[[["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:2025-09-04 (世界標準時間)。"],[],[],null,["# Monitor a deployed index\n\nVertex AI provides two metrics for monitoring the `IndexEndpoint` of a\ndeployed index:\n\n- `aiplatform.googleapis.com/matching_engine/current_shards`\n\n The number of shards of the `DeployedIndex`. As data is added and deleted,\n Vector Search automatically reshards the index to\n achieve optimal performance. This metric indicates the current number of\n shards of the deployed index.\n- `aiplatform.googleapis.com/matching_engine/current_replicas`\n\n The total number of active replica servers being used by the\n `DeployedIndex`. To match query volume,\n Vector Search automatically turns up\n or down replica servers based on the minimum and maximum replica settings\n specified when deploying the index.\n\n If the index has multiple shards, each shard can be served by using a\n different number of replica servers. This metric is the total number of\n replica servers across all shards of the given index.\n\n### What's next\n\n- Learn [how to query your indexes to find their\n nearest neighbors](/vertex-ai/docs/vector-search/query-index-public-endpoint).\n- Learn [how to select, query, and display these metrics in\n Metrics Explorer](/monitoring/charts/metrics-selector)."]]