New Case Study:See how Anthropic automated 95% of dependency reviews with Socket.Learn More →
Socket
Sign inDemoInstall
Socket
Sign inDemoInstall

chatgpt-v3

Package Overview
Dependencies
Maintainers
1
Versions
6
Alerts
File Explorer

Advanced tools

License
Socket logo

Install Socket

Detect and block malicious and high-risk dependencies

Install

chatgpt-v3

Node.js client for the unofficial ChatGPT API.

  • 3.5.7
  • latest
  • Source
  • npm
  • Socket score
Version published
Weekly downloads
3
decreased by-57.14%
Maintainers
1
Weekly downloads
 
Created
Source

Update January 12, 2023

This package allows you to access ChatGPT from Node.js – even with OpenAI's Cloudflare protections. It uses a fully automated browser-based solution, which uses Puppeteer and CAPTCHA solvers under the hood. 🔥

import { ChatGPTAPIBrowser } from 'chatgpt'

const api = new ChatGPTAPIBrowser({
  email: process.env.OPENAI_EMAIL,
  password: process.env.OPENAI_PASSWORD
})
await api.initSession()

const result = await api.sendMessage('Hello World!')
console.log(result.response)

This solution is not lightweight, but it does work a lot more consistently than the previous REST API-based approach. For example, I'm currently using this approach to automate N concurrent OpenAI accounts for my Twitter bot. 😂

We recently added support for CAPTCHA automation using either nopecha or 2captcha. Keep in mind that this package will be updated to use the official API as soon as it's released, so things should get much easier over time. 💪

There are some restrictions to be aware of, however:

  • Cloudflare doesn't like requests coming from data center IPs, so you'll likely either need to run it locally or use a residential IP proxy.
  • You should only have one sendMessage request at a time per browser instance and OpenAI account.
  • It can be difficult to reliably process sendMessage requests after awhile. My best advice for handling this is to wrap your usage in some basic retry logic as well as a daemon which restarts your Node.js process every hour or so. This is unfortunately a by-product of there not being an official API, so keep that in mind before using this in production.

If you run into any issues, we do have a pretty active Discord with a bunch of ChatGPT hackers from the Node.js & Python communities.

Lastly, please consider starring this repo and following me on twitter twitter to help support the project.

Thanks && cheers, Travis

Example usage

ChatGPT API

Node.js client for the unofficial ChatGPT API.

NPM Build Status MIT License Prettier Code Formatting

Intro

This package is a Node.js wrapper around ChatGPT by OpenAI. TS batteries included. ✨

You can use it to start building projects powered by ChatGPT like chatbots, websites, etc...

Install

npm install chatgpt puppeteer

puppeteer is an optional peer dependency used to automate bypassing the Cloudflare protections via getOpenAIAuth. The main API wrapper uses fetch directly.

Usage

import { ChatGPTAPIBrowser } from 'chatgpt'

async function example() {
  // use puppeteer to bypass cloudflare (headful because of captchas)
  const api = new ChatGPTAPIBrowser({
    email: process.env.OPENAI_EMAIL,
    password: process.env.OPENAI_PASSWORD
  })

  await api.initSession()

  const result = await api.sendMessage('Hello World!')
  console.log(result.response)
}
Or, if you want to use the REST-based version: (not advised at this time) 
import { ChatGPTAPI, getOpenAIAuth } from 'chatgpt'

async function example() {
  // use puppeteer to bypass cloudflare (headful because of captchas)
  const openAIAuth = await getOpenAIAuth({
    email: process.env.OPENAI_EMAIL,
    password: process.env.OPENAI_PASSWORD
  })

  const api = new ChatGPTAPI({ ...openAIAuth })
  await api.initSession()

  // send a message and wait for the response
  const result = await api.sendMessage('Write a python version of bubble sort.')

