AutoGineer
Generated banner for Azure AI Projects Java
Generated logo for Azure AI Projects Java

Azure AI Projects Java

MicrosoftOfficialCreated by Microsoft

  • Skill
  • Tool integration
  • Software development
  • MIT
  • No issues found
Download ZIP

From the author

Azure AI Projects SDK for Java. High-level SDK for Azure AI Foundry project management including connections, datasets, indexes, and evaluations. Triggers: "AIProjectClient java", "azure ai projects java", "Foundry project java", "ConnectionsClient", "DatasetsClient", "IndexesClient".
— the description by Microsoft

AutoGineer summary

Written by AutoGineer from the skill’s own files, not by the author

The Azure AI Projects SDK for Java provides a high-level interface for interacting with Azure AI Foundry. It enables developers to programmatically manage project resources such as connections to external services, datasets, search indexes, and AI model deployments. The SDK features a modular client architecture, allowing users to instantiate specific sub-clients for tasks like running evaluations, scheduling operations, or managing search indexes, all while leveraging standard Azure authentication patterns.

What it does

  • Provides a centralized builder for creating specialized sub-clients.
  • Manages connections to external Azure resources.
  • Facilitates the creation and management of search indexes.
  • Supports the execution and configuration of AI model evaluations.
  • Enables programmatic access to dataset management and model deployments.
  • Integrates with standard Azure identity and credential providers.

When to use it

  • When building Java applications that interact with Azure AI Foundry.
  • When you need to automate the lifecycle of AI project resources.
  • When integrating AI model evaluation workflows into Java-based pipelines.
  • When managing search indexes or data connections within an Azure AI environment.

Advantages

  • Modular client design for efficient resource management.
  • Native support for Azure identity and security best practices.
  • Comprehensive coverage of AI Foundry project operations.
  • Supports both synchronous and asynchronous operations.

Usage examples

“How do I initialize the Azure AI Projects client in Java?”
You use the AIProjectClientBuilder, providing your project endpoint and a TokenCredential (such as DefaultAzureCredential) to build the client.
“How can I list all connections in my Azure AI project using Java?”
Build a ConnectionsClient from the main builder and call the listConnections() method, which returns a PagedIterable of available connections.

Install

  1. Download the skill as a ZIP:

    https://mp-staging.autogineer.com/agent-skills/microsoft/azure-ai-projects-java/download

  2. Unzip it into the cross-client skills folder of your project:

    mkdir -p .agents/skills && unzip azure-ai-projects-java.zip -d .agents/skills

Documentation by Microsoft

Azure AI Projects SDK for Java

High-level SDK for Azure AI Foundry project management with access to connections, datasets, indexes, and evaluations.

Installation

<dependency>
    <groupId>com.azure</groupId>
    <artifactId>azure-ai-projects</artifactId>
    <version>1.0.0-beta.1</version>
</dependency>

Environment Variables

PROJECT_ENDPOINT=https://<resource>.services.ai.azure.com/api/projects/<project> # Required for project configuration
AZURE_TOKEN_CREDENTIALS=prod  # Required only if DefaultAzureCredential is used in production

Authentication

import com.azure.ai.projects.AIProjectClientBuilder;
import com.azure.core.credential.TokenCredential;
import com.azure.identity.AzureIdentityEnvVars;
import com.azure.identity.DefaultAzureCredentialBuilder;
import com.azure.identity.ManagedIdentityCredentialBuilder;

TokenCredential credential = new DefaultAzureCredentialBuilder()
    .requireEnvVars(AzureIdentityEnvVars.AZURE_TOKEN_CREDENTIALS)
    .build();
// Or use a specific credential directly in production:
// See https://learn.microsoft.com/java/api/overview/azure/identity-readme?view=azure-java-stable#credential-classes
// TokenCredential credential = new ManagedIdentityCredentialBuilder().build();

AIProjectClientBuilder builder = new AIProjectClientBuilder()
    .endpoint(System.getenv("PROJECT_ENDPOINT"))
    .credential(credential);

Client Hierarchy

The SDK provides multiple sub-clients for different operations:

ClientPurpose
ConnectionsClientEnumerate connected Azure resources
DatasetsClientUpload documents and manage datasets
DeploymentsClientEnumerate AI model deployments
IndexesClientCreate and manage search indexes
EvaluationsClientRun AI model evaluations
EvaluatorsClientManage evaluator configurations
SchedulesClientManage scheduled operations
// Build sub-clients from builder
ConnectionsClient connectionsClient = builder.buildConnectionsClient();
DatasetsClient datasetsClient = builder.buildDatasetsClient();
DeploymentsClient deploymentsClient = builder.buildDeploymentsClient();
IndexesClient indexesClient = builder.buildIndexesClient();
EvaluationsClient evaluationsClient = builder.buildEvaluationsClient();

