Vertex AI Gemini の API を試す

# TODO(developer): Vertex AI SDK - uncomment below & run
# pip3 install --upgrade --user google-cloud-aiplatform
# gcloud auth application-default login

import vertexai
from vertexai.generative_models import GenerativeModel, Part

def generate_text(project_id: str, location: str) -> str:
    # Initialize Vertex AI
    vertexai.init(project=project_id, location=location)
    # Load the model
    multimodal_model = GenerativeModel("gemini-1.0-pro-vision")
    # Query the model
    response = multimodal_model.generate_content(
        [
            # Add an example image
            Part.from_uri(
                "gs://generativeai-downloads/images/scones.jpg", mime_type="image/jpeg"
            ),
            # Add an example query
            "what is shown in this image?",
        ]
    )
    print(response)
    return response.text

const {VertexAI} = require('@google-cloud/vertexai');

/**
 * TODO(developer): Update these variables before running the sample.
 */
async function createNonStreamingMultipartContent(
  projectId = 'PROJECT_ID',
  location = 'us-central1',
  model = 'gemini-1.0-pro-vision',
  image = 'gs://generativeai-downloads/images/scones.jpg',
  mimeType = 'image/jpeg'
) {
  // Initialize Vertex with your Cloud project and location
  const vertexAI = new VertexAI({project: projectId, location: location});

  // Instantiate the model
  const generativeVisionModel = vertexAI.getGenerativeModel({
    model: model,
  });

  // For images, the SDK supports both Google Cloud Storage URI and base64 strings
  const filePart = {
    fileData: {
      fileUri: image,
      mimeType: mimeType,
    },
  };

  const textPart = {
    text: 'what is shown in this image?',
  };

  const request = {
    contents: [{role: 'user', parts: [filePart, textPart]}],
  };

  console.log('Prompt Text:');
  console.log(request.contents[0].parts[1].text);

  console.log('Non-Streaming Response Text:');
  // Create the response stream
  const responseStream =
    await generativeVisionModel.generateContentStream(request);

  // Wait for the response stream to complete
  const aggregatedResponse = await responseStream.response;

  // Select the text from the response
  const fullTextResponse =
    aggregatedResponse.candidates[0].content.parts[0].text;

  console.log(fullTextResponse);
}

import com.google.cloud.vertexai.VertexAI;
import com.google.cloud.vertexai.api.GenerateContentResponse;
import com.google.cloud.vertexai.generativeai.ContentMaker;
import com.google.cloud.vertexai.generativeai.GenerativeModel;
import com.google.cloud.vertexai.generativeai.PartMaker;
import java.io.IOException;

public class Quickstart {

  public static void main(String[] args) throws IOException {
    // TODO(developer): Replace these variables before running the sample.
    String projectId = "your-google-cloud-project-id";
    String location = "us-central1";
    String modelName = "gemini-1.0-pro-vision";

    String output = quickstart(projectId, location, modelName);
    System.out.println(output);
  }

  // Analyzes the provided Multimodal input.
  public static String quickstart(String projectId, String location, String modelName)
      throws IOException {
    // 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 (VertexAI vertexAI = new VertexAI(projectId, location)) {
      String imageUri = "gs://generativeai-downloads/images/scones.jpg";

      GenerativeModel model = new GenerativeModel(modelName, vertexAI);
      GenerateContentResponse response = model.generateContent(ContentMaker.fromMultiModalData(
          PartMaker.fromMimeTypeAndData("image/jpg", imageUri),
          "What's in this photo"
      ));

      return response.toString();
    }
  }
}

import (
	"context"
	"encoding/json"
	"fmt"
	"io"

	"cloud.google.com/go/vertexai/genai"
)

var projectId = "PROJECT_ID"
var region = "us-central1"

func tryGemini(w io.Writer, projectId string, region string, modelName string) error {

	ctx := context.Background()
	client, err := genai.NewClient(ctx, projectId, region)
	gemini := client.GenerativeModel(modelName)

	img := genai.FileData{
		MIMEType: "image/jpeg",
		FileURI:  "gs://generativeai-downloads/images/scones.jpg",
	}
	prompt := genai.Text("What is in this image?")
	resp, err := gemini.GenerateContent(ctx, img, prompt)
	if err != nil {
		return fmt.Errorf("error generating content: %w", err)
	}
	rb, _ := json.MarshalIndent(resp, "", "  ")
	fmt.Fprintln(w, string(rb))
	return nil
}

using Google.Api.Gax.Grpc;
using Google.Cloud.AIPlatform.V1;
using System.Collections.Generic;
using System.Text;
using System.Threading.Tasks;

public class GeminiQuickstart
{
    public async Task<string> GenerateContent(
        string projectId = "your-project-id",
        string location = "us-central1",
        string publisher = "google",
        string model = "gemini-1.0-pro-vision"
    )
    {
        // Create client
        var predictionServiceClient = new PredictionServiceClientBuilder
        {
            Endpoint = $"{location}-aiplatform.googleapis.com"
        }.Build();

        // Prompt
        string prompt = "What's in this photo";
        string imageUri = "gs://generativeai-downloads/images/scones.jpg";

        // Initialize request argument(s)
        var content = new Content
        {
            Role = "USER"
        };
        content.Parts.AddRange(new List<Part>()
        {
            new() {
                Text = prompt
            },
            new() {
                FileData = new() {
                    MimeType = "image/png",
                    FileUri = imageUri
                }
            }
        });

        var generateContentRequest = new GenerateContentRequest
        {
            Model = $"projects/{projectId}/locations/{location}/publishers/{publisher}/models/{model}",
            GenerationConfig = new GenerationConfig
            {
                Temperature = 0.4f,
                TopP = 1,
                TopK = 32,
                MaxOutputTokens = 2048
            }
        };
        generateContentRequest.Contents.Add(content);

        // Make the request, returning a streaming response
        using PredictionServiceClient.StreamGenerateContentStream response = predictionServiceClient.StreamGenerateContent(generateContentRequest);

        StringBuilder fullText = new();

        // Read streaming responses from server until complete
        AsyncResponseStream<GenerateContentResponse> responseStream = response.GetResponseStream();
        await foreach (GenerateContentResponse responseItem in responseStream)
        {
            fullText.Append(responseItem.Candidates[0].Content.Parts[0].Text);
        }

        return fullText.ToString();
    }
}