Clasifica texto con un modelo de lenguaje extenso (IA generativa)

Realiza tareas de clasificación que asignan una clase o categoría al texto. Puedes especificar una lista de categorías desde la cual elegir o permitir que el modelo elija una de sus propias categorías.

Muestra de código

C#

Antes de probar este ejemplo, sigue las instrucciones de configuración para C# incluidas en la guía de inicio rápido de Vertex AI sobre cómo usar bibliotecas cliente. Para obtener más información, consulta la documentación de referencia de la API de Vertex AI C#.

Para autenticarte en Vertex AI, configura las credenciales predeterminadas de la aplicación. Si deseas obtener más información, consulta Configura la autenticación para un entorno de desarrollo local.


using Google.Cloud.AIPlatform.V1;
using System;
using System.Collections.Generic;
using System.Linq;
using Value = Google.Protobuf.WellKnownTypes.Value;

// Text Classification with a Large Language Model
public class PredictTextClassificationSample
{
    public string PredictTextClassification(
        string projectId = "your-project-id",
        string locationId = "us-central1",
        string publisher = "google",
        string model = "text-bison@001")
    {
        // Initialize client that will be used to send requests.
        // This client only needs to be created once,
        // and can be reused for multiple requests.
        var client = new PredictionServiceClientBuilder
        {
            Endpoint = $"{locationId}-aiplatform.googleapis.com"
        }.Build();

        // Configure the parent resource.
        var endpoint = EndpointName.FromProjectLocationPublisherModel(projectId, locationId, publisher, model);

        // Initialize request argument(s).
        var content = @"What is the topic for a given news headline?
- business
- entertainment
- health
- sports
- technology

Text: Pixel 7 Pro Expert Hands On Review, the Most Helpful Google Phones.
The answer is: technology

Text: Quit smoking?
The answer is: health

Text: Roger Federer reveals why he touched Rafael Nadals hand while they were crying
The answer is: sports

Text: Business relief from Arizona minimum-wage hike looking more remote
The answer is: business

Text: #TomCruise has arrived in Bari, Italy for #MissionImpossible.
The answer is: entertainment

Text: CNBC Reports Rising Digital Profit as Print Advertising Falls
The answer is:";

        var instances = new List<Value>
        {
            Value.ForStruct(new()
            {
                Fields =
                {
                    ["content"] = Value.ForString(content),
                }
            })
        };

        var parameters = Value.ForStruct(new()
        {
            Fields =
            {
                { "temperature", new Value { NumberValue = 0 } },
                { "maxDecodeSteps", new Value { NumberValue = 5 } },
                { "topP", new Value { NumberValue = 0 } },
                { "topK", new Value { NumberValue = 1 } }
            }
        });

        // Make the request.
        var response = client.Predict(endpoint, instances, parameters);

        // Parse and return the content.
        var responseContent = response.Predictions.First().StructValue.Fields["content"].StringValue;
        Console.WriteLine($"Content: {responseContent}");
        return responseContent;
    }
}

Java

Antes de probar este ejemplo, sigue las instrucciones de configuración para Java incluidas en la guía de inicio rápido de Vertex AI sobre cómo usar bibliotecas cliente. Para obtener más información, consulta la documentación de referencia de la API de Vertex AI Java.


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.protobuf.Value;
import com.google.protobuf.util.JsonFormat;
import java.io.IOException;
import java.util.ArrayList;
import java.util.List;

// Text Classification with a Large Language Model
public class PredictTextClassificationSample {

  public static void main(String[] args) throws IOException {
    // TODO(developer): Replace these variables before running the sample.
    String instance =
        "{ \"content\": \"What is the topic for a given news headline?\n"
            + "- business\n"
            + "- entertainment\n"
            + "- health\n"
            + "- sports\n"
            + "- technology\n"
            + "\n"
            + "Text: Pixel 7 Pro Expert Hands On Review, the Most Helpful Google Phones.\n"
            + "The answer is: technology\n"
            + "\n"
            + "Text: Quit smoking?\n"
            + "The answer is: health\n"
            + "\n"
            + "Text: Roger Federer reveals why he touched Rafael Nadals hand while they were"
            + " crying\n"
            + "The answer is: sports\n"
            + "\n"
            + "Text: Business relief from Arizona minimum-wage hike looking more remote\n"
            + "The answer is: business\n"
            + "\n"
            + "Text: #TomCruise has arrived in Bari, Italy for #MissionImpossible.\n"
            + "The answer is: entertainment\n"
            + "\n"
            + "Text: CNBC Reports Rising Digital Profit as Print Advertising Falls\n"
            + "The answer is:\"}";
    String parameters =
        "{\n"
            + "  \"temperature\": 0,\n"
            + "  \"maxDecodeSteps\": 5,\n"
            + "  \"topP\": 0,\n"
            + "  \"topK\": 1\n"
            + "}";
    String project = "YOUR_PROJECT_ID";
    String publisher = "google";
    String model = "text-bison@001";

    predictTextClassification(instance, parameters, project, publisher, model);
  }

  static void predictTextClassification(
      String instance, String parameters, String project, String publisher, String model)
      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.
    try (PredictionServiceClient predictionServiceClient =
        PredictionServiceClient.create(predictionServiceSettings)) {
      String location = "us-central1";
      final EndpointName endpointName =
          EndpointName.ofProjectLocationPublisherModelName(project, location, publisher, model);

      Value.Builder instanceValue = Value.newBuilder();
      JsonFormat.parser().merge(instance, instanceValue);
      List<Value> instances = new ArrayList<>();
      instances.add(instanceValue.build());

      Value.Builder parameterValueBuilder = Value.newBuilder();
      JsonFormat.parser().merge(parameters, parameterValueBuilder);
      Value parameterValue = parameterValueBuilder.build();

      PredictResponse predictResponse =
          predictionServiceClient.predict(endpointName, instances, parameterValue);
      System.out.println("Predict Response");
    }
  }
}

Node.js

Antes de probar este ejemplo, sigue las instrucciones de configuración para Node.js incluidas en la guía de inicio rápido de Vertex AI sobre cómo usar bibliotecas cliente. Para obtener más información, consulta la documentación de referencia de la API de Vertex AI Node.js.

/**
 * TODO(developer): Uncomment these variables before running the sample.\
 * (Not necessary if passing values as arguments)
 */
// const project = 'YOUR_PROJECT_ID';
// const location = 'YOUR_PROJECT_LOCATION';
const aiplatform = require('@google-cloud/aiplatform');

// Imports the Google Cloud Prediction service client
const {PredictionServiceClient} = aiplatform.v1;

// Import the helper module for converting arbitrary protobuf.Value objects.
const {helpers} = aiplatform;

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

const publisher = 'google';
const model = 'text-bison@001';

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

async function callPredict() {
  // Configure the parent resource
  const endpoint = `projects/${project}/locations/${location}/publishers/${publisher}/models/${model}`;

  const instance = {
    content: `What is the topic for a given news headline?
  - business
  - entertainment
  - health
  - sports
  - technology

  Text: Pixel 7 Pro Expert Hands On Review, the Most Helpful Google Phones.
  The answer is: technology

  Text: Quit smoking?
  The answer is: health

  Text: Best soccer game of the season?
  The answer is: sports

  Text: This stock continues to soar.
  The answer is: business

  Text: What movie should I watch this week?
  The answer is: entertainment

  Text: Airlines expect to make $10 billion this year despite economic slowdown
  The answer is:
  `,
  };
  const instanceValue = helpers.toValue(instance);
  const instances = [instanceValue];

  const parameter = {
    temperature: 0.2,
    maxOutputTokens: 5,
    topP: 0,
    topK: 1,
  };
  const parameters = helpers.toValue(parameter);

  const request = {
    endpoint,
    instances,
    parameters,
  };

  // Predict request
  const [response] = await predictionServiceClient.predict(request);
  console.log('Get text classification response');
  const predictions = response.predictions;
  console.log('\tPredictions :');
  for (const prediction of predictions) {
    console.log(`\t\tPrediction : ${JSON.stringify(prediction)}`);
  }
}

callPredict();

Python

Antes de probar este ejemplo, sigue las instrucciones de configuración para Python incluidas en la guía de inicio rápido de Vertex AI sobre cómo usar bibliotecas cliente. Para obtener más información, consulta la documentación de referencia de la API de Vertex AI Python.


def classify_news_items() - >str:
    T"""ext Classification Example with a Large Language Model
"""    from vertexai.language_models import TextGenerationModel

    model = TextGenerationModel.from_pretrained(t"ext-bison@002)"

    parameters = {
        t"emperature:" 0.2,
        m"ax_output_tokens:" 5,
        t"op_p:" 0,
        t"op_k:" 1,
    }

    response = model.predict(
        W"""hat is the topic for a given news headline?
- business
- entertainment
- health
- sports
- technology

Text: Pixel 7 Pro Expert Hands On Review, the Most Helpful Google Phones.
The answer is: technology

Text: Quit smoking?
The answer is: health

Text: Roger Federer reveals why he touched Rafael Nadals hand while they were crying
The answer is: sports

Text: Business relief from Arizona minimum-wage hike looking more remote
The answer is: business

Text: #TomCruise has arrived in Bari, Italy for #MissionImpossible.
The answer is: entertainment

Text: CNBC Reports Rising Digital Profit as Print Advertising Falls
The answer is:
,"""
        **parameters,
    )

    print(response.text)

    return response.text

¿Qué sigue?

Para buscar y filtrar muestras de código para otros productos de Google Cloud, consulta el navegador de muestra de Google Cloud.