Core Operations

List Connections
import com.azure.ai.projects.models.Connection;
import com.azure.core.http.rest.PagedIterable;

PagedIterable<Connection> connections = connectionsClient.listConnections();
for (Connection connection : connections) {
    System.out.println("Name: " + connection.getName());
    System.out.println("Type: " + connection.getType());
    System.out.println("Credential Type: " + connection.getCredentials().getType());
}
List Indexes
indexesClient.listLatest().forEach(index -> {
    System.out.println("Index name: " + index.getName());
    System.out.println("Version: " + index.getVersion());
    System.out.println("Description: " + index.getDescription());
});
Create or Update Index
import com.azure.ai.projects.models.AzureAISearchIndex;
import com.azure.ai.projects.models.Index;

String indexName = "my-index";
String indexVersion = "1.0";
String searchConnectionName = System.getenv("AI_SEARCH_CONNECTION_NAME");
String searchIndexName = System.getenv("AI_SEARCH_INDEX_NAME");

Index index = indexesClient.createOrUpdate(
    indexName,
    indexVersion,
    new AzureAISearchIndex()
        .setConnectionName(searchConnectionName)
        .setIndexName(searchIndexName)
);

System.out.println("Created index: " + index.getName());
Access OpenAI Evaluations

The SDK exposes OpenAI's official SDK for evaluations:

import com.openai.services.EvalService;

EvalService evalService = evaluationsClient.getOpenAIClient();
// Use OpenAI evaluation APIs directly

Best Practices

  1. Use DefaultAzureCredential for production authentication

  2. Reuse client builder to create multiple sub-clients efficiently

  3. Handle pagination when listing resources with PagedIterable

  4. Use environment variables for connection names and configuration

  5. Check connection types before accessing credentials

Error Handling

import com.azure.core.exception.HttpResponseException;
import com.azure.core.exception.ResourceNotFoundException;

try {
    Index index = indexesClient.get(indexName, version);
} catch (ResourceNotFoundException e) {
    System.err.println("Index not found: " + indexName);
} catch (HttpResponseException e) {
    System.err.println("Error: " + e.getResponse().getStatusCode());
}

Reference Links

ResourceURL
Product Docshttps://learn.microsoft.com/azure/ai-studio/
API Referencehttps://learn.microsoft.com/rest/api/aifoundry/aiprojects/
GitHub Sourcehttps://github.com/Azure/azure-sdk-for-java/tree/main/sdk/ai/azure-ai-projects
Sampleshttps://github.com/Azure/azure-sdk-for-java/tree/main/sdk/ai/azure-ai-projects/src/samples

Files

references/examples.md

Azure AI Projects Java SDK - Examples

Comprehensive code examples for the Azure AI Projects SDK for Java.

Table of Contents

  • Maven Dependency

  • Client Creation

  • Working with Connections

  • Working with Deployments

  • Working with Datasets

  • Async Clients

Maven Dependency

<dependency>
    <groupId>com.azure</groupId>
    <artifactId>azure-ai-projects</artifactId>
    <version>1.0.0-beta.1</version>
</dependency>

<dependency>
    <groupId>com.azure</groupId>
    <artifactId>azure-identity</artifactId>
    <version>1.15.3</version>
</dependency>

Client Creation

Creating AIProjectClient and Sub-Clients
import com.azure.ai.projects.*;
import com.azure.core.util.Configuration;
import com.azure.identity.DefaultAzureCredentialBuilder;

public class ClientInitializationSample {

    public static void main(String[] args) {
        // Create the builder with endpoint and credentials
        AIProjectClientBuilder builder = new AIProjectClientBuilder()
            .endpoint(Configuration.getGlobalConfiguration().get("AZURE_AI_PROJECTS_ENDPOINT"))
            .credential(new DefaultAzureCredentialBuilder().build());

        // Build specific sub-clients as needed
        ConnectionsClient connectionsClient = builder.buildConnectionsClient();
        DatasetsClient datasetsClient = builder.buildDatasetsClient();
        DeploymentsClient deploymentsClient = builder.buildDeploymentsClient();
        EvaluationRulesClient evaluationRulesClient = builder.buildEvaluationRulesClient();
        EvaluationsClient evaluationsClient = builder.buildEvaluationsClient();
        EvaluationTaxonomiesClient evaluationTaxonomiesClient = builder.buildEvaluationTaxonomiesClient();
        EvaluatorsClient evaluatorsClient = builder.buildEvaluatorsClient();
        IndexesClient indexesClient = builder.buildIndexesClient();
        InsightsClient insightsClient = builder.buildInsightsClient();
        RedTeamsClient redTeamsClient = builder.buildRedTeamsClient();
        SchedulesClient schedulesClient = builder.buildSchedulesClient();
        
