Also known as: prompt engineering (prompt design)
Le prompt engineering est la pratique consistant à concevoir, tester et affiner les entrées des modèles d’IA générative afin qu’ils produisent plus fiablement les sorties souhaitées. Il peut impliquer la spécification de rôles, de contraintes, d’exemples, de contexte, de format et de critères d’évaluation sans modifier les poids sous-jacents du modèle. Dans les environnements de production, le prompt engineering est souvent traité comme un artefact itératif et testable plutôt que comme une instruction ponctuelle.
The art of creating prompts that elicit the desired responses from a large language model. Humans perform prompt engineering. Writing well-structured prompts is an essential part of ensuring useful responses from a large language model. Prompt engineering depends on many factors, including: - The dataset used to pre-train and possibly fine-tune the large language model. - The temperature and other decoding parameters that the model uses to generate responses. Prompt design is a synonym for prompt engineering. See Introduction to prompt design for more details on writing helpful prompts.
Prompt engineering in generative AI is the process of crafting effective prompts to elicit desired outputs from large language models (LLMs). It's an iterative, test-driven process focused on refining inputs to achieve specific outcomes. This involves considering both the content and structure of the prompt to ensure accurate and high-quality responses. Effective prompt engineering is crucial for complex tasks, even though simpler tasks may not require it. The goal is to rapidly prototype LLM-based applications. For more information, see Introduction to prompt engineering.
Prompt engineering is the act of writing and re-writing prompts to produce outputs that align with your users' expectations. A well-written prompt states how the LLM should build its response, consists of multiple components that can be versioned, tested, and improved over time, and can act as a shared artifact for collaboration across teams.
A side-by-side comparison of Prompt Engineering and Prompt Tuning. Understand how human-designed model inputs differ from learned task-specific soft prompts.
A side-by-side comparison of Function Calling and Prompt Engineering. Understand how structured tool invocation differs from designing model inputs to improve output behavior.