This documentation is for AutoML Natural Language, which is different from Vertex AI. If you are using Vertex AI, see the Vertex AI documentation.

Analyzing documents

After you have created (trained) a model, you can request predictions from the model. A prediction occurs when you submit a document to the model and ask it to analyze the document according to the objective for that model (classification, entity extraction, or sentiment analysis).

AutoML Natural Language supports both online prediction, where you submit a single document and the model returns the analysis synchronously, and batch prediction, where you submit a collection of documents that the model analyzes asynchronously.

Online prediction

To make a prediction using the AutoML Natural Language UI:

  1. Click the lightbulb icon in the left navigation bar to display the available models.

    To view the models for a different project, select the project from the drop-down list in the upper right of the title bar.

  2. Click the row for the model you want to use to analyze the document.

  3. Click the Test & Use tab just below the title bar.

  4. Enter the text you want to analyze into the text box, or click Select a file on Cloud Storage and enter the Cloud Storage path for a PDF or TIFF file.

  5. Click Predict.

Code samples

Classification

REST & CMD LINE

Before using any of the request data, make the following replacements:

  • project-id: your project ID
  • location-id: the location for the resource, us-central1 for the Global location or eu for the European Union
  • model-id: your model ID

HTTP method and URL:

POST https://automl.googleapis.com/v1/projects/project-id/locations/location-id/models/model-id:predict

Request JSON body:

{
  "payload" : {
    "textSnippet": {
      "content": "Google, headquartered in Mountain View, unveiled the new Android phone at the Consumer Electronic Show.  Sundar Pichai said in his keynote that users love their new Android phones.",
        "mime_type": "text/plain"
      },
  }
}

To send your request, expand one of these options:

You should receive a JSON response similar to the following:

{
  "payload": [
    {
      "displayName": "Technology",
      "classification": {
        "score": 0.8989502
      }
    },
    {
      "displayName": "Automobiles",
      "classification": {
        "score": 0.10098731
      }
    }
  ]
}

Python

from google.cloud import automl

# TODO(developer): Uncomment and set the following variables
# project_id = "YOUR_PROJECT_ID"
# model_id = "YOUR_MODEL_ID"
# content = "text to predict"

prediction_client = automl.PredictionServiceClient()

# Get the full path of the model.
model_full_id = automl.AutoMlClient.model_path(project_id, "us-central1", model_id)

# Supported mime_types: 'text/plain', 'text/html'
# https://cloud.google.com/automl/docs/reference/rpc/google.cloud.automl.v1#textsnippet
text_snippet = automl.TextSnippet(content=content, mime_type="text/plain")
payload = automl.ExamplePayload(text_snippet=text_snippet)

response = prediction_client.predict(name=model_full_id, payload=payload)

for annotation_payload in response.payload:
    print(u"Predicted class name: {}".format(annotation_payload.display_name))
    print(
        u"Predicted class score: {}".format(annotation_payload.classification.score)
    )

Java

import com.google.cloud.automl.v1.AnnotationPayload;
import com.google.cloud.automl.v1.ExamplePayload;
import com.google.cloud.automl.v1.ModelName;
import com.google.cloud.automl.v1.PredictRequest;
import com.google.cloud.automl.v1.PredictResponse;
import com.google.cloud.automl.v1.PredictionServiceClient;
import com.google.cloud.automl.v1.TextSnippet;
import java.io.IOException;

class LanguageTextClassificationPredict {

  public static void main(String[] args) throws IOException {
    // TODO(developer): Replace these variables before running the sample.
    String projectId = "YOUR_PROJECT_ID";
    String modelId = "YOUR_MODEL_ID";
    String content = "text to predict";
    predict(projectId, modelId, content);
  }

  static void predict(String projectId, String modelId, String content) throws IOException {
    // 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.
    try (PredictionServiceClient client = PredictionServiceClient.create()) {
      // Get the full path of the model.
      ModelName name = ModelName.of(projectId, "us-central1", modelId);

      // For available mime types, see:
      // https://cloud.google.com/automl/docs/reference/rest/v1/projects.locations.models/predict#textsnippet
      TextSnippet textSnippet =
          TextSnippet.newBuilder()
              .setContent(content)
              .setMimeType("text/plain") // Types: text/plain, text/html
              .build();
      ExamplePayload payload = ExamplePayload.newBuilder().setTextSnippet(textSnippet).build();
      PredictRequest predictRequest =
          PredictRequest.newBuilder().setName(name.toString()).setPayload(payload).build();

