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

A tiny async production-ready wrapper for OpenAI GPT-3 API.

This is an unofficial library and has no affiliations with OpenAI

Installation

Via npm

npm install openai

Via yarn

yarn add openai

Usage

Initialize OpenAI

import { OpenAI } from 'openai';
// or the commonJS way:
const { OpenAI } = require('openai');

// new OpenAI(apikey: string, organization?: string, version?: string)
const openai = new OpenAI(process.env.API_KEY, 'my-organization');

Engine

Get all engines:

const engines = await openai.getEngines();

Get specific engine:

const engine = await openai.getEngine('curie');

Completion

Make a completion:

const completion = await openai.complete('curie', {
    prompt: 'Q: Hello\nA:',
    user: 'user-123'
});

The options argument(2nd) properties follow the exactly same names as shown on official docs.

Make a completion from a fine-tuned model:

const completion = await openai.completeFromModel('FINE_TUNED_MODEL', {
    prompt: 'Q: Hello\nA:'
});

Make a completion and stream the response:

// Very experimental! Don't use on production!!!
// This API may change at any time
const stream = await openai.completionTextStream('curie', {
    prompt: 'Q: Hello\nA:',
    user: 'user-123'
});

stream.pipe(response)

Make a content filter:

const isSafe = (await openai.contentFilter('hi I am cool')) === 0;

Search

Make a search:

const search = await openai.search('curie', {
    query: 'the president',
    documents: [
        'whitehouse',
        'school',
        'hospital'
    ]
});

The options argument(2nd) properties follow the exactly same names as shown on official docs.

Classification

Classify a document:

const classification = await openai.classify({
    examples: [
        ['A happy moment', 'Positive'],
        ['I am sad.', 'Negative'],
        ['I am feeling awesome', 'Positive']
    ],
    labels: ['Positive', 'Negative', 'Neutral'],
    query: 'It is a raining day :(',
    search_model: 'ada',
    model: 'curie'
});

The argument properties follow the exactly same names as shown on official docs.

Answer

Answer a question:

const answer = await openai.answer({
    documents: ['Puppy A is happy.', 'Puppy B is sad.'],
    question: 'which puppy is happy?',
    search_model: 'ada',
    model: 'curie',
    examples_context: 'In 2017, U.S. life expectancy was 78.6 years.',
    examples: [['What is human life expectancy in the United States?','78 years.']],
});

The argument properties follow the exactly same names as shown on official docs.

File

Get all files:

const files = await openai.getFiles();

Upload a single file:

const result = await openai.uploadFile('filename.json', await fs.readFileSync('somefile.json'), 'fine-tune');

Get a single file by id:

const file = await openai.getFile('file-29u89djwq');

Delete a single file by id:

await openai.deleteFile('file-29u89djwq');

Fine-tuning

Fine-tune from a file:

const result = await openai.finetune({
    training_file: 'file-29u89djwq'
});

The argument properties follow the exactly same names as shown on official docs.

Get all fine-tunes:

const finetunes = await openai.getFinetunes();

Get a specific fine-tune:

const finetune = await openai.getFinetune('ftjob-AF1WoRqd3aJ');

Cancel a fine-tune:

await openai.cancelFinetune('ftjob-AF1WoRqd3aJ');

Get fine-tune events of a fine-tune:

const events = await openai.getFinetuneEvents('ftjob-AF1WoRqd3aJ');