[[["容易理解","easyToUnderstand","thumb-up"],["確實解決了我的問題","solvedMyProblem","thumb-up"],["其他","otherUp","thumb-up"]],[["難以理解","hardToUnderstand","thumb-down"],["資訊或程式碼範例有誤","incorrectInformationOrSampleCode","thumb-down"],["缺少我需要的資訊/範例","missingTheInformationSamplesINeed","thumb-down"],["翻譯問題","translationIssue","thumb-down"],["其他","otherDown","thumb-down"]],["上次更新時間:2025-05-02 (世界標準時間)。"],[[["\u003cp\u003eThis Architecture Center page offers resources for understanding and implementing AI and machine learning (ML) solutions, including generative AI, traditional AI, and MLOps.\u003c/p\u003e\n"],["\u003cp\u003eThe content provides guidance on designing, building, and deploying AI and ML solutions on Google Cloud, with a focus on various generative AI applications and use cases.\u003c/p\u003e\n"],["\u003cp\u003eThe page includes a range of example architectures, like document summarization and knowledge bases, as well as RAG implementations across several products like Cloud SQL, Vertex AI, and GKE.\u003c/p\u003e\n"],["\u003cp\u003eResources are categorized into generative AI, model training, MLOps, and AI/ML applications, offering a comprehensive overview of available content.\u003c/p\u003e\n"],["\u003cp\u003eYou can explore various AI/ML solutions and filter resources based on product names or descriptions to find relevant information for specific needs and build your AI and ML applications.\u003c/p\u003e\n"]]],[],null,["# AI and machine learning resources\n\n\u003cbr /\u003e\n\nThe Architecture Center provides content resources across a wide variety of AI\nand machine learning subjects. This page provides information to help you get\nstarted with generative AI, traditional AI, and machine learning. It also\nprovides a list of all the AI and machine learning (ML) content in the\nArchitecture Center.\n\nGet started\n-----------\n\nThe documents listed on this page can help you get started with designing,\nbuilding, and deploying AI and ML solutions on Google Cloud.\n\n### Explore generative AI\n\nStart by learning about the fundamentals of generative AI on\nGoogle Cloud, on the Cloud documentation site:\n\n- To learn the stages of developing a generative AI application and explore the products and tools for your use case, see [Build a generative AI application on Google Cloud](/docs/ai-ml/generative-ai).\n- To identify when generative AI, traditional AI (which includes prediction and classification), or a combination of both might suit your business use case, see [When to use generative AI or traditional AI](/docs/ai-ml/generative-ai/generative-ai-or-traditional-ai).\n- To define an AI business use case with a business value-driven decision approach, see [Evaluate and define your generative AI business use case](/docs/ai-ml/generative-ai/evaluate-define-generative-ai-use-case).\n- To address the challenges of model selection, evaluation, tuning, and development, see [Develop a generative AI application](/docs/ai-ml/generative-ai/develop-generative-ai-application).\n\nTo explore a generative AI and machine learning blueprint that deploys a pipeline for creating AI models, see [Build and deploy generative AI and machine learning models in an enterprise](/architecture/blueprints/genai-mlops-blueprint). The guide explains the entire AI development lifecycle, from preliminary data exploration and experimentation through model training, deployment, and monitoring.\n\nBrowse the following example architectures that use generative AI:\n\n- [Generative AI document summarization](/architecture/ai-ml/generative-ai-document-summarization)\n- [Generative AI knowledge base](/architecture/ai-ml/generative-ai-knowledge-base)\n- [Generative AI RAG with Cloud SQL](/architecture/ai-ml/generative-ai-rag)\n- [Infrastructure for a RAG-capable generative AI application using Vertex AI and Vector Search](/architecture/gen-ai-rag-vertex-ai-vector-search)\n- [Infrastructure for a RAG-capable generative AI application using Vertex AI and AlloyDB for PostgreSQL](/architecture/rag-capable-gen-ai-app-using-vertex-ai)\n- [Infrastructure for a RAG-capable generative AI application using GKE and Cloud SQL](/architecture/rag-capable-gen-ai-app-using-gke)\n- [Model development and data labeling with Google Cloud and Labelbox](/architecture/partners/model-development-data-labeling-labelbox-google-cloud)\n\nFor information about Google Cloud generative AI offerings, see\n[Vertex AI](/vertex-ai/generative-ai/docs/multimodal/overview)\nand\n[running your foundation model on GKE](/kubernetes-engine/docs/integrations/ai-infra).\n\n### Design and build\n\nTo select the best combination of storage options for your AI workload, see\n[Design storage for AI and ML workloads in Google Cloud](/architecture/ai-ml/storage-for-ai-ml).\n\nGoogle Cloud provides a\n[suite of AI and machine learning services](/products/ai)\nto help you summarize documents with generative AI, build image processing\npipelines, and innovate with generative AI solutions.\n\nKeep exploring\n--------------\n\nThe documents that are listed in the \"AI and machine learning\" section of the\nleft navigation can help you build an AI or ML solution."]]