bigquery-ai-ml

Generate BigQuery SQL using AI.* functions for forecasting, anomaly detection, and semantic search.

21.1k|3.8k|Updated Apr 1, 2025
One-click install
npx skills add https://github.com/google/adk-python --skill bigquery-ai-ml
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: bigquery-ai-ml
Source: https://github.com/google/adk-python/tree/main/src/google/adk/tools/bigquery/skills/bigquery-ai-ml
Command: npx skills add https://github.com/google/adk-python --skill bigquery-ai-ml

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill helps you perform BigQuery AI and Machine Learning tasks like forecasting, anomaly detection, classification, and semantic search using standard SQL, so you can keep your analytics in one query language.

Core Features & Use Cases

  • Time-series forecasting: Use AI.FORECAST (TimesFM) to generate future predictions from historical metrics.
  • Anomaly detection: Use AI.DETECT_ANOMALIES (TimesFM) to flag deviations in time-series data against prior history.
  • Semantic understanding in queries: Use AI.GENERATE, AI.CLASSIFY, AI.SCORE, AI.SIMILARITY, AI.SEARCH, and AI.IF to generate labels, rank relevance, compute similarity, run semantic search, and evaluate natural-language conditions.

Quick Start

Ask your agent to produce a BigQuery SQL query that calls AI.FORECAST for your data, but only after it reads the required reference file in references/bigquery_ai_forecast.md.

Frequently Asked Questions about bigquery-ai-ml

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I run time-series forecasting and anomaly detection in BigQuery?

To run semantic search and text classification in BigQuery SQL, use the AI.SEARCH, AI.SIMILARITY, and AI.CLASSIFY functions to compute similarity scores and generate labels directly within your queries.

Can I perform semantic search and text classification directly in SQL?

To run semantic search and text classification in BigQuery SQL, use the AI.SEARCH, AI.SIMILARITY, and AI.CLASSIFY functions to compute similarity scores and generate labels directly within your queries.

Do I need dedicated ML tools to generate content and rank relevance in BigQuery?

To start forecasting historical metrics in BigQuery, request a SQL query that calls AI.FORECAST after the agent reads the required reference file, ensuring accurate standard AI.* function syntax.

How do I start forecasting historical metrics using BigQuery AI functions?

To start forecasting historical metrics in BigQuery, request a SQL query that calls AI.FORECAST after the agent reads the required reference file, ensuring accurate standard AI.* function syntax.

Are there limitations when using BigQuery AI functions for natural-language conditional filtering?

When using BigQuery AI functions like AI.IF for natural-language conditional filtering, you must use execute_sql with standard AI.* functions rather than dedicated tools, routing to exact reference documents for accurate generation.