Google Distributed Cloud(GDC)エアギャップ上の Vertex AI には、エアギャップ アプリケーションでテスト、デプロイ、実装できる基盤となる生成 AI モデルがあり、その数は増え続けています。基盤モデルは特定のユースケースに合わせてファインチューニングされており、さまざまな価格で提供されます。このページでは、GDC の生成 AI API で使用可能なモデル ファミリーの概要と、ユースケースごとに選択するモデルに関するガイダンスを示します。
[[["わかりやすい","easyToUnderstand","thumb-up"],["問題の解決に役立った","solvedMyProblem","thumb-up"],["その他","otherUp","thumb-up"]],[["わかりにくい","hardToUnderstand","thumb-down"],["情報またはサンプルコードが不正確","incorrectInformationOrSampleCode","thumb-down"],["必要な情報 / サンプルがない","missingTheInformationSamplesINeed","thumb-down"],["翻訳に関する問題","translationIssue","thumb-down"],["その他","otherDown","thumb-down"]],["最終更新日 2025-09-04 UTC。"],[],[],null,["# Available Generative AI models\n\n| **Important:** This content applies to version 1.14.4 and later.\n\nVertex AI on Google Distributed Cloud (GDC) air-gapped features a growing\nlist of foundation Generative AI models you can test, deploy, and implement\nfor your air-gapped applications. Foundation models are fine-tuned for specific\nuse cases and offered at different prices. This page summarizes the model\nfamilies available in the Generative AI APIs on GDC\nand guides you on which models to choose by use case.\n\nEmbeddings models\n-----------------\n\nEmbeddings convert textual data written in a natural language into numerical\nvectors. These vector representations are designed to capture the semantic\nmeaning and context of the words they represent. Text embedding models can\ngenerate optimized embeddings for various task types, such as document\nretrieval, questions and answers, classification, and fact verification. For\nEnglish text, use `text-embedding-004`. For multilingual text, use\n`text-multilingual-embedding-002`.\n\nThe following table summarizes the models available in the Embeddings API.\nFor more information on embeddings, see\n[Text embeddings](/distributed-cloud/hosted/docs/latest/gdch/application/ao-user/genai/text-embeddings-overview)."]]