Azure AI Formrecognizer Java

<dependency>
    <groupId>com.azure</groupId>
    <artifactId>azure-ai-documentintelligence</artifactId>
    <version>1.0.0</version>
</dependency>

<!-- For DefaultAzureCredential -->
<dependency>
    <groupId>com.azure</groupId>
    <artifactId>azure-identity</artifactId>
    <version>1.14.2</version>
</dependency>

DOCUMENT_INTELLIGENCE_ENDPOINT=https://<resource>.cognitiveservices.azure.com/ # Required for all auth methods
AZURE_TOKEN_CREDENTIALS=prod  # Required only if DefaultAzureCredential is used in production

import com.azure.ai.documentintelligence.DocumentIntelligenceClient;
import com.azure.ai.documentintelligence.DocumentIntelligenceClientBuilder;
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();

DocumentIntelligenceClient client = new DocumentIntelligenceClientBuilder()
    .endpoint(System.getenv("DOCUMENT_INTELLIGENCE_ENDPOINT"))
    .credential(credential)
    .buildClient();

import com.azure.core.credential.AzureKeyCredential;

DocumentIntelligenceClient client = new DocumentIntelligenceClientBuilder()
    .endpoint(System.getenv("DOCUMENT_INTELLIGENCE_ENDPOINT"))
    .credential(new AzureKeyCredential(System.getenv("DOCUMENT_INTELLIGENCE_KEY")))
    .buildClient();

import com.azure.ai.documentintelligence.DocumentIntelligenceAdministrationClient;
import com.azure.ai.documentintelligence.DocumentIntelligenceAdministrationClientBuilder;
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();

DocumentIntelligenceAdministrationClient adminClient = new DocumentIntelligenceAdministrationClientBuilder()
    .endpoint(System.getenv("DOCUMENT_INTELLIGENCE_ENDPOINT"))
    .credential(credential)
    .buildClient();

import com.azure.ai.documentintelligence.DocumentIntelligenceAsyncClient;
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();

DocumentIntelligenceAsyncClient asyncClient = new DocumentIntelligenceClientBuilder()
    .endpoint(System.getenv("DOCUMENT_INTELLIGENCE_ENDPOINT"))
    .credential(credential)
    .buildAsyncClient();

import com.azure.ai.documentintelligence.models.*;
import com.azure.core.util.BinaryData;
import com.azure.core.util.polling.SyncPoller;
import java.io.File;

File document = new File("document.pdf");
BinaryData documentData = BinaryData.fromFile(document.toPath(), (int) document.length());

SyncPoller<AnalyzeOperationDetails, AnalyzeResult> poller =
    client.beginAnalyzeDocument("prebuilt-layout",
        new AnalyzeDocumentOptions(documentData));

AnalyzeResult result = poller.getFinalResult();

String documentUrl = "https://example.com/invoice.pdf";

SyncPoller<AnalyzeOperationDetails, AnalyzeResult> poller =
    client.beginAnalyzeDocument("prebuilt-invoice",
        new AnalyzeDocumentOptions(documentUrl));

AnalyzeResult result = poller.getFinalResult();

AnalyzeResult result = poller.getFinalResult();

for (DocumentPage page : result.getPages()) {
    System.out.printf("Page has width: %.2f and height: %.2f, measured with unit: %s%n",
        page.getWidth(), page.getHeight(), page.getUnit());

    // Lines
    for (DocumentLine line : page.getLines()) {
        System.out.printf("Line '%s' is within bounding box %s.%n",
            line.getContent(), line.getPolygon());
    }

    // Selection marks
    for (DocumentSelectionMark mark : page.getSelectionMarks()) {
        System.out.printf("Selection mark is '%s' with confidence %.2f.%n",
            mark.getState(), mark.getConfidence());
    }
}

// Tables
for (DocumentTable table : result.getTables()) {
    System.out.printf("Table: %d rows x %d columns%n",
        table.getRowCount(), table.getColumnCount());
    for (DocumentTableCell cell : table.getCells()) {
        System.out.printf("Cell[%d,%d]: %s%n",
            cell.getRowIndex(), cell.getColumnIndex(), cell.getContent());
    }
}

