Google Cloud Tech: Build cross-cloud agents with the borderless Lakehouse

Learn how to build cross-cloud agents and leverage BigQuery multimodality, AI functions, embeddings, and vector search with the borderless Lakehouse.



## SUMMARY

In this episode of Google Cloud Live, learn how to build cross-cloud agents using a borderless Lakehouse architecture. Explore how BigQuery handles multimodal data and native AI functions to generate automated descriptions, update product metadata, and generate embeddings.



Discover step-by-step techniques for joining structured and unstructured data, performing vector search, configuring data chunks, and connecting external platforms into your Google Cloud Lakehouse workflow.



## WHAT YOU'LL LEARN

* **Create ObjectRef external tables** for multimodal data analysis in BigQuery.

* **Use AI functions** to generate brand descriptions, image descriptions, and metadata.

* **Generate text embeddings** and perform vector search over multimodal datasets.

* **Structure data chunks** and manage single vs. multi-response column outputs.

* **Integrate cross-cloud components** with borderless Lakehouse tables.



#GoogleCloud #BigQuery #Lakehouse



Speakers: Brad Miro, Tilde Thurium

Products Mentioned:, Borderless Lakehouse, Big Query