An overview of popular techniques to confine LLMs' output to a predefined schema, covering API providers, prompting/reprompting strategies, and constrained decoding.
This document details the features, best practices, and migration guidance for GPT-5, OpenAI's most intelligent model. It covers new API features like minimal reasoning effort, verbosity control, custom tools, and allowed tools, along with prompting guidance and migration strategies from older models and APIs.
OpenAI's documentation for their o1 and o3 'reasoning models' includes tips on how to best prompt them, such as using developer messages, delimiters, and specific instructions.
