Text Generation
Learn how to generate text from a prompt.
Overview
OpenAI provides simple APIs to use a large language model to generate text from a prompt, as you might using ChatGPT. These models have been trained on vast quantities of data to understand multimedia inputs and natural language instructions.
Quickstart
To generate text, you can use the chat completions endpoint in the REST API. You can either use the REST API from the HTTP client of your choice, or use one of OpenAI's official SDKs.
Generate Prose
Create a human-like response to a prompt
import OpenAI from "openai";
const openai = new OpenAI();
const completion = await openai.chat.completions.create({
model: "gpt-4o",
messages: [
{ role: "developer", content: "You are a helpful assistant." },
{
role: "user",
content: "Write a haiku about recursion in programming.",
},
],
});
console.log(completion.choices[0].message);Analyze an Image
Describe the contents of an image
import OpenAI from "openai";
const openai = new OpenAI();
const completion = await openai.chat.completions.create({
model: "gpt-4o",
messages: [
{
role: "user",
content: [
{ type: "text", text: "What's in this image?" },
{
type: "image_url",
image_url: {
"url": "https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg",
},
}
],
},
],
});
console.log(completion.choices[0].message);Generate JSON Data
Generate JSON data based on a JSON Schema
import OpenAI from "openai";
const openai = new OpenAI();
const completion = await openai.chat.completions.create({
model: "gpt-4o-2024-08-06",
messages: [
{ role: "developer", content: "You extract email addresses into JSON data." },
{
role: "user",
content: "Feeling stuck? Send a message to help@mycompany.com.",
},
],
response_format: {
type: "json_schema",
json_schema: {
name: "email_schema",
schema: {
type: "object",
properties: {
email: {
description: "The email address that appears in the input",
type: "string"
}
},
additionalProperties: false
}
}
}
});
console.log(completion.choices[0].message.content);Choosing a Model
Large Model
GPT-4o offers high intelligence and strong performance, with higher cost per token.
Small Model
GPT-4o-mini is faster and less expensive, with good intelligence for focused tasks.
Reasoning Model
o1 models excel at complex reasoning and multi-step planning tasks.
Building Prompts
Prompt engineering is the process of crafting prompts to get the right output from a model. The chat completions API uses different message roles to influence how the model interprets input.
Developer Messages
Messages with the developer role provide instructions that are prioritized ahead of user messages.
Example of a developer message
const response = await openai.chat.completions.create({
model: "gpt-4o",
messages: [
{
"role": "developer",
"content": [
{
"type": "text",
"text": `
You are a helpful assistant that answers programming
questions in the style of a southern belle from the
southeast United States.
`
}
]
},
{
"role": "user",
"content": [
{
"type": "text",
"text": "Are semicolons optional in JavaScript?"
}
]
}
]
});Conversations
Implement multi-turn conversations by providing additional messages in your requests.
Example of a conversation
const response = await openai.chat.completions.create({
model: "gpt-4o",
messages: [
{
"role": "user",
"content": [{ "type": "text", "text": "knock knock." }]
},
{
"role": "assistant",
"content": [{ "type": "text", "text": "Who's there?" }]
},
{
"role": "user",
"content": [{ "type": "text", "text": "Orange." }]
}
]
});Optimization
Accuracy
Ensure accurate responses through prompt engineering, RAG, and model fine-tuning.
Cost
Reduce costs by optimizing token usage and using appropriate models.
Latency
Decrease response time through prompt engineering and code optimization.