A well-written prompt provides enough information for the model to know what you want and how it should respond. A general rule is to think about how you would write a word problem for a middle school student to solve. Its success generally depends on the complexity of the task and quality of your prompt. This simple, "text in, text out" interface means you can "program" the model by providing instructions or just a few examples of what you'd like it to do. You can control this behavior with the temperature setting. In other words, you might get a slightly different completion every time you call it, even if your prompt stays the same. The actual completion results you see may differ because the API is stochastic by default. Once you submit, you'll see something like the following generated: write a tagline for an ice cream shop You can start with a simple example like the following: It's a simple text box where you can submit a prompt to generate a completion. The best way to start exploring completions is through our playground in Azure OpenAI Studio. For example, if you give the API the prompt, "As Descartes said, I think, therefore", it will return the completion " I am" with high probability. You input some text as a prompt, and the model will generate a text completion that attempts to match whatever context or pattern you gave it. It provides a simple but powerful text-in, text-out interface to any of our models. The completions endpoint can be used for a wide variety of tasks.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |