Previsione per l'estrazione delle entità di testo

Recupera una previsione per l'estrazione delle entità di testo utilizzando il metodo di previsione.

Per saperne di più

Per la documentazione dettagliata che include questo esempio di codice, vedi quanto segue:

Ottenere previsioni da un modello di estrazione delle entità di testo

Esempio di codice

Java

Prima di provare questo esempio, segui le istruzioni di configurazione di Java riportate nella guida rapida di Vertex AI sull'utilizzo delle librerie client. Per maggiori informazioni, consulta la documentazione di riferimento dell'API Java Vertex AI.

Per eseguire l'autenticazione in Vertex AI, configura le Credenziali predefinite dell'applicazione. Per maggiori informazioni, consulta Configurare l'autenticazione per un ambiente di sviluppo locale.


import com.google.cloud.aiplatform.util.ValueConverter;
import com.google.cloud.aiplatform.v1.EndpointName;
import com.google.cloud.aiplatform.v1.PredictResponse;
import com.google.cloud.aiplatform.v1.PredictionServiceClient;
import com.google.cloud.aiplatform.v1.PredictionServiceSettings;
import com.google.cloud.aiplatform.v1.schema.predict.instance.TextExtractionPredictionInstance;
import com.google.cloud.aiplatform.v1.schema.predict.prediction.TextExtractionPredictionResult;
import com.google.protobuf.Value;
import java.io.IOException;
import java.util.ArrayList;
import java.util.List;

public class PredictTextEntityExtractionSample {

  public static void main(String[] args) throws IOException {
    // TODO(developer): Replace these variables before running the sample.
    String project = "YOUR_PROJECT_ID";
    String content = "YOUR_TEXT_CONTENT";
    String endpointId = "YOUR_ENDPOINT_ID";

    predictTextEntityExtraction(project, content, endpointId);
  }

  static void predictTextEntityExtraction(String project, String content, String endpointId)
      throws IOException {
    PredictionServiceSettings predictionServiceSettings =
        PredictionServiceSettings.newBuilder()
            .setEndpoint("us-central1-aiplatform.googleapis.com:443")
            .build();

    // 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 predictionServiceClient =
        PredictionServiceClient.create(predictionServiceSettings)) {
      String location = "us-central1";
      String jsonString = "{\"content\": \"" + content + "\"}";

      EndpointName endpointName = EndpointName.of(project, location, endpointId);

      TextExtractionPredictionInstance instance =
          TextExtractionPredictionInstance.newBuilder().setContent(content).build();

      List<Value> instances = new ArrayList<>();
      instances.add(ValueConverter.toValue(instance));

      PredictResponse predictResponse =
          predictionServiceClient.predict(endpointName, instances, ValueConverter.EMPTY_VALUE);
      System.out.println("Predict Text Entity Extraction Response");
      System.out.format("\tDeployed Model Id: %s\n", predictResponse.getDeployedModelId());

      System.out.println("Predictions");
      for (Value prediction : predictResponse.getPredictionsList()) {
        TextExtractionPredictionResult.Builder resultBuilder =
            TextExtractionPredictionResult.newBuilder();

        TextExtractionPredictionResult result =
            (TextExtractionPredictionResult) ValueConverter.fromValue(resultBuilder, prediction);

        for (int i = 0; i < result.getIdsCount(); i++) {
          long textStartOffset = result.getTextSegmentStartOffsets(i);
          long textEndOffset = result.getTextSegmentEndOffsets(i);
          String entity = content.substring((int) textStartOffset, (int) textEndOffset);

          System.out.format("\tEntity: %s\n", entity);
          System.out.format("\tEntity type: %s\n", result.getDisplayNames(i));
          System.out.format("\tConfidences: %f\n", result.getConfidences(i));
          System.out.format("\tIDs: %d\n", result.getIds(i));
        }
      }
    }
  }
}

Node.js

Prima di provare questo esempio, segui le istruzioni di configurazione di Node.js riportate nella guida rapida di Vertex AI sull'utilizzo delle librerie client. Per maggiori informazioni, consulta la documentazione di riferimento dell'API Node.js Vertex AI.

/**
 * TODO(developer): Uncomment these variables before running the sample.\
 * (Not necessary if passing values as arguments)
 */

// const text = "YOUR_PREDICTION_TEXT";
// const endpointId = "YOUR_ENDPOINT_ID";
// const project = 'YOUR_PROJECT_ID';
// const location = 'YOUR_PROJECT_LOCATION';
const aiplatform = require('@google-cloud/aiplatform');
const {instance, prediction} =
  aiplatform.protos.google.cloud.aiplatform.v1.schema.predict;

// Imports the Google Cloud Model Service Client library
const {PredictionServiceClient} = aiplatform.v1;

// Specifies the location of the api endpoint
const clientOptions = {
  apiEndpoint: 'us-central1-aiplatform.googleapis.com',
};

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

async function predictTextEntityExtraction() {
  // Configure the endpoint resource
  const endpoint = `projects/${project}/locations/${location}/endpoints/${endpointId}`;

  const instanceObj = new instance.TextExtractionPredictionInstance({
    content: text,
  });
  const instanceVal = instanceObj.toValue();
  const instances = [instanceVal];

  const request = {
    endpoint,
    instances,
  };

  // Predict request
  const [response] = await predictionServiceClient.predict(request);

  console.log('Predict text entity extraction response :');
  console.log(`\tDeployed model id : ${response.deployedModelId}`);

  console.log('\nPredictions :');
  for (const predictionResultValue of response.predictions) {
    const predictionResult =
      prediction.TextExtractionPredictionResult.fromValue(
        predictionResultValue
      );

    for (const [i, label] of predictionResult.displayNames.entries()) {
      const textStartOffset = parseInt(
        predictionResult.textSegmentStartOffsets[i]
      );
      const textEndOffset = parseInt(
        predictionResult.textSegmentEndOffsets[i]
      );
      const entity = text.substring(textStartOffset, textEndOffset);
      console.log(`\tEntity: ${entity}`);
      console.log(`\tEntity type: ${label}`);
      console.log(`\tConfidences: ${predictionResult.confidences[i]}`);
      console.log(`\tIDs: ${predictionResult.ids[i]}\n\n`);
    }
  }
}
predictTextEntityExtraction();

Python

Prima di provare questo esempio, segui le istruzioni di configurazione di Python riportate nella guida rapida di Vertex AI sull'utilizzo delle librerie client. Per maggiori informazioni, consulta la documentazione di riferimento dell'API Python Vertex AI.

from google.cloud import aiplatform
from google.cloud.aiplatform.gapic.schema import predict
from google.protobuf import json_format
from google.protobuf.struct_pb2 import Value

def predict_text_entity_extraction_sample(
    project: str,
    endpoint_id: str,
    content: str,
    location: str = "us-central1",
    api_endpoint: str = "us-central1-aiplatform.googleapis.com",
):
    # The AI Platform services require regional API endpoints.
    client_options = {"api_endpoint": api_endpoint}
    # Initialize client that will be used to create and send requests.
    # This client only needs to be created once, and can be reused for multiple requests.
    client = aiplatform.gapic.PredictionServiceClient(client_options=client_options)
    # The format of each instance should conform to the deployed model's prediction input schema
    instance = predict.instance.TextExtractionPredictionInstance(
        content=content,
    ).to_value()
    instances = [instance]
    parameters_dict = {}
    parameters = json_format.ParseDict(parameters_dict, Value())
    endpoint = client.endpoint_path(
        project=project, location=location, endpoint=endpoint_id
    )
    response = client.predict(
        endpoint=endpoint, instances=instances, parameters=parameters
    )
    print("response")
    print(" deployed_model_id:", response.deployed_model_id)
    # See gs://google-cloud-aiplatform/schema/predict/prediction/text_extraction_1.0.0.yaml for the format of the predictions.
    predictions = response.predictions
    for prediction in predictions:
        print(" prediction:", dict(prediction))

Passaggi successivi

Per cercare e filtrare esempi di codice per altri prodotti Google Cloud, consulta il browser di esempio Google Cloud.