Membuat teks dari perintah multimodal menggunakan Gemini API

Tetap teratur dengan koleksi Simpan dan kategorikan konten berdasarkan preferensi Anda.

import FirebaseVertexAI

// Initialize the Vertex AI service
let vertex = VertexAI.vertexAI()

// Create a `GenerativeModel` instance with a model that supports your use case
let model = vertex.generativeModel(modelName: "gemini-2.0-flash")

guard let image = UIImage(systemName: "bicycle") else { fatalError() }

// Provide a text prompt to include with the image
let prompt = "What's in this picture?"

// To stream generated text output, call generateContentStream and pass in the prompt
let contentStream = try model.generateContentStream(image, prompt)
for try await chunk in contentStream {
  if let text = chunk.text {
    print(text)
  }
}

// Initialize the Vertex AI service and create a `GenerativeModel` instance
// Specify a model that supports your use case
val generativeModel = Firebase.vertexAI.generativeModel("gemini-2.0-flash")

// Loads an image from the app/res/drawable/ directory
val bitmap: Bitmap = BitmapFactory.decodeResource(resources, R.drawable.sparky)

// Provide a prompt that includes the image specified above and text
val prompt = content {
  image(bitmap)
  text("What developer tool is this mascot from?")
}

// To stream generated text output, call generateContentStream with the prompt
var fullResponse = ""
generativeModel.generateContentStream(prompt).collect { chunk ->
  print(chunk.text)
  fullResponse += chunk.text
}

// Initialize the Vertex AI service and create a `GenerativeModel` instance
// Specify a model that supports your use case
GenerativeModel gm = FirebaseVertexAI.getInstance()
        .generativeModel("gemini-2.0-flash");
GenerativeModelFutures model = GenerativeModelFutures.from(gm);

Bitmap bitmap = BitmapFactory.decodeResource(getResources(), R.drawable.sparky);

// Provide a prompt that includes the image specified above and text
Content prompt = new Content.Builder()
        .addImage(bitmap)
        .addText("What developer tool is this mascot from?")
        .build();

// To stream generated text output, call generateContentStream with the prompt
Publisher<GenerateContentResponse> streamingResponse = model.generateContentStream(prompt);

final String[] fullResponse = {""};

streamingResponse.subscribe(new Subscriber<GenerateContentResponse>() {
    @Override
    public void onNext(GenerateContentResponse generateContentResponse) {
        String chunk = generateContentResponse.getText();
        fullResponse[0] += chunk;
    }

    @Override
    public void onComplete() {
        System.out.println(fullResponse[0]);
    }

    @Override
    public void onError(Throwable t) {
        t.printStackTrace();
    }

    @Override
    public void onSubscribe(Subscription s) {
    }
});

import { initializeApp } from "firebase/app";
import { getVertexAI, getGenerativeModel } from "firebase/vertexai";

// TODO(developer) Replace the following with your app's Firebase configuration
// See: https://firebase.google.com/docs/web/learn-more#config-object
const firebaseConfig = {
  // ...
};

// Initialize FirebaseApp
const firebaseApp = initializeApp(firebaseConfig);

// Initialize the Vertex AI service
const vertexAI = getVertexAI(firebaseApp);

// Create a `GenerativeModel` instance with a model that supports your use case
const model = getGenerativeModel(vertexAI, { model: "gemini-2.0-flash" });

// Converts a File object to a Part object.
async function fileToGenerativePart(file) {
  const base64EncodedDataPromise = new Promise((resolve) => {
    const reader = new FileReader();
    reader.onloadend = () => resolve(reader.result.split(',')[1]);
    reader.readAsDataURL(file);
  });
  return {
    inlineData: { data: await base64EncodedDataPromise, mimeType: file.type },
  };
}

async function run() {
  // Provide a text prompt to include with the image
  const prompt = "What do you see?";

  // Prepare image for input
  const fileInputEl = document.querySelector("input[type=file]");
  const imagePart = await fileToGenerativePart(fileInputEl.files[0]);

  // To stream generated text output, call generateContentStream with the text and image
  const result = await model.generateContentStream([prompt, imagePart]);

  for await (const chunk of result.stream) {
    const chunkText = chunk.text();
    console.log(chunkText);
  }
}

run();

import 'package:firebase_vertexai/firebase_vertexai.dart';
import 'package:firebase_core/firebase_core.dart';
import 'firebase_options.dart';

await Firebase.initializeApp(
  options: DefaultFirebaseOptions.currentPlatform,
);

// Initialize the Vertex AI service and create a `GenerativeModel` instance
// Specify a model that supports your use case
final model =
      FirebaseVertexAI.instance.generativeModel(model: 'gemini-2.0-flash');

// Provide a text prompt to include with the image
final prompt = TextPart("What's in the picture?");
// Prepare images for input
final image = await File('image0.jpg').readAsBytes();
final imagePart = InlineDataPart('image/jpeg', image);

// To stream generated text output, call generateContentStream with the text and image
final response = await model.generateContentStream([
  Content.multi([prompt,imagePart])
]);
await for (final chunk in response) {
  print(chunk.text);
}

import FirebaseVertexAI

// Initialize the Vertex AI service
let vertex = VertexAI.vertexAI()

// Create a `GenerativeModel` instance with a model that supports your use case
let model = vertex.generativeModel(modelName: "gemini-2.0-flash")

guard let image1 = UIImage(systemName: "car") else { fatalError() }
guard let image2 = UIImage(systemName: "car.2") else { fatalError() }

// Provide a text prompt to include with the images
let prompt = "What's different between these pictures?"

// To stream generated text output, call generateContentStream and pass in the prompt
let contentStream = try model.generateContentStream(image1, image2, prompt)
for try await chunk in contentStream {
  if let text = chunk.text {
    print(text)
  }
}

// Initialize the Vertex AI service and create a `GenerativeModel` instance
// Specify a model that supports your use case
val generativeModel = Firebase.vertexAI.generativeModel("gemini-2.0-flash")

// Loads an image from the app/res/drawable/ directory
val bitmap1: Bitmap = BitmapFactory.decodeResource(resources, R.drawable.sparky)
val bitmap2: Bitmap = BitmapFactory.decodeResource(resources, R.drawable.sparky_eats_pizza)

// Provide a prompt that includes the images specified above and text
val prompt = content {
    image(bitmap1)
    image(bitmap2)
    text("What's different between these pictures?")
}

// To stream generated text output, call generateContentStream with the prompt
var fullResponse = ""
generativeModel.generateContentStream(prompt).collect { chunk ->
  print(chunk.text)
  fullResponse += chunk.text
}

// Initialize the Vertex AI service and create a `GenerativeModel` instance
// Specify a model that supports your use case
GenerativeModel gm = FirebaseVertexAI.getInstance()
        .generativeModel("gemini-2.0-flash");
GenerativeModelFutures model = GenerativeModelFutures.from(gm);

Bitmap bitmap1 = BitmapFactory.decodeResource(getResources(), R.drawable.sparky);
Bitmap bitmap2 = BitmapFactory.decodeResource(getResources(), R.drawable.sparky_eats_pizza);

// Provide a prompt that includes the images specified above and text
Content prompt = new Content.Builder()
    .addImage(bitmap1)
    .addImage(bitmap2)
    .addText("What's different between these pictures?")
    .build();

// To stream generated text output, call generateContentStream with the prompt
Publisher<GenerateContentResponse> streamingResponse = model.generateContentStream(prompt);

final String[] fullResponse = {""};

streamingResponse.subscribe(new Subscriber<GenerateContentResponse>() {
    @Override
    public void onNext(GenerateContentResponse generateContentResponse) {
        String chunk = generateContentResponse.getText();
        fullResponse[0] += chunk;
    }

    @Override
    public void onComplete() {
        System.out.println(fullResponse[0]);
    }

    @Override
    public void onError(Throwable t) {
        t.printStackTrace();
    }

    @Override
    public void onSubscribe(Subscription s) {
    }
});

import { initializeApp } from "firebase/app";
import { getVertexAI, getGenerativeModel } from "firebase/vertexai";

// TODO(developer) Replace the following with your app's Firebase configuration
// See: https://firebase.google.com/docs/web/learn-more#config-object
const firebaseConfig = {
  // ...
};

// Initialize FirebaseApp
const firebaseApp = initializeApp(firebaseConfig);

// Initialize the Vertex AI service
const vertexAI = getVertexAI(firebaseApp);

// Create a `GenerativeModel` instance with a model that supports your use case
const model = getGenerativeModel(vertexAI, { model: "gemini-2.0-flash" });

// Converts a File object to a Part object.
async function fileToGenerativePart(file) {
  const base64EncodedDataPromise = new Promise((resolve) => {
    const reader = new FileReader();
    reader.onloadend = () => resolve(reader.result.split(',')[1]);
    reader.readAsDataURL(file);
  });
  return {
    inlineData: { data: await base64EncodedDataPromise, mimeType: file.type },
  };
}

async function run() {
  // Provide a text prompt to include with the images
  const prompt = "What's different between these pictures?";

  const fileInputEl = document.querySelector("input[type=file]");
  const imageParts = await Promise.all(
    [...fileInputEl.files].map(fileToGenerativePart)
  );

  // To stream generated text output, call generateContentStream with the text and images
  const result = await model.generateContentStream([prompt, ...imageParts]);

  for await (const chunk of result.stream) {
    const chunkText = chunk.text();
    console.log(chunkText);
  }
}

run();

import 'package:firebase_vertexai/firebase_vertexai.dart';
import 'package:firebase_core/firebase_core.dart';
import 'firebase_options.dart';

await Firebase.initializeApp(
  options: DefaultFirebaseOptions.currentPlatform,
);

// Initialize the Vertex AI service and create a `GenerativeModel` instance
// Specify a model that supports your use case
final model =
      FirebaseVertexAI.instance.generativeModel(model: 'gemini-2.0-flash');

final (firstImage, secondImage) = await (
  File('image0.jpg').readAsBytes(),
  File('image1.jpg').readAsBytes()
).wait;
// Provide a text prompt to include with the images
final prompt = TextPart("What's different between these pictures?");
// Prepare images for input
final imageParts = [
  InlineDataPart('image/jpeg', firstImage),
  InlineDataPart('image/jpeg', secondImage),
];

// To stream generated text output, call generateContentStream with the text and images
final response = await model.generateContentStream([
  Content.multi([prompt, ...imageParts])
]);
await for (final chunk in response) {
  print(chunk.text);
}

import FirebaseVertexAI

// Initialize the Vertex AI service
let vertex = VertexAI.vertexAI()

// Create a `GenerativeModel` instance with a model that supports your use case
let model = vertex.generativeModel(modelName: "gemini-2.0-flash")

// Provide the video as `Data` with the appropriate MIME type
let video = InlineDataPart(data: try Data(contentsOf: videoURL), mimeType: "video/mp4")

// Provide a text prompt to include with the video
let prompt = "What is in the video?"

// To stream generated text output, call generateContentStream with the text and video
let contentStream = try model.generateContentStream(video, prompt)
for try await chunk in contentStream {
  if let text = chunk.text {
    print(text)
  }
}

// Initialize the Vertex AI service and create a `GenerativeModel` instance
// Specify a model that supports your use case
val generativeModel = Firebase.vertexAI.generativeModel("gemini-2.0-flash")

val contentResolver = applicationContext.contentResolver
contentResolver.openInputStream(videoUri).use { stream ->
  stream?.let {
    val bytes = stream.readBytes()

    // Provide a prompt that includes the video specified above and text
    val prompt = content {
        inlineData(bytes, "video/mp4")
        text("What is in the video?")
    }

    // To stream generated text output, call generateContentStream with the prompt
    var fullResponse = ""
    generativeModel.generateContentStream(prompt).collect { chunk ->
        Log.d(TAG, chunk.text ?: "")
        fullResponse += chunk.text
    }
  }
}

