Stage 1 · Lesson 6 of 8
One module for every model call
In an LLM app, the equivalent of a training script is a single module that every uses to call a model. It holds the model name, , temperature, timeout and retry settings as , calls the provider SDK (software development kit) in one place, and returns a typed result.
Every call then records which model and prompt answered, which you will need for and evals later. Swapping providers, changing a deprecated model or adding a fallback becomes a one-file change. Set a timeout on every call, because the default can be very long, and limit retries so a provider outage does not multiply your traffic.
Common trapcalling the SDK directly from a dozen files with hard-coded model names, so nobody knows which version a user saw.
A question to check yourself, an AI practice session and 2 cheat sheet entries come with the full roadmap. Unlock
Resources for this stage
Start with· follow one of these
- CoursePaidGrokking Python Fundamentals
Design Gurus · Beginner · $50
If your Python stops at notebooks: modules, functions, classes and error handling done properly
- CourseFreeMade With ML
Goku Mohandas · Advanced
Free: the scripting, CLI, testing and documentation lessons turn notebook code into a real project