      PredictResponse response = client.predict(predictRequest);

      for (AnnotationPayload annotationPayload : response.getPayloadList()) {
        System.out.format("Predicted class name: %s\n", annotationPayload.getDisplayName());
        System.out.format(
            "Predicted sentiment score: %.2f\n\n",
            annotationPayload.getClassification().getScore());
      }
    }
  }
}

Node.js

/**
 * TODO(developer): Uncomment these variables before running the sample.
 */
// const projectId = 'YOUR_PROJECT_ID';
// const location = 'us-central1';
// const modelId = 'YOUR_MODEL_ID';
// const content = 'text to predict'

// Imports the Google Cloud AutoML library
const {PredictionServiceClient} = require('@google-cloud/automl').v1;

// Instantiates a client
const client = new PredictionServiceClient();

async function predict() {
  // Construct request
  const request = {
    name: client.modelPath(projectId, location, modelId),
    payload: {
      textSnippet: {
        content: content,
        mimeType: 'text/plain', // Types: 'text/plain', 'text/html'
      },
    },
  };

  const [response] = await client.predict(request);

  for (const annotationPayload of response.payload) {
    console.log(`Predicted class name: ${annotationPayload.displayName}`);
    console.log(
      `Predicted class score: ${annotationPayload.classification.score}`
    );
  }
}

predict();

Go

import (
	"context"
	"fmt"
	"io"

	automl "cloud.google.com/go/automl/apiv1"
	automlpb "google.golang.org/genproto/googleapis/cloud/automl/v1"
)

// languageTextClassificationPredict does a prediction for text classification.
func languageTextClassificationPredict(w io.Writer, projectID string, location string, modelID string, content string) error {
	// projectID := "my-project-id"
	// location := "us-central1"
	// modelID := "TCN123456789..."
	// content := "text to classify"

	ctx := context.Background()
	client, err := automl.NewPredictionClient(ctx)
	if err != nil {
		return fmt.Errorf("NewPredictionClient: %v", err)
	}
	defer client.Close()

	req := &automlpb.PredictRequest{
		Name: fmt.Sprintf("projects/%s/locations/%s/models/%s", projectID, location, modelID),
		Payload: &automlpb.ExamplePayload{
			Payload: &automlpb.ExamplePayload_TextSnippet{
				TextSnippet: &automlpb.TextSnippet{
					Content:  content,
					MimeType: "text/plain", // Types: "text/plain", "text/html"
				},
			},
		},
	}

	resp, err := client.Predict(ctx, req)
	if err != nil {
		return fmt.Errorf("Predict: %v", err)
	}

	for _, payload := range resp.GetPayload() {
		fmt.Fprintf(w, "Predicted class name: %v\n", payload.GetDisplayName())
		fmt.Fprintf(w, "Predicted class score: %v\n", payload.GetClassification().GetScore())
	}

	return nil
}

Additional languages

C#: Please follow the C# setup instructions on the client libraries page and then visit the AutoML Natural Language reference documentation for .NET.

PHP: Please follow the PHP setup instructions on the client libraries page and then visit the AutoML Natural Language reference documentation for PHP.

Ruby: Please follow the Ruby setup instructions on the client libraries page and then visit the AutoML Natural Language reference documentation for Ruby.

Entity extraction

REST & CMD LINE

Before using any of the request data, make the following replacements:

  • project-id: your project ID
  • location-id: the location for the resource, us-central1 for the Global location or eu for the European Union
  • model-id: your model ID

HTTP method and URL:

POST https://automl.googleapis.com/v1/projects/project-id/locations/location-id/models/model-id:predict

Request JSON body:

{
  "payload" : {
    "textSnippet": {
      "content": "The Wilms tumor-suppressor gene, WT1, plays a key role in urogenital development, and WT1 dysfunction is implicated in both neoplastic and nonneoplastic (glomerulosclerosis) disease. The analysis of diseases linked specifically with WT1 mutations, such as Denys-Drash syndrome (DDS), can provide valuable insight concerning the role of WT1 in development and disease.  We report that heterozygosity for a targeted murine Wt1 allele, Wt1 (tmT396), which truncates ZF3 at codon 396, induces mesangial sclerosis characteristic of DDS in adult heterozygous and chimeric mice. Male genital defects also were evident and there was a single case of Wilms tumor in which the transcript of the nontargeted allele showed an exon 9 skipping event, implying a causal link between Wt1 dysfunction and Wilms tumorigenesis in mice. However, the mutant WT1 (tmT396) protein accounted for only 5% of WT1 in both heterozygous embryonic stem cells and the WT. This has implications regarding the mechanism by which the mutant allele exerts its effect.",
      "mime_type": "text/plain"
      },
   }
}

