Traiter les images, la vidéo, l'audio et le texte avec Gemini 1.5 Pro

Cet exemple vous montre comment traiter simultanément des images, une vidéo, de l'audio et du texte. Cet exemple ne fonctionne qu'avec Gemini 1.5 Pro.

En savoir plus

Pour obtenir une documentation détaillée incluant cet exemple de code, consultez les articles suivants :

Envoyer des requêtes d'invites multimodales

Exemple de code

C#

Avant d'essayer cet exemple, suivez les instructions de configuration pour C# décrites dans le guide de démarrage rapide de Vertex AI à l'aide des bibliothèques clientes. Pour en savoir plus, consultez la documentation de référence de l'API Vertex AI C#.

Pour vous authentifier auprès de Vertex AI, configurez le service Identifiants par défaut de l'application. Pour en savoir plus, consultez Configurer l'authentification pour un environnement de développement local.


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

public class MultimodalAllInput
{
    public async Task<string> AnswerFromMultimodalInput(
        string projectId = "your-project-id",
        string location = "us-central1",
        string publisher = "google",
        string model = "gemini-1.5-pro-preview-0409")
    {

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

        string prompt = "Watch each frame in the video carefully and answer the questions.\n"
                  + "Only base your answers strictly on what information is available in "
                  + "the video attached. Do not make up any information that is not part "
                  + "of the video and do not be too verbose, be to the point.\n\n"
                  + "Questions:\n"
                  + "- When is the moment in the image happening in the video? "
                  + "Provide a timestamp.\n"
                  + "- What is the context of the moment and what does the narrator say about it?";

        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/behind_the_scenes_pixel.mp4" } },
                        new Part { FileData = new() { MimeType = "image/png", FileUri = "gs://cloud-samples-data/generative-ai/image/a-man-and-a-dog.png" } }
                    }
                }
            }
        };

        GenerateContentResponse response = await predictionServiceClient.GenerateContentAsync(generateContentRequest);

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

        return responseText;
    }
}

Go

Avant d'essayer cet exemple, suivez les instructions de configuration pour Go décrites dans le guide de démarrage rapide de Vertex AI à l'aide des bibliothèques clientes. Pour en savoir plus, consultez la documentation de référence de l'API Vertex AI Go.

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

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

// multimodalPrompt is a sample prompt type consisting of one video, one image, and a text question.
type multimodalPrompt struct {
	// video and image are Google Cloud Storage paths starting with "gs://"
	video, image string
	// question is the question asked to the model
	question string
}

// generateContentFromVideoWithAudio shows how to send a multi-modal prompt to a model, writing the response to
// the provided io.Writer.
func generateContentFromVideoWithAudio(w io.Writer, prompt multimodalPrompt, projectID, location, modelName string) error {
	// prompt := multimodalPrompt{
	// 	video: "gs://cloud-samples-data/generative-ai/video/behind_the_scenes_pixel.mp4",
	// 	image: "gs://cloud-samples-data/generative-ai/image/a-man-and-a-dog.png",
	// 	question: `
	// 		Watch each frame in the video carefully and answer the questions.
	// 		Only base your answers strictly on what information is available in the video attached.
	// 		Do not make up any information that is not part of the video and do not be too
	// 		verbose, be to the point.
	//
	// 		Questions:
	// 		- When is the moment in the image happening in the video? Provide a timestamp.
	// 		- What is the context of the moment and what does the narrator say about it?
	// `,
	// location := "us-central1"
	// modelName := "gemini-1.5-pro-preview-0409"
	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)

	vidPart := genai.FileData{
		MIMEType: mime.TypeByExtension(filepath.Ext(prompt.video)),
		FileURI:  prompt.video,
	}

	imgPart := genai.FileData{
		MIMEType: mime.TypeByExtension(filepath.Ext(prompt.image)),
		FileURI:  prompt.image,
	}

	res, err := model.GenerateContent(ctx, vidPart, imgPart, genai.Text(prompt.question))
	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
}

Java

Avant d'essayer cet exemple, suivez les instructions de configuration pour Java décrites dans le guide de démarrage rapide de Vertex AI à l'aide des bibliothèques clientes. Pour en savoir plus, consultez la documentation de référence de l'API Vertex AI Java.


