Class DocumentAnalysisClient

Extract data from an input using a model given by its unique ID.

This operation supports custom as well as prebuilt models. For example, to use the prebuilt invoice model, provide the model ID "prebuilt-invoice", or to use the simpler prebuilt layout model, provide the model ID "prebuilt-layout".

The fields produced in the AnalyzeResult depend on the model that is used for analysis, and the values in any extracted documents' fields depend on the document types in the model (if any) and their corresponding field schemas.

This method supports streamable request bodies (FormRecognizerRequestBody) such as Node.JS ReadableStream objects, browser Blobs, and ArrayBuffers. The contents of the body will be uploaded to the service for analysis.

import * as fs from "fs";

const file = fs.createReadStream("path/to/receipt.pdf");

// The model that is passed to the following function call determines the type of the eventual result. In the
// example, we will use the prebuilt receipt model, but you could use a custom model ID/name instead.
const poller = await client.beginAnalyzeDocument("prebuilt-receipt", file);

// The result is a long-running operation (poller), which must itself be polled until the operation completes
const {
  pages, // pages extracted from the document, which contain lines and words
  tables, // extracted tables, organized into cells that contain their contents
  styles, // text styles (ex. handwriting) that were observed in the document
  keyValuePairs, // extracted pairs of elements  (directed associations from one element in the input to another)
  entities, // extracted entities in the input's content, which are categorized (ex. "Location" or "Organization")
  documents // extracted documents (instances of one of the model's document types and its field schema)
} = await poller.pollUntilDone();

// Extract the fields of the first document. These fields constitute a receipt, because we used the receipt model
const [{ fields: receipt }] = documents;

// The fields correspond to the model's document types and their field schemas. Refer to the Form Recognizer
// documentation for information about the document types and field schemas within a model, or use the `getModel`
// operation to view this information programmatically.
console.log("The type of this receipt is:", receipt?.["ReceiptType"]?.value);

Returns

a long-running operation (poller) that will eventually produce an AnalyzeResult

Extract data from an input using a model that has a known, strongly-typed document schema (a DocumentModel).

The fields produced in the AnalyzeResult depend on the model that is used for analysis. In TypeScript, the type of the result for this method overload is inferred from the type of the input DocumentModel.

This method supports streamable request bodies (FormRecognizerRequestBody) such as Node.JS ReadableStream objects, browser Blobs, and ArrayBuffers. The contents of the body will be uploaded to the service for analysis.

If the input provided is a string, it will be treated as a URL to the location of a document to be analyzed. See the beginAnalyzeDocumentFromUrl method for more information. Use of that method is preferred when using URLs, and URL support is only provided in this method for backwards compatibility.

import * as fs from "fs";

// See the `prebuilt` folder in the SDK samples (http://aka.ms/azsdk/formrecognizer/js/samples) for examples of
// DocumentModels for known prebuilts.
import { PrebuiltReceiptModel } from "./prebuilt-receipt.ts";

const file = fs.createReadStream("path/to/receipt.pdf");

// The model that is passed to the following function call determines the type of the eventual result. In the
// example, we will use the prebuilt receipt model.
const poller = await client.beginAnalyzeDocument(PrebuiltReceiptModel, file);

// The result is a long-running operation (poller), which must itself be polled until the operation completes
const {
  pages, // pages extracted from the document, which contain lines and words
  tables, // extracted tables, organized into cells that contain their contents
  styles, // text styles (ex. handwriting) that were observed in the document
  keyValuePairs, // extracted pairs of elements  (directed associations from one element in the input to another)

  documents // extracted documents (instances of one of the model's document types and its field schema)
} = await poller.pollUntilDone();

// Extract the fields of the first document. These fields constitute a receipt, because we used the receipt model
const [{ fields: receipt }] = documents;

// Since we used the strongly-typed PrebuiltReceiptModel object instead of the "prebuilt-receipt" model ID
// string, the fields of the receipt are strongly-typed and have camelCase names (as opposed to PascalCase).
console.log("The type of this receipt is:", receipt.receiptType?.value);

Returns

a long-running operation (poller) that will eventually produce an AnalyzeResult with documents that have the result type associated with the input model

Extract data from an input using a model given by its unique ID.

This operation supports custom as well as prebuilt models. For example, to use the prebuilt invoice model, provide the model ID "prebuilt-invoice", or to use the simpler prebuilt layout model, provide the model ID "prebuilt-layout".

The fields produced in the AnalyzeResult depend on the model that is used for analysis, and the values in any extracted documents' fields depend on the document types in the model (if any) and their corresponding field schemas.

This method supports extracting data from a file at a given URL. The Form Recognizer service will attempt to download a file using the submitted URL, so the URL must be accessible from the public internet. For example, a SAS token can be used to grant read access to a blob in Azure Storage, and the service will use the SAS-encoded URL to request the file.