To send your request, expand one of these options:

You should receive a JSON response similar to the following:

{
  "annotations": [
    {
      "text_extraction": {
        "text_segment": {
          "end_offset": 67,
          "start_offset": 62
        }
      },
      "display_name": "Modifier"
    },
    {
      "text_extraction": {
        "text_segment": {
          "end_offset": 158,
          "start_offset": 141
        }
      },
      "display_name": "SpecificDisease"
    },
    {
      "text_extraction": {
        "text_segment": {
          "end_offset": 330,
          "start_offset": 290
        }
      },
      "display_name": "SpecificDisease"
    },
    {
      "text_extraction": {
        "text_segment": {
          "end_offset": 337,
          "start_offset": 332
        }
      },
      "display_name": "SpecificDisease"
    },
    {
      "text_extraction": {
        "text_segment": {
          "end_offset": 627,
          "start_offset": 610
        }
      },
      "display_name": "Modifier"
    },
    {
      "text_extraction": {
        "text_segment": {
          "end_offset": 754,
          "start_offset": 749
        }
      },
      "display_name": "Modifier"
    },
    {
      "text_extraction": {
        "text_segment": {
          "end_offset": 875,
          "start_offset": 865
        }
      },
      "display_name": "Modifier"
    },
    {
      "text_extraction": {
        "text_segment": {
          "end_offset": 968,
          "start_offset": 951
        }
      },
      "display_name": "Modifier"
    },
    {
      "text_extraction": {
        "text_segment": {
          "end_offset": 1553,
          "start_offset": 1548
        }
      },
      "display_name": "Modifier"
    },
    {
      "text_extraction": {
        "text_segment": {
          "end_offset": 1652,
          "start_offset": 1606
        }
      },
      "display_name": "CompositeMention"
    },
    {
      "text_extraction": {
        "text_segment": {
          "end_offset": 1833,
          "start_offset": 1826
        }
      },
      "display_name": "DiseaseClass"
    },
    {
      "text_extraction": {
        "text_segment": {
          "end_offset": 1860,
          "start_offset": 1843
        }
      },
      "display_name": "SpecificDisease"
    },
    {
      "text_extraction": {
        "text_segment": {
          "end_offset": 1930,
          "start_offset": 1913
        }
      },
      "display_name": "SpecificDisease"
    },
    {
      "text_extraction": {
        "text_segment": {
          "end_offset": 2129,
          "start_offset": 2111
        }
      },
      "display_name": "SpecificDisease"
    },
    {
      "text_extraction": {
        "text_segment": {
          "end_offset": 2188,
          "start_offset": 2160
        }
      },
      "display_name": "SpecificDisease"
    },
    {
      "text_extraction": {
        "text_segment": {
          "end_offset": 2260,
          "start_offset": 2243
        }
      },
      "display_name": "Modifier"
    },
    {
      "text_extraction": {
        "text_segment": {
          "end_offset": 2356,
          "start_offset": 2339
        }
      },
      "display_name": "Modifier"
    }
  ],
}

Python

from google.cloud import automl

# TODO(developer): Uncomment and set the following variables
# project_id = "YOUR_PROJECT_ID"
# model_id = "YOUR_MODEL_ID"
# content = "text to predict"

prediction_client = automl.PredictionServiceClient()

# Get the full path of the model.
model_full_id = automl.AutoMlClient.model_path(project_id, "us-central1", model_id)

# Supported mime_types: 'text/plain', 'text/html'
# https://cloud.google.com/automl/docs/reference/rpc/google.cloud.automl.v1#textsnippet
text_snippet = automl.TextSnippet(content=content, mime_type="text/plain")
payload = automl.ExamplePayload(text_snippet=text_snippet)

response = prediction_client.predict(name=model_full_id, payload=payload)

for annotation_payload in response.payload:
    print("Text Extract Entity Types: {}".format(annotation_payload.display_name))
    print("Text Score: {}".format(annotation_payload.text_extraction.score))
    text_segment = annotation_payload.text_extraction.text_segment
    print("Text Extract Entity Content: {}".format(text_segment.content))
    print("Text Start Offset: {}".format(text_segment.start_offset))
    print("Text End Offset: {}".format(text_segment.end_offset))

