<dependencyManagement><dependencies><dependency><groupId>com.google.cloud</groupId><artifactId>libraries-bom</artifactId><version>26.76.0</version><type>pom</type><scope>import</scope></dependency>  </dependencies></dependencyManagement><dependencies>  <dependency>    <groupId>com.google.cloud</groupId><artifactId>google-cloud-document-ai</artifactId></dependency></dependencies>

implementation'com.google.cloud:google-cloud-document-ai:2.89.0'

libraryDependencies+="com.google.cloud"%"google-cloud-document-ai"%"2.89.0"

#include"google/cloud/documentai/v1/document_processor_client.h"#include"google/cloud/location.h"#include <fstream>#include <iostream>#include <string>intmain(intargc,char*argv[])try{if(argc!=5){std::cerr <<"Usage: " <<argv[0]              <<" project-id location-id processor-id filename (PDF only)\n";return1;}std::stringconstlocation_id=argv[2];if(location_id!="us" &&location_id!="eu"){std::cerr <<"location-id must be either 'us' or 'eu'\n";return1;}autoconstlocation=google::cloud::Location(argv[1],location_id);namespacedocumentai=::google::cloud::documentai_v1;autoclient=documentai::DocumentProcessorServiceClient(documentai::MakeDocumentProcessorServiceConnection(location.location_id()));google::cloud::documentai::v1::ProcessRequestreq;req.set_name(location.FullName()+"/processors/"+argv[3]);req.set_skip_human_review(true);auto&doc=*req.mutable_raw_document();doc.set_mime_type("application/pdf");std::ifstreamis(argv[4]);doc.set_content(std::string{std::istreambuf_iterator<char>(is),{}});autoresp=client.ProcessDocument(std::move(req));if(!resp)throwstd::move(resp).status();std::cout <<resp->document().text() <<"\n";return0;}catch(google::cloud::Statusconst&status){std::cerr <<"google::cloud::Status thrown: " <<status <<"\n";return1;}

usingGoogle.Cloud.DocumentAI.V1;usingGoogle.Protobuf;usingSystem;usingSystem.IO;publicclassQuickstartSample{publicDocumentQuickstart(stringprojectId="your-project-id",stringlocationId="your-processor-location",stringprocessorId="your-processor-id",stringlocalPath="my-local-path/my-file-name",stringmimeType="application/pdf"){// Create clientvarclient=newDocumentProcessorServiceClientBuilder{Endpoint=$"{locationId}-documentai.googleapis.com"}.Build();// Read in local fileusingvarfileStream=File.OpenRead(localPath);varrawDocument=newRawDocument{Content=ByteString.FromStream(fileStream),MimeType=mimeType};// Initialize request argument(s)varrequest=newProcessRequest{Name=ProcessorName.FromProjectLocationProcessor(projectId,locationId,processorId).ToString(),RawDocument=rawDocument};// Make the requestvarresponse=client.ProcessDocument(request);vardocument=response.Document;Console.WriteLine(document.Text);returndocument;}}

import("context""flag""fmt""os"documentai"cloud.google.com/go/documentai/apiv1""cloud.google.com/go/documentai/apiv1/documentaipb""google.golang.org/api/option")funcmain(){projectID:=flag.String("project_id","PROJECT_ID","Cloud Project ID")location:=flag.String("location","us","The Processor location")// Create a Processor before running sampleprocessorID:=flag.String("processor_id","aaaaaaaa","The Processor ID")filePath:=flag.String("file_path","invoice.pdf","The path to the file to parse")mimeType:=flag.String("mime_type","application/pdf","The mimeType of the file")flag.Parse()ctx:=context.Background()endpoint:=fmt.Sprintf("%s-documentai.googleapis.com:443",*location)client,err:=documentai.NewDocumentProcessorClient(ctx,option.WithEndpoint(endpoint))iferr!=nil{fmt.Println(fmt.Errorf("error creating Document AI client: %w",err))}deferclient.Close()// Open local file.data,err:=os.ReadFile(*filePath)iferr!=nil{fmt.Println(fmt.Errorf("os.ReadFile: %w",err))}req:=&documentaipb.ProcessRequest{Name:fmt.Sprintf("projects/%s/locations/%s/processors/%s",*projectID,*location,*processorID),Source:&documentaipb.ProcessRequest_RawDocument{RawDocument:&documentaipb.RawDocument{Content:data,MimeType:*mimeType,},},}resp,err:=client.ProcessDocument(ctx,req)iferr!=nil{fmt.Println(fmt.Errorf("processDocument: %w",err))}// Handle the results.document:=resp.GetDocument()fmt.Printf("Document Text: %s",document.GetText())}

