Generative AI Solutions with Databricks

Chapter 3. Agents, Tools and Function Calling

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 8th 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].

Background/Theory

In recent years we have seen a huge surge in LLM based innovative applications. But we are just scratching the surface with RAG powered LLM applications. Now we are in an agentic era of LLM applications where there is a resurgence of agents and everyone wants to be a part of this agentic journey. But let’s understand why everyone is so hyped about the agents before we jump into how they work within Databricks.

To understand in a better way, let’s think about building a smart assistant which can not only answer your questions but can also actually do things for you. It could access your mails surely with your permission, check your calendar, prepare your to do list, check alerts like your weekly or monthly sales number, send alerts and even render the important information in a nice user intuitive dashboard. That’s called as smart assistant which can either be single agent or a group of agents.

Starting with the OpenAI in 2022, ...