Anfragen für Text-Prompts senden

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?**
# ...

import (
	"context"
	"fmt"
	"io"

	aiplatform "cloud.google.com/go/aiplatform/apiv1beta1"
	"cloud.google.com/go/aiplatform/apiv1beta1/aiplatformpb"
	"google.golang.org/api/option"
	"google.golang.org/protobuf/types/known/structpb"
)

// textPredict generates text with certain prompt and configurations.
func textPredict(w io.Writer, projectID, location, model string) error {
	ctx := context.Background()

	prompt := "Hello, say something nice."
	publisher := "google"
	parameters := map[string]interface{}{
		"temperature":     0.8,
		"maxOutputTokens": 256,
		"topP":            0.4,
		"topK":            40,
	}

	apiEndpoint := fmt.Sprintf("%s-aiplatform.googleapis.com:443", location)

	client, err := aiplatform.NewPredictionClient(ctx, option.WithEndpoint(apiEndpoint))
	if err != nil {
		fmt.Fprintf(w, "unable to create prediction client: %v", err)
		return err
	}
	defer client.Close()

	// PredictRequest requires an endpoint, instances, and parameters
	// Endpoint
	base := fmt.Sprintf("projects/%s/locations/%s/publishers/%s/models", projectID, location, publisher)
	url := fmt.Sprintf("%s/%s", base, model)

	// Instances: the prompt to use with the text model
	promptValue, err := structpb.NewValue(map[string]interface{}{
		"prompt": prompt,
	})
	if err != nil {
		fmt.Fprintf(w, "unable to convert prompt to Value: %v", err)
		return err
	}

	// Parameters: the model configuration parameters
	parametersValue, err := structpb.NewValue(parameters)
	if err != nil {
		fmt.Fprintf(w, "unable to convert parameters to Value: %v", err)
		return err
	}

	// PredictRequest: create the model prediction request
	req := &aiplatformpb.PredictRequest{
		Endpoint:   url,
		Instances:  []*structpb.Value{promptValue},
		Parameters: parametersValue,
	}

	// PredictResponse: receive the response from the model
	resp, err := client.Predict(ctx, req)
	if err != nil {
		fmt.Fprintf(w, "error in prediction: %v", err)
		return err
	}

	fmt.Fprintf(w, "text-prediction response: %v", resp.Predictions[0])
	return nil
}

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);
    }
  }
}

/**
 * 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();

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

public class PredictTextPromptSample
{
    public string PredictTextPrompt(
        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 prompt = "Give me ten interview questions for the role of program manager.";

        var instanceValue = Value.ForStruct(new()
        {
            Fields =
            {
                ["prompt"] = Value.ForString(prompt)
            }
        });

        var instances = new List<Value>
        {
            instanceValue
        };

        var parameters = Value.ForStruct(new()
        {
            Fields =
            {
                { "temperature", new Value { NumberValue = 0.2 } },
                { "maxOutputTokens", new Value { NumberValue = 256 } },
                { "topP", new Value { NumberValue = 0.95 } },
                { "topK", new Value { NumberValue = 40 } }
            }
        });

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

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

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