An overview of popular techniques to confine LLMs' output to a predefined schema, covering API providers, prompting/reprompting strategies, and constrained decoding.
Model Context Protocol server to run Python code in a sandbox using Pyodide in Deno, isolated from the operating system.
An analysis showing that structured outputs can sometimes perform worse than unstructured ones in certain tasks for different LLM models, emphasizing the importance of testing both approaches.
