如需在隔离的环境中使用笔记本,您可以创建 Vertex AI Workbench 实例。然后,在 Vertex AI Workbench 实例的笔记本中安装 Vertex AI SDK 并运行 Python 脚本。如需了解详情,请参阅创建 Vertex AI Workbench 实例。
安装或更新 Vertex AI SDK 软件包
如需安装或更新 Vertex AI SDK,请在虚拟环境中运行以下命令:
pip install --upgrade google-cloud-aiplatform
初始化 Vertex AI SDK
安装 Vertex AI SDK for Python 后,您必须使用 Vertex AI 和 Google Cloud 详细信息初始化 SDK。例如,初始化 SDK 时,您可以指定项目名称、区域和暂存 Cloud Storage 存储桶等信息。以下示例展示了初始化 Vertex AI SDK 的方法。
[[["易于理解","easyToUnderstand","thumb-up"],["解决了我的问题","solvedMyProblem","thumb-up"],["其他","otherUp","thumb-up"]],[["很难理解","hardToUnderstand","thumb-down"],["信息或示例代码不正确","incorrectInformationOrSampleCode","thumb-down"],["没有我需要的信息/示例","missingTheInformationSamplesINeed","thumb-down"],["翻译问题","translationIssue","thumb-down"],["其他","otherDown","thumb-down"]],["最后更新时间 (UTC):2025-09-04。"],[],[],null,["# Install the Vertex AI SDK for Python\n\nUse the Vertex AI SDK for Python to automate your machine learning (ML) workflows.\nThis topic shows you how to install the Vertex AI SDK for Python. For more\ninformation about the Vertex AI SDK, see the following resources:\n\n- To learn about the Vertex AI SDK for Python, see [Introduction to the Vertex AI SDK for Python](/vertex-ai/docs/python-sdk/use-vertex-ai-python-sdk).\n- To learn how to train a model using the Vertex AI SDK for Python, see the [Train\n a model using Vertex AI and the Python\n SDK](/vertex-ai/docs/tutorials/tabular-bq-prediction).\n- To learn about the classes and methods in the Vertex AI SDK for Python, see the [Vertex AI SDK reference](/python/docs/reference/aiplatform/latest/google.cloud.aiplatform).\n\nInstallation of the Vertex AI SDK for Python includes the following steps:\n\n1. [Create an isolated Python environment](#create-isolated-environment)\n2. [Install the Vertex AI SDK package](#install-python-sdk)\n3. [Initialize the Vertex AI SDK](#initialize-python-sdk)\n\nCreate an isolated Python environment\n-------------------------------------\n\nA Python best practice is to install the Vertex AI SDK in an\nisolated Python environment for each project. This helps prevent dependency,\nversion, and permissions conflicts. You can create an isolated environment for\nusing the command line in a shell or for using a notebook.\n\nTo create an isolated environment when you use the command line, [activate a\n`venv` environment](/python/docs/setup#installing_and_using_virtualenv). After\nthe `venv` environment is activated, you're ready to install the\nVertex AI SDK and run your Python scripts. For more information, see\n[Use `venv` to isolate dependencies](/python/docs/setup#installing_and_using_virtualenv)\nand [Set up a Python development environment](/python/docs/setup).\n\nTo use a notebook in an isolated environment, you can create a\nVertex AI Workbench instance. Then, install the Vertex AI SDK\nand run your Python scripts from a notebook on your Vertex AI Workbench instance.\nFor more information, see\n[Create a Vertex AI Workbench instance](/vertex-ai/docs/workbench/instances/create).\n\nInstall or update the Vertex AI SDK package\n-------------------------------------------\n\nTo install or update the Vertex AI SDK, run the following command in your\nvirtual environment: \n\n```\npip install --upgrade google-cloud-aiplatform\n```\n\nInitialize the Vertex AI SDK\n----------------------------\n\nAfter you install the Vertex AI SDK for Python, you must initialize the SDK with\nyour Vertex AI and Google Cloud details. For example, when you\ninitialize the SDK, you specify information such as your project name, region,\nand your staging Cloud Storage bucket. The following method is an example of\na method that initializes the Vertex AI SDK. \n\n def init_sample(\n project: Optional[str] = None,\n location: Optional[str] = None,\n experiment: Optional[str] = None,\n staging_bucket: Optional[str] = None,\n credentials: Optional[google.auth.credentials.Credentials] = None,\n encryption_spec_key_name: Optional[str] = None,\n service_account: Optional[str] = None,\n ):\n\n import https://cloud.google.com/python/docs/reference/vertexai/latest/\n\n https://cloud.google.com/python/docs/reference/vertexai/latest/.init(\n project=project,\n location=location,\n experiment=experiment,\n staging_bucket=staging_bucket,\n credentials=credentials,\n encryption_spec_key_name=encryption_spec_key_name,\n service_account=service_account,\n )\n\nWhat's next\n-----------\n\n- Learn more about the [Vertex AI SDK](/vertex-ai/docs/python-sdk/use-vertex-ai-python-sdk)."]]