使用本地图片和 Google Cloud Storage 中的图片生成文本

此示例演示了如何使用本地图片和 Google Cloud Storage 中的图片生成文本

深入探索

如需查看包含此代码示例的详细文档，请参阅以下内容：

• 图片推理

代码示例

Go

在尝试此示例之前，请按照《Vertex AI 快速入门：使用客户端库》中的 Go 设置说明执行操作。 如需了解详情，请参阅 Vertex AI Go API 参考文档。

如需向 Vertex AI 进行身份验证，请设置应用默认凭证。 如需了解详情，请参阅为本地开发环境设置身份验证。

import (
	"context"
	"fmt"
	"io"
	"os"

	genai "google.golang.org/genai"
)

// generateWithMultiImg shows how to generate text using multiple image inputs.
func generateWithMultiImg(w io.Writer) error {
	ctx := context.Background()

	client, err := genai.NewClient(ctx, &genai.ClientConfig{
		HTTPOptions: genai.HTTPOptions{APIVersion: "v1"},
	})
	if err != nil {
		return fmt.Errorf("failed to create genai client: %w", err)
	}

	// TODO(Developer): Update the path to file (image source:
	//   https://storage.googleapis.com/cloud-samples-data/generative-ai/image/latte.jpg )
	imageBytes, err := os.ReadFile("./latte.jpg")
	if err != nil {
		return fmt.Errorf("failed to read image: %w", err)
	}

	contents := []*genai.Content{
		{Parts: []*genai.Part{
			{Text: "Write an advertising jingle based on the items in both images."},
			{FileData: &genai.FileData{
				// Image source: https://storage.googleapis.com/cloud-samples-data/generative-ai/image/scones.jpg
				FileURI:  "gs://cloud-samples-data/generative-ai/image/scones.jpg",
				MIMEType: "image/jpeg",
			}},
			{InlineData: &genai.Blob{
				Data:     imageBytes,
				MIMEType: "image/jpeg",
			}},
		}},
	}
	modelName := "gemini-2.5-flash"

	resp, err := client.Models.GenerateContent(ctx, modelName, contents, nil)
	if err != nil {
		return fmt.Errorf("failed to generate content: %w", err)
	}

	respText := resp.Text()

	fmt.Fprintln(w, respText)

	// Example response:
	// Okay, here's an advertising jingle inspired by the blueberry scones, coffee, flowers, chocolate cake, and latte:
	//
	// (Upbeat, jazzy music)
	// ...

	return nil
}

Java

在尝试此示例之前，请按照《Vertex AI 快速入门：使用客户端库》中的 Java 设置说明执行操作。 如需了解详情，请参阅 Vertex AI Java API 参考文档。

如需向 Vertex AI 进行身份验证，请设置应用默认凭证。 如需了解详情，请参阅为本地开发环境设置身份验证。

import com.google.genai.Client;
import com.google.genai.types.Content;
import com.google.genai.types.GenerateContentResponse;
import com.google.genai.types.HttpOptions;
import com.google.genai.types.Part;
import java.io.IOException;
import java.nio.file.Files;
import java.nio.file.Paths;

public class TextGenerationWithMultiImage {

  public static void main(String[] args) throws IOException {
    // TODO(developer): Replace these variables before running the sample.
    String modelId = "gemini-2.5-flash";
    // Content from Google Cloud Storage
    String gcsFileImagePath = "gs://cloud-samples-data/generative-ai/image/scones.jpg";
    String localImageFilePath = "resources/latte.jpg";
    generateContent(modelId, gcsFileImagePath, localImageFilePath);
  }

  // Generates text with multiple images
  public static String generateContent(
      String modelId, String gcsFileImagePath, String localImageFilePath) 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 (Client client =
        Client.builder()
            .location("global")
            .vertexAI(true)
            .httpOptions(HttpOptions.builder().apiVersion("v1").build())
            .build()) {

