Text Generation
Generate natural language content using AI with flexible input methods - from simple prompts to structured message sequences.
Basic Generation
When you need to generate text content from a simple prompt, use .generate.text(). This is useful for creating content like explanations, summaries, or reports. Learn more about basic text generation.
const {
data: { payload }
} = await unbody.generate
.text("Explain AI's impact on healthcare");Generation with Options
Sometimes you need more control over the generated content. Use options like temperature and token limits to fine-tune the output style and length. Learn more about Options
const {
data: { payload }
} = await unbody.generate
.text("Write a report on climate change", {
model: "gpt-4",
topP: 0.7,
maxTokens: 1000,
temperature: 0.7,
presencePenalty: 0,
frequencyPenalty: 0
});Multi-Message Generation
When you need to send role-based messages array as a prompt, use Message-Based Input. This approach helps when providing system instructions or creating multi-turn conversations with different roles. This works particularly well for creating expert personas or maintaining specific conversation contexts.
const {
data: { payload }
} = await unbody.generate
.text([
{
role: "system",
content: "You are an expert on AI"
},
{
role: "user",
content: "What are the latest AI trends in 2024?"
}
], {
model: "gpt-4",
topP: 0.7,
maxTokens: 1000,
temperature: 0.7,
presencePenalty: 0,
frequencyPenalty: 0
});Learn more about text generation in detail in our Text Generation Guide.