importcom.google.cloud.documentai.v1.Document;importcom.google.cloud.documentai.v1.DocumentProcessorServiceClient;importcom.google.cloud.documentai.v1.DocumentProcessorServiceSettings;importcom.google.cloud.documentai.v1.ProcessRequest;importcom.google.cloud.documentai.v1.ProcessResponse;importcom.google.cloud.documentai.v1.RawDocument;importcom.google.protobuf.ByteString;importjava.io.IOException;importjava.nio.file.Files;importjava.nio.file.Paths;importjava.util.List;importjava.util.concurrent.ExecutionException;importjava.util.concurrent.TimeoutException;publicclassQuickStart{publicstaticvoidmain(String[]args)throwsIOException,InterruptedException,ExecutionException,TimeoutException{// TODO(developer): Replace these variables before running the sample.StringprojectId="your-project-id";Stringlocation="your-project-location";// Format is "us" or "eu".StringprocessorId="your-processor-id";StringfilePath="path/to/input/file.pdf";quickStart(projectId,location,processorId,filePath);}publicstaticvoidquickStart(StringprojectId,Stringlocation,StringprocessorId,StringfilePath)throwsIOException,InterruptedException,ExecutionException,TimeoutException{// Initialize client that will be used to send requests. This client only needs// to be created// once, and can be reused for multiple requests. After completing all of your// requests, call// the "close" method on the client to safely clean up any remaining background// resources.Stringendpoint=String.format("%s-documentai.googleapis.com:443",location);DocumentProcessorServiceSettingssettings=DocumentProcessorServiceSettings.newBuilder().setEndpoint(endpoint).build();try(DocumentProcessorServiceClientclient=DocumentProcessorServiceClient.create(settings)){// The full resource name of the processor, e.g.:// projects/project-id/locations/location/processor/processor-id// You must create new processors in the Cloud Console firstStringname=String.format("projects/%s/locations/%s/processors/%s",projectId,location,processorId);// Read the file.byte[]imageFileData=Files.readAllBytes(Paths.get(filePath));// Convert the image data to a Buffer and base64 encode it.ByteStringcontent=ByteString.copyFrom(imageFileData);RawDocumentdocument=RawDocument.newBuilder().setContent(content).setMimeType("application/pdf").build();// Configure the process request.ProcessRequestrequest=ProcessRequest.newBuilder().setName(name).setRawDocument(document).build();// Recognizes text entities in the PDF documentProcessResponseresult=client.processDocument(request);DocumentdocumentResponse=result.getDocument();// Get all of the document text as one big stringStringtext=documentResponse.getText();// Read the text recognition output from the processorSystem.out.println("The document contains the following paragraphs:");Document.PagefirstPage=documentResponse.getPages(0);List<Document.Page.Paragraph>paragraphs=firstPage.getParagraphsList();for(Document.Page.Paragraphparagraph:paragraphs){StringparagraphText=getText(paragraph.getLayout().getTextAnchor(),text);System.out.printf("Paragraph text:\n%s\n",paragraphText);}}}// Extract shards from the text fieldprivatestaticStringgetText(Document.TextAnchortextAnchor,Stringtext){if(textAnchor.getTextSegmentsList().size() >0){intstartIdx=(int)textAnchor.getTextSegments(0).getStartIndex();intendIdx=(int)textAnchor.getTextSegments(0).getEndIndex();returntext.substring(startIdx,endIdx);}return"[NO TEXT]";}}

/** * TODO(developer): Uncomment these variables before running the sample. */// const projectId = 'YOUR_PROJECT_ID';// const location = 'YOUR_PROJECT_LOCATION'; // Format is 'us' or 'eu'// const processorId = 'YOUR_PROCESSOR_ID'; // Create processor in Cloud Console// const filePath = '/path/to/local/pdf';const{DocumentProcessorServiceClient}=require('@google-cloud/documentai').v1;// Instantiates a client// apiEndpoint regions available: eu-documentai.googleapis.com, us-documentai.googleapis.com (Required if using eu based processor)// const client = new DocumentProcessorServiceClient({apiEndpoint: 'eu-documentai.googleapis.com'});constclient=newDocumentProcessorServiceClient();asyncfunctionquickstart(){// The full resource name of the processor, e.g.:// projects/project-id/locations/location/processor/processor-id// You must create new processors in the Cloud Console firstconstname=`projects/${projectId}/locations/${location}/processors/${processorId}`;// Read the file into memory.constfs=require('fs').promises;constimageFile=awaitfs.readFile(filePath);// Convert the image data to a Buffer and base64 encode it.constencodedImage=Buffer.from(imageFile).toString('base64');constrequest={name,rawDocument:{content:encodedImage,mimeType:'application/pdf',},};// Recognizes text entities in the PDF documentconst[result]=awaitclient.processDocument(request);const{document}=result;// Get all of the document text as one big stringconst{text}=document;// Extract shards from the text fieldconstgetText=textAnchor=>{if(!textAnchor.textSegments||textAnchor.textSegments.length===0){return'';}// First shard in document doesn't have startIndex propertyconststartIndex=textAnchor.textSegments[0].startIndex||0;constendIndex=textAnchor.textSegments[0].endIndex;returntext.substring(startIndex,endIndex);};// Read the text recognition output from the processorconsole.log('The document contains the following paragraphs:');const[page1]=document.pages;const{paragraphs}=page1;for(constparagraphofparagraphs){constparagraphText=getText(paragraph.layout.textAnchor);console.log(`Paragraph text:\n${paragraphText}`);}}

