Vertex AI 中的 Gemini API 快速入门

本快速入门将向您介绍如何为所选语言安装 Google Gen AI SDK，然后发出您的第一个 API 请求。示例会根据您是使用 API 密钥还是应用默认凭据 (ADC) 向 Vertex AI 进行身份验证而略有不同。

选择身份验证方法：

API 密钥 ADC

---

准备工作

配置应用默认凭据（如果您尚未配置）。

所需的角色

如需获得在 Vertex AI 中使用 Gemini API 所需的权限，请让您的管理员为您授予项目的 Vertex AI User (roles/aiplatform.user) IAM 角色。 如需详细了解如何授予角色，请参阅管理对项目、文件夹和组织的访问权限。

您也可以通过自定义角色或其他预定义角色来获取所需的权限。

安装 SDK 并设置环境

在您的本地机器上，点击以下标签页之一，安装相应编程语言的 SDK。

Gen AI SDK for Python

运行以下命令，安装并更新 Gen AI SDK for Python。

pip install --upgrade google-genai

设置环境变量：

# Replace the `GOOGLE_CLOUD_PROJECT` and `GOOGLE_CLOUD_LOCATION` values
# with appropriate values for your project.
export GOOGLE_CLOUD_PROJECT=GOOGLE_CLOUD_PROJECT
export GOOGLE_CLOUD_LOCATION=global
export GOOGLE_GENAI_USE_VERTEXAI=True

Gen AI SDK for Go

运行以下命令，安装并更新 Go 版 Gen AI SDK。

go get google.golang.org/genai

设置环境变量：

# Replace the `GOOGLE_CLOUD_PROJECT` and `GOOGLE_CLOUD_LOCATION` values
# with appropriate values for your project.
export GOOGLE_CLOUD_PROJECT=GOOGLE_CLOUD_PROJECT
export GOOGLE_CLOUD_LOCATION=global
export GOOGLE_GENAI_USE_VERTEXAI=True

适用于 Node.js 的 Gen AI SDK

运行以下命令，安装并更新 Node.js 版 Gen AI SDK。

npm install @google/genai

设置环境变量：

# Replace the `GOOGLE_CLOUD_PROJECT` and `GOOGLE_CLOUD_LOCATION` values
# with appropriate values for your project.
export GOOGLE_CLOUD_PROJECT=GOOGLE_CLOUD_PROJECT
export GOOGLE_CLOUD_LOCATION=global
export GOOGLE_GENAI_USE_VERTEXAI=True

Gen AI SDK for Java

运行以下命令，安装并更新 Gen AI SDK for Java。

Maven

将以下内容添加到 pom.xml 中：

<dependencies>
  <dependency>
    <groupId>com.google.genai</groupId>
    <artifactId>google-genai</artifactId>
    <version>0.7.0</version>
  </dependency>
</dependencies>

设置环境变量：

# Replace the `GOOGLE_CLOUD_PROJECT` and `GOOGLE_CLOUD_LOCATION` values
# with appropriate values for your project.
export GOOGLE_CLOUD_PROJECT=GOOGLE_CLOUD_PROJECT
export GOOGLE_CLOUD_LOCATION=global
export GOOGLE_GENAI_USE_VERTEXAI=True

REST

设置环境变量：

GOOGLE_CLOUD_PROJECT=GOOGLE_CLOUD_PROJECT
GOOGLE_CLOUD_LOCATION=global
API_ENDPOINT=YOUR_API_ENDPOINT
MODEL_ID="gemini-2.5-flash"
GENERATE_CONTENT_API="generateContent"

提交第一个请求

使用 generateContent 方法向 Vertex AI 中的 Gemini API 发送请求：

Python

from google import genai
from google.genai.types import HttpOptions

client = genai.Client(http_options=HttpOptions(api_version="v1"))
response = client.models.generate_content(
    model="gemini-2.5-flash",
    contents="How does AI work?",
)
print(response.text)
# Example response:
# Okay, let's break down how AI works. It's a broad field, so I'll focus on the ...
#
# Here's a simplified overview:
# ...

Go

import (
	"context"
	"fmt"
	"io"

	"google.golang.org/genai"
)

// generateWithText shows how to generate text using a text prompt.
func generateWithText(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)
	}

	resp, err := client.Models.GenerateContent(ctx,
		"gemini-2.5-flash",
		genai.Text("How does AI work?"),
		nil,
	)
	if err != nil {
		return fmt.Errorf("failed to generate content: %w", err)
	}

	respText := resp.Text()

	fmt.Fprintln(w, respText)
	// Example response:
	// That's a great question! Understanding how AI works can feel like ...
	// ...
	// **1. The Foundation: Data and Algorithms**
	// ...

	return nil
}

Node.js

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 ai = new GoogleGenAI({
    vertexai: true,
    project: projectId,
    location: location,
  });

  const response = await ai.models.generateContent({
    model: 'gemini-2.5-flash',
    contents: 'How does AI work?',
  });

  console.log(response.text);

  return response.text;
}

Java

import com.google.genai.Client;
import com.google.genai.types.GenerateContentResponse;
import com.google.genai.types.HttpOptions;

public class TextGenerationWithText {

  public static void main(String[] args) {
    // TODO(developer): Replace these variables before running the sample.
    String modelId = "gemini-2.5-flash";
    generateContent(modelId);
  }

