Use Gemini to summarize local video file

This sample demonstrates how to use Gemini to summarize a local video file.

Code sample

Java

Before trying this sample, follow the Java setup instructions in the Vertex AI quickstart using client libraries. For more information, see the Vertex AI Java API reference documentation.

To authenticate to Vertex AI, set up Application Default Credentials. For more information, see Set up authentication for a local development environment.

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 TextGenerationWithLocalVideo {

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

  // Generates text with local video input
  public static String generateContent(String modelId) throws IOException {
    // Client Initialization. Once created, it 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 the local video.
      byte[] videoData = Files.readAllBytes(Paths.get("resources/describe_video_content.mp4"));

      GenerateContentResponse response =
          client.models.generateContent(
              modelId,
              Content.fromParts(
                  Part.fromBytes(videoData, "video/mp4"),
                  Part.fromText("Write a short and engaging blog post based on this video.")),
              null);

      System.out.print(response.text());
      // Example response:
      // More Than Just a Climb: Finding Your Flow on the Wall
      // There's something captivating about watching a climber in their element. This short clip
      // offers a perfect glimpse into the focused world of indoor climbing, where precision meets
      // power...
      return response.text();
    }
  }
}

Node.js

Before trying this sample, follow the Node.js setup instructions in the Vertex AI quickstart using client libraries. For more information, see the Vertex AI Node.js API reference documentation.

To authenticate to Vertex AI, set up Application Default Credentials. For more information, see Set up authentication for a local development environment.

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';

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

  const videoContent = fs.readFileSync('test-data/describe_video_content.mp4');

  const response = await client.models.generateContent({
    model: 'gemini-2.5-flash',
    contents: [
      {text: 'hello-world'},
      {
        inlineData: {
          data: videoContent.toString('base64'),
          mimeType: 'video/mp4',
        },
      },
      {text: 'Write a short and engaging blog post based on this video.'},
    ],
  });

  console.log(response.text);

  // Example response:
  // Okay, here's a short and engaging blog post based on the climbing video:
  // **Title: Conquering the Wall: A Glimpse into the World of Indoor Climbing**
  // ...

  return response.text;
}

Python

Before trying this sample, follow the Python setup instructions in the Vertex AI quickstart using client libraries. For more information, see the Vertex AI Python API reference documentation.

To authenticate to Vertex AI, set up Application Default Credentials. For more information, see Set up authentication for a local development environment.

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

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

# Read local video file content
with open("test_data/describe_video_content.mp4", "rb") as fp:
    # Video source: https://storage.googleapis.com/cloud-samples-data/generative-ai/video/describe_video_content.mp4
    video_content = fp.read()

response = client.models.generate_content(
    model=model_id,
    contents=[
        Part.from_text(text="hello-world"),
        Part.from_bytes(data=video_content, mime_type="video/mp4"),
        "Write a short and engaging blog post based on this video.",
    ],
)

print(response.text)
# Example response:
# Okay, here's a short and engaging blog post based on the climbing video:
# **Title: Conquering the Wall: A Glimpse into the World of Indoor Climbing**
# ...

What's next

To search and filter code samples for other Google Cloud products, see the Google Cloud sample browser.