Bigquery Ai Ml

作者 google55b4e13eba6d无许可证21K 个星标收录于 2026年10月8日更新于 2026年10月8日仓库今天更新

Leverages BigQuery's built-in machine learning and GenAI capabilities for advanced data analytics. Use when you need to write SQL queries that perform time-series forecasting, predict values, detect outliers or anomalies, find key drivers, perform semantic search or vector search, classify text, calculate similarity, summarize content, translate language, evaluate models, filter by semantic conditions, measure the causal effect of an intervention, compute correlations between columns, detect change points or structural breaks, extract trend or seasonality components, or leverage generative AI capabilities in BigQuery. Do not use for general BigQuery dataset, table, or job management requests.

精选仅含说明Data & Analytics
AI 生成的概览

指导编写使用 BigQuery 内置 AI 和机器学习函数的 SQL,用于预测、异常检测、分类和语义搜索。

功能
该技能为在 SQL 查询中使用 BigQuery 内置 AI 和机器学习函数提供参考指导,包括 AI.FORECAST、AI.KEY_DRIVERS、AI.DETECT_ANOMALIES、AI.GENERATE、AI.CLASSIFY、AI.SEARCH 和 ML.CORRELATION。内容涵盖时间序列预测、异常与变化点检测、关键驱动因素与贡献分析、趋势与季节性提取、文本分类、语义与向量搜索、嵌入、相似度、模型评估以及因果效应度量。其产出是 SQL 查询指导,而非生成的文件或脚本。
适用场景
当需要编写执行机器学习或生成式 AI 分析的 BigQuery SQL 时使用,例如预测、离群值检测、语义搜索或文本分类。它不适用于一般的 BigQuery 数据集、表或作业管理请求。
运行要求
需要 BigQuery 及其内置 AI 和机器学习函数,对于生成式和远程模型函数还需要 Vertex AI 集成。仅为说明文档,不包含脚本。

BigQuery AI & ML

BigQuery integrates with Vertex AI to provide powerful machine learning and generative AI capabilities directly within SQL queries using built-in functions like AI.FORECAST, AI.KEY_DRIVERS, AI.DETECT_ANOMALIES, and AI.GENERATE.

Reference Directory

  • Functions Reference:

    • AI.AGG: ai_agg.md [blocked] - Multi-row semantic aggregation and summarization.
    • AI.CAUSAL_EFFECT: ai_causal_effect.md [blocked] - Quantifies the impact of an intervention on a time series.
    • AI.CLASSIFY: ai_classify.md [blocked] - Classify text.
    • AI.DETECT_ANOMALIES: ai_detect_anomalies.md [blocked] - Detect anomalies.
    • AI.EVALUATE: ai_evaluate.md [blocked] - Evaluate models.
    • AI.FORECAST: ai_forecast.md [blocked] - Time-series forecasting.
    • AI.GENERATE: ai_generate.md [blocked] - Generate text using LLMs.
    • AI.GENERATE_EMBEDDING: ai_generate_embedding.md [blocked] - Generate embeddings.
    • AI.GENERATE_TABLE: ai_generate_table.md [blocked] - Table-valued AI generation.
    • AI.IF: ai_if.md [blocked] - Evaluate semantic conditions.
    • AI.KEY_DRIVERS: ai_key_drivers.md [blocked] - Identifies key drivers, this is a TVF.
    • AI.SCORE: ai_score.md [blocked] - Score data.
    • AI.SEARCH: ai_search.md [blocked] - Semantic search.
    • AI.SIMILARITY: ai_similarity.md [blocked] - Semantic similarity.
    • Remote Models: remote_models.md [blocked] - Working with remote models (Vertex AI).
    • CONTRIBUTION_ANALYSIS: ml_contribution_analysis.md [blocked]
      • Finds contributing factors, key drivers of change. Requires creating a MODEL entity.
    • ML.CORRELATION: ml_correlation.md [blocked] - Calculates correlation between columns, optionally sliced by dimensions.
    • ML.DETECT_CHANGE_POINTS: ml_detect_change_points.md [blocked] - Detects structural breaks or sustained shifts in a time series.
    • ML.SEASONALITY: ml_seasonality.md [blocked] - Extracts seasonal components from a time series.
    • ML.TREND: ml_trend.md [blocked] - Extracts the long-term trend component from a time series.
    • VECTOR_SEARCH: vector_search.md [blocked] - Vector search best practices.

Related Skills

  • BigQuery Basics Skill: SKILL.md file for core BigQuery concepts, resource management, CLI, and client libraries.

来源与署名

来源:google/skills位于skills/cloud/bigquery-ai-ml提交55b4e13

许可证: 无许可证

内容归原作者所有。SourceWeft 从公开仓库中收录这些内容。

举报或申请下架

更多来自 google/skills 的技能