        // For async clients, use the async builder methods
        ConnectionsAsyncClient connectionsAsyncClient = builder.buildConnectionsAsyncClient();
        DatasetsAsyncClient datasetsAsyncClient = builder.buildDatasetsAsyncClient();
        DeploymentsAsyncClient deploymentsAsyncClient = builder.buildDeploymentsAsyncClient();
    }
}

Working with Connections

List Connections
import com.azure.ai.projects.models.Connection;
import com.azure.ai.projects.models.ConnectionType;
import com.azure.core.http.rest.PagedIterable;

public class ConnectionsSample {

    private static ConnectionsClient connectionsClient;

    public static void listConnections() {
        PagedIterable<Connection> connections = connectionsClient.listConnections();
        for (Connection connection : connections) {
            System.out.println("Connection name: " + connection.getName());
            System.out.println("Connection type: " + connection.getType());
            System.out.println("Connection credential type: " + connection.getCredentials().getType());
            System.out.println("-------------------------------------------------");
        }
    }

    public static void getConnectionWithoutCredentials() {
        String connectionName = "my-connection";
        Connection connection = connectionsClient.getConnection(connectionName);
        System.out.printf("Connection name: %s%n", connection.getName());
    }

    public static void getConnectionWithCredentials() {
        String connectionName = "my-connection";
        Connection connection = connectionsClient.getConnectionWithCredentials(connectionName);
        System.out.printf("Connection name: %s%n", connection.getName());
        System.out.printf("Connection credentials: %s%n", connection.getCredentials().getType());
    }

    // Filter connections by type
    public static void listConnectionsWithFilters() {
        // List only Azure OpenAI connections
        Iterable<Connection> azureOpenAIConnections = 
            connectionsClient.listConnections(ConnectionType.AZURE_OPEN_AI, null);
        
        azureOpenAIConnections.forEach(connection -> {
            System.out.println("Azure OpenAI Connection: " + connection.getName());
        });

        // List only default connections
        Iterable<Connection> defaultConnections = connectionsClient.listConnections(null, true);
        defaultConnections.forEach(connection -> {
            System.out.println("Default Connection: " + connection.getName());
        });
    }
}

Working with Deployments

List and Get Deployments
import com.azure.ai.projects.models.Deployment;
import com.azure.core.http.rest.PagedIterable;

public class DeploymentsSample {

    private static DeploymentsClient deploymentsClient;

    public static void listDeployments() {
        PagedIterable<Deployment> deployments = deploymentsClient.list();
        for (Deployment deployment : deployments) {
            System.out.printf("Deployment name: %s%n", deployment.getName());
        }
    }

    public static void getDeployment() {
        String deploymentName = "gpt-4o";
        Deployment deployment = deploymentsClient.get(deploymentName);

        System.out.printf("Deployment name: %s%n", deployment.getName());
        System.out.printf("Deployment type: %s%n", deployment.getType().getValue());
    }
}

Working with Datasets

Create Dataset with File Upload
import com.azure.ai.projects.models.DatasetVersion;
import com.azure.ai.projects.models.FileDatasetVersion;

import java.nio.file.Path;

public class DatasetsSample {

    private static DatasetsClient datasetsClient;

    // Create a dataset by uploading a file
    public static void createDatasetWithFile() {
        String datasetName = "my-dataset";
        String datasetVersionString = "1.0";

        Path filePath = Path.of("product_info.md");

        FileDatasetVersion createdDatasetVersion = datasetsClient.createDatasetWithFile(
            datasetName, 
            datasetVersionString, 
            filePath
        );

        System.out.println("Created dataset version: " + createdDatasetVersion.getId());
    }

    // List all datasets (latest versions)
    public static void listDatasets() {
        System.out.println("Listing all datasets (latest versions):");
        datasetsClient.listLatest().forEach(dataset -> {
            System.out.println("\nDataset name: " + dataset.getName());
            System.out.println("Dataset Id: " + dataset.getId());
            System.out.println("Dataset version: " + dataset.getVersion());
            System.out.println("Dataset type: " + dataset.getType());
            if (dataset.getDescription() != null) {
                System.out.println("Description: " + dataset.getDescription());
            }
        });
    }

    // List all versions of a specific dataset
    public static void listDatasetVersions() {
        String datasetName = "my-dataset";

        System.out.println("Listing all versions of dataset: " + datasetName);
        datasetsClient.listVersions(datasetName).forEach(version -> {
            System.out.println("\nDataset name: " + version.getName());
            System.out.println("Dataset version: " + version.getVersion());
            System.out.println("Dataset type: " + version.getType());
            if (version.getDataUri() != null) {
                System.out.println("Data URI: " + version.getDataUri());
            }
        });
    }

    // Get a specific dataset version
    public static void getDataset() {
        String datasetName = "my-dataset";
        String datasetVersion = "1.0";

