準備好從應用程式呼叫 Vertex AI Gemini API 後,請按照 Firebase AI Logic 入門指南的「步驟 1」操作,在應用程式中設定 Firebase 和 SDK。
新增 Gradle 依附元件
將下列 Gradle 依附元件新增至應用程式模組:
dependencies{// ... other androidx dependencies// Import the BoM for the Firebase platformimplementation(platform("com.google.firebase:firebase-bom:34.1.0"))// Add the dependency for the Firebase AI Logic library. When using the BoM,// you don't specify versions in Firebase library dependenciesimplementation("com.google.firebase:firebase-ai")}
如要進一步瞭解可搭配 Gemini Developer API 使用的模型,請參閱 Firebase 說明文件。您也可以瞭解如何設定模型參數。
生成文字
如要生成文字回覆,請使用提示呼叫 generateContent()。
Kotlin
// Note: generateContent() is a suspend function, which integrates well// with existing Kotlin code.scope.launch{valresponse=model.generateContent("Write a story about a magic backpack.")}
Java
Contentprompt=newContent.Builder().addText("Write a story about a magic backpack.").build();ListenableFuture<GenerateContentResponse>response=model.generateContent(prompt);Futures.addCallback(response,newFutureCallback<GenerateContentResponse>(){@OverridepublicvoidonSuccess(GenerateContentResponseresult){StringresultText=result.getText();[...]}@OverridepublicvoidonFailure(Throwablet){t.printStackTrace();}},executor);
[[["容易理解","easyToUnderstand","thumb-up"],["確實解決了我的問題","solvedMyProblem","thumb-up"],["其他","otherUp","thumb-up"]],[["缺少我需要的資訊","missingTheInformationINeed","thumb-down"],["過於複雜/步驟過多","tooComplicatedTooManySteps","thumb-down"],["過時","outOfDate","thumb-down"],["翻譯問題","translationIssue","thumb-down"],["示例/程式碼問題","samplesCodeIssue","thumb-down"],["其他","otherDown","thumb-down"]],["上次更新時間:2025-08-17 (世界標準時間)。"],[],[],null,["# Vertex AI Gemini API\n\n| **Note:** if you previously integrated Vertex AI in Firebase (with Gradle `import\n| com.google.firebase:vertex-ai`) you can continue using Vertex AI as an API provider with the Firebase AI Logic SDK.\n\nIf you are new to the Gemini API, the [Gemini Developer API](/ai/gemini-developer-api) is the\nrecommended [API provider](/ai/gemini#api-providers) for Android Developers. But if you have specific\ndata [location requirements](https://cloud.google.com/compute/docs/regions-zones) or you are already embedded in the\nVertex AI or Google Cloud environment, you can use the Vertex AI Gemini API.\n\nMigration from Vertex AI in Firebase\n------------------------------------\n\nIf you originally integrated the Gemini Flash and Pro models using Vertex AI in\nFirebase, you can migrate to and continue using Vertex AI as an API provider.\nRead the Firebase documentation for a detailed [migration guide](https://firebase.google.com/docs/vertex-ai/migrate-to-latest-sdk).\n\nGetting started\n---------------\n\nBefore you interact with the Vertex AI Gemini API directly from your app, you\ncan experiment with prompts in [Vertex AI Studio](https://console.cloud.google.com/vertex-ai/studio).\n\n### Set up a Firebase project and connect your app to Firebase\n\nOnce you're ready to call the Vertex AI Gemini API from your app, follow the\ninstructions in the \"Step 1\" Firebase AI Logic getting started guide to set up\nFirebase and the SDK in your app.\n\n### Add the Gradle dependency\n\nAdd the following Gradle dependency to your app module: \n\n dependencies {\n // ... other androidx dependencies\n\n // Import the BoM for the Firebase platform\n implementation(platform(\"com.google.firebase:firebase-bom:34.1.0\"))\n\n // Add the dependency for the Firebase AI Logic library. When using the BoM,\n // you don't specify versions in Firebase library dependencies\n implementation(\"com.google.firebase:firebase-ai\")\n }\n\n### Initialize the generative model\n\nStart by instantiating a `GenerativeModel` and specifying the model name: \n\n### Kotlin\n\n val model = Firebase.ai(backend = GenerativeBackend.vertexAI())\n .generativeModel(\"gemini-2.5-flash\")\n\n### Java\n\n GenerativeModel firebaseAI = FirebaseAI.getInstance(GenerativeBackend.vertexAI())\n .generativeModel(\"gemini-2.5-flash\");\n\n GenerativeModelFutures model = GenerativeModelFutures.from(firebaseAI);\n\nIn the Firebase documentation, you can learn more about the [available\nmodels](https://firebase.google.com/docs/vertex-ai/gemini-models) for use with the Gemini Developer API. You can also learn\nabout [configuring model parameters](https://firebase.google.com/docs/vertex-ai/model-parameters?platform=android).\n\n### Generate text\n\nTo generate a text response, call `generateContent()` with your prompt. \n\n### Kotlin\n\n // Note: generateContent() is a suspend function, which integrates well\n // with existing Kotlin code.\n scope.launch {\n val response = model.generateContent(\"Write a story about a magic backpack.\")\n }\n\n### Java\n\n Content prompt = new Content.Builder()\n .addText(\"Write a story about a magic backpack.\")\n .build();\n\n ListenableFuture\u003cGenerateContentResponse\u003e response = model.generateContent(prompt);\n Futures.addCallback(response, new FutureCallback\u003cGenerateContentResponse\u003e() {\n @Override\n public void onSuccess(GenerateContentResponse result) {\n String resultText = result.getText();\n [...]\n }\n\n @Override\n public void onFailure(Throwable t) {\n t.printStackTrace();\n }\n }, executor);\n\nSimilar to the Gemini Developer API, you can also pass images, audio, video and\nfiles with your text prompt (see \"Interact [with the Gemini Developer API from\nyour app\"](/ai/gemini/developer-api#interact-gemini)).\n\nTo learn more about Firebase AI Logic SDK, read the [Firebase documentation](https://firebase.google.com/docs/vertex-ai/get-started?platform=android)."]]