Chat écrit

def send_chat() -> str:
    from vertexai.language_models import ChatModel, InputOutputTextPair

    chat_model = ChatModel.from_pretrained("chat-bison@002")

    parameters = {
        "temperature": 0.2,
        "max_output_tokens": 256,
        "top_p": 0.95,
        "top_k": 40,
    }

    chat = chat_model.start_chat(
        context="My name is Miles. You are an astronomer, knowledgeable about the solar system.",
        examples=[
            InputOutputTextPair(
                input_text="How many moons does Mars have?",
                output_text="The planet Mars has two moons, Phobos and Deimos.",
            ),
        ],
    )

    response = chat.send_message(
        "How many planets are there in the solar system?", **parameters
    )
    print(response.text)

    return response.text

/**
 * 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 = 'chat-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 prompt = {
    context:
      'My name is Miles. You are an astronomer, knowledgeable about the solar system.',
    examples: [
      {
        input: {content: 'How many moons does Mars have?'},
        output: {
          content: 'The planet Mars has two moons, Phobos and Deimos.',
        },
      },
    ],
    messages: [
      {
        author: 'user',
        content: 'How many planets are there in the solar system?',
      },
    ],
  };
  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 chat prompt response');
  const predictions = response.predictions;
  console.log('\tPredictions :');
  for (const prediction of predictions) {
    console.log(`\t\tPrediction : ${JSON.stringify(prediction)}`);
  }
}

callPredict();

import com.google.cloud.aiplatform.v1beta1.EndpointName;
import com.google.cloud.aiplatform.v1beta1.PredictResponse;
import com.google.cloud.aiplatform.v1beta1.PredictionServiceClient;
import com.google.cloud.aiplatform.v1beta1.PredictionServiceSettings;
import com.google.protobuf.Value;
import com.google.protobuf.util.JsonFormat;
import java.io.IOException;
import java.util.ArrayList;
import java.util.List;

// Send a Predict request to a large language model to test a chat prompt
public class PredictChatPromptSample {

  public static void main(String[] args) throws IOException {
    // TODO(developer): Replace these variables before running the sample.
    String instance =
        "{\n"
            + "   \"context\":  \"My name is Ned. You are my personal assistant. My favorite movies"
            + " are Lord of the Rings and Hobbit.\",\n"
            + "   \"examples\": [ { \n"
            + "       \"input\": {\"content\": \"Who do you work for?\"},\n"
            + "       \"output\": {\"content\": \"I work for Ned.\"}\n"
            + "    },\n"
            + "    { \n"
            + "       \"input\": {\"content\": \"What do I like?\"},\n"
            + "       \"output\": {\"content\": \"Ned likes watching movies.\"}\n"
            + "    }],\n"
            + "   \"messages\": [\n"
            + "    { \n"
            + "       \"author\": \"user\",\n"
            + "       \"content\": \"Are my favorite movies based on a book series?\"\n"
            + "    }]\n"
            + "}";
    String parameters =
        "{\n"
            + "  \"temperature\": 0.3,\n"
            + "  \"maxDecodeSteps\": 200,\n"
            + "  \"topP\": 0.8,\n"
            + "  \"topK\": 40\n"
            + "}";
    String project = "YOUR_PROJECT_ID";
    String publisher = "google";
    String model = "chat-bison@001";

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

  static void predictChatPrompt(
      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");
    }
  }
}