# Include the autoloader for libraries installed with Composer.require __DIR__ . '/vendor/autoload.php';# Import the Google Cloud client library.use Google\Cloud\DocumentAI\V1\Client\DocumentProcessorServiceClient;use Google\Cloud\DocumentAI\V1\RawDocument;use Google\Cloud\DocumentAI\V1\ProcessRequest;# TODO(developer): Update the following lines before running the sample.# Your Google Cloud Platform project ID.$projectId = 'YOUR_PROJECT_ID';# Your Processor Location.$location = 'us';# Your Processor ID as hexadecimal characters.# Not to be confused with the Processor Display Name.$processorId = 'YOUR_PROCESSOR_ID';# Path for the file to read.$documentPath = 'resources/invoice.pdf';# Create Client.$client = new DocumentProcessorServiceClient();# Read in file.$handle = fopen($documentPath, 'rb');$contents = fread($handle, filesize($documentPath));fclose($handle);# Load file contents into a RawDocument.$rawDocument = (new RawDocument())    ->setContent($contents)    ->SetMimeType('application/pdf');# Get the Fully-qualified Processor Name.$fullProcessorName = $client->processorName($projectId, $location, $processorId);# Send a ProcessRequest and get a ProcessResponse.$request = (new ProcessRequest())    ->setName($fullProcessorName)    ->setRawDocument($rawDocument);$response = $client->processDocument($request);# Show the text found in the document.printf('Document Text: %s', $response->getDocument()->getText());

fromgoogle.api_core.client_optionsimportClientOptionsfromgoogle.cloudimportdocumentai_v1# TODO(developer): Create a processor of type "OCR_PROCESSOR".# TODO(developer): Update and uncomment these variables before running the sample.# project_id = "MY_PROJECT_ID"# Processor ID as hexadecimal characters.# Not to be confused with the Processor Display Name.# processor_id = "MY_PROCESSOR_ID"# Processor location. For example: "us" or "eu".# location = "MY_PROCESSOR_LOCATION"# Path for file to process.# file_path = "/path/to/local/pdf"# Set `api_endpoint` if you use a location other than "us".opts=ClientOptions(api_endpoint=f"{location}-documentai.googleapis.com")# Initialize Document AI client.client=documentai_v1.DocumentProcessorServiceClient(client_options=opts)# Get the Fully-qualified Processor path.full_processor_name=client.processor_path(project_id,location,processor_id)# Get a Processor reference.request=documentai_v1.GetProcessorRequest(name=full_processor_name)processor=client.get_processor(request=request)# `processor.name` is the full resource name of the processor.# For example: `projects/{project_id}/locations/{location}/processors/{processor_id}`print(f"Processor Name:{processor.name}")# Read the file into memory.withopen(file_path,"rb")asimage:image_content=image.read()# Load binary data.# For supported MIME types, refer to https://cloud.google.com/document-ai/docs/file-typesraw_document=documentai_v1.RawDocument(content=image_content,mime_type="application/pdf",)# Send a request and get the processed document.request=documentai_v1.ProcessRequest(name=processor.name,raw_document=raw_document)result=client.process_document(request=request)document=result.document# Read the text recognition output from the processor.# For a full list of `Document` object attributes, reference this page:# https://cloud.google.com/document-ai/docs/reference/rest/v1/Documentprint("The document contains the following text:")print(document.text)

require"google/cloud/document_ai/v1"### Document AI quickstart## @param project_id [String] Your Google Cloud project (e.g. "my-project")# @param location_id [String] Your Processor Location (e.g. "us")# @param processor_id [String] Your Processor ID (e.g. "a14dae8f043b60bd")# @param file_path [String] Path to Local File (e.g. "invoice.pdf")# @param mime_type [String] Refer to https://cloud.google.com/document-ai/docs/file-types (e.g. "application/pdf")#defquickstartproject_id:,location_id:,processor_id:,file_path:,mime_type:# Create the Document AI client.client=::Google::Cloud::DocumentAI::V1::DocumentProcessorService::Client.newdo|config|config.endpoint="#{location_id}-documentai.googleapis.com"end# Build the resource name from the project.name=client.processor_path(project:project_id,location:location_id,processor:processor_id)# Read the bytes into memorycontent=File.binreadfile_path# Create requestrequest=Google::Cloud::DocumentAI::V1::ProcessRequest.new(skip_human_review:true,name:name,raw_document:{content:content,mime_type:mime_type})# Process documentresponse=client.process_documentrequest# Handle responseputsresponse.document.textend