azure-ai-formrecognizer-java – Coding skill for AI agents

Azure Document Intelligence (Form Recognizer) SDK for Java

Build document analysis applications using the Azure AI Document Intelligence SDK for Java.

Version and document boundaries

These examples target the legacy azure-ai-formrecognizer API and a prerelease dependency; verify the selected artifact/service API and supported model IDs before use, rather than assuming parity with newer Document Intelligence SDKs. Obtain permission before uploading documents, especially identity and financial records; use short-lived narrowly scoped SAS URLs and never log their query strings or extracted content. Build/delete model operations change billable resources. OCR fields and confidence are uncertain: check null/type for each nested Items field before calling its typed getter, validate results against source documents, and handle terminal polling failures/timeouts as well as initiation errors. Client declarations are alternative independent snippets, not one compilable file.

Installation

<dependency>
    <groupId>com.azure</groupId>
    <artifactId>azure-ai-formrecognizer</artifactId>
    <version>4.2.0-beta.1</version>
</dependency>

Client Creation

DocumentAnalysisClient

import com.azure.ai.formrecognizer.documentanalysis.DocumentAnalysisClient;
import com.azure.ai.formrecognizer.documentanalysis.DocumentAnalysisClientBuilder;
import com.azure.core.credential.AzureKeyCredential;

DocumentAnalysisClient client = new DocumentAnalysisClientBuilder()
    .credential(new AzureKeyCredential("{key}"))
    .endpoint("{endpoint}")
    .buildClient();

DocumentModelAdministrationClient

import com.azure.ai.formrecognizer.documentanalysis.administration.DocumentModelAdministrationClient;
import com.azure.ai.formrecognizer.documentanalysis.administration.DocumentModelAdministrationClientBuilder;

DocumentModelAdministrationClient adminClient = new DocumentModelAdministrationClientBuilder()
    .credential(new AzureKeyCredential("{key}"))
    .endpoint("{endpoint}")
    .buildClient();

With DefaultAzureCredential

import com.azure.identity.DefaultAzureCredentialBuilder;

DocumentAnalysisClient client = new DocumentAnalysisClientBuilder()
    .endpoint("{endpoint}")
    .credential(new DefaultAzureCredentialBuilder().build())
    .buildClient();

Prebuilt Models

| Model ID | Purpose |

|----------|---------|

| prebuilt-layout | Extract text, tables, selection marks |

| prebuilt-document | General document with key-value pairs |

| prebuilt-receipt | Receipt data extraction |

| prebuilt-invoice | Invoice field extraction |

| prebuilt-businessCard | Business card parsing |

| prebuilt-idDocument | ID document (passport, license) |

| prebuilt-tax.us.w2 | US W2 tax forms |

Core Patterns

Extract Layout

import com.azure.ai.formrecognizer.documentanalysis.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());

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

AnalyzeResult result = poller.getFinalResult();

// Process pages
for (DocumentPage page : result.getPages()) {
    System.out.printf("Page %d: %.2f x %.2f %s%n",
        page.getPageNumber(),
        page.getWidth(),
        page.getHeight(),
        page.getUnit());
    
    // Lines
    for (DocumentLine line : page.getLines()) {
        System.out.println("Line: " + line.getContent());
    }
    
    // Selection marks (checkboxes)
    for (DocumentSelectionMark mark : page.getSelectionMarks()) {
        System.out.printf("Checkbox: %s (confidence: %.2f)%n",
            mark.getSelectionMarkState(),
            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());
    }
}

Analyze from URL

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

SyncPoller<OperationResult, AnalyzeResult> poller = 
    client.beginAnalyzeDocumentFromUrl("prebuilt-invoice", documentUrl);

AnalyzeResult result = poller.getFinalResult();

Analyze Receipt

SyncPoller<OperationResult, AnalyzeResult> poller = 
    client.beginAnalyzeDocumentFromUrl("prebuilt-receipt", 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.getValueAsString(),
            merchantName.getConfidence());
    }
    
    DocumentField transactionDate = fields.get("TransactionDate");
    if (transactionDate != null && transactionDate.getType() == DocumentFieldType.DATE) {
        System.out.printf("Date: %s%n", transactionDate.getValueAsDate());
    }
    
    DocumentField items = fields.get("Items");
    if (items != null && items.getType() == DocumentFieldType.LIST) {
        for (DocumentField item : items.getValueAsList()) {
            Map<String, DocumentField> itemFields = item.getValueAsMap();
            System.out.printf("Item: %s, Price: %.2f%n",
                itemFields.get("Name").getValueAsString(),
                itemFields.get("Price").getValueAsDouble());
        }
    }
}

General Document Analysis

SyncPoller<OperationResult, AnalyzeResult> poller = 
    client.beginAnalyzeDocumentFromUrl("prebuilt-document", documentUrl);

AnalyzeResult result = poller.getFinalResult();

// Key-value pairs
for (DocumentKeyValuePair kvp : result.getKeyValuePairs()) {
    System.out.printf("Key: %s => Value: %s%n",
        kvp.getKey().getContent(),
        kvp.getValue() != null ? kvp.getValue().getContent() : "null");
}

Custom Models

Build Custom Model

import com.azure.ai.formrecognizer.documentanalysis.administration.models.*;

String blobContainerUrl = "{SAS_URL_of_training_data}";
String prefix = "training-docs/";

SyncPoller<OperationResult, DocumentModelDetails> poller = adminClient.beginBuildDocumentModel(
    blobContainerUrl,
    DocumentModelBuildMode.TEMPLATE,
    prefix,
    new BuildDocumentModelOptions()
        .setModelId("my-custom-model")
        .setDescription("Custom invoice model"),
    Context.NONE);

DocumentModelDetails model = poller.getFinalResult();

System.out.println("Model ID: " + model.getModelId());
System.out.println("Created: " + model.getCreatedOn());

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

Analyze with Custom Model

SyncPoller<OperationResult, AnalyzeResult> poller = 
    client.beginAnalyzeDocumentFromUrl("my-custom-model", documentUrl);

AnalyzeResult result = poller.getFinalResult();

for (AnalyzedDocument doc : result.getDocuments()) {
    System.out.printf("Document type: %s (confidence: %.2f)%n",
        doc.getDocType(),
        doc.getConfidence());
    
    doc.getFields().forEach((name, field) -> {
        System.out.printf("Field '%s': %s (confidence: %.2f)%n",
            name,
            field.getContent(),
            field.getConfidence());
    });
}

Compose Models

List<String> modelIds = Arrays.asList("model-1", "model-2", "model-3");

SyncPoller<OperationResult, DocumentModelDetails> poller = 
    adminClient.beginComposeDocumentModel(
        modelIds,
        new ComposeDocumentModelOptions()
            .setModelId("composed-model")
            .setDescription("Composed from multiple models"));

DocumentModelDetails composedModel = poller.getFinalResult();

Manage Models

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

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

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

// Check resource limits
ResourceDetails resources = adminClient.getResourceDetails();
System.out.printf("Models: %d / %d%n",
    resources.getCustomDocumentModelCount(),
    resources.getCustomDocumentModelLimit());

Document

… (full content is in the download package)