      // Read content from a local file.
      byte[] localFileImgBytes = Files.readAllBytes(Paths.get(localImageFilePath));

      GenerateContentResponse response =
          client.models.generateContent(
              modelId,
              Content.fromParts(
                  Part.fromText("Generate a list of all the objects contained in both images"),
                  Part.fromBytes(localFileImgBytes, "image/jpeg"),
                  Part.fromUri(gcsFileImagePath, "image/jpeg")),
              null);

      System.out.print(response.text());
      // Example response:
      // Okay, here's the list of objects present in both images:
      //
      // **Image 1 (Scones):**
      //
      // *   Scones
      // *   Plate
      // *   Jam/Preserve
      // *   Cream/Butter
      // *   Table/Surface
      // *   Napkin/Cloth (possibly)
      //
      // **Image 2 (Latte):**
      //
      // *   Latte/Coffee cup
      // *   Saucer
      // *   Spoon
      // *   Table/Surface
      // *   Foam/Latte art
      //
      // **Objects potentially in both (depending on interpretation and specific items):**
      //
      // *   Plate/Saucer (both are serving dishes)
      // *   Table/Surface
      return response.text();
    }
  }
}

Node.js

在尝试此示例之前，请按照《Vertex AI 快速入门：使用客户端库》中的 Node.js 设置说明执行操作。 如需了解详情，请参阅 Vertex AI Node.js API 参考文档。

如需向 Vertex AI 进行身份验证，请设置应用默认凭证。 如需了解详情，请参阅为本地开发环境设置身份验证。

const {GoogleGenAI} = require('@google/genai');

const GOOGLE_CLOUD_PROJECT = process.env.GOOGLE_CLOUD_PROJECT;
const GOOGLE_CLOUD_LOCATION = process.env.GOOGLE_CLOUD_LOCATION || 'global';

async function generateContent(
  projectId = GOOGLE_CLOUD_PROJECT,
  location = GOOGLE_CLOUD_LOCATION
) {
  const client = new GoogleGenAI({
    vertexai: true,
    project: projectId,
    location: location,
  });

  const image1 = {
    fileData: {
      fileUri: 'gs://cloud-samples-data/generative-ai/image/scones.jpg',
      mimeType: 'image/jpeg',
    },
  };

  const image2 = {
    fileData: {
      fileUri: 'gs://cloud-samples-data/generative-ai/image/fruit.png',
      mimeType: 'image/png',
    },
  };

  const response = await client.models.generateContent({
    model: 'gemini-2.5-flash',
    contents: [
      image1,
      image2,
      'Generate a list of all the objects contained in both images.',
    ],
  });

  console.log(response.text);

  return response.text;
}

Python

在尝试此示例之前，请按照《Vertex AI 快速入门：使用客户端库》中的 Python 设置说明执行操作。 如需了解详情，请参阅 Vertex AI Python API 参考文档。

如需向 Vertex AI 进行身份验证，请设置应用默认凭证。 如需了解详情，请参阅为本地开发环境设置身份验证。

from google import genai
from google.genai.types import HttpOptions, Part

client = genai.Client(http_options=HttpOptions(api_version="v1"))

# Read content from GCS
gcs_file_img_path = "gs://cloud-samples-data/generative-ai/image/scones.jpg"

# Read content from a local file
with open("test_data/latte.jpg", "rb") as f:
    local_file_img_bytes = f.read()

response = client.models.generate_content(
    model="gemini-2.5-flash",
    contents=[
        "Generate a list of all the objects contained in both images.",
        Part.from_uri(file_uri=gcs_file_img_path, mime_type="image/jpeg"),
        Part.from_bytes(data=local_file_img_bytes, mime_type="image/jpeg"),
    ],
)
print(response.text)
# Example response:
# Okay, here's the list of objects present in both images:
# ...

后续步骤

如需搜索和过滤其他 Google Cloud 产品的代码示例，请参阅Google Cloud 示例浏览器。