Test text prompts (Generative AI)

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

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);
    }
  }
}

require "google/cloud/ai_platform/v1"

##
# Vertex AI Predict Text Prompt
#
# @param project_id [String] Your Google Cloud project (e.g. "my-project")
# @param location_id [String] Your Processor Location (e.g. "us-central1")
# @param publisher [String] The Model Publisher (e.g. "google")
# @param model [String] The Model Identifier (e.g. "text-bison@001")
#
def predict_text_prompt project_id:, location_id:, publisher:, model:
  # Create the Vertex AI client.
  client = ::Google::Cloud::AIPlatform::V1::PredictionService::Client.new do |config|
    config.endpoint = "#{location_id}-aiplatform.googleapis.com"
  end

  # Build the resource name from the project.
  endpoint = client.endpoint_path(
    project: project_id,
    location: location_id,
    publisher: publisher,
    model: model
  )

  prompt = "Give me ten interview questions for the role of program manager."

  # Initialize the request arguments
  instance = Google::Protobuf::Value.new(
    struct_value: Google::Protobuf::Struct.new(
      fields: {
        "prompt" => Google::Protobuf::Value.new(
          string_value: prompt
        )
      }
    )
  )

  instances = [instance]

  parameters = Google::Protobuf::Value.new(
    struct_value: Google::Protobuf::Struct.new(
      fields: {
        "temperature" => Google::Protobuf::Value.new(number_value: 0.2),
        "maxOutputTokens" => Google::Protobuf::Value.new(number_value: 256),
        "topP" => Google::Protobuf::Value.new(number_value: 0.95),
        "topK" => Google::Protobuf::Value.new(number_value: 40)
      }
    )
  )

  # Make the prediction request
  response = client.predict endpoint: endpoint, instances: instances, parameters: parameters

  # Handle the prediction response
  puts "Predict Response"
  puts response
end