Generate Text with System Prompt
When interacting with language models, you can guide their behavior by providing initial instructions. A system prompt sets the overall context and behavior for the model before it processes any user messages. This example shows how to use system prompts to control model behavior.
import { Mastra } from '@mastra/core';
const mastra = new Mastra();
const llm = mastra.LLM({
provider: 'OPEN_AI',
name: 'gpt-4',
});
const response = await llm.generate([
{ role: 'system', content: 'You are a helpful assistant.' },
{ role: 'user', content: 'What is the meaning of life?' },
]);
console.log(response.text);
View Example on GitHub