Java

import com.google.cloud.automl.v1.AnnotationPayload;
import com.google.cloud.automl.v1.ExamplePayload;
import com.google.cloud.automl.v1.ModelName;
import com.google.cloud.automl.v1.PredictRequest;
import com.google.cloud.automl.v1.PredictResponse;
import com.google.cloud.automl.v1.PredictionServiceClient;
import com.google.cloud.automl.v1.TextSegment;
import com.google.cloud.automl.v1.TextSnippet;
import java.io.IOException;

class LanguageEntityExtractionPredict {

  static void predict() throws IOException {
    // TODO(developer): Replace these variables before running the sample.
    String projectId = "YOUR_PROJECT_ID";
    String modelId = "YOUR_MODEL_ID";
    String content = "text to predict";
    predict(projectId, modelId, content);
  }

  static void predict(String projectId, String modelId, String content) throws IOException {
    // 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.
    try (PredictionServiceClient client = PredictionServiceClient.create()) {
      // Get the full path of the model.
      ModelName name = ModelName.of(projectId, "us-central1", modelId);

      // For available mime types, see:
      // https://cloud.google.com/automl/docs/reference/rest/v1/projects.locations.models/predict#textsnippet
      TextSnippet textSnippet =
          TextSnippet.newBuilder()
              .setContent(content)
              .setMimeType("text/plain") // Types: text/plain, text/html
              .build();
      ExamplePayload payload = ExamplePayload.newBuilder().setTextSnippet(textSnippet).build();
      PredictRequest predictRequest =
          PredictRequest.newBuilder().setName(name.toString()).setPayload(payload).build();

      PredictResponse response = client.predict(predictRequest);

      for (AnnotationPayload annotationPayload : response.getPayloadList()) {
        System.out.format("Text Extract Entity Type: %s\n", annotationPayload.getDisplayName());
        System.out.format("Text score: %.2f\n", annotationPayload.getTextExtraction().getScore());
        TextSegment textSegment = annotationPayload.getTextExtraction().getTextSegment();
        System.out.format("Text Extract Entity Content: %s\n", textSegment.getContent());
        System.out.format("Text Start Offset: %s\n", textSegment.getStartOffset());
        System.out.format("Text End Offset: %s\n\n", textSegment.getEndOffset());
      }
    }
  }
}

Node.js

/**
 * TODO(developer): Uncomment these variables before running the sample.
 */
// const projectId = 'YOUR_PROJECT_ID';
// const location = 'us-central1';
// const modelId = 'YOUR_MODEL_ID';
// const content = 'text to predict'

// Imports the Google Cloud AutoML library
const {PredictionServiceClient} = require('@google-cloud/automl').v1;

// Instantiates a client
const client = new PredictionServiceClient();

async function predict() {
  // Construct request
  const request = {
    name: client.modelPath(projectId, location, modelId),
    payload: {
      textSnippet: {
        content: content,
        mimeType: 'text/plain', // Types: 'test/plain', 'text/html'
      },
    },
  };

  const [response] = await client.predict(request);

  for (const annotationPayload of response.payload) {
    console.log(
      `Text Extract Entity Types: ${annotationPayload.displayName}`
    );
    console.log(`Text Score: ${annotationPayload.textExtraction.score}`);
    const textSegment = annotationPayload.textExtraction.textSegment;
    console.log(`Text Extract Entity Content: ${textSegment.content}`);
    console.log(`Text Start Offset: ${textSegment.startOffset}`);
    console.log(`Text End Offset: ${textSegment.endOffset}`);
  }
}

predict();

Go

import (
	"context"
	"fmt"
	"io"

	automl "cloud.google.com/go/automl/apiv1"
	automlpb "google.golang.org/genproto/googleapis/cloud/automl/v1"
)

// languageEntityExtractionPredict does a prediction for text entity extraction.
func languageEntityExtractionPredict(w io.Writer, projectID string, location string, modelID string, content string) error {
	// projectID := "my-project-id"
	// location := "us-central1"
	// modelID := "TEN123456789..."
	// content := "text to extract entities"

	ctx := context.Background()
	client, err := automl.NewPredictionClient(ctx)
	if err != nil {
		return fmt.Errorf("NewPredictionClient: %v", err)
	}
	defer client.Close()

