How to get started with the Azure AI SDK

The Azure AI SDK is a family of packages that provide access to Azure AI services such as Azure OpenAI.

In this article, you'll learn how to get started with the Azure AI SDK for generative AI applications. You can either:

• Install the SDK into an existing development environment or
• Use the Azure AI SDK without installing it

Install the SDK into an existing development environment

Install Python

First, install Python 3.10 or higher, create a virtual environment or conda environment, and install your packages into that virtual or conda environment. DO NOT install the Generative AI SDK into your global python installation. You should always use a virtual or conda environment when installing python packages, otherwise you can break your system install of Python.

Install Python via virtual environments

Follow the instructions in the VS Code Python Tutorial for the easiest way of installing Python and creating a virtual environment on your operating system.

If you already have Python 3.10 or higher installed, you can create a virtual environment using the following commands:

py -3 -m venv .venv
.venv\scripts\activate

python3 -m venv .venv
source .venv/bin/activate

python3 -m venv .venv
source .venv/bin/activate

Install Python via Conda environments

First, install miniconda following the instructions here.

Then, create and activate a new Python 3.10 environment:

conda create --name ai_env python=3.10
conda activate ai_env

Install the Azure AI Generative SDK

Currently to use the generative packages of the Azure AI SDK, you install a set of packages as described in this section.

Option 1: Install via pip

pip install azure-ai-generative[index,evaluate,promptflow]
pip install azure-identity

Option 2: Install via requirements.txt

1. Create a new text file named requirements.txt in your project directory.

2. Copy the content from the Azure/aistudio-copilot-sample requirements.txt repository on GitHub into your requirements.txt file.

3. Enter the following command to install the packages from the requirements.txt file:

   pip install -r requirements.txt
   

The Azure AI SDK should now be installed and ready to use!

Use the Azure AI SDK without installing it

You can install the Azure AI SDK locally as described previously, or run it via an internet browser or Docker container.

Option 1: Using VS Code (web) in Azure AI Studio

VS Code (web) in Azure AI Studio creates and runs the development container on a compute instance. To get started with this approach, follow the instructions in Work with Azure AI projects in VS Code.

Our prebuilt development environments are based on a docker container that has the Azure AI Generative SDK, the Azure AI CLI, the prompt flow SDK, and other tools. It's configured to run VS Code remotely inside of the container. The docker container is defined in this Dockerfile, and is based on Microsoft's Python 3.10 Development Container Image.

OPTION 2: Visual Studio Code Dev Container

You can run the Azure AI SDK in a Docker container using VS Code Dev Containers:

1. Follow the installation instructions for VS Code Dev Containers.
2. Clone the aistudio-copilot-sample repository and open it with VS Code:

   git clone https://github.com/azure/aistudio-copilot-sample
   code aistudio-copilot-sample
   

3. Select the Reopen in Dev Containers button. If it doesn't appear, open the command palette (Ctrl+Shift+P on Windows and Linux, Cmd+Shift+P on Mac) and run the Dev Containers: Reopen in Container command.

OPTION 3: GitHub Codespaces

The Azure AI code samples in GitHub Codespaces help you quickly get started without having to install anything locally.

Next steps

• Build your own copilot using Azure AI CLI and SDK
• Try the Azure AI CLI from Azure AI Studio in a browser
• Azure SDK for Python reference documentation