Azure AI Document Intelligence TS

Azure Document Intelligence REST SDK for TypeScript

Selective Reading Rule

Start with:

• references/senior-master-standard.md
• references/usage-routing.md
• references/quality-checklist.md

Then load only the inherited docs, scripts, assets, or examples that match the user's actual task.

Extract text, tables, and structured data from documents using prebuilt and custom models.

Installation

npm install @azure-rest/ai-document-intelligence @azure/identity

Environment Variables

DOCUMENT_INTELLIGENCE_ENDPOINT=https://<resource>.cognitiveservices.azure.com
DOCUMENT_INTELLIGENCE_API_KEY=<api-key>

Authentication

Important: This is a REST client. DocumentIntelligence is a function, not a class.

DefaultAzureCredential

import DocumentIntelligence from "@azure-rest/ai-document-intelligence";
import { DefaultAzureCredential } from "@azure/identity";

const client = DocumentIntelligence(
  process.env.DOCUMENT_INTELLIGENCE_ENDPOINT!,
  new DefaultAzureCredential()
);

API Key

import DocumentIntelligence from "@azure-rest/ai-document-intelligence";

const client = DocumentIntelligence(
  process.env.DOCUMENT_INTELLIGENCE_ENDPOINT!,
  { key: process.env.DOCUMENT_INTELLIGENCE_API_KEY! }
);

Analyze Document (URL)

import DocumentIntelligence, {
  isUnexpected,
  getLongRunningPoller,
  AnalyzeOperationOutput
} from "@azure-rest/ai-document-intelligence";

const initialResponse = await client
  .path("/documentModels/{modelId}:analyze", "prebuilt-layout")
  .post({
    contentType: "application/json",
    body: {
      urlSource: "https://example.com/document.pdf"
    },
    queryParameters: { locale: "en-US" }
  });

if (isUnexpected(initialResponse)) {
  throw initialResponse.body.error;
}

const poller = getLongRunningPoller(client, initialResponse);
const result = (await poller.pollUntilDone()).body as AnalyzeOperationOutput;

console.log("Pages:", result.analyzeResult?.pages?.length);
console.log("Tables:", result.analyzeResult?.tables?.length);

Analyze Document (Local File)

import { readFile } from "node:fs/promises";

const fileBuffer = await readFile("./document.pdf");
const base64Source = fileBuffer.toString("base64");

const initialResponse = await client
  .path("/documentModels/{modelId}:analyze", "prebuilt-invoice")
  .post({
    contentType: "application/json",
    body: { base64Source }
  });

if (isUnexpected(initialResponse)) {
  throw initialResponse.body.error;
}

const poller = getLongRunningPoller(client, initialResponse);
const result = (await poller.pollUntilDone()).body as AnalyzeOperationOutput;

Prebuilt Models

Extract Invoice Fields

const initialResponse = await client
  .path("/documentModels/{modelId}:analyze", "prebuilt-invoice")
  .post({
    contentType: "application/json",
    body: { urlSource: invoiceUrl }
  });

if (isUnexpected(initialResponse)) {
  throw initialResponse.body.error;
}

const poller = getLongRunningPoller(client, initialResponse);
const result = (await poller.pollUntilDone()).body as AnalyzeOperationOutput;

const invoice = result.analyzeResult?.documents?.[0];
if (invoice) {
  console.log("Vendor:", invoice.fields?.VendorName?.content);
  console.log("Total:", invoice.fields?.InvoiceTotal?.content);
  console.log("Due Date:", invoice.fields?.DueDate?.content);
}

Extract Receipt Fields

const initialResponse = await client
  .path("/documentModels/{modelId}:analyze", "prebuilt-receipt")
  .post({
    contentType: "application/json",
    body: { urlSource: receiptUrl }
  });

const poller = getLongRunningPoller(client, initialResponse);
const result = (await poller.pollUntilDone()).body as AnalyzeOperationOutput;

const receipt = result.analyzeResult?.documents?.[0];
if (receipt) {
  console.log("Merchant:", receipt.fields?.MerchantName?.content);
  console.log("Total:", receipt.fields?.Total?.content);
  
  for (const item of receipt.fields?.Items?.values || []) {
    console.log("Item:", item.properties?.Description?.content);
    console.log("Price:", item.properties?.TotalPrice?.content);
  }
}