  // result.response is a markdown-formatted string
  console.log(result.response)
}

ChatGPT responses are formatted as markdown by default. If you want to work with plaintext instead, you can use:

const api = new ChatGPTAPIBrowser({ email, password, markdown: false })

If you want to track the conversation, use the conversationId and messageId in the result object, and pass them to sendMessage as conversationId and parentMessageId respectively.

const api = new ChatGPTAPIBrowser({ email, password })
await api.initSession()

// send a message and wait for the response
let res = await api.sendMessage('What is OpenAI?')
console.log(res.response)

// send a follow-up
res = await api.sendMessage('Can you expand on that?', {
  conversationId: res.conversationId,
  parentMessageId: res.messageId
})
console.log(res.response)

// send another follow-up
// send a follow-up
res = await api.sendMessage('What were we talking about?', {
  conversationId: res.conversationId,
  parentMessageId: res.messageId
})
console.log(res.response)

Sometimes, ChatGPT will hang for an extended period of time before beginning to respond. This may be due to rate limiting or it may be due to OpenAI's servers being overloaded.

To mitigate these issues, you can add a timeout like this:

// timeout after 2 minutes (which will also abort the underlying HTTP request)
const response = await api.sendMessage('this is a timeout test', {
  timeoutMs: 2 * 60 * 1000
})
Usage in CommonJS (Dynamic import) 
async function example() {
  // To use ESM in CommonJS, you can use a dynamic import
  const { ChatGPTAPI, getOpenAIAuth } = await import('chatgpt')

  const openAIAuth = await getOpenAIAuth({
    email: process.env.OPENAI_EMAIL,
    password: process.env.OPENAI_PASSWORD
  })

  const api = new ChatGPTAPI({ ...openAIAuth })
  await api.initSession()

  const result = await api.sendMessage('Hello World!')
  console.log(result)
}

Docs

See the auto-generated docs for more info on methods and parameters. Here are the docs for the browser-based version.

Demos

To run the included demos:

  1. clone repo
  2. install node deps
  3. set OPENAI_EMAIL and OPENAI_PASSWORD in .env

A basic demo is included for testing purposes:

npx tsx demos/demo.ts

A google auth demo:

npx tsx demos/demo-google-auth.ts

A demo showing on progress handler:

npx tsx demos/demo-on-progress.ts

The on progress demo uses the optional onProgress parameter to sendMessage to receive intermediary results as ChatGPT is "typing".

A conversation demo:

npx tsx demos/demo-conversation.ts

Authentication

The authentication section relates to the REST-based version (using getOpenAIAuth + ChatGPTAPI). The browser-based solution, ChatGPTAPIBrowser, takes care of all the authentication for you.

On December 11, 2022, OpenAI added some additional Cloudflare protections which make it more difficult to access the unofficial API.

You'll need a valid OpenAI "session token" and Cloudflare "clearance token" in order to use the API.

We've provided an automated, Puppeteer-based solution getOpenAIAuth to fetch these for you, but you may still run into cases where you have to manually pass the CAPTCHA. We're working on a solution to automate this further.

You can also get these tokens manually, but keep in mind that the clearanceToken only lasts for max 2 hours.

Getting tokens manually

To get session token manually:

  1. Go to https://chat.openai.com/chat and log in or sign up.
  2. Open dev tools.
  3. Open Application > Cookies. ChatGPT cookies
  4. Copy the value for __Secure-next-auth.session-token and save it to your environment. This will be your sessionToken.
  5. Copy the value for cf_clearance and save it to your environment. This will be your clearanceToken.
  6. Copy the value of the user-agent header from any request in your Network tab, or copy the result of navigator.userAgent command on Console tab. This will be your userAgent.

Pass sessionToken, clearanceToken, and userAgent to the ChatGPTAPI constructor.

Note This package will switch to using the official API once it's released, which will make this process much simpler.

