openai

What is openai?

The openai npm package is a Node.js client library for accessing the OpenAI API, which provides access to powerful AI models such as GPT-3 for natural language processing tasks, including text generation, translation, summarization, and more. The package allows developers to easily integrate OpenAI's AI capabilities into their Node.js applications.

What are openai's main functionalities?

Text Completion

Generates text completions for a given prompt using the GPT-3 model.

const { Configuration, OpenAIApi } = require('openai');

const configuration = new Configuration({
  apiKey: process.env.OPENAI_API_KEY,
});
const openai = new OpenAIApi(configuration);

openai.createCompletion({
  model: 'text-davinci-003',
  prompt: 'Translate the following English text to French: Hello, how are you?',
  max_tokens: 60
}).then(response => {
  console.log(response.data.choices[0].text);
});

Text Classification

Classifies a piece of text into one of the specified categories.

const { Configuration, OpenAIApi } = require('openai');

const configuration = new Configuration({
  apiKey: process.env.OPENAI_API_KEY,
});
const openai = new OpenAIApi(configuration);

openai.createClassification({
  model: 'text-davinci-003',
  examples: [
    ['A movie about space wars and intergalactic politics', 'Science Fiction'],
    ['A film focusing on the love life of a New York City woman', 'Romance']
  ],
  query: 'A story about a boy who learns he is a wizard and attends a magical school',
  labels: ['Science Fiction', 'Romance', 'Fantasy']
}).then(response => {
  console.log(response.data);
});

Text Summarization

Summarizes a longer piece of text into a concise version.

const { Configuration, OpenAIApi } = require('openai');

const configuration = new Configuration({
  apiKey: process.env.OPENAI_API_KEY,
});
const openai = new OpenAIApi(configuration);

openai.createCompletion({
  model: 'text-davinci-003',
  prompt: 'Summarize the following text: ...',
  max_tokens: 60,
  temperature: 0.7
}).then(response => {
  console.log(response.data.choices[0].text);
});

Other packages similar to openai

watson-developer-cloud

This package provides access to IBM Watson's AI services, which include natural language processing, speech to text, text to speech, and language translation. It is similar to openai in providing AI-powered language services, but it uses IBM's Watson AI instead of OpenAI's models.

google-cloud

The Google Cloud npm package allows developers to interact with Google Cloud services, including its AI and machine learning services like the Natural Language API and the Translation API. It offers functionalities similar to openai but is integrated with Google's cloud ecosystem.

microsoft-cognitiveservices-speech-sdk

This package is part of Microsoft's Azure Cognitive Services and provides capabilities for speech recognition, text-to-speech, and speech translation. It offers different services compared to openai, focusing more on speech technologies rather than text-based AI models.

README

OpenAI Node API Library

The OpenAI Node library provides convenient access to the OpenAI REST API from applications written in server-side JavaScript. It includes TypeScript definitions for all request params and response fields.

⚠️ Important note: this library is meant for server-side usage only, as using it in client-side browser code will expose your secret API key. See here for more details.

Documentation

To learn how to use the OpenAI API, check out our API Reference and Documentation.

Installation

npm install --save openai
# or
yarn add openai

Usage

import OpenAI from 'openai';

const openai = new OpenAI({
  apiKey: 'my api key', // defaults to process.env["OPENAI_API_KEY"]
});

async function main() {
  const completion = await openai.completions.create({
    model: 'text-davinci-002',
    prompt: 'Say this is a test',
    max_tokens: 6,
    temperature: 0,
  });

  console.log(completion.choices);
}
main().catch(console.error);

Streaming Responses

We provide support for streaming responses using Server Side Events (SSE).

import OpenAI from 'openai';

const client = new OpenAI();

const stream = await client.completions.create({
  prompt: 'Say this is a test',
  model: 'text-davinci-003',
  stream: true,
});
for await (const part of stream) {
  process.stdout.write(part.choices[0]?.text || '');
}

If you need to cancel a stream, you can break from the loop or call stream.controller.abort().

Usage with TypeScript

Importing, instantiating, and interacting with the library are the same as above. If you like, you may reference our types directly:

import OpenAI from 'openai';

const openai = new OpenAI({
  apiKey: 'my api key', // defaults to process.env["OPENAI_API_KEY"]
});

async function main() {
  const params: OpenAI.CompletionCreateParams = {
    model: 'text-davinci-002',
    prompt: 'Say this is a test',
    max_tokens: 6,
    temperature: 0,
  };
  const completion: OpenAI.Completion = await openai.completions.create(params);
}
main().catch(console.error);

Documentation for each method, request param, and response field are available in docstrings and will appear on hover in most modern editors.

