Gemini API を使用して画像ファイルを分析する

bookmark_border コレクションでコンテンツを整理 必要に応じて、コンテンツの保存と分類を行います。

// Initialize the Gemini Developer API backend service
// Create a `GenerativeModel` instance with a model that supports your use case
val model = Firebase.ai(backend = GenerativeBackend.googleAI())
                        .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 Gemini Developer API backend service
// Create a `GenerativeModel` instance with a model that supports your use case
GenerativeModel ai = FirebaseAI.getInstance(GenerativeBackend.googleAI())
        .generativeModel("gemini-2.0-flash");

// Use the GenerativeModelFutures Java compatibility layer which offers
// support for ListenableFuture and Publisher APIs
GenerativeModelFutures model = GenerativeModelFutures.from(ai);


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 { getAI, getGenerativeModel, GoogleAIBackend } from "firebase/ai";

// 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 Gemini Developer API backend service
const ai = getAI(firebaseApp, { backend: new GoogleAIBackend() });

// Create a `GenerativeModel` instance with a model that supports your use case
const model = getGenerativeModel(ai, { 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_ai/firebase_ai.dart';
import 'package:firebase_core/firebase_core.dart';
import 'firebase_options.dart';

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

// Initialize the Gemini Developer API backend service
// Create a `GenerativeModel` instance with a model that supports your use case
final model =
      FirebaseAI.googleAI().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);
}

using Firebase;
using Firebase.AI;

// Initialize the Gemini Developer API backend service
var ai = FirebaseAI.GetInstance(FirebaseAI.Backend.GoogleAI());

// Create a `GenerativeModel` instance with a model that supports your use case
var model = ai.GetGenerativeModel(modelName: "gemini-2.0-flash");


// Convert Texture2Ds into InlineDataParts
var black = ModelContent.InlineData("image/png",
      UnityEngine.ImageConversion.EncodeToPNG(UnityEngine.Texture2D.blackTexture));
var white = ModelContent.InlineData("image/png",
      UnityEngine.ImageConversion.EncodeToPNG(UnityEngine.Texture2D.whiteTexture));

// Provide a text prompt to include with the images
var prompt = ModelContent.Text("What's different between these pictures?");

// To stream generated text output, call GenerateContentStreamAsync and pass in the prompt
var responseStream = model.GenerateContentStreamAsync(new [] { black, white, prompt });
await foreach (var response in responseStream) {
  if (!string.IsNullOrWhiteSpace(response.Text)) {
    UnityEngine.Debug.Log(response.Text);
  }
}