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 MultimodalAllInput {

  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-pro-preview-0409";

    multimodalAllInput(projectId, location, modelName);
  }

  // A request containing a text prompt, a video, and a picture.
  public static String multimodalAllInput(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/behind_the_scenes_pixel.mp4";
      String imageUri = "gs://cloud-samples-data/generative-ai/image/a-man-and-a-dog.png";

      GenerativeModel model = new GenerativeModel(modelName, vertexAI);
      GenerateContentResponse response = model.generateContent(
          ContentMaker.fromMultiModalData(
              PartMaker.fromMimeTypeAndData("video/mp4", videoUri),
              PartMaker.fromMimeTypeAndData("image/png", imageUri),
              "Watch each frame in the video carefully and answer the questions.\n"
                  + "Only base your answers strictly on what information is available in "
                  + "the video attached. Do not make up any information that is not part "
                  + "of the video and do not be too verbose, be to the point.\n\n"
                  + "Questions:\n"
                  + "- When is the moment in the image happening in the video? "
                  + "Provide a timestamp.\n"
                  + "- What is the context of the moment and what does the narrator say about it?"
          ));

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

      return output;
    }
  }
}

Node.js

Avant d'essayer cet exemple, suivez les instructions de configuration pour Node.js décrites dans le guide de démarrage rapide de Vertex AI à l'aide des bibliothèques clientes. Pour en savoir plus, consultez la documentation de référence de l'API Vertex AI Node.js.

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

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

  const generativeModel = vertexAI.getGenerativeModel({
    model: 'gemini-1.5-pro-preview-0409',
  });

  const videoFilePart = {
    file_data: {
      file_uri:
        'gs://cloud-samples-data/generative-ai/video/behind_the_scenes_pixel.mp4',
      mime_type: 'video/mp4',
    },
  };
  const imageFilePart = {
    file_data: {
      file_uri:
        'gs://cloud-samples-data/generative-ai/image/a-man-and-a-dog.png',
      mime_type: 'image/png',
    },
  };

  const textPart = {
    text: `
    Watch each frame in the video carefully and answer the questions.
    Only base your answers strictly on what information is available in the video attached.
    Do not make up any information that is not part of the video and do not be too
    verbose, be to the point.

    Questions:
    - When is the moment in the image happening in the video? Provide a timestamp.
    - What is the context of the moment and what does the narrator say about it?`,
  };

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

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

Python

Avant d'essayer cet exemple, suivez les instructions de configuration pour Python décrites dans le guide de démarrage rapide de Vertex AI à l'aide des bibliothèques clientes. Pour en savoir plus, consultez la documentation de référence de l'API Vertex AI Python.


  import vertexai
  from vertexai.generative_models import GenerativeModel, Part

  # TODO(developer): Update and un-comment below lines
  # project_id = "PROJECT_ID"

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

  model = GenerativeModel(model_name="gemini-1.5-flash-preview-0514")

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

  image_file_uri = "gs://cloud-samples-data/generative-ai/image/a-man-and-a-dog.png"
  image_file = Part.from_uri(image_file_uri, mime_type="image/png")

  prompt = """
  Watch each frame in the video carefully and answer the questions.
  Only base your answers strictly on what information is available in the video attached.
  Do not make up any information that is not part of the video and do not be too
  verbose, be to the point.

  Questions:
  - When is the moment in the image happening in the video? Provide a timestamp.
  - What is the context of the moment and what does the narrator say about it?
"""

  contents = [
      video_file,
      image_file,
      prompt,
  ]

  response = model.generate_content(contents)
  print(response.text)

Étapes suivantes

Pour rechercher et filtrer des exemples de code pour d'autres produits Google Cloud, consultez l'explorateur d'exemples Google Cloud.