File Uploads

Request parameters that correspond to file uploads can be passed in many different forms:

• File (or an object with the same structure)
• a fetch Response (or an object with the same structure)
• an fs.ReadStream
• the return value of our toFile helper

import fs from 'fs';
import fetch from 'node-fetch';
import OpenAI, { toFile } from 'openai';

const openai = new OpenAI();

// If you have access to Node `fs` we recommend using `fs.createReadStream()`:
await openai.files.create({ file: fs.createReadStream('input.jsonl'), purpose: 'fine-tune' });

// Or if you have the web `File` API you can pass a `File` instance:
await openai.files.create({ file: new File(['my bytes'], 'input.jsonl'), purpose: 'fine-tune' });

// You can also pass a `fetch` `Response`:
await openai.files.create({ file: await fetch('https://somesite/input.jsonl'), purpose: 'fine-tune' });

// Finally, if none of the above are convenient, you can use our `toFile` helper:
await openai.files.create({
  file: await toFile(Buffer.from('my bytes'), 'input.jsonl'),
  purpose: 'fine-tune',
});
await openai.files.create({
  file: await toFile(new Uint8Array([0, 1, 2]), 'input.jsonl'),
  purpose: 'fine-tune',
});

Handling errors

When the library is unable to connect to the API, or if the API returns a non-success status code (i.e., 4xx or 5xx response), a subclass of APIError will be thrown:

async function main() {
  const fineTune = await openai.fineTunes
    .create({ training_file: 'file-XGinujblHPwGLSztz8cPS8XY' })
    .catch((err) => {
      if (err instanceof OpenAI.APIError) {
        console.log(err.status); // 400
        console.log(err.name); // BadRequestError

        console.log(err.headers); // {server: 'nginx', ...}
      }
    });
}
main().catch(console.error);

Error codes are as followed:

Status Code	Error Type
400	BadRequestError
401	AuthenticationError
403	PermissionDeniedError
404	NotFoundError
422	UnprocessableEntityError
429	RateLimitError
>=500	InternalServerError
N/A	APIConnectionError

Retries

Certain errors will be automatically retried 2 times by default, with a short exponential backoff. Connection errors (for example, due to a network connectivity problem), 409 Conflict, 429 Rate Limit, and >=500 Internal errors will all be retried by default.

You can use the maxRetries option to configure or disable this:

// Configure the default for all requests:
const openai = new OpenAI({
  maxRetries: 0, // default is 2
});

// Or, configure per-request:
openai.embeddings.create({ model: 'text-similarity-babbage-001',input: 'The food was delicious and the waiter...' }, {
  maxRetries: 5,
});

Timeouts

Requests time out after 60 seconds by default. You can configure this with a timeout option:

// Configure the default for all requests:
const openai = new OpenAI({
  timeout: 20 * 1000, // 20 seconds (default is 60s)
});

// Override per-request:
openai.edits.create({ model: 'text-davinci-edit-001',input: 'What day of the wek is it?',instruction: 'Fix the spelling mistakes' }, {
  timeout: 5 * 1000,
});

On timeout, an APIConnectionTimeoutError is thrown.

Note that requests which time out will be retried twice by default.

Configuring an HTTP(S) Agent (e.g., for proxies)

By default, this library uses a stable agent for all http/https requests to reuse TCP connections, eliminating many TCP & TLS handshakes and shaving around 100ms off most requests.

If you would like to disable or customize this behavior, for example to use the API behind a proxy, you can pass an httpAgent which is used for all requests (be they http or https), for example:

import http from 'http';
import HttpsProxyAgent from 'https-proxy-agent';

// Configure the default for all requests:
const openai = new OpenAI({
  httpAgent: new HttpsProxyAgent(process.env.PROXY_URL),
});

// Override per-request:
openai.models.list({
  baseURL: 'http://localhost:8080/test-api',
  httpAgent: new http.Agent({ keepAlive: false }),
})

Status

This package is in beta. Its internals and interfaces are not stable and subject to change without a major semver bump; please reach out if you rely on any undocumented behavior.

We are keen for your feedback; please open an issue with questions, bugs, or suggestions.

Requirements

The following runtimes are supported:

• Node.js 16 LTS or later (non-EOL) versions.
• Deno v1.28.0 or higher (experimental). Use import OpenAI from "npm:openai".

If you are interested in other runtime environments, please open or upvote an issue on GitHub.