Building AI Agent Platforms

Chapter 4. Accessing Generative Models

A Note for Early Release Readers

With Early Release ebooks, you get books in their earliest form—the authors’ 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 4th 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].

All models are wrong, but some are useful.

George Box

As referenced in Chapter 3, AI models are the fundamental building blocks of AI applications. Given the wide variety of applications being built, it is essential for a platform to provide access to diverse types of models and the various modalities they support.

The AI ecosystem evolves rapidly, new Large Language Models (LLMs) are frequently released with novel capabilities and improved performance. In particular, state-of-the-art models often enable new use cases that were previously impossible. Therefore, it is critical that a platform does not become a bottleneck, ensuring teams have seamless access to the latest models.

The frequent release of models, also makes it impossible for this book to provide a curated list of models, as it would probably be out of date by the time you finish reading this chapter. Rather than chasing every single release, this chapter focuses on the broader landscape. ...