Generate Text with Chat Prompt

Learn how to generate text with chat prompt using the AI TOOLKIT and Node

1 min readnodechatView source

Previously, we were able to generate text and objects using either a single message prompt, a system prompt, or a combination of both of them. However, there may be times when you want to generate text based on a series of messages. A chat completion allows you to generate text based on a series of messages. This series of messages can be any series of interactions between any number of systems, but the most popular and relatable use case has been a series of messages that represent a conversation between a user and a model. import { generateText } from 'ai-toolkit'; const result = await generateText({ model: 'openai/gpt-4o', maxOutputTokens: 1024, system: 'You are a helpful chatbot.', messages: [ { role: 'user', content: [{ type: 'text', text: 'Hello!' }], }, { role: 'assistant', content: [{ type: 'text', text: 'Hello! How can I help you today?' }], }, { role: 'user', content: [{ type: 'text', text: 'I need help with my computer.' }], }, ], }); console.log(result.text);

index.ts
ts
  1. 1import { generateText } from 'ai-toolkit';
  2. 2const result = await generateText({
  3. 3model: 'openai/gpt-4o',
  4. 4maxOutputTokens: 1024,
  5. 5system: 'You are a helpful chatbot.',
  6. 6messages: [
  7. 7{
  8. 8role: 'user',
  9. 9content: [{ type: 'text', text: 'Hello!' }],
  10. 10},
  11. 11{
  12. 12role: 'assistant',
  13. 13content: [{ type: 'text', text: 'Hello! How can I help you today?' }],
  14. 14},
  15. 15{
  16. 16role: 'user',
  17. 17content: [{ type: 'text', text: 'I need help with my computer.' }],
  18. 18},
  19. 19],
  20. 20});
  21. 21console.log(result.text);

Run it locally

$ npm install ai