SyncPoller<AnalyzeOperationDetails, AnalyzeResult> poller =
    client.beginAnalyzeDocument("prebuilt-receipt",
        new AnalyzeDocumentOptions(receiptUrl));

AnalyzeResult result = poller.getFinalResult();

for (AnalyzedDocument doc : result.getDocuments()) {
    Map<String, DocumentField> fields = doc.getFields();

    DocumentField merchantName = fields.get("MerchantName");
    if (merchantName != null && merchantName.getType() == DocumentFieldType.STRING) {
        System.out.printf("Merchant: %s (confidence: %.2f)%n",
            merchantName.getValueString(), merchantName.getConfidence());
    }

    DocumentField transactionDate = fields.get("TransactionDate");
    if (transactionDate != null && transactionDate.getType() == DocumentFieldType.DATE) {
        System.out.printf("Date: %s%n", transactionDate.getValueDate());
    }
}

SyncPoller<AnalyzeOperationDetails, AnalyzeResult> poller =
    client.beginAnalyzeDocument("my-custom-model",
        new AnalyzeDocumentOptions(documentUrl)
            .setPages(Collections.singletonList("1-3"))
            .setLocale("en-US")
            .setDocumentAnalysisFeatures(Arrays.asList(DocumentAnalysisFeature.LANGUAGES))
            .setOutputContentFormat(DocumentContentFormat.TEXT));

String blobContainerUrl = "{SAS_URL_of_training_data}";

SyncPoller<DocumentModelBuildOperationDetails, DocumentModelDetails> poller =
    adminClient.beginBuildDocumentModel(
        new BuildDocumentModelOptions("my-custom-model", DocumentBuildMode.TEMPLATE)
            .setAzureBlobSource(new AzureBlobContentSource(blobContainerUrl)));

DocumentModelDetails model = poller.getFinalResult();
System.out.printf("Model ID: %s%n", model.getModelId());
System.out.printf("Created: %s%n", model.getCreatedOn());

model.getDocumentTypes().forEach((docType, details) -> {
    details.getFieldSchema().forEach((field, schema) -> {
        System.out.printf("Field: %s (%s)%n", field, schema.getType());
    });
});

// Resource limits
DocumentIntelligenceResourceDetails resourceDetails = adminClient.getResourceDetails();
System.out.printf("Models: %d / %d%n",
    resourceDetails.getCustomDocumentModels().getCount(),
    resourceDetails.getCustomDocumentModels().getLimit());

// List models
PagedIterable<DocumentModelDetails> models = adminClient.listModels();
for (DocumentModelDetails model : models) {
    System.out.printf("Model: %s, Created: %s%n",
        model.getModelId(), model.getCreatedOn());
}

// Get model
DocumentModelDetails model = adminClient.getModel("model-id");

// Delete model
adminClient.deleteModel("model-id");

Map<String, ClassifierDocumentTypeDetails> docTypes = new HashMap<>();
docTypes.put("invoice", new ClassifierDocumentTypeDetails()
    .setAzureBlobSource(new AzureBlobContentSource(containerUrl).setPrefix("invoices/")));
docTypes.put("receipt", new ClassifierDocumentTypeDetails()
    .setAzureBlobSource(new AzureBlobContentSource(containerUrl).setPrefix("receipts/")));

SyncPoller<DocumentClassifierBuildOperationDetails, DocumentClassifierDetails> poller =
    adminClient.beginBuildClassifier(
        new BuildDocumentClassifierOptions("my-classifier", docTypes));

DocumentClassifierDetails classifier = poller.getFinalResult();

SyncPoller<AnalyzeOperationDetails, AnalyzeResult> poller =
    client.beginClassifyDocument("my-classifier",
        new ClassifyDocumentOptions(documentUrl));

AnalyzeResult result = poller.getFinalResult();
for (AnalyzedDocument doc : result.getDocuments()) {
    System.out.printf("Classified as: %s (confidence: %.2f)%n",
        doc.getDocumentType(), doc.getConfidence());
}

import com.azure.core.exception.HttpResponseException;

try {
    client.beginAnalyzeDocument("prebuilt-receipt",
        new AnalyzeDocumentOptions("invalid-url"));
} catch (HttpResponseException e) {
    System.out.printf("Status: %d, Error: %s%n",
        e.getResponse().getStatusCode(), e.getMessage());
}