Documentation - GPT-3 DaVinci Codex

Installation

Install the DaVinci Codex client library using your preferred package manager:

# Using npm
npm install @davinci/codex

# Using yarn
yarn add @davinci/codex

# Using pnpm
pnpm add @davinci/codex

Quick Start

Get up and running with DaVinci Codex in minutes. Here's a simple example to generate your first AI completion:

import { DaVinciCodex } from '@davinci/codex';

const codex = new DaVinciCodex({
  apiKey: 'your-api-key'
});

async function generateText() {
  const response = await codex.completions.create({
    model: 'davinci-codex',
    prompt: 'Write a function to calculate fibonacci numbers',
    max_tokens: 150,
    temperature: 0.7
  });
  
  console.log(response.choices[0].text);
}

API Authentication

To use DaVinci Codex, you'll need an API key. Here's how to authenticate your requests:

⚠️

Keep your API key secure

Never expose your API key in client-side code. Always use environment variables or secure server-side storage.

// Set your API key as an environment variable
process.env.DAVINCI_CODEX_API_KEY = 'your-secret-key';

// Or pass it directly to the client
const codex = new DaVinciCodex({
  apiKey: process.env.DAVINCI_CODEX_API_KEY
});

Text Completions

The completions endpoint is the core of DaVinci Codex. Use it to generate text, complete code, or create conversational AI:

const completion = await codex.completions.create({
  model: 'davinci-codex',
  prompt: 'Explain quantum computing in simple terms:',
  max_tokens: 100,
  temperature: 0.7,
  top_p: 1,
  frequency_penalty: 0,
  presence_penalty: 0
});

console.log(completion.choices[0].text);

Rate Limits

To ensure fair usage and optimal performance, DaVinci Codex implements rate limiting:

Plan	Requests per minute	Tokens per minute
Free	20	40,000
Pro	3,500	350,000
Enterprise	Custom	Custom