Node.JS and Azure Cognitive Services

Simple example on how you can use Node.JS processor with connection to Azure cognitive services especially Form Recogniser. Before going further review the Form Recogniser service description and use: Invoice data extraction – Document Intelligence (formerly Form Recognizer) - Azure AI services | Microsoft Learn

In my case I want to use prebuilt model as well custom model for additional fields on the invoice. I want to use same endpoint for getting the data from invoices (invoice-prebuilt + custom) and generic document with model prebuilt-document.

Attachment is stored in Xeelo so in the first place I download the attachment content using Xeelo Attachment Download connector. Then I pass the data into Azure services. I want to run the data extraction for prebuilt-invoice and custom model in parallel so I use const responseAll = await Promoise.all([promise1, promise2]); where promises are coming from my own function that posts the data in Azure and in loop with one-second delay trying to get the results.

Azure credentials (key) as well as URL of endpoint under my subscription are stored in general variables as sensitive data so I do not expose them by accident.

// functions

async function getOCRData(stringURL){

  const Key =  "${#AzureOCR_Key}"

  // upload file to Azure OCR
  const responsePOST = await fetch(stringURL, {
    method: "POST",
    body: JSON.stringify({"base64Source": inputData[0].DocumentContent}),
    //body: JSON.stringify({"urlSourc1e": DocumentUrl}), 
    headers: {
      "Content-Type": "application/json", 
      "Ocp-Apim-Subscription-Key": Key

    log.error("Upload of document into Azure OCR was not successful with following error:");
    const resp = await responsePOST.json();

  // extract call back url from document upload
  const CallbackURL = responsePOST.headers.get("Operation-Location");

  var OCRDataStatus = "new";
  var OCRData = null;

  // get document OCR in cycle with 3 second delay
  while(OCRDataStatus != "succeeded"){

    const responseGET = await fetch(CallbackURL, {
      method: "GET",
      headers: {
        "Ocp-Apim-Subscription-Key": Key

      log.error("Document fetch from Azure OCR was not successful.")

    OCRData = await responseGET.json();
    OCRDataStatus = OCRData.status;

    if(OCRDataStatus != 'succeeded'){
      log.warn("Azure OCR status: " + OCRDataStatus);
      await sleep(1000);


  return OCRData;


// main code

const EndpointURL = "${#AzureOCR_URL}";
const ModelID = inputData[0].ModelID;

var OCRData = {}

if(ModelID == "prebuilt-invoice"){

  const AzureURL = EndpointURL + "/formrecognizer/documentModels/prebuilt-invoice:analyze?api-version=2023-07-31&features=keyValuePairs"
  const OCRDataPromise = getOCRData(AzureURL);

  const AzureURLExt = EndpointURL + "/formrecognizer/documentModels/Invoice_Extended_v12:analyze?api-version=2023-07-31"
  const OCRData2Promise = getOCRData(AzureURLExt);

  const OCRDataResult = await Promise.all([OCRDataPromise, OCRData2Promise]);

  OCRData = OCRDataResult[0];
  const OCRData2 = OCRDataResult[1];

  if(OCRData2.analyzeResult.documents?.length > 0){

} else {

  const AzureURL = EndpointURL + "/formrecognizer/documentModels/prebuilt-document:analyze?api-version=2023-07-31"
  OCRData = await getOCRData(AzureURL);


return [{
  "JSON": OCRData