bigquery-ai-ml
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, detect outliers, find key drivers, or leverage generative AI capabilities in BigQuery.
- License 许可
- MIT
- 最近更新
- 2026-08-31
- Stars
- ★ 1
- Forks
- 0
01 前言 Front Matter
- name
- bigquery-ai-ml
- metadata
- { "version": "v1" }
- description
- 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, detect outliers, find key drivers, or leverage generative AI capabilities in BigQuery.
02 资源文件 18
- 其他OWNERS69 B
- 参考文档references/ai_agg.md3.5 KB
- 参考文档references/ai_classify.md3.7 KB
- 参考文档references/ai_detect_anomalies.md4.5 KB
- 参考文档references/ai_evaluate.md2.2 KB
- 参考文档references/ai_forecast.md6.5 KB
- 参考文档references/ai_function_best_practices.md2.8 KB
- 参考文档references/ai_generate_embedding.md1.6 KB
- 参考文档references/ai_generate_table.md2.9 KB
- 参考文档references/ai_generate.md3.9 KB
- 参考文档references/ai_if.md2.0 KB
- 参考文档references/ai_key_drivers.md4.0 KB
- 参考文档references/ai_score.md1.9 KB
- 参考文档references/ai_search.md3.7 KB
- 参考文档references/ai_similarity.md2.7 KB
- 参考文档references/ml_contribution_analysis.md4.8 KB
- 参考文档references/remote_models.md871 B
- 参考文档references/vector_search.md4.0 KB
03 SKILL.md 正文
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.
[!IMPORTANT] You MUST read and follow the global constraints and mandatory function routing rules in ai_function_best_practices.md before writing any BQML AI/ML SQL query.
Reference Directory
-
Best Practices: ai_function_best_practices.md
-
Functions Reference:
- AI.AGG: ai_agg.md - Multi-row semantic aggregation and summarization.
- AI.CLASSIFY: ai_classify.md - Classify text.
- AI.DETECT_ANOMALIES: ai_detect_anomalies.md - Detect anomalies.
- AI.EVALUATE: ai_evaluate.md - Evaluate models.
- AI.FORECAST: ai_forecast.md - Time-series forecasting.
- AI.GENERATE: ai_generate.md - Generate text using LLMs.
- AI.GENERATE_EMBEDDING: ai_generate_embedding.md - Generate embeddings.
- AI.GENERATE_TABLE: ai_generate_table.md - Table-valued AI generation.
- AI.IF: ai_if.md - Evaluate semantic conditions.
- AI.KEY_DRIVERS: ai_key_drivers.md - Identifies key drivers, this is a TVF.
- AI.SCORE: ai_score.md - Score data.
- AI.SEARCH: ai_search.md - Semantic search.
- AI.SIMILARITY: ai_similarity.md - Semantic similarity.
- Remote Models: remote_models.md - Working with remote models (Vertex AI).
- CONTRIBUTION_ANALYSIS:
ml_contribution_analysis.md
- Finds contributing factors, key drivers of change. Requires creating a MODEL entity.
- VECTOR_SEARCH: vector_search.md - Vector search best practices.
04 同仓库更多 Skills
xcode-project-setup
Safely modifies Xcode projects (.pbxproj) to add Swift Packages and link files. Use this skill whenever an iOS project needs dependencies installed (e.g. Firebase, Alamofire).
writing-skills
Use when creating new skills, editing existing skills, or verifying skills work before deployment
writing-plans
Use when you have a spec or requirements for a multi-step task, before touching code
workflow-skill-creator
Distills a completed user workflow or interaction into a reusable agent skill. Use when the user asks to turn their workflow, interaction, or multi-step process into a skill, or when they say "make this a skill", "create a skill from what we just did", "package this workflow" or similar. Do not use for creating skills from scratch without an existing workflow (use a generic skill-creator for that).
verify-and-stop
Prove existing work meets acceptance conditions without expanding scope. Use for validation-only tasks, completion checks, focused gate runs, and last-mile proof.
verification-before-completion
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always