视频理解

import vertexai

from vertexai.generative_models import GenerativeModel, Part

# TODO(developer): Update and un-comment below line
# PROJECT_ID = "your-project-id"

vertexai.init(project=PROJECT_ID, location="us-central1")

vision_model = GenerativeModel("gemini-1.5-flash-002")

# Generate text
response = vision_model.generate_content(
    [
        Part.from_uri(
            "gs://cloud-samples-data/video/animals.mp4", mime_type="video/mp4"
        ),
        "What is in the video?",
    ]
)
print(response.text)
# Example response:
# Here's a summary of the video's content.
# The video shows a series of animals at the Los Angeles Zoo interacting
# with waterproof cameras attached to various devices.
# ...

import com.google.cloud.vertexai.VertexAI;
import com.google.cloud.vertexai.api.GenerateContentResponse;
import com.google.cloud.vertexai.generativeai.ContentMaker;
import com.google.cloud.vertexai.generativeai.GenerativeModel;
import com.google.cloud.vertexai.generativeai.PartMaker;
import com.google.cloud.vertexai.generativeai.ResponseHandler;
import java.io.IOException;

public class MultimodalVideoInput {

  public static void main(String[] args) throws IOException {
    // TODO(developer): Replace these variables before running the sample.
    String projectId = "your-google-cloud-project-id";
    String location = "us-central1";
    String modelName = "gemini-1.5-flash-001";

    multimodalVideoInput(projectId, location, modelName);
  }

  // Analyzes the given video input.
  public static void multimodalVideoInput(String projectId, String location, String modelName)
      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 (VertexAI vertexAI = new VertexAI(projectId, location)) {
      String videoUri = "gs://cloud-samples-data/video/animals.mp4";

      GenerativeModel model = new GenerativeModel(modelName, vertexAI);
      GenerateContentResponse response = model.generateContent(
          ContentMaker.fromMultiModalData(
              "What is in the video?",
              PartMaker.fromMimeTypeAndData("video/mp4", videoUri)
          ));

      String output = ResponseHandler.getText(response);
      System.out.println(output);
    }
  }
}

const {VertexAI} = require('@google-cloud/vertexai');

/**
 * TODO(developer): Update these variables before running the sample.
 */
async function sendMultiModalPromptWithVideo(
  projectId = 'PROJECT_ID',
  location = 'us-central1',
  model = 'gemini-1.5-flash-001'
) {
  // Initialize Vertex with your Cloud project and location
  const vertexAI = new VertexAI({project: projectId, location: location});

  const generativeVisionModel = vertexAI.getGenerativeModel({
    model: model,
  });

  // Pass multimodal prompt
  const request = {
    contents: [
      {
        role: 'user',
        parts: [
          {
            fileData: {
              fileUri: 'gs://cloud-samples-data/video/animals.mp4',
              mimeType: 'video/mp4',
            },
          },
          {
            text: 'What is in the video?',
          },
        ],
      },
    ],
  };

  // Create the response
  const response = await generativeVisionModel.generateContent(request);
  // Wait for the response to complete
  const aggregatedResponse = await response.response;
  // Select the text from the response
  const fullTextResponse =
    aggregatedResponse.candidates[0].content.parts[0].text;

  console.log(fullTextResponse);
}

import (
	"context"
	"errors"
	"fmt"
	"io"
	"mime"
	"path/filepath"

	"cloud.google.com/go/vertexai/genai"
)

// generateMultimodalContent generates a response into w, based upon the prompt and video.
func generateMultimodalContent(w io.Writer, projectID, location, modelName string) error {
	// location := "us-central1"
	// modelName := "gemini-1.5-flash-001"
	ctx := context.Background()

	client, err := genai.NewClient(ctx, projectID, location)
	if err != nil {
		return fmt.Errorf("unable to create client: %w", err)
	}
	defer client.Close()

	model := client.GenerativeModel(modelName)
	model.SetTemperature(0.4)

