I am trying to create PoC for Google Cloud DocumentAI V1 using this
I am using DocAI to convert .pdf files into text using DocAI BatchProcessing. I have created console application with below code, which is working fine with single document. But when I try to process multiple pdf documents it's throwing exception,
Grpc.Core.RpcException: 'Status(StatusCode="DeadlineExceeded",
Detail="Deadline Exceeded",
DebugException="Grpc.Core.Internal.CoreErrorDetailException:
{"created":"@1650465671.748000000","description":"Deadline
Exceeded","file":"......\src\core\ext\filters\deadline\deadline_filter.cc","file_line":81,"grpc_status":4}")'
public static class DocAIBatchProcess
{
const string projectId = "PROJECTID";
const string processorId = "PROCESSID";
const string location = "us";
const string gcsInputBucketName = "BUCKETNAME";
const string gcsOutputBucketName = "gs://BUCKETNAME/OUTPUTFOLDER/";
const string gcsOutputUriPrefix = "PREFIX";
const string prefix = "INPUTFOLDER/";
const string delimiter = "/";
public static bool BatchProcessDocument(this IEnumerable<GCPStorage.Object> storageObjects)
{
Console.WriteLine("\n");
Console.WriteLine("Processing documents started...");
Console.WriteLine("-------------------------------");
DocumentProcessorServiceClient documentProcessorServiceClient = DocumentProcessorServiceClient.Create();
string name = $"projects/{projectId}/locations/{location}/processors/{processorId}";
GcsDocument gcsDocument = null;
GcsDocuments gcsDocuments = new GcsDocuments();
var storage = StorageClient.Create();
foreach (var storageObject in storageObjects)
{
if (storageObject.Name != prefix)
{
gcsDocument = new GcsDocument()
{
GcsUri = $"gs://gcsInputBucketName/{storageObject.Name}",
MimeType = "application/pdf"
};
gcsDocuments.Documents.Add(gcsDocument);
}
}
//Input Config
BatchDocumentsInputConfig inputConfig = new BatchDocumentsInputConfig();
inputConfig.GcsDocuments = gcsDocuments;
//Output Config
var fullGcsPath = $"gs://{gcsOutputBucketName}/{gcsOutputUriPrefix}/";
GcsOutputConfig gcsOutputConfig = new GcsOutputConfig();
gcsOutputConfig.GcsUri = gcsOutputBucketName;
DocumentOutputConfig documentOutputConfig = new DocumentOutputConfig();
documentOutputConfig.GcsOutputConfig = gcsOutputConfig;
// Configure the batch process request.
BatchProcessRequest batchProcessRequest = new BatchProcessRequest();
batchProcessRequest.Name = name;
batchProcessRequest.InputDocuments = inputConfig;
batchProcessRequest.DocumentOutputConfig = documentOutputConfig;
// Make the request
Operation<BatchProcessResponse, BatchProcessMetadata> response = documentProcessorServiceClient.BatchProcessDocuments(batchProcessRequest);
// Poll until the returned long-running operation is complete
Operation<BatchProcessResponse, BatchProcessMetadata> completedResponse = response.PollUntilCompleted();
// Retrieve the operation result
BatchProcessResponse result = completedResponse.Result;
}
}
DeadlineExceeded : "Deadline expired before operation could complete."
I tried looking into documentation but couldn't find anything concreate. If someone knows about why this is happening ? Any assistance would be greatly appreciated.