	req := &automlpb.PredictRequest{
		Name: fmt.Sprintf("projects/%s/locations/%s/models/%s", projectID, location, modelID),
		Payload: &automlpb.ExamplePayload{
			Payload: &automlpb.ExamplePayload_TextSnippet{
				TextSnippet: &automlpb.TextSnippet{
					Content:  content,
					MimeType: "text/plain", // Types: "text/plain", "text/html"
				},
			},
		},
	}

	resp, err := client.Predict(ctx, req)
	if err != nil {
		return fmt.Errorf("Predict: %v", err)
	}

	for _, payload := range resp.GetPayload() {
		fmt.Fprintf(w, "Text extract entity types: %v\n", payload.GetDisplayName())
		fmt.Fprintf(w, "Text score: %v\n", payload.GetTextExtraction().GetScore())
		textSegment := payload.GetTextExtraction().GetTextSegment()
		fmt.Fprintf(w, "Text extract entity content: %v\n", textSegment.GetContent())
		fmt.Fprintf(w, "Text start offset: %v\n", textSegment.GetStartOffset())
		fmt.Fprintf(w, "Text end offset: %v\n", textSegment.GetEndOffset())
	}

	return nil
}

Additional languages

C#: Please follow the C# setup instructions on the client libraries page and then visit the AutoML Natural Language reference documentation for .NET.

PHP: Please follow the PHP setup instructions on the client libraries page and then visit the AutoML Natural Language reference documentation for PHP.

Ruby: Please follow the Ruby setup instructions on the client libraries page and then visit the AutoML Natural Language reference documentation for Ruby.

Sentiment analysis

REST & CMD LINE

Before using any of the request data, make the following replacements:

  • project-id: your project ID
  • location-id: the location for the resource, us-central1 for the Global location or eu for the European Union
  • model-id: your model ID

HTTP method and URL:

POST https://automl.googleapis.com/v1/projects/project-id/locations/location-id/models/model-id:predict

Request JSON body:

{
  "payload" : {
    "textSnippet": {
      "content": "Enjoy your vacation!",
         "mime_type": "text/plain"
       },
  }
}

To send your request, expand one of these options:

You should receive a successful status code (2xx) and an empty response.

Python

from google.cloud import automl

# TODO(developer): Uncomment and set the following variables
# project_id = "YOUR_PROJECT_ID"
# model_id = "YOUR_MODEL_ID"
# content = "text to predict"

prediction_client = automl.PredictionServiceClient()

# Get the full path of the model.
model_full_id = automl.AutoMlClient.model_path(project_id, "us-central1", model_id)

# Supported mime_types: 'text/plain', 'text/html'
# https://cloud.google.com/automl/docs/reference/rpc/google.cloud.automl.v1#textsnippet
text_snippet = automl.TextSnippet(content=content, mime_type="text/plain")
payload = automl.ExamplePayload(text_snippet=text_snippet)

response = prediction_client.predict(name=model_full_id, payload=payload)

for annotation_payload in response.payload:
    print("Predicted class name: {}".format(annotation_payload.display_name))
    print(
        "Predicted sentiment score: {}".format(
            annotation_payload.text_sentiment.sentiment
        )
    )

Java

import com.google.cloud.automl.v1.AnnotationPayload;
import com.google.cloud.automl.v1.ExamplePayload;
import com.google.cloud.automl.v1.ModelName;
import com.google.cloud.automl.v1.PredictRequest;
import com.google.cloud.automl.v1.PredictResponse;
import com.google.cloud.automl.v1.PredictionServiceClient;
import com.google.cloud.automl.v1.TextSnippet;
import java.io.IOException;

class LanguageSentimentAnalysisPredict {

  static void predict() throws IOException {
    // TODO(developer): Replace these variables before running the sample.
    String projectId = "YOUR_PROJECT_ID";
    String modelId = "YOUR_MODEL_ID";
    String content = "text to predict";
    predict(projectId, modelId, content);
  }

  static void predict(String projectId, String modelId, String content) throws IOException {
    // 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.
    try (PredictionServiceClient client = PredictionServiceClient.create()) {
      // Get the full path of the model.
      ModelName name = ModelName.of(projectId, "us-central1", modelId);

      // For available mime types, see:
      // https://cloud.google.com/automl/docs/reference/rest/v1/projects.locations.models/predict#textsnippet
      TextSnippet textSnippet =
          TextSnippet.newBuilder()
              .setContent(content)
              .setMimeType("text/plain") // Types: text/plain, text/html
              .build();
      ExamplePayload payload = ExamplePayload.newBuilder().setTextSnippet(textSnippet).build();
      PredictRequest predictRequest =
          PredictRequest.newBuilder().setName(name.toString()).setPayload(payload).build();

