Explore discussions on generative artificial intelligence techniques and applications within the Databricks Community. Share ideas, challenges, and breakthroughs in this cutting-edge field.
If your aim is to easily pass the genie space between different environments withing the same workspace, I believe Asset Bundles are actually the recommended route. Within the Asset Bundle (.yaml file), the Genie space should be explicitly referenced via its workspace path. The benefit to this method verses exporting the Genie Space is that all dependencies should also be referenced, meaning it can be seamlessly deployed in your different environments. https://docs.databricks.com/aws/en/dev-tools/bundles
As a final comment, it is worth noting that swapping the Genie space between environments should allow all instructions and settings to persist; however, the chat history will be wiped each time.
