This folder contains examples adapted from the Mistral Cookbook repository.
The samples were modified slightly to better run with the GitHub Models service.
The following cookbook examples are available:
- Evaluation: Provides a number of examples for evaluating the performance of a task performed by an LLM, concretely information extraction, code generation, summarization
- Function Calling: Simple example to demonstrate how function calling works with Mistral models
- Prefix: Use Cases: Add a prefix to the model's response via the API
- Prompting Capabilities: Example prompts showing classification, summarization, personalization, and evaluation