	// Given a video file URL, prepare video file as genai.Part
	part := genai.FileData{
		MIMEType: mime.TypeByExtension(filepath.Ext("animals.mp4")),
		FileURI:  "gs://cloud-samples-data/video/animals.mp4",
	}

	res, err := model.GenerateContent(ctx, part, genai.Text("What is in this video?"))
	if err != nil {
		return fmt.Errorf("unable to generate contents: %w", err)
	}

	if len(res.Candidates) == 0 ||
		len(res.Candidates[0].Content.Parts) == 0 {
		return errors.New("empty response from model")
	}

	fmt.Fprintf(w, "generated response: %s\n", res.Candidates[0].Content.Parts[0])
	return nil
}

using Google.Api.Gax.Grpc;
using Google.Cloud.AIPlatform.V1;
using System.Text;
using System.Threading.Tasks;

public class MultimodalVideoInput
{
    public async Task<string> GenerateContent(
        string projectId = "your-project-id",
        string location = "us-central1",
        string publisher = "google",
        string model = "gemini-1.5-flash-001"
    )
    {
        var predictionServiceClient = new PredictionServiceClientBuilder
        {
            Endpoint = $"{location}-aiplatform.googleapis.com"
        }.Build();

        var generateContentRequest = new GenerateContentRequest
        {
            Model = $"projects/{projectId}/locations/{location}/publishers/{publisher}/models/{model}",
            Contents =
            {
                new Content
                {
                    Role = "USER",
                    Parts =
                    {
                        new Part { Text = "What's in the video?" },
                        new Part { FileData = new() { MimeType = "video/mp4", FileUri = "gs://cloud-samples-data/video/animals.mp4" }}
                    }
                }
            }
        };

        using PredictionServiceClient.StreamGenerateContentStream response = predictionServiceClient.StreamGenerateContent(generateContentRequest);

        StringBuilder fullText = new();

        AsyncResponseStream<GenerateContentResponse> responseStream = response.GetResponseStream();
        await foreach (GenerateContentResponse responseItem in responseStream)
        {
            fullText.Append(responseItem.Candidates[0].Content.Parts[0].Text);
        }
        return fullText.ToString();
    }
}

import vertexai
from vertexai.generative_models import GenerativeModel, Part

# TODO(developer): Update and un-comment below line
# PROJECT_ID = "your-project-id"

vertexai.init(project=PROJECT_ID, location="us-central1")

model = GenerativeModel("gemini-1.5-flash-002")

prompt = """
Provide a description of the video.
The description should also contain anything important which people say in the video.
"""

video_file = Part.from_uri(
    uri="gs://cloud-samples-data/generative-ai/video/pixel8.mp4",
    mime_type="video/mp4",
)

contents = [video_file, prompt]

response = model.generate_content(contents)
print(response.text)
# Example response:
# Here is a description of the video.
# ... Then, the scene changes to a woman named Saeko Shimada..
# She says, "Tokyo has many faces. The city at night is totally different
# from what you see during the day."
# ...

import com.google.cloud.vertexai.VertexAI;
import com.google.cloud.vertexai.api.GenerateContentResponse;
import com.google.cloud.vertexai.generativeai.ContentMaker;
import com.google.cloud.vertexai.generativeai.GenerativeModel;
import com.google.cloud.vertexai.generativeai.PartMaker;
import com.google.cloud.vertexai.generativeai.ResponseHandler;
import java.io.IOException;

public class VideoInputWithAudio {

  public static void main(String[] args) throws IOException {
    // TODO(developer): Replace these variables before running the sample.
    String projectId = "your-google-cloud-project-id";
    String location = "us-central1";
    String modelName = "gemini-1.5-flash-001";

    videoAudioInput(projectId, location, modelName);
  }

  // Analyzes the given video input, including its audio track.
  public static String videoAudioInput(String projectId, String location, String modelName)
      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 (VertexAI vertexAI = new VertexAI(projectId, location)) {
      String videoUri = "gs://cloud-samples-data/generative-ai/video/pixel8.mp4";