// Initialize the Vertex AI service and create a `GenerativeModel` instance
// Specify a model that supports your use case
GenerativeModel gm = FirebaseVertexAI.getInstance()
        .generativeModel("gemini-2.0-flash");
GenerativeModelFutures model = GenerativeModelFutures.from(gm);

ContentResolver resolver = getApplicationContext().getContentResolver();
try (InputStream stream = resolver.openInputStream(videoUri)) {
    File videoFile = new File(new URI(videoUri.toString()));
    int videoSize = (int) videoFile.length();
    byte[] videoBytes = new byte[videoSize];
    if (stream != null) {
        stream.read(videoBytes, 0, videoBytes.length);
        stream.close();

        // Provide a prompt that includes the video specified above and text
        Content prompt = new Content.Builder()
                .addInlineData(videoBytes, "video/mp4")
                .addText("What is in the video?")
                .build();

        // To stream generated text output, call generateContentStream with the prompt
        Publisher<GenerateContentResponse> streamingResponse =
                model.generateContentStream(prompt);

        final String[] fullResponse = {""};

        streamingResponse.subscribe(new Subscriber<GenerateContentResponse>() {
            @Override
            public void onNext(GenerateContentResponse generateContentResponse) {
                String chunk = generateContentResponse.getText();
                fullResponse[0] += chunk;
            }

            @Override
            public void onComplete() {
                System.out.println(fullResponse[0]);
            }

            @Override
            public void onError(Throwable t) {
                t.printStackTrace();
            }

            @Override
            public void onSubscribe(Subscription s) {
            }
         });
    }
} catch (IOException e) {
    e.printStackTrace();
} catch (URISyntaxException e) {
    e.printStackTrace();
}

import { initializeApp } from "firebase/app";
import { getVertexAI, getGenerativeModel } from "firebase/vertexai";

// TODO(developer) Replace the following with your app's Firebase configuration
// See: https://firebase.google.com/docs/web/learn-more#config-object
const firebaseConfig = {
  // ...
};

// Initialize FirebaseApp
const firebaseApp = initializeApp(firebaseConfig);

// Initialize the Vertex AI service
const vertexAI = getVertexAI(firebaseApp);

// Create a `GenerativeModel` instance with a model that supports your use case
const model = getGenerativeModel(vertexAI, { model: "gemini-2.0-flash" });

// Converts a File object to a Part object.
async function fileToGenerativePart(file) {
  const base64EncodedDataPromise = new Promise((resolve) => {
    const reader = new FileReader();
    reader.onloadend = () => resolve(reader.result.split(',')[1]);
    reader.readAsDataURL(file);
  });
  return {
    inlineData: { data: await base64EncodedDataPromise, mimeType: file.type },
  };
}

async function run() {
  // Provide a text prompt to include with the video
  const prompt = "What do you see?";

  const fileInputEl = document.querySelector("input[type=file]");
  const videoPart = await fileToGenerativePart(fileInputEl.files[0]);

  // To stream generated text output, call generateContentStream with the text and video
  const result = await model.generateContentStream([prompt, videoPart]);

  for await (const chunk of result.stream) {
    const chunkText = chunk.text();
    console.log(chunkText);
  }
}

run();

import 'package:firebase_vertexai/firebase_vertexai.dart';
import 'package:firebase_core/firebase_core.dart';
import 'firebase_options.dart';

await Firebase.initializeApp(
  options: DefaultFirebaseOptions.currentPlatform,
);

// Initialize the Vertex AI service and create a `GenerativeModel` instance
// Specify a model that supports your use case
final model =
      FirebaseVertexAI.instance.generativeModel(model: 'gemini-2.0-flash');

// Provide a text prompt to include with the video
final prompt = TextPart("What's in the video?");

// Prepare video for input
final video = await File('video0.mp4').readAsBytes();

// Provide the video as `Data` with the appropriate mimetype
final videoPart = InlineDataPart('video/mp4', video);

// To stream generated text output, call generateContentStream with the text and image
final response = await model.generateContentStream([
  Content.multi([prompt,videoPart])
]);
await for (final chunk in response) {
  print(chunk.text);
}