根据多模态提示生成文本

此示例演示了如何使用 Gemini 模型根据多模态提示生成文本。提示由三张图片和两个文本提示组成。模型生成描述图片和文本提示的文本回复。

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"
)

// generateWithMultiLocalImages shows how to generate text using multiple local image inputs.
func generateWithMultiLocalImages(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)
	}

	// Read local image files
	image1, err := os.ReadFile("latte.jpg")
	if err != nil {
		return fmt.Errorf("failed to read image1: %w", err)
	}
	image2, err := os.ReadFile("scones.jpg")
	if err != nil {
		return fmt.Errorf("failed to read image2: %w", err)
	}

	modelName := "gemini-2.5-flash"
	contents := []*genai.Content{
		{
			Role: "user",
			Parts: []*genai.Part{
				{Text: "Generate a list of all the objects contained in both images."},
				{InlineData: &genai.Blob{
					MIMEType: "image/jpeg",
					Data:     image1,
				}},
				{InlineData: &genai.Blob{
					MIMEType: "image/jpeg",
					Data:     image2,
				}},
			},
		},
	}

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

	fmt.Fprintln(w, resp.Text())

	// Example response:
	// Here is a list of all the distinct objects found in both images:
	// 1.  **Coffee** (in mugs/cups; one is clearly a latte with heart art, others are also coffee/latte)
	// 2.  **Mug(s)/Cup(s)** (yellow in the top image, white in the bottom image)
	// 3.  **Cake** (sliced, in the top image)
	// 4.  **Plate** (white, under the cake slice in the top image)
	// 5.  **Fork** (partially visible on the plate in the top image)
	// 6.  **Scones/Biscuits** (blueberry, in the bottom image)
	// 7.  **Blueberries** (scattered and in a bowl in the bottom image)
	// 8.  **Bowl** (small, dark, holding blueberries in the bottom image)
	// 9.  **Spoon** (silver, with "LET'S JAM" inscription, in the bottom image)
	// 10. **Flowers** (peonies, in the bottom image)
	// 11. **Leaves** (green, possibly mint, in the bottom image)
	// 12. **Paper** (parchment or wax paper, in the bottom image)
	// 13. **Table/Surface** (wooden in the top image, textured/painted in the bottom image)
	// ...

	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 TextGenerationWithMultiLocalImage {

  public static void main(String[] args) throws IOException {
    // TODO(developer): Replace these variables before running the sample.
    String modelId = "gemini-2.5-flash";
    String localImageFilePath1 = "your/local/img1.jpg";
    String localImageFilePath2 = "your/local/img2.jpg";
    generateContent(modelId, localImageFilePath1, localImageFilePath2);
  }

  // Generates text using multiple local images
  public static String generateContent(
      String modelId, String localImageFilePath1, String localImageFilePath2) 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 local files.
      byte[] localFileImg1Bytes = Files.readAllBytes(Paths.get(localImageFilePath1));
      byte[] localFileImg2Bytes = Files.readAllBytes(Paths.get(localImageFilePath2));

      GenerateContentResponse response =
          client.models.generateContent(
              modelId,
              Content.fromParts(
                  Part.fromBytes(localFileImg1Bytes, "image/jpeg"),
                  Part.fromBytes(localFileImg2Bytes, "image/jpeg"),
                  Part.fromText("Generate a list of all the objects contained in both images")),
              null);

      System.out.print(response.text());
      // Example response:
      // Based on both images, here are the objects contained in both:
      //
      // 1.  **Coffee cups (or mugs)**: Both images feature one or more cups containing a beverage.
      // 2.  **Coffee (or a similar beverage)**: Both images contain a liquid beverage in the cups,
      // appearing to be coffee or a coffee-like drink.
      // 3.  **Table (or a flat surface)**: Both compositions are set on a flat surface, likely a
      // table or countertop.
      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 fs = require('fs');

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

function loadImageAsBase64(path) {
  const bytes = fs.readFileSync(path);
  return bytes.toString('base64');
}

async function generateContent(
  projectId = GOOGLE_CLOUD_PROJECT,
  location = GOOGLE_CLOUD_LOCATION,
  imagePath1,
  imagePath2
) {
  const client = new GoogleGenAI({
    vertexai: true,
    project: projectId,
    location: location,
  });

  // TODO(Developer): Update the below file paths to your images
  const image1 = loadImageAsBase64(imagePath1);
  const image2 = loadImageAsBase64(imagePath2);

  const response = await client.models.generateContent({
    model: 'gemini-2.5-flash',
    contents: [
      {
        role: 'user',
        parts: [
          {
            text: 'Generate a list of all the objects contained in both images.',
          },
          {
            inlineData: {
              data: image1,
              mimeType: 'image/jpeg',
            },
          },
          {
            inlineData: {
              data: image2,
              mimeType: 'image/jpeg',
            },
          },
        ],
      },
    ],
  });

  console.log(response.text);

  // Example response:
  //  Okay, here's a jingle combining the elements of both sets of images, focusing on ...
  //  ...

  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"))
# TODO(Developer): Update the below file paths to your images
# image_path_1 = "path/to/your/image1.jpg"
# image_path_2 = "path/to/your/image2.jpg"
with open(image_path_1, "rb") as f:
    image_1_bytes = f.read()
with open(image_path_2, "rb") as f:
    image_2_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_bytes(data=image_1_bytes, mime_type="image/jpeg"),
        Part.from_bytes(data=image_2_bytes, mime_type="image/jpeg"),
    ],
)
print(response.text)
# Example response:
# Okay, here's a jingle combining the elements of both sets of images, focusing on ...
# ...

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。