Text Generation API

The .generate.text() method creates text content based on a prompt or a sequence of messages. It supports configurable options for model selection, token limits, and streaming for real-time generation.

Usage

Example 1 - Basic Prompt

Generate text using a simple string prompt:

unbody.generate.text("Explain AI's impact on healthcare.");

Example 2 - Prompt with Options

Add options to control the output:

unbody.generate.text("Write a report on climate change.", {
  model: "gpt-4",
  topP: 0.7,
  maxTokens: 1000,
  temperature: 0.7,
});

Example 3 - Message-Based Input

Guide the generation using a series of messages:

unbody.generate.text(
  [
    { role: "system", content: "You are an AI specialist." },
    { role: "user", content: "What are the key AI trends in 2024?" },
  ],
  {
    model: "gpt-4",
    temperature: 0.7,
    maxTokens: 1000,
  }
);

Example 4 - Streaming Text Generation

Generate text with real-time streaming:

const stream = await unbody.generate.text(
  "Write a detailed explanation of quantum computing.",
  {
    model: "gpt-4",
    temperature: 0.7,
    stream: true,
  }
);
 
for await (const chunk of stream) {
  if (chunk.finished) {
    console.log('Stream finished');
    console.log('Final response:', chunk.content);
    break;
  } else {
    console.log(chunk.content);
  }
}

Options

• model: AI model to use (e.g., gpt-4).
• topP: Diversity control via nucleus sampling (0 to 1).
• maxTokens: Maximum length of the response.
• temperature: Creativity adjustment (0 to 1).
• presencePenalty: Penalize new tokens based on input presence (-2.0 to 2.0).
• frequencyPenalty: Penalize tokens based on frequency of occurrence (-2.0 to 2.0).
• stream: Enable streaming for real-time content generation (boolean).