Config-Driven Development for LLMs: Versioning, Routing, & Evaluating LLMs


He will cover how to manage AI prompts and model generation settings as JSON-serializable configs – enabling version control, evaluation, and rapid prototyping.🚀

During the session, he will introduce AIConfig, an open-source framework to build production-ready Generative AI apps.

Topics that will be covered:

✅  Learn about JSON-serializable configs, their structure, and how they can be used to manage AI prompts and model generation settings.

✅  Learn how to integrate these configurations with version control systems for better tracking and management of LLM changes.

✅  Learn how AIConfig, an open-source framework can technically enhance collaboration, strengthen governance, and ensure reproducibility.

LLMOps.Space LLMOps.Space

Deepchecks is a founding member of LLMOps.Space, a global community for LLM
practitioners. The community focuses on LLMOps-related content, discussions, and
events. Join thousands of practitioners on our Discord.
Join Discord ServerJoin Discord Server