      PredictResponse response = client.predict(predictRequest);

      for (AnnotationPayload annotationPayload : response.getPayloadList()) {
        System.out.format("Predicted class name: %s\n", annotationPayload.getDisplayName());
        System.out.format(
            "Predicted sentiment score: %d\n", annotationPayload.getTextSentiment().getSentiment());
      }
    }
  }
}

Node.js

/**
 * TODO(developer): Uncomment these variables before running the sample.
 */
// const projectId = 'YOUR_PROJECT_ID';
// const location = 'us-central1';
// const modelId = 'YOUR_MODEL_ID';
// const content = 'text to predict'

// Imports the Google Cloud AutoML library
const {PredictionServiceClient} = require('@google-cloud/automl').v1;

// Instantiates a client
const client = new PredictionServiceClient();

async function predict() {
  // Construct request
  const request = {
    name: client.modelPath(projectId, location, modelId),
    payload: {
      textSnippet: {
        content: content,
        mimeType: 'text/plain', // Types: 'test/plain', 'text/html'
      },
    },
  };

  const [response] = await client.predict(request);

  for (const annotationPayload of response.payload) {
    console.log(`Predicted class name: ${annotationPayload.displayName}`);
    console.log(
      `Predicted sentiment score: ${annotationPayload.textSentiment.sentiment}`
    );
  }
}

predict();

Go

import (
	"context"
	"fmt"
	"io"

	automl "cloud.google.com/go/automl/apiv1"
	automlpb "google.golang.org/genproto/googleapis/cloud/automl/v1"
)

// languageSentimentAnalysisPredict does a prediction for text sentiment analysis.
func languageSentimentAnalysisPredict(w io.Writer, projectID string, location string, modelID string, content string) error {
	// projectID := "my-project-id"
	// location := "us-central1"
	// modelID := "TST123456789..."
	// content := "text to analyze sentiment"

	ctx := context.Background()
	client, err := automl.NewPredictionClient(ctx)
	if err != nil {
		return fmt.Errorf("NewPredictionClient: %v", err)
	}
	defer client.Close()

	req := &automlpb.PredictRequest{
		Name: fmt.Sprintf("projects/%s/locations/%s/models/%s", projectID, location, modelID),
		Payload: &automlpb.ExamplePayload{
			Payload: &automlpb.ExamplePayload_TextSnippet{
				TextSnippet: &automlpb.TextSnippet{
					Content:  content,
					MimeType: "text/plain", // Types: "text/plain", "text/html"
				},
			},
		},
	}

	resp, err := client.Predict(ctx, req)
	if err != nil {
		return fmt.Errorf("Predict: %v", err)
	}

	for _, payload := range resp.GetPayload() {
		fmt.Fprintf(w, "Predicted class name: %v\n", payload.GetDisplayName())
		fmt.Fprintf(w, "Predicted sentiment score: %v\n", payload.GetTextSentiment().GetSentiment())
	}

	return nil
}

Additional languages

C#: Please follow the C# setup instructions on the client libraries page and then visit the AutoML Natural Language reference documentation for .NET.

PHP: Please follow the PHP setup instructions on the client libraries page and then visit the AutoML Natural Language reference documentation for PHP.

Ruby: Please follow the Ruby setup instructions on the client libraries page and then visit the AutoML Natural Language reference documentation for Ruby.

Batch prediction

If you would like to use your model to do high-throughput asynchronous prediction on a corpus of documents you can use the batchPredict method. The batch prediction methods require you to specify input and output URIs that point to locations in Cloud Storage buckets.

The input URI points to a CSV or JSONL file, which specifies the content to analyze. Use a CSV file for classification and sentiment analysis. Use a JSONL file for entity extraction. The output specifies a location where AutoML Natural Language saves results from the batch prediction.

For classification and sentiment analysis, create a CSV file with a single column that lists the input files to classify, one file per row. The CSV file and each input file needs to be stored in your Cloud Storage bucket.

gs://folder/text1.txt
gs://folder/text2.pdf

For entity extraction, you need to prepare a JSONL file that contains all of the content to analyze, either inline or as links to files that are stored in a Cloud Storage bucket. The following example shows inline content that is included in the JSONL file. Each item must include a unique id.