// the URL must be publicly accessible
const url = "<receipt document url>";

// The model that is passed to the following function call determines the type of the eventual result. In the
// example, we will use the prebuilt receipt model, but you could use a custom model ID/name instead.
const poller = await client.beginAnalyzeDocument("prebuilt-receipt", url);

// The result is a long-running operation (poller), which must itself be polled until the operation completes
const {
  pages, // pages extracted from the document, which contain lines and words
  tables, // extracted tables, organized into cells that contain their contents
  styles, // text styles (ex. handwriting) that were observed in the document
  keyValuePairs, // extracted pairs of elements  (directed associations from one element in the input to another)

  documents // extracted documents (instances of one of the model's document types and its field schema)
} = await poller.pollUntilDone();

// Extract the fields of the first document. These fields constitute a receipt, because we used the receipt model
const [{ fields: receipt }] = documents;

// The fields correspond to the model's document types and their field schemas. Refer to the Form Recognizer
// documentation for information about the document types and field schemas within a model, or use the `getModel`
// operation to view this information programmatically.
console.log("The type of this receipt is:", receipt?.["ReceiptType"]?.value);

Returns

a long-running operation (poller) that will eventually produce an AnalyzeResult

Extract data from an input using a model that has a known, strongly-typed document schema (a DocumentModel).

The fields produced in the AnalyzeResult depend on the model that is used for analysis. In TypeScript, the type of the result for this method overload is inferred from the type of the input DocumentModel.

This method supports extracting data from a file at a given URL. The Form Recognizer service will attempt to download a file using the submitted URL, so the URL must be accessible from the public internet. For example, a SAS token can be used to grant read access to a blob in Azure Storage, and the service will use the SAS-encoded URL to request the file.

// See the `prebuilt` folder in the SDK samples (http://aka.ms/azsdk/formrecognizer/js/samples) for examples of
// DocumentModels for known prebuilts.
import { PrebuiltReceiptModel } from "./prebuilt-receipt.ts";

// the URL must be publicly accessible
const url = "<receipt document url>";

// The model that is passed to the following function call determines the type of the eventual result. In the
// example, we will use the prebuilt receipt model.
const poller = await client.beginAnalyzeDocument(PrebuiltReceiptModel, url);

// The result is a long-running operation (poller), which must itself be polled until the operation completes
const {
  pages, // pages extracted from the document, which contain lines and words
  tables, // extracted tables, organized into cells that contain their contents
  styles, // text styles (ex. handwriting) that were observed in the document
  keyValuePairs, // extracted pairs of elements  (directed associations from one element in the input to another)

  documents // extracted documents (instances of one of the model's document types and its field schema)
} = await poller.pollUntilDone();

// Extract the fields of the first document. These fields constitute a receipt, because we used the receipt model
const [{ fields: receipt }] = documents;

// Since we used the strongly-typed PrebuiltReceiptModel object instead of the "prebuilt-receipt" model ID
// string, the fields of the receipt are strongly-typed and have camelCase names (as opposed to PascalCase).
console.log("The type of this receipt is:", receipt.receiptType?.value);

Returns

a long-running operation (poller) that will eventually produce an AnalyzeResult

Classify a document using a custom classifier given by its ID.

This method produces a long-running operation (poller) that will eventually produce an AnalyzeResult. This is the same type as beginAnalyzeDocument and beginAnalyzeDocumentFromUrl, but the result will only contain a small subset of its fields. Only the documents field and pages field will be populated, and only minimal page information will be returned. The documents field will contain information about all the identified documents and the docType that they were classified as.

This method supports streamable request bodies (FormRecognizerRequestBody) such as Node.JS ReadableStream objects, browser Blobs, and ArrayBuffers. The contents of the body will be uploaded to the service for analysis.

import * as fs from "fs";

const file = fs.createReadStream("path/to/file.pdf");

const poller = await client.beginClassifyDocument("<classifier ID>", file);

// The result is a long-running operation (poller), which must itself be polled until the operation completes
const {
  pages, // pages extracted from the document, which contain only basic information for classifiers
  documents // extracted documents and their types
} = await poller.pollUntilDone();

// We'll print the documents and their types
for (const { docType } of documents) {
  console.log("The type of this document is:", docType);
}

Returns

a long-running operation (poller) that will eventually produce an AnalyzeResult

Classify a document from a URL using a custom classifier given by its ID.

This method produces a long-running operation (poller) that will eventually produce an AnalyzeResult. This is the same type as beginAnalyzeDocument and beginAnalyzeDocumentFromUrl, but the result will only contain a small subset of its fields. Only the documents field and pages field will be populated, and only minimal page information will be returned. The documents field will contain information about all the identified documents and the docType that they were classified as.

This method supports extracting data from a file at a given URL. The Form Recognizer service will attempt to download a file using the submitted URL, so the URL must be accessible from the public internet. For example, a SAS token can be used to grant read access to a blob in Azure Storage, and the service will use the SAS-encoded URL to request the file.

// the URL must be publicly accessible
const url = "<file url>";

const poller = await client.beginClassifyDocument("<classifier ID>", url);

// The result is a long-running operation (poller), which must itself be polled until the operation completes
const {
  pages, // pages extracted from the document, which contain only basic information for classifiers
  documents // extracted documents and their types
} = await poller.pollUntilDone();

// We'll print the documents and their types
for (const { docType } of documents) {
  console.log("The type of this document is:", docType);
}

Returns