Armin Catovic

Helping enhance your understanding and optimal usage of structured outputs and LLMs Armin Catovic · Follow Published in Towards Data Science · 8 min read · 5 hours ago — Figure 1 — steps that are executed both explicitly, as well as implicitly, from the user’s perspective, when applying structured outputs; image by the author In the previous article, we were introduced to structured outputs using OpenAI. Since the general availability release in ChatCompletions API

Building robustness and determinism in LLM applications Armin Catovic · Follow Published in Towards Data Science · 5 min read · 12 hours ago — Image by the author OpenAI recently announced support for Structured Outputs in its latest gpt-4o-2024–08–06 models. Structured outputs in relation to large language models (LLMs) are nothing new — developers have either used various prompt engineering techniques, or 3rd party tools. In this article we will explain what structured outputs