New to BigQuery AI? Here’s some material and documentation to get you started:

**Approach 1: The AI Architect 🧠**

* Sample Colab notebooks:   
  * SQL: [goo.gle/bq-ai-functions-sample](https://github.com/GoogleCloudPlatform/generative-ai/blob/main/gemini/use-cases/applying-llms-to-data/bigquery_generative_ai_intro.ipynb)  
  * Python: [goo.gle/bqdf-ai-forecast-sample](https://github.com/googleapis/python-bigquery-dataframes/blob/main/notebooks/kaggle/bq_dataframes_ai_forecast.ipynb)   
* Documentation:  
  * [AI.GENERATE](https://cloud.google.com/bigquery/docs/reference/standard-sql/bigqueryml-syntax-ai-generate) ([Python](https://cloud.google.com/python/docs/reference/bigframes/latest/bigframes.ml.llm.GeminiTextGenerator))  
  * [AI.FORECAST](https://cloud.google.com/bigquery/docs/reference/standard-sql/bigqueryml-syntax-ai-forecast) ([Python](https://cloud.google.com/python/docs/reference/bigframes/latest/bigframes.operations.ai.AIAccessor#bigframes_operations_ai_AIAccessor_forecast))  
* Blog: [What’s new with BigQuery AI and ML?](https://cloud.google.com/blog/products/data-analytics/bigquery-adds-new-ai-capabilities?e=48754805)

### **Approach 2: The Semantic Detective 🕵️‍♀️**

* Sample Colab notebooks:   
  * SQL: [goo.gle/bq-vector-search-sample](https://github.com/GoogleCloudPlatform/generative-ai/blob/main/gemini/use-cases/applying-llms-to-data/bigquery_embeddings_vector_search.ipynb)  
  * Python: [goo.gle/bqdf-vector-search-sample](https://github.com/googleapis/python-bigquery-dataframes/blob/main/notebooks/kaggle/vector-search-with-bigframes-over-national-jukebox.ipynb)  
* Documentation:  
  * [Introduction to vector search](https://cloud.google.com/bigquery/docs/vector-search-intro) ([Python](https://cloud.google.com/python/docs/reference/bigframes/latest/bigframes.bigquery#bigframes_bigquery_vector_search))  
  * [Generate embeddings](https://cloud.google.com/bigquery/docs/reference/standard-sql/bigqueryml-syntax-generate-embedding) ([Python](https://cloud.google.com/python/docs/reference/bigframes/latest/bigframes.ml.llm.TextEmbeddingGenerator))  
* Blog: [BigQuery vector search, setting the stage for a new class of AI-powered analytics](https://cloud.google.com/blog/products/data-analytics/bigquery-vector-search-is-now-ga)

### **Approach 3: The Multimodal Pioneer 🖼️**

* Sample Colab notebooks:   
  * SQL: [goo.gle/bq-multimodal-sample](https://github.com/GoogleCloudPlatform/generative-ai/blob/main/gemini/use-cases/applying-llms-to-data/multimodal-analysis-bigquery/analyze_multimodal_data_bigquery.ipynb)  
  * Python: [goo.gle/bqdf-multimodal-sample](https://github.com/googleapis/python-bigquery-dataframes/blob/main/notebooks/kaggle/describe-product-images-with-bigframes-multimodal.ipynb)   
* Documentation: [Analyze multimodal data in BigQuery](https://cloud.google.com/bigquery/docs/analyze-multimodal-data)  
* Blog: [A Practical Guide to Multimodal Data Analytics](https://medium.com/google-cloud/a-practical-guide-to-multimodal-data-analytics-ae706a3f14e0)

Or try out an end-to-end Codelab that blends all three approaches [**here**](https://codelabs.developers.google.com/devsite/codelabs/petverse_multimodal?utm_campaign=CDR_0x6cb6c9c7_platform_b433288268&utm_medium=external&utm_source=event#0)\!