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 [blocked] before writing any BQML AI/ML SQL query.
Reference Directory
-
Best Practices: ai_function_best_practices.md [blocked]
-
Functions Reference:
- AI.AGG: ai_agg.md [blocked] - Multi-row semantic aggregation and summarization.
- 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.
- VECTOR_SEARCH: vector_search.md [blocked] - Vector search best practices.
