Interacting with Luminous models
You can interact with a Luminous model by sending it a text. We call this a prompt. It will then produce text that continues your input and return it to you. This is what we call a completion. Generally speaking, our models attempt to find the best continuation for a given input. Practically, this means that the model first recognizes the style of the prompt and then attempts to continue it accordingly. Depending on the task at hand, the structure and content of the prompt are essential to generating completions that match the input task. By using a set of techniques, which we lay out in the following sections, you can instruct our models to solve a wide variety of text-based tasks. Note that increasing task complexity may require larger models. Find examples for tasks of varying complexities below:
Continue the proverb: An apple a day keeps the doctor away.
Find a suitable topic for the following text: On the day we went public, our shares rose 23%. Topic: Finance
Summarize the following news article: Lumi provides support, for example, when dealing with the authorities and knows how to re-register one's residence within Heidelberg or when the paper garbage will be collected. To this end, the AI draws on publicly available information from the city of Heidelberg to provide the most tailored answer possible for each request. In order for Lumi to learn what exactly Heidelberg residents are interested in and how they formulate their concerns, the AI has to gather experience - and that works best in conversation with users. Summary: Lumi is an AI that helps people navigate the bureaucracy of Heidelberg. It learns by talking to people.
Apart from generating completions, our luminous models possess the ability to semantically compare texts, summarize documents, perform Q&A tasks and more.
To find out how you can perform these tasks with our Python API, please refer to the Tasks section.
All models provided in the API were trained in five languages (English, Spanish, German, French, Italian), so you can prompt and work with the model in every one of these languages.
Ein blindes Huhn findet auch mal ein Korn.
German equivalent to: “A blind man may sometimes hit the mark.”