additional recommendations include setting up a Jupyter-like environment for interactive Python coding and ensuring a stable internet connection during the lab.

Uploaded by

workwithabhishek2
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
17 views4 pages

Hands-On Lab - CU

This document outlines the prerequisites for attending the Agentic AI hands-on lab, including the need for Ubuntu 22.04 or later, Visual Studio Code, and Python 3.10 or later. Participants must also have an active Azure for Students subscription and deploy the Azure OpenAI Service, along with access to the GPT-4o model. Additional recommendations include setting up a Jupyter-like environment for interactive Python coding and ensuring a stable internet connection during the lab.

Uploaded by

workwithabhishek2
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/ 4

Prerequisite Sheet: Agentic AI Hands-on Lab

This document outlines the prerequisites you need to have in place before attending the
hands-on lab on Agentic AI using VS Code, Python and OpenAI. Please ensure you have
completed all the steps below before the lab session.

1. Operating System:

• Requirement: Ubuntu 22.04 or later installed on your machine or accessible via a


virtual machine.

• Action: If you don't have Ubuntu 22.04 or later, please install it or set up a virtual
machine with the required OS.

2. Integrated Development Environment (IDE):

• Requirement: Visual Studio Code (VS Code) installed on your machine.

• Action: Download and install VS Code from the official website:


https://code.visualstudio.com/

3. Programming Language and Libraries:

• Requirement: Python 3.10 or later installed on your Ubuntu machine.

• Action: Verify your Python version by opening a terminal and running:

o python3 --version or python --version. If it's older than 3.8, please upgrade.

• Requirement: Essential Python libraries for Agentic AI development.

• Action: We will be using libraries like openai, potentially llama-index or similar


frameworks. Please ensure you have pip installed (sudo apt update && sudo apt
install python3-pip) and be prepared to install these libraries during the lab setup on
April, 2nd.

4. Azure Subscription for Students:

• Requirement: An active Azure for Students subscription.

• Action: Follow these steps to sign up for an Azure for Students subscription:

1. Go to the Azure for Students website: https://azure.microsoft.com/en-


us/free/students/

2. Click on the "Start free".


3. You will need to verify your student status. This typically involves using your
academic email address provided by your educational institution.

4. Follow the on-screen instructions to complete the signup process. You may
need to agree to the terms and conditions.

5. Once your student status is verified, your Azure subscription will be activated
with $100 credits.

5. Deploy Azure OpenAI Service:

• Requirement: An Azure OpenAI Service resource deployed in your Azure


subscription.

• Action: Follow these steps to deploy the Azure OpenAI Service:

1. Log in to the Azure portal: https://portal.azure.com/ using your Azure for


Students account.

2. Click on "+ Create a resource" in the top-left corner.

3. Search for "Azure OpenAI" and select it.

4. Click on "Create".

5. On the "Create Azure OpenAI" page, provide the following details:

 Subscription: Select your Azure for Students subscription.

 Resource group: Create a new resource group (e.g., agentic-ai-lab-rg)


or select an existing one.

 Region: Choose a region where the GPT-4o model is available. You


can check the Azure OpenAI Service documentation for the latest
supported regions. (try to choose Sweden central, East US, East US2
etc.)

 Name: Give your Azure OpenAI Service resource a unique name (e.g.,
agentic-ai-lab-openai).

 Pricing tier: The free tier might have limitations. Consider a standard
tier as you will get $100 credits as part of your sign-up.

6. Click "Review + create" and then "Create".

7. Once the deployment is complete, navigate to your newly created Azure


OpenAI Service resource in the Azure portal.
6. Deploy and Request GPT-4o Quota:

• Requirement: Access to the GPT-4o model with a quota of at least 100K-150K


tokens per minute.

• Action: Follow these steps:

1. Go to https://ai.azure.com/

2. Click on "+ Create Project".

3. In the "Create project" pane:

 Project name: Choose a name.

 Create HUB: Create a new HUB when prompted.

 In the left Pane, choose Model Catalog and search for GPT-4o model.

 Click “Deploy”

 Deployment name: Give your deployment a name (e.g., gpt4o-


deployment).

 Deployment type: Keep it as "Global Standard".

 Customize: Click customize and only change “token per minute rate
limit to maximum available (should be >=150K)

4. Click "Create".

7. Python Notebook Environment:

• Requirement: A Jupyter-like environment for running Python code interactively.

• Suggestion: You have several options:

o Jupyter Notebook: Install Jupyter Notebook on your Ubuntu machine using


pip: pip install notebook. You can then run it from your terminal using the
command jupyter notebook.

o JupyterLab: A more feature-rich interactive development environment for


working with notebooks, code, and data. Install using pip: pip install
jupyterlab. Run it using jupyter lab.

o VS Code with Python Extension: VS Code has excellent built-in support for
Jupyter Notebooks through the Python extension. Once you have the Python
extension installed in VS Code, you can create and run .ipynb files directly
within the IDE. This is often the most convenient option as you will be using
VS Code for the lab.

Important Notes:

• Ensure you have a stable internet connection throughout the lab.

• Bring your laptop with all the prerequisites installed and configured.

You might also like