  // Generates text with text input
  public static String generateContent(String modelId) {
    // 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()) {

      GenerateContentResponse response =
          client.models.generateContent(modelId, "How does AI work?", null);

      System.out.print(response.text());
      // Example response:
      // Okay, let's break down how AI works. It's a broad field, so I'll focus on the ...
      //
      // Here's a simplified overview:
      // ...
      return response.text();
    }
  }
}

REST

如需发送此提示请求，请从命令行运行 curl 命令，或在应用中添加 REST 调用。

curl
-X POST
-H "Content-Type: application/json"
-H "Authorization: Bearer $(gcloud auth print-access-token)"
"https://${API_ENDPOINT}/v1/projects/${GOOGLE_CLOUD_PROJECT}/locations/${GOOGLE_CLOUD_LOCATION}/publishers/google/models/${MODEL_ID}:${GENERATE_CONTENT_API}" -d
$'{
  "contents": {
    "role": "user",
    "parts": {
      "text": "Explain how AI works in a few words"
    }
  }
}'

模型会返回回复。 请注意，系统分多个部分生成回复，其中每个部分会分别评估安全性。

生成图片

Gemini 可以通过对话方式生成和处理图片。您可以通过文本、图片或两者的组合来提示 Gemini，以完成各种与图片相关的任务，例如图片生成和编辑。以下代码演示了如何根据描述性提示生成图片：

您必须在配置中添加 responseModalities: ["TEXT", "IMAGE"]。这些模型不支持仅图片输出。

Python

from google import genai
from google.genai.types import GenerateContentConfig, Modality
from PIL import Image
from io import BytesIO

client = genai.Client()

response = client.models.generate_content(
    model="gemini-2.5-flash-image-preview",
    contents=("Generate an image of the Eiffel tower with fireworks in the background."),
    config=GenerateContentConfig(
        response_modalities=[Modality.TEXT, Modality.IMAGE],
        candidate_count=1,
        safety_settings=[
            {"method": "PROBABILITY"},
            {"category": "HARM_CATEGORY_DANGEROUS_CONTENT"},
            {"threshold": "BLOCK_MEDIUM_AND_ABOVE"},
        ],
    ),
)
for part in response.candidates[0].content.parts:
    if part.text:
        print(part.text)
    elif part.inline_data:
        image = Image.open(BytesIO((part.inline_data.data)))
        image.save("output_folder/example-image-eiffel-tower.png")
# Example response:
#   I will generate an image of the Eiffel Tower at night, with a vibrant display of
#   colorful fireworks exploding in the dark sky behind it. The tower will be
#   illuminated, standing tall as the focal point of the scene, with the bursts of
#   light from the fireworks creating a festive atmosphere.

Node.js

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

const GOOGLE_CLOUD_PROJECT = process.env.GOOGLE_CLOUD_PROJECT;
const GOOGLE_CLOUD_LOCATION =
  process.env.GOOGLE_CLOUD_LOCATION || 'us-central1';

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

  const response = await ai.models.generateContentStream({
    model: 'gemini-2.0-flash-exp',
    contents:
      'Generate an image of the Eiffel tower with fireworks in the background.',
    config: {
      responseModalities: [Modality.TEXT, Modality.IMAGE],
    },
  });

  const generatedFileNames = [];
  let imageIndex = 0;
  for await (const chunk of response) {
    const text = chunk.text;
    const data = chunk.data;
    if (text) {
      console.debug(text);
    } else if (data) {
      const fileName = `generate_content_streaming_image_${imageIndex++}.png`;
      console.debug(`Writing response image to file: ${fileName}.`);
      try {
        fs.writeFileSync(fileName, data);
        generatedFileNames.push(fileName);
      } catch (error) {
        console.error(`Failed to write image file ${fileName}:`, error);
      }
    }
  }

  return generatedFileNames;
}

图片理解

Gemini 还可以理解图片。以下代码使用上一部分中生成的图片，并使用其他模型来推断有关该图片的信息：

Python

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

client = genai.Client(http_options=HttpOptions(api_version="v1"))
response = client.models.generate_content(
    model="gemini-2.5-flash",
    contents=[
        "What is shown in this image?",
        Part.from_uri(
            file_uri="gs://cloud-samples-data/generative-ai/image/scones.jpg",
            mime_type="image/jpeg",
        ),
    ],
)
print(response.text)
# Example response:
# The image shows a flat lay of blueberry scones arranged on parchment paper. There are ...

