Predict entity extraction

Stay organized with collections Save and categorize content based on your preferences.

Predicts text entity extraction.

Explore further

For detailed documentation that includes this code sample, see the following:

Code sample

Go

import (
	"context"
	"fmt"
	"io"

	automl "cloud.google.com/go/automl/apiv1"
	"cloud.google.com/go/automl/apiv1/automlpb"
)

// 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
}

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();

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))

What's next

To search and filter code samples for other Google Cloud products, see the Google Cloud sample browser.