Cloud Document AI API C++ Client Library

An idiomatic C++ client library for the Cloud Document AI API, a service that uses machine learning on a scalable cloud-based platform to help your organization efficiently scan, analyze, and understand documents.

While this library is GA, please note Google Cloud C++ client libraries do not follow Semantic Versioning.


The following shows the code that you'll run in the google/cloud/documentai/quickstart/ directory, which should give you a taste of the Cloud Document AI API C++ client library API.

#include "google/cloud/documentai/v1/document_processor_client.h"
#include <fstream>
#include <iostream>

int main(int argc, char* argv[]) try {
  if (argc != 5) {
    std::cerr << "Usage: " << argv[0]
              << " project-id location-id processor-id filename (PDF only)\n";
    return 1;
  std::string const location = argv[2];
  if (location != "us" && location != "eu") {
    std::cerr << "location-id must be either 'us' or 'eu'\n";
    return 1;

  namespace documentai = ::google::cloud::documentai_v1;
  auto client = documentai::DocumentProcessorServiceClient(

  auto const resource = std::string{"projects/"} + argv[1] + "/locations/" +
                        location + "/processors/" + argv[3];

  google::cloud::documentai::v1::ProcessRequest req;
  auto& doc = *req.mutable_raw_document();
  std::ifstream is(argv[4]);
  doc.set_content(std::string{std::istreambuf_iterator<char>(is), {}});

  auto resp = client.ProcessDocument(std::move(req));
  if (!resp) throw std::move(resp).status();
  std::cout << resp->document().text() << "\n";

  return 0;
} catch (google::cloud::Status const& status) {
  std::cerr << "google::cloud::Status thrown: " << status << "\n";
  return 1;

Main classes

The main class in this library is documentai_v1::DocumentProcessorServiceClient. All RPCs are exposed as member functions of this class. Other classes provide helpers, configuration parameters, and infrastructure to mock documentai_v1::DocumentProcessorServiceClient when testing your application.

Retry, Backoff, and Idempotency Policies.

The library automatically retries requests that fail with transient errors, and uses exponential backoff to backoff between retries. Application developers can override the default policies.

More Information