        DatasetVersion dataset = datasetsClient.getDatasetVersion(datasetName, datasetVersion);

        System.out.println("Retrieved dataset:");
        System.out.println("Name: " + dataset.getName());
        System.out.println("Version: " + dataset.getVersion());
        System.out.println("Type: " + dataset.getType());
    }

    // Create or update a dataset with a data URI
    public static void createOrUpdateDataset() {
        String datasetName = "my-dataset";
        String datasetVersion = "1.0";
        String dataUri = "https://example.com/data.txt";

        // Create a new FileDatasetVersion with provided dataUri
        FileDatasetVersion fileDataset = new FileDatasetVersion()
            .setDataUri(dataUri)
            .setDescription("Sample dataset created via SDK");

        // Create or update the dataset
        FileDatasetVersion createdDataset = (FileDatasetVersion) datasetsClient.createOrUpdateVersion(
            datasetName, 
            datasetVersion, 
            fileDataset
        );

        System.out.println("Created/Updated dataset:");
        System.out.println("Name: " + createdDataset.getName());
        System.out.println("Version: " + createdDataset.getVersion());
        System.out.println("Data URI: " + createdDataset.getDataUri());
    }

    // Delete a dataset version
    public static void deleteDataset() {
        String datasetName = "my-dataset";
        String datasetVersion = "1.0";

        datasetsClient.deleteVersion(datasetName, datasetVersion);
        System.out.println("Dataset version deleted successfully");
    }
}

Async Clients

List Connections (Async)
import com.azure.ai.projects.models.Connection;
import reactor.core.publisher.Flux;
import reactor.core.publisher.Mono;

public class ConnectionsAsyncSample {

    private static ConnectionsAsyncClient connectionsAsyncClient;

    public static Flux<Connection> listConnections() {
        return connectionsAsyncClient.listConnections()
            .doOnNext(connection -> System.out.printf("Connection name: %s%n", connection.getName()));
    }

    public static Mono<Connection> getConnectionWithoutCredentials() {
        String connectionName = "my-connection";
        return connectionsAsyncClient.getConnection(connectionName)
            .doOnNext(connection -> System.out.printf("Connection name: %s%n", connection.getName()));
    }

    public static Mono<Connection> getConnectionWithCredentials() {
        String connectionName = "my-connection";
        return connectionsAsyncClient.getConnectionWithCredentials(connectionName)
            .doOnNext(connection -> {
                System.out.printf("Connection name: %s%n", connection.getName());
                System.out.printf("Connection credentials: %s%n", connection.getCredentials().getType());
            });
    }

    public static void main(String[] args) {
        // Using block() to wait for the async operations to complete in the sample
        listConnections().blockLast();
        getConnectionWithoutCredentials().block();
        getConnectionWithCredentials().block();
    }
}
Datasets (Async)
import com.azure.ai.projects.models.DatasetVersion;
import reactor.core.publisher.Flux;
import reactor.core.publisher.Mono;

public class DatasetsAsyncSample {

    private static DatasetsAsyncClient datasetsAsyncClient;

    public static Flux<DatasetVersion> listLatestDatasets() {
        return datasetsAsyncClient.listLatest()
            .doOnNext(dataset -> {
                System.out.println("Dataset: " + dataset.getName());
                System.out.println("Version: " + dataset.getVersion());
            });
    }

    public static Mono<DatasetVersion> getDataset(String name, String version) {
        return datasetsAsyncClient.getDatasetVersion(name, version)
            .doOnNext(dataset -> {
                System.out.println("Retrieved: " + dataset.getName());
            });
    }

    public static void main(String[] args) {
        listLatestDatasets().blockLast();
        getDataset("my-dataset", "1.0").block();
    }
}

Requirements and compatibility

Works with: Claude Code, Claude apps, OpenAI Codex, GitHub Copilot, Cursor, Gemini CLI, Kiro, OpenCode, Goose, Amp, Roo Code, JetBrains Junie, Factory Droid, Devin (ex-Windsurf), Mistral Vibe, OpenHands, Letta

“Works with” means the tool reads the open Agent Skills format; a skill written for one tool may use features others lack.

Security

No issues found by our static scan· No issues found

A static scan is not a guarantee. Skills are third-party content: review a skill before you let an agent use it.

Attribution and licence

Created by
Microsoft
Publisher
Microsoft (Official)
Source
microsoft/skills · .github/plugins/azure-sdk-java/skills/azure-ai-projects-java · commit 0696600
Licence
MIT License (redistribution allowed)
  • LICENSE (added by AutoGineer from LICENSE)
  • ATTRIBUTION.md (written by AutoGineer)
Synced

AutoGineer is not affiliated with or endorsed by Microsoft.

Download ZIP

The ZIP holds the skill’s files, its licence files and an ATTRIBUTION.md. Download azure-ai-projects-java.zip