使用 Gemini Multimodal 总结包含音频的视频文件

此示例展示了如何总结包含音频的视频文件，并返回带有时间戳的章节。

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：

• 快速入门：使用 Vertex AI Gemini API 生成文本

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"

	genai "google.golang.org/genai"
)

// generateWithVideo shows how to generate text using a video input.
func generateWithVideo(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: `Analyze the provided video file, including its audio.
Summarize the main points of the video concisely.
Create a chapter breakdown with timestamps for key sections or topics discussed.`},
			{FileData: &genai.FileData{
				FileURI:  "gs://cloud-samples-data/generative-ai/video/pixel8.mp4",
				MIMEType: "video/mp4",
			}},
		},
			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:
	// Here's an analysis of the provided video file:
	//
	// **Summary**
	//
	// The video features Saeka Shimada, a photographer in Tokyo, who uses the new Pixel phone ...
	//
	// **Chapter Breakdown**
	//
	// *   **0:00-0:05**: Introduction to Saeka Shimada and her work as a photographer in Tokyo.
	// ...

	return nil
}

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

  const prompt = `
  Analyze the provided video file, including its audio.
  Summarize the main points of the video concisely.
  Create a chapter breakdown with timestamps for key sections or topics discussed.
 `;

  const video = {
    fileData: {
      fileUri: 'gs://cloud-samples-data/generative-ai/video/pixel8.mp4',
      mimeType: 'video/mp4',
    },
  };

  const response = await ai.models.generateContent({
    model: 'gemini-2.5-flash',
    contents: [video, prompt],
  });

  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"))
prompt = """
Analyze the provided video file, including its audio.
Summarize the main points of the video concisely.
Create a chapter breakdown with timestamps for key sections or topics discussed.
"""
response = client.models.generate_content(
    model="gemini-2.5-flash",
    contents=[
        Part.from_uri(
            file_uri="gs://cloud-samples-data/generative-ai/video/pixel8.mp4",
            mime_type="video/mp4",
        ),
        prompt,
    ],
)

print(response.text)
# Example response:
# Here's a breakdown of the video:
#
# **Summary:**
#
# Saeka Shimada, a photographer in Tokyo, uses the Google Pixel 8 Pro's "Video Boost" feature to ...
#
# **Chapter Breakdown with Timestamps:**
#
# * **[00:00-00:12] Introduction & Tokyo at Night:** Saeka Shimada introduces herself ...
# ...

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。