      GenerativeModel model = new GenerativeModel(modelName, vertexAI);
      GenerateContentResponse response = model.generateContent(
          ContentMaker.fromMultiModalData(
              "Provide a description of the video.\n The description should also "
                  + "contain anything important which people say in the video.",
              PartMaker.fromMimeTypeAndData("video/mp4", videoUri)
          ));

      String output = ResponseHandler.getText(response);
      System.out.println(output);

      return output;
    }
  }
}

const {VertexAI} = require('@google-cloud/vertexai');

/**
 * TODO(developer): Update these variables before running the sample.
 */
async function analyze_video_with_audio(projectId = 'PROJECT_ID') {
  const vertexAI = new VertexAI({project: projectId, location: 'us-central1'});

  const generativeModel = vertexAI.getGenerativeModel({
    model: 'gemini-1.5-flash-001',
  });

  const filePart = {
    file_data: {
      file_uri: 'gs://cloud-samples-data/generative-ai/video/pixel8.mp4',
      mime_type: 'video/mp4',
    },
  };
  const textPart = {
    text: `
    Provide a description of the video.
    The description should also contain anything important which people say in the video.`,
  };

  const request = {
    contents: [{role: 'user', parts: [filePart, textPart]}],
  };

  const resp = await generativeModel.generateContent(request);
  const contentResponse = await resp.response;
  console.log(JSON.stringify(contentResponse));
}

import (
	"context"
	"errors"
	"fmt"
	"io"
	"mime"
	"path/filepath"

	"cloud.google.com/go/vertexai/genai"
)

// generateMultimodalContent shows how to send video and text prompts to a model, writing the response to
// the provided io.Writer.
func generateMultimodalContent(w io.Writer, projectID, location, modelName string) error {
	// location := "us-central1"
	// modelName := "gemini-1.5-flash-001"
	ctx := context.Background()

	client, err := genai.NewClient(ctx, projectID, location)
	if err != nil {
		return fmt.Errorf("unable to create client: %w", err)
	}
	defer client.Close()

	model := client.GenerativeModel(modelName)

	// Given a video file URL, prepare video file as genai.Part
	part := genai.FileData{
		MIMEType: mime.TypeByExtension(filepath.Ext("pixel8.mp4")),
		FileURI:  "gs://cloud-samples-data/generative-ai/video/pixel8.mp4",
	}

	res, err := model.GenerateContent(ctx, part, genai.Text(`
			Provide a description of the video.
			The description should also contain anything important which people say in the video.
	`))
	if err != nil {
		return fmt.Errorf("unable to generate contents: %w", err)
	}

	if len(res.Candidates) == 0 ||
		len(res.Candidates[0].Content.Parts) == 0 {
		return errors.New("empty response from model")
	}

	fmt.Fprintf(w, "generated response: %s\n", res.Candidates[0].Content.Parts[0])
	return nil
}

using Google.Cloud.AIPlatform.V1;
using System;
using System.Threading.Tasks;

public class VideoInputWithAudio
{
    public async Task<string> DescribeVideo(
        string projectId = "your-project-id",
        string location = "us-central1",
        string publisher = "google",
        string model = "gemini-1.5-flash-001")
    {

        var predictionServiceClient = new PredictionServiceClientBuilder
        {
            Endpoint = $"{location}-aiplatform.googleapis.com"
        }.Build();

        string prompt = @"Provide a description of the video.
The description should also contain anything important which people say in the video.";

        var generateContentRequest = new GenerateContentRequest
        {
            Model = $"projects/{projectId}/locations/{location}/publishers/{publisher}/models/{model}",
            Contents =
            {
                new Content
                {
                    Role = "USER",
                    Parts =
                    {
                        new Part { Text = prompt },
                        new Part { FileData = new() { MimeType = "video/mp4", FileUri = "gs://cloud-samples-data/generative-ai/video/pixel8.mp4" }}
                    }
                }
            }
        };

        GenerateContentResponse response = await predictionServiceClient.GenerateContentAsync(generateContentRequest);

        string responseText = response.Candidates[0].Content.Parts[0].Text;
        Console.WriteLine(responseText);

        return responseText;
    }
}