arize-可观测性 arize-observability

Arize AI 可观测性技能,专注于生产环境机器学习模型监控、性能分析与漂移检测。该技能提供全面的MLOps解决方案,包括数据记录、嵌入向量漂移检测、实时仪表板、根因分析、A/B测试监控和自定义告警。适用于NLP、CV等AI模型的部署后生命周期管理,确保模型在生产环境中的稳定性、公平性和高性能。关键词:机器学习监控,模型漂移检测,MLOps,生产ML,性能分析,Arize AI,可观测性,AI运维。

AI应用 0 次安装 0 次浏览 更新于 2/23/2026

name: arize-observability description: Arize AI 技能,用于生产环境机器学习监控、嵌入漂移检测和性能分析。 allowed-tools:

  • Read
  • Write
  • Bash
  • Glob
  • Grep

arize-observability

概述

Arize AI 技能,用于生产环境机器学习监控、嵌入漂移检测和全面的性能分析。

功能

  • 生产数据记录
  • NLP/CV模型的嵌入漂移检测
  • 性能监控仪表板
  • 根因分析
  • 针对细分群体的切片分析
  • 偏差监控
  • A/B测试监控
  • 自定义指标和监控器

目标流程

  • 模型性能监控与漂移检测
  • ML系统可观测性与事件响应
  • 模型评估与验证框架

工具与库

  • Arize AI SDK
  • pandas
  • numpy

输入模式

{
  "type": "object",
  "required": ["action"],
  "properties": {
    "action": {
      "type": "string",
      "enum": ["log", "monitor", "analyze", "alert-config", "compare"],
      "description": "要执行的Arize操作"
    },
    "logConfig": {
      "type": "object",
      "properties": {
        "modelId": { "type": "string" },
        "modelVersion": { "type": "string" },
        "modelType": { "type": "string", "enum": ["score_categorical", "regression", "ranking"] },
        "environment": { "type": "string", "enum": ["training", "validation", "production"] },
        "dataPath": { "type": "string" },
        "predictionIdColumn": { "type": "string" },
        "timestampColumn": { "type": "string" },
        "featureColumns": { "type": "array", "items": { "type": "string" } },
        "embeddingColumns": { "type": "array", "items": { "type": "string" } },
        "predictionColumn": { "type": "string" },
        "actualColumn": { "type": "string" }
      }
    },
    "monitorConfig": {
      "type": "object",
      "properties": {
        "metrics": { "type": "array", "items": { "type": "string" } },
        "thresholds": { "type": "object" },
        "schedule": { "type": "string" }
      }
    },
    "analysisConfig": {
      "type": "object",
      "properties": {
        "analysisType": { "type": "string", "enum": ["drift", "performance", "fairness", "data_quality"] },
        "timeRange": { "type": "object" },
        "segments": { "type": "array", "items": { "type": "string" } }
      }
    }
  }
}

输出模式

{
  "type": "object",
  "required": ["status", "action"],
  "properties": {
    "status": {
      "type": "string",
      "enum": ["success", "error"]
    },
    "action": {
      "type": "string"
    },
    "logId": {
      "type": "string"
    },
    "dashboardUrl": {
      "type": "string"
    },
    "analysis": {
      "type": "object",
      "properties": {
        "overallScore": { "type": "number" },
        "driftMetrics": { "type": "object" },
        "performanceMetrics": { "type": "object" },
        "topIssues": { "type": "array" },
        "recommendations": { "type": "array", "items": { "type": "string" } }
      }
    },
    "alerts": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "name": { "type": "string" },
          "severity": { "type": "string" },
          "triggered": { "type": "boolean" }
        }
      }
    }
  }
}

使用示例

{
  kind: 'skill',
  title: '将生产预测记录到Arize',
  skill: {
    name: 'arize-observability',
    context: {
      action: 'log',
      logConfig: {
        modelId: 'fraud-detector',
        modelVersion: '2.0.0',
        modelType: 'score_categorical',
        environment: 'production',
        dataPath: 'data/production_predictions.parquet',
        predictionIdColumn: 'request_id',
        timestampColumn: 'timestamp',
        featureColumns: ['amount', 'merchant_category', 'hour'],
        predictionColumn: 'fraud_probability',
        actualColumn: 'is_fraud'
      }
    }
  }
}