SDK REST do Azure Document Intelligence para TypeScript

Extraia texto, tabelas e dados estruturados de documentos usando modelos pré-criados e personalizados.

Instalação

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

Variáveis de Ambiente

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

Autenticação

Importante: Este é um cliente REST. DocumentIntelligence é uma função, não uma classe.

DefaultAzureCredential

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

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

Chave de API

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

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

Analisar Documento https://example.com

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);

Analisar Documento (Arquivo Local)

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;

Modelos Pré-criados

Extrair Campos de Fatura

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);
}

Extrair Campos de Recibo

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);
  }
}

…