[[["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,["# Manage model monitor\n\n| **Preview**\n|\n|\n| This product or feature is subject to the \"Pre-GA Offerings Terms\" in the General Service Terms section\n| of the [Service Specific Terms](/terms/service-terms#1).\n|\n| Pre-GA products and features are available \"as is\" and might have limited support.\n|\n| For more information, see the\n| [launch stage descriptions](/products#product-launch-stages).\n\nThis page describes how to update and delete model monitors.\n\nUpdate a model monitor\n----------------------\n\nUpdate a model monitor to modify the default configuration for monitoring jobs.\nYou can't change the model version that a model monitor is associated with.\nInstead, create a new model monitor. \n\n### Console\n\n1. In the Google Cloud console, go to the **Monitoring** page.\n\n [Go to Monitoring](https://console.cloud.google.com/vertex-ai/model-monitoring/model-monitors)\n2. Click the model monitor to go to the **Monitor details** page.\n\n3. Click **Edit configuration** to update the model monitor.\n\n4. Modify your schema, notifications, training data source, and objectives.\n\n5. Click **Save**.\n\n### Python SDK\n\nYou can update the following specifications:\n\n- Display name\n- Training dataset\n- Model schema\n- Default monitoring objectives\n- Default monitoring output specification\n- Default monitoring notification specification\n- Default explanation specification for feature attribution\n\nThe following example updates the model schema: \n\n```python\nmonitor_2.update(model_monitoring_schema=MODEL_MONITORING_SCHEMA)\n```\n\nDelete a model monitor\n----------------------\n\nRemove model monitors to prevent authorized users from inadvertently running\nmonitoring jobs on unused model monitors. When you delete a model monitor, any\nassociated monitoring data is deleted except for metrics and statistics exported\nby Monitoring, which remain in Cloud Monitoring and in your\nCloud Storage. \n\n### Console\n\n1. In the Google Cloud console, go to the **Monitoring** page.\n\n [Go to Monitoring](https://console.cloud.google.com/vertex-ai/model-monitoring/model-monitors)\n2. Click the model monitor to go to the **Monitor details** page.\n\n3. Click **Edit configuration** to update the model monitor.\n\n### Python SDK\n\n```python\nfrom google.cloud.aiplatform.private_preview.centralized_model_monitoring\nimport model_monitor\n\nmy_model_monitor.delete(force=true)\n```"]]