Go

import (
	"context"
	"fmt"
	"io"

	genai "google.golang.org/genai"
)

// generateWithTextImage shows how to generate text using both text and image input
func generateWithTextImage(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)
	}

	modelName := "gemini-2.5-flash"
	contents := []*genai.Content{
		{Parts: []*genai.Part{
			{Text: "What is shown in this image?"},
			{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",
			}},
		},
			Role: "user"},
	}

	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:
	// The image shows an overhead shot of a rustic, artistic arrangement on a surface that ...

	return nil
}

Node.js

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 ai = new GoogleGenAI({
    vertexai: true,
    project: projectId,
    location: location,
  });

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

  const response = await ai.models.generateContent({
    model: 'gemini-2.5-flash',
    contents: [image, 'What is shown in this image?'],
  });

  console.log(response.text);

  return response.text;
}

Java

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;

public class TextGenerationWithTextAndImage {

  public static void main(String[] args) {
    // TODO(developer): Replace these variables before running the sample.
    String modelId = "gemini-2.5-flash";
    generateContent(modelId);
  }

  // Generates text with text and image input
  public static String generateContent(String modelId) {
    // 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()) {

      GenerateContentResponse response =
          client.models.generateContent(
              modelId,
              Content.fromParts(
                  Part.fromText("What is shown in this image?"),
                  Part.fromUri(
                      "gs://cloud-samples-data/generative-ai/image/scones.jpg", "image/jpeg")),
              null);

      System.out.print(response.text());
      // Example response:
      // The image shows a flat lay of blueberry scones arranged on parchment paper. There are ...
      return response.text();
    }
  }
}

代码执行

Vertex AI 中的 Gemini API 代码执行功能可让模型生成和运行 Python 代码，并从结果中迭代学习，直到获得最终输出。Vertex AI 提供代码执行作为工具，类似于函数调用。利用此代码执行功能，您可以构建可受益于基于代码的推理并生成文本输出的应用。例如：

Python

from google import genai
from google.genai.types import (
    HttpOptions,
    Tool,
    ToolCodeExecution,
    GenerateContentConfig,
)

client = genai.Client(http_options=HttpOptions(api_version="v1"))
model_id = "gemini-2.5-flash"

code_execution_tool = Tool(code_execution=ToolCodeExecution())
response = client.models.generate_content(
    model=model_id,
    contents="Calculate 20th fibonacci number. Then find the nearest palindrome to it.",
    config=GenerateContentConfig(
        tools=[code_execution_tool],
        temperature=0,
    ),
)
print("# Code:")
print(response.executable_code)
print("# Outcome:")
print(response.code_execution_result)

# Example response:
# # Code:
# def fibonacci(n):
#     if n <= 0:
#         return 0
#     elif n == 1:
#         return 1
#     else:
#         a, b = 0, 1
#         for _ in range(2, n + 1):
#             a, b = b, a + b
#         return b
#
# fib_20 = fibonacci(20)
# print(f'{fib_20=}')
#
# # Outcome:
# fib_20=6765

Go

import (
	"context"
	"fmt"
	"io"

	genai "google.golang.org/genai"
)

// generateWithCodeExec shows how to generate text using the code execution tool.
func generateWithCodeExec(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)
	}

	prompt := "Calculate 20th fibonacci number. Then find the nearest palindrome to it."
	contents := []*genai.Content{
		{Parts: []*genai.Part{
			{Text: prompt},
		},
			Role: "user"},
	}
	config := &genai.GenerateContentConfig{
		Tools: []*genai.Tool{
			{CodeExecution: &genai.ToolCodeExecution{}},
		},
		Temperature: genai.Ptr(float32(0.0)),
	}
	modelName := "gemini-2.5-flash"

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

	for _, p := range resp.Candidates[0].Content.Parts {
		if p.Text != "" {
			fmt.Fprintf(w, "Gemini: %s", p.Text)
		}
		if p.ExecutableCode != nil {
			fmt.Fprintf(w, "Language: %s\n%s\n", p.ExecutableCode.Language, p.ExecutableCode.Code)
		}
		if p.CodeExecutionResult != nil {
			fmt.Fprintf(w, "Outcome: %s\n%s\n", p.CodeExecutionResult.Outcome, p.CodeExecutionResult.Output)
		}
	}

	// Example response:
	// Gemini: Okay, I can do that. First, I'll calculate the 20th Fibonacci number. Then, I need ...
	//
	// Language: PYTHON
	//
	// def fibonacci(n):
	//    ...
	//
	// fib_20 = fibonacci(20)
	// print(f'{fib_20=}')
	//
	// Outcome: OUTCOME_OK
	// fib_20=6765
	//
	// Now that I have the 20th Fibonacci number (6765), I need to find the nearest palindrome. ...
	// ...

	return nil
}

Node.js

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 ai = new GoogleGenAI({
    vertexai: true,
    project: projectId,
    location: location,
  });

  const response = await ai.models.generateContent({
    model: 'gemini-2.5-flash',
    contents:
      'What is the sum of the first 50 prime numbers? Generate and run code for the calculation, and make sure you get all 50.',
    config: {
      tools: [{codeExecution: {}}],
      temperature: 0,
    },
  });

  console.debug(response.executableCode);
  console.debug(response.codeExecutionResult);

  return response.codeExecutionResult;
}

如需查看更多代码执行示例，请参阅代码执行文档。

后续步骤

现在，您已发出第一个 API 请求，不妨探索以下指南，了解如何为生产代码设置更高级的 Vertex AI 功能：

• Google Gen AI 库
• OpenAI 兼容性