CAPTCHAs

The browser portions of this package use Puppeteer to automate as much as possible, including solving all CAPTCHAs. 🔥

Basic Cloudflare CAPTCHAs are handled by default, but if you want to automate the email + password Recaptchas, you'll need to sign up for one of these paid providers:

  • nopecha - Uses AI to solve CAPTCHAS
    • Faster and cheaper
    • Set the NOPECHA_KEY env var to your nopecha API key
    • Demo video of nopecha solving the login Recaptcha (41 seconds)
  • 2captcha - Uses real people to solve CAPTCHAS
    • More well-known solution that's been around longer
    • Set the CAPTCHA_TOKEN env var to your 2captcha API token

Alternatively, if your OpenAI account uses Google Auth, you shouldn't encounter any of the more complicated Recaptchas — and can avoid using these third-party providers. To use Google auth, make sure your OpenAI account is using Google and then set isGoogleLogin to true whenever you're passing your email and password. For example:

const api = new ChatGPTAPIBrowser({
  email: process.env.OPENAI_EMAIL,
  password: process.env.OPENAI_PASSWORD,
  isGoogleLogin: true
})

Using Proxies

The browser implementation supports setting a proxy server. This is useful if you're running into rate limiting issues or if you want to use a proxy to hide your IP address.

To use a proxy, pass the proxyServer option to the ChatGPTAPIBrowser constructor, or simply set the PROXY_SERVER env var. For more information on the format, see here.

const api = new ChatGPTAPIBrowser({
  email: process.env.OPENAI_EMAIL,
  password: process.env.OPENAI_PASSWORD,
  proxyServer: '<ip>:<port>'
})

You can also set the PROXY_VALIDATE_IP env var to your proxy's IP address. This will be used to validate that the proxy is working correctly, and will throw an error if it's not.

Restrictions

These restrictions are for the getOpenAIAuth + ChatGPTAPI solution, which uses the unofficial API. The browser-based solution, ChatGPTAPIBrowser, generally doesn't have any of these restrictions.

Please read carefully

  • You must use node >= 18 at the moment. I'm using v19.2.0 in my testing.
  • Cloudflare cf_clearance tokens expire after 2 hours, so right now we recommend that you refresh your cf_clearance token every hour or so.
  • Your user-agent and IP address must match from the real browser window you're logged in with to the one you're using for ChatGPTAPI.
    • This means that you currently can't log in with your laptop and then run the bot on a server or proxy somewhere.
  • Cloudflare will still sometimes ask you to complete a CAPTCHA, so you may need to keep an eye on it and manually resolve the CAPTCHA.
  • You should not be using this account while the bot is using it, because that browser window may refresh one of your tokens and invalidate the bot's session.

Note Prior to v1.0.0, this package used a headless browser via Playwright to automate the web UI. Here are the docs for the initial browser version.

Projects

All of these awesome projects are built using the chatgpt package. 🤯

If you create a cool integration, feel free to open a PR and add it to the list.

Compatibility

This package is ESM-only. It supports:

  • Node.js >= 18
    • Node.js 17, 16, and 14 were supported in earlier versions, but OpenAI's Cloudflare update caused a bug with undici on v17 and v16 that needs investigation. So for now, use node >= 18
  • We recommend against using chatgpt from client-side browser code because it would expose your private session token
  • If you want to build a website using chatgpt, we recommend using it only from your backend API

Credits

License

MIT © Travis Fischer

If you found this project interesting, please consider sponsoring me or following me on twitter twitter

Keywords

FAQs

Package last updated on 14 May 2023

Did you know?

Socket

Socket for GitHub automatically highlights issues in each pull request and monitors the health of all your open source dependencies. Discover the contents of your packages and block harmful activity before you install or update your dependencies.

Install

Related posts

Oracle Drags Its Feet in the JavaScript Trademark Dispute

Security News

Oracle Drags Its Feet in the JavaScript Trademark Dispute

Oracle seeks to dismiss fraud claims in the JavaScript trademark dispute, delaying the case and