Generative AI Solutions with Databricks

Chapter 6. Assembling and Deploying

A Note for Early Release Readers

With Early Release ebooks, you get books in their earliest form—the author’s raw and unedited content as they write—so you can take advantage of these technologies long before the official release of these titles.

This will be the 13th chapter of the final book. Please note that the GitHub repo will be made active later on.

If you’d like to be actively involved in reviewing and commenting on this draft, please reach out to the editor at [e-mail].

Creating a solution is only part of the generative solution creation process. We must package up that solution and deploy it to high-level environments. This chapter discusses the importance of automated development. We dig into environments and data platforms, and the art of building AI systems without violating data policies or deploying things that only work in non-production environment. We will discuss models, prompts, data, indexes, and all things related to deploying generative and agentic solutions. We will close with a discussion of deploying Databricks Apps and automated deployment using GitHub actions and DevOps pipelines.

Importance of Automate Deployment

Since the advent and adoption of DevOps, iterative software development and deployment have become the standard. Developing agentic and generative solutions follows an iterative pattern as well. Generally, we get to a working solution, and then improve it over time. To make sure that those ...