List Document Models

import DocumentIntelligence, { isUnexpected, paginate } from "@azure-rest/ai-document-intelligence";

const response = await client.path("/documentModels").get();

if (isUnexpected(response)) {
  throw response.body.error;
}

for await (const model of paginate(client, response)) {
  console.log(model.modelId);
}

Build Custom Model

const initialResponse = await client.path("/documentModels:build").post({
  body: {
    modelId: "my-custom-model",
    description: "Custom model for purchase orders",
    buildMode: "template",  // or "neural"
    azureBlobSource: {
      containerUrl: process.env.TRAINING_CONTAINER_SAS_URL!,
      prefix: "training-data/"
    }
  }
});

if (isUnexpected(initialResponse)) {
  throw initialResponse.body.error;
}

const poller = getLongRunningPoller(client, initialResponse);
const result = await poller.pollUntilDone();
console.log("Model built:", result.body);

Build Document Classifier

import { DocumentClassifierBuildOperationDetailsOutput } from "@azure-rest/ai-document-intelligence";

const containerSasUrl = process.env.TRAINING_CONTAINER_SAS_URL!;

const initialResponse = await client.path("/documentClassifiers:build").post({
  body: {
    classifierId: "my-classifier",
    description: "Invoice vs Receipt classifier",
    docTypes: {
      invoices: {
        azureBlobSource: { containerUrl: containerSasUrl, prefix: "invoices/" }
      },
      receipts: {
        azureBlobSource: { containerUrl: containerSasUrl, prefix: "receipts/" }
      }
    }
  }
});

if (isUnexpected(initialResponse)) {
  throw initialResponse.body.error;
}

const poller = getLongRunningPoller(client, initialResponse);
const result = (await poller.pollUntilDone()).body as DocumentClassifierBuildOperationDetailsOutput;
console.log("Classifier:", result.result?.classifierId);

Classify Document

const initialResponse = await client
  .path("/documentClassifiers/{classifierId}:analyze", "my-classifier")
  .post({
    contentType: "application/json",
    body: { urlSource: documentUrl },
    queryParameters: { split: "auto" }
  });

if (isUnexpected(initialResponse)) {
  throw initialResponse.body.error;
}

const poller = getLongRunningPoller(client, initialResponse);
const result = await poller.pollUntilDone();
console.log("Classification:", result.body.analyzeResult?.documents);

Get Service Info

const response = await client.path("/info").get();

if (isUnexpected(response)) {
  throw response.body.error;
}

console.log("Custom model limit:", response.body.customDocumentModels.limit);
console.log("Custom model count:", response.body.customDocumentModels.count);

Polling Pattern

import DocumentIntelligence, {
  isUnexpected,
  getLongRunningPoller,
  AnalyzeOperationOutput
} from "@azure-rest/ai-document-intelligence";

// 1. Start operation
const initialResponse = await client
  .path("/documentModels/{modelId}:analyze", "prebuilt-layout")
  .post({ contentType: "application/json", body: { urlSource } });

// 2. Check for errors
if (isUnexpected(initialResponse)) {
  throw initialResponse.body.error;
}

// 3. Create poller
const poller = getLongRunningPoller(client, initialResponse);

// 4. Optional: Monitor progress
poller.onProgress((state) => {
  console.log("Status:", state.status);
});

// 5. Wait for completion
const result = (await poller.pollUntilDone()).body as AnalyzeOperationOutput;

Key Types

import DocumentIntelligence, {
  isUnexpected,
  getLongRunningPoller,
  paginate,
  parseResultIdFromResponse,
  AnalyzeOperationOutput,
  DocumentClassifierBuildOperationDetailsOutput
} from "@azure-rest/ai-document-intelligence";

Best Practices

1. Use getLongRunningPoller() - Document analysis is async, always poll for results
2. Check isUnexpected() - Type guard for proper error handling
3. Choose the right model - Use prebuilt models when possible, custom for specialized docs
4. Handle confidence scores - Fields have confidence values, set thresholds for your use case
5. Use pagination - Use paginate() helper for listing models
6. Prefer neural mode - For custom models, neural handles more variation than template

When to Use

This skill is applicable to execute the workflow or actions described in the overview.

Limitations

• Use this skill only when the task clearly matches the scope described above.
• Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
• Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.