Google Cloud Vision

Google Cloud Vision analyzes images and returns insights such as labels, text, faces and landmarks. The gRPC API is exposed through the google.cloud.vision.v1.ImageAnnotator service, reached at vision.googleapis.com:443 over TLS, and the main method is BatchAnnotateImages, which annotates a batch of images in a single call.

Requests are built with TsgcGRPCVisionBatchAnnotateImagesRequest: call AddRequest to add an image (Image.Source.GcsImageUri for a gs:// image) and AddFeature to request a feature, setting FeatureType (for example LABEL_DETECTION) and MaxResults.

The example below authenticates with a service-account JWT, wires a TsgcGRPCClient over a TsgcHTTP2Client to the Vision host, sets the authorization Bearer metadata and calls BatchAnnotateImages to run label detection on a gs:// image:

    oHTTP2 := TsgcHTTP2Client.Create(nil);
    oHTTP2.Host := 'vision.googleapis.com';
    oHTTP2.Port := 443;
    oHTTP2.TLS := True;

    oGRPC := TsgcGRPCClient.Create(nil);
    oGRPC.Client := oHTTP2;

    // service-account JWT authentication
    oGRPC.GoogleCloudOptions.JWT.KeyFile := 'service-account.json';
    oGRPC.GoogleCloudOptions.JWT.API_Endpoint := 'https://vision.googleapis.com/';
    oGRPC.DefaultMetadata.AddValue('authorization', 'Bearer ' + oGRPC.GoogleCloudOptions.JWT.Token);

    // build the typed request and call the method
    oRequest := TsgcGRPCVisionBatchAnnotateImagesRequest.Create;
    try
      oImage := oRequest.AddRequest;
      oImage.Image.Source.GcsImageUri := 'gs://my-bucket/photo.jpg';
      oImage.AddFeature('LABEL_DETECTION', 10);
      oResponse := oGRPC.Call('google.cloud.vision.v1.ImageAnnotator', 'BatchAnnotateImages', oRequest.ToBytes);
      ShowMessage(oResponse.DataString);
    finally
      oRequest.Free;
    end;