> ## Documentation Index
> Fetch the complete documentation index at: https://azure-foundry.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# How to get started with Azure AI Foundry SDK

> This article provides an overview of the Azure AI Foundry SDK and how to get started using it.

# Azure AI Foundry SDK client libraries

The Azure AI Foundry SDK is a comprehensive toolchain designed to simplify the development of AI applications on Azure. It enables developers to:

* Access popular models from various model providers through a single interface
* Easily combine together models, data, and AI services to build AI-powered applications
* Evaluate, debug, and improve application quality & safety across development, testing, and production environments

The Azure AI Foundry SDK is a set of client libraries and services designed to work together.

<Note>
  This article applies to a **Foundry Project**. For more information, see [Types of projects](../../what-is-azure-ai-foundry.md#project-types).
</Note>

## Prerequisites

* An Azure subscription. If you don't have one, create a [free account](https://azure.microsoft.com/free/).

* [Create a Foundry project](../create-projects) if you don't have one already.

* Sign in with the Azure CLI using the same account that you use to access your project:

  ```bash theme={"system"}
  az login
  ```

## Unified Projects client library

The Azure AI Foundry Projects client library is a unified library that enables you to use multiple client libraries together by connecting to a single project endpoint.

<Tabs>
  <Tab title="Python">
    * Install the project client library
      ```bash theme={"system"}
      pip install azure-ai-projects azure-identity
      ```

    * Create a project client in code. **Copy** the Azure AI Foundry project endpoint from the Overview page of the project and update the connections string value.

      ```python wrap theme={"system"}
      from azure.identity import DefaultAzureCredential
      from azure.ai.projects import AIProjectClient

      project = AIProjectClient(
        endpoint="your_project_endpoint",  # Replace with your endpoint
        credential=DefaultAzureCredential())
      ```
  </Tab>

  <Tab title="Java">
    * Add these packages to your installation (preview):
      * `com.azure.ai.projects`
      * `com.azure.core`

    * Create a project client in code. **Copy** the Azure AI Foundry project endpoint from the Overview page of the project and update the connections string value.

      ```java wrap theme={"system"}
      import com.azure.ai.projects.ProjectsClient;
      import com.azure.ai.projects.ProjectsClientBuilder;
      import com.azure.core.credential.AzureKeyCredential;

      String endpoint ="your_project_endpoint"; // Replace with your endpoint

      ProjectsClient projectClient = new ProjectsClientBuilder()
          .credential(new DefaultAzureCredential())
          .endpoint(endpoint)
          .buildClient();
      ```
  </Tab>

  <Tab title="JavaScript">
    * Install dependencies (preview):

      ```bash theme={"system"}
      npm install @azure/ai-projects @azure/identity
      ```

    * Create a project client in code. **Copy** the Azure AI Foundry project endpoint from the Overview page of the project and update the connections string value.

      ```javascript wrap theme={"system"}
      import { AIProjectClient } from '@azure/ai-projects';
      import { DefaultAzureCredential } from '@azure/identity';

      const endpoint = "your_project_endpoint"; // Replace with your actual endpoint
      const project = new AIProjectClient(endpoint, new DefaultAzureCredential());
      ```
  </Tab>

  <Tab title="C#">
    * Install packages:

      ```bash theme={"system"}
      dotnet add package Azure.Identity
      dotnet add package Azure.Core
      dotnet add package Azure.AI.Inference
      ```

    * Create a project client in code. **Copy** the Azure AI Foundry project endpoint from the Overview page of the project and update the connections string value.

      ```csharp wrap theme={"system"}
      using Azure;
      using Azure.Identity;
      using Azure.AI.Inference;
      using Azure.Core;
      using Azure.Core.Pipeline;

      var endpointUrl = "your_project_endpoint"; // Replace with your actual endpoint
      var credential = new DefaultAzureCredential();

      AzureAIInferenceClientOptions clientOptions = new AzureAIInferenceClientOptions();
      BearerTokenAuthenticationPolicy tokenPolicy = new BearerTokenAuthenticationPolicy(
          credential, 
          new string[] { "https://cognitiveservices.azure.com/.default" }
      );
      clientOptions.AddPolicy(tokenPolicy, HttpPipelinePosition.PerRetry);

      var projectClient = new ChatCompletionsClient(
          endpointUrl, 
          credential,
          clientOptions
      );
      ```
  </Tab>
</Tabs>

* Using the project endpoint, you can:
  * [Use Foundry Model](../../quickstarts/get-started-code), including Azure OpenAI
  * [Use Foundry Agent Service](../../../ai-services/agents/quickstart.md?context=/azure/ai-foundry/context/context)
  * [Run evaluations in the cloud](../../../ai-services/openai/how-to/evaluations.md?context=/azure/ai-foundry/context/context)
  * [Enable tracing for your app](../../concepts/trace)
  * Retrieve endpoints and keys for external resource connections