{ "id": "0", "text_snippet": { "content": "First item content to be analyzed." } }
{ "id": "1", "text_snippet": { "content": "Second item content to be analyzed." } }
...
{ "id": "n", "text_snippet": { "content": "Last item content to be analyzed." } }

The following example shows a JSONL file that contains links to input files, which must be in Cloud Storage buckets.

{ "document": { "input_config": { "gcs_source": { "input_uris": [ "gs://folder/document1.pdf" ] } } } }
{ "document": { "input_config": { "gcs_source": { "input_uris": [ "gs://folder/document2.tif" ] } } } }
...

REST & CMD LINE

Before using any of the request data, make the following replacements:

  • project-id: your project ID
  • location-id: the location for the resource, us-central1 for the Global location or eu for the European Union
  • model-id: your model ID

HTTP method and URL:

POST https://automl.googleapis.com/v1/projects/project-id/locations/location-id/models/model-id:batchPredict

Request JSON body:

{
  "input_config": { "gcs_source": { "input_uris": [ "csv-file-URI"] } },
  "output_config": { "gcs_destination": { "output_uri_prefix": "dest-dir-URI" } }
 }

To send your request, expand one of these options:

You should see output similar to the following. You can use the operation ID to get the status of the task. For an example, see Getting the status of an operation.

{
  "name": "projects/434039606874/locations/us-central1/operations/TCN8195786061721370625",
  "metadata": {
    "@type": "type.googleapis.com/google.cloud.automl.v1beta1.OperationMetadata",
    "createTime": "2019-03-13T15:37:49.972372Z",
    "updateTime": "2019-03-13T15:37:49.972372Z"
  }
}

Python

from google.cloud import automl

# TODO(developer): Uncomment and set the following variables
# project_id = "YOUR_PROJECT_ID"
# model_id = "YOUR_MODEL_ID"
# input_uri = "gs://YOUR_BUCKET_ID/path/to/your/input/csv_or_jsonl"
# output_uri = "gs://YOUR_BUCKET_ID/path/to/save/results/"

prediction_client = automl.PredictionServiceClient()

# Get the full path of the model.
model_full_id = f"projects/{project_id}/locations/us-central1/models/{model_id}"

gcs_source = automl.GcsSource(input_uris=[input_uri])

input_config = automl.BatchPredictInputConfig(gcs_source=gcs_source)
gcs_destination = automl.GcsDestination(output_uri_prefix=output_uri)
output_config = automl.BatchPredictOutputConfig(gcs_destination=gcs_destination)

response = prediction_client.batch_predict(
    name=model_full_id, input_config=input_config, output_config=output_config
)

print("Waiting for operation to complete...")
print(
    f"Batch Prediction results saved to Cloud Storage bucket. {response.result()}"
)

Java

import com.google.api.gax.longrunning.OperationFuture;
import com.google.cloud.automl.v1.BatchPredictInputConfig;
import com.google.cloud.automl.v1.BatchPredictOutputConfig;
import com.google.cloud.automl.v1.BatchPredictRequest;
import com.google.cloud.automl.v1.BatchPredictResult;
import com.google.cloud.automl.v1.GcsDestination;
import com.google.cloud.automl.v1.GcsSource;
import com.google.cloud.automl.v1.ModelName;
import com.google.cloud.automl.v1.OperationMetadata;
import com.google.cloud.automl.v1.PredictionServiceClient;
import java.io.IOException;
import java.util.concurrent.ExecutionException;

class BatchPredict {

  static void batchPredict() throws IOException, ExecutionException, InterruptedException {
    // TODO(developer): Replace these variables before running the sample.
    String projectId = "YOUR_PROJECT_ID";
    String modelId = "YOUR_MODEL_ID";
    String inputUri = "gs://YOUR_BUCKET_ID/path_to_your_input_csv_or_jsonl";
    String outputUri = "gs://YOUR_BUCKET_ID/path_to_save_results/";
    batchPredict(projectId, modelId, inputUri, outputUri);
  }

  static void batchPredict(String projectId, String modelId, String inputUri, String outputUri)
      throws IOException, ExecutionException, InterruptedException {
    // 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.
    try (PredictionServiceClient client = PredictionServiceClient.create()) {
      // Get the full path of the model.
      ModelName name = ModelName.of(projectId, "us-central1", modelId);
      GcsSource gcsSource = GcsSource.newBuilder().addInputUris(inputUri).build();
      BatchPredictInputConfig inputConfig =
          BatchPredictInputConfig.newBuilder().setGcsSource(gcsSource).build();
      GcsDestination gcsDestination =
          GcsDestination.newBuilder().setOutputUriPrefix(outputUri).build();
      BatchPredictOutputConfig outputConfig =
          BatchPredictOutputConfig.newBuilder().setGcsDestination(gcsDestination).build();
      BatchPredictRequest request =
          BatchPredictRequest.newBuilder()
              .setName(name.toString())
              .setInputConfig(inputConfig)
              .setOutputConfig(outputConfig)
              .build();

      OperationFuture<BatchPredictResult, OperationMetadata> future =
          client.batchPredictAsync(request);

      System.out.println("Waiting for operation to complete...");
      BatchPredictResult response = future.get();
      System.out.println("Batch Prediction results saved to specified Cloud Storage bucket.");
    }
  }
}

Node.js

/**
 * TODO(developer): Uncomment these variables before running the sample.
 */
// const projectId = 'YOUR_PROJECT_ID';
// const location = 'us-central1';
// const modelId = 'YOUR_MODEL_ID';
// const inputUri = 'gs://YOUR_BUCKET_ID/path_to_your_input_csv_or_jsonl';
// const outputUri = 'gs://YOUR_BUCKET_ID/path_to_save_results/';

// Imports the Google Cloud AutoML library
const {PredictionServiceClient} = require('@google-cloud/automl').v1;

// Instantiates a client
const client = new PredictionServiceClient();

async function batchPredict() {
  // Construct request
  const request = {
    name: client.modelPath(projectId, location, modelId),
    inputConfig: {
      gcsSource: {
        inputUris: [inputUri],
      },
    },
    outputConfig: {
      gcsDestination: {
        outputUriPrefix: outputUri,
      },
    },
  };

  const [operation] = await client.batchPredict(request);

  console.log('Waiting for operation to complete...');
  // Wait for operation to complete.
  const [response] = await operation.promise();
  console.log(
    `Batch Prediction results saved to Cloud Storage bucket. ${response}`
  );
}

batchPredict();

Go

import (
	"context"
	"fmt"
	"io"

	automl "cloud.google.com/go/automl/apiv1"
	automlpb "google.golang.org/genproto/googleapis/cloud/automl/v1"
)

// batchPredict does a batch prediction.
func batchPredict(w io.Writer, projectID string, location string, modelID string, inputURI string, outputURI string) error {
	// projectID := "my-project-id"
	// location := "us-central1"
	// modelID := "ICN123456789..."
	// inputURI := "gs://BUCKET_ID/path_to_your_input_csv_or_jsonl"
	// outputURI := "gs://BUCKET_ID/path_to_save_results/"

	ctx := context.Background()
	client, err := automl.NewPredictionClient(ctx)
	if err != nil {
		return fmt.Errorf("NewPredictionClient: %v", err)
	}
	defer client.Close()

	req := &automlpb.BatchPredictRequest{
		Name: fmt.Sprintf("projects/%s/locations/%s/models/%s", projectID, location, modelID),
		InputConfig: &automlpb.BatchPredictInputConfig{
			Source: &automlpb.BatchPredictInputConfig_GcsSource{
				GcsSource: &automlpb.GcsSource{
					InputUris: []string{inputURI},
				},
			},
		},
		OutputConfig: &automlpb.BatchPredictOutputConfig{
			Destination: &automlpb.BatchPredictOutputConfig_GcsDestination{
				GcsDestination: &automlpb.GcsDestination{
					OutputUriPrefix: outputURI,
				},
			},
		},
		Params: map[string]string{
			"score_threshold": "0.8", // [0.0-1.0] Only produce results higher than this value
		},
	}

	op, err := client.BatchPredict(ctx, req)
	if err != nil {
		return fmt.Errorf("BatchPredict: %v", err)
	}
	fmt.Fprintf(w, "Processing operation name: %q\n", op.Name())

	resp, err := op.Wait(ctx)
	if err != nil {
		return fmt.Errorf("Wait: %v", err)
	}

	fmt.Fprintf(w, "Batch Prediction results saved to Cloud Storage bucket.\n")
	fmt.Fprintf(w, "%v", resp)

	return nil
}

Additional languages

C#: Please follow the C# setup instructions on the client libraries page and then visit the AutoML Natural Language reference documentation for .NET.

PHP: Please follow the PHP setup instructions on the client libraries page and then visit the AutoML Natural Language reference documentation for PHP.

Ruby: Please follow the Ruby setup instructions on the client libraries page and then visit the AutoML Natural Language reference documentation for Ruby.