Text

import vertexai

from vertexai.language_models import TextGenerationModel

# TODO(developer): Update and un-comment below line
# PROJECT_ID = "your-project-id"
vertexai.init(project=PROJECT_ID, location="us-central1")
parameters = {
    "temperature": 0.2,  # Temperature controls the degree of randomness in token selection.
    "max_output_tokens": 256,  # Token limit determines the maximum amount of text output.
    "top_p": 0.8,  # Tokens are selected from most probable to least until the sum of their probabilities equals the top_p value.
    "top_k": 40,  # A top_k of 1 means the selected token is the most probable among all tokens.
}

model = TextGenerationModel.from_pretrained("text-bison@002")
response = model.predict(
    "Give me ten interview questions for the role of program manager.",
    **parameters,
)
print(f"Response from Model: {response.text}")
# Example response:
# Response from Model:  1. **Tell me about your experience managing programs.**
# 2. **What are your strengths and weaknesses as a program manager?**
# 3. **What do you think are the most important qualities for a successful program manager?**
# ...

/**
 * TODO(developer): Update these variables before running the sample.
 */
const PROJECT_ID = process.env.CAIP_PROJECT_ID;
const LOCATION = 'us-central1';
const PUBLISHER = 'google';
const MODEL = 'text-bison@001';
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',
};

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

async function callPredict() {
  // Configure the parent resource
  const endpoint = `projects/${PROJECT_ID}/locations/${LOCATION}/publishers/${PUBLISHER}/models/${MODEL}`;

  const prompt = {
    prompt:
      'Give me ten interview questions for the role of program manager.',
  };
  const instanceValue = helpers.toValue(prompt);
  const instances = [instanceValue];

  const parameter = {
    temperature: 0.2,
    maxOutputTokens: 256,
    topP: 0.95,
    topK: 40,
  };
  const parameters = helpers.toValue(parameter);

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

  // Predict request
  const response = await predictionServiceClient.predict(request);
  console.log('Get text prompt response');
  console.log(response);
}

callPredict();

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;

public class PredictTextPromptSample {

  public static void main(String[] args) throws IOException {
    // TODO(developer): Replace these variables before running the sample.
    // Details of designing text prompts for supported large language models:
    // https://cloud.google.com/vertex-ai/docs/generative-ai/text/text-overview
    String instance =
        "{ \"prompt\": " + "\"Give me ten interview questions for the role of program manager.\"}";
    String parameters =
        "{\n"
            + "  \"temperature\": 0.2,\n"
            + "  \"maxOutputTokens\": 256,\n"
            + "  \"topP\": 0.95,\n"
            + "  \"topK\": 40\n"
            + "}";
    String project = "YOUR_PROJECT_ID";
    String location = "us-central1";
    String publisher = "google";
    String model = "text-bison@001";

    predictTextPrompt(instance, parameters, project, location, publisher, model);
  }

  // Get a text prompt from a supported text model
  public static void predictTextPrompt(
      String instance,
      String parameters,
      String project,
      String location,
      String publisher,
      String model)
      throws IOException {
    String endpoint = String.format("%s-aiplatform.googleapis.com:443", location);
    PredictionServiceSettings predictionServiceSettings =
        PredictionServiceSettings.newBuilder().setEndpoint(endpoint).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)) {
      final EndpointName endpointName =
          EndpointName.ofProjectLocationPublisherModelName(project, location, publisher, model);

      // Initialize client that will be used to send requests. This client only needs to be created
      // once, and can be reused for multiple requests.
      Value.Builder instanceValue = Value.newBuilder();
      JsonFormat.parser().merge(instance, instanceValue);
      List<Value> instances = new ArrayList<>();
      instances.add(instanceValue.build());

      // Use Value.Builder to convert instance to a dynamically typed value that can be
      // processed by the service.
      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");
      System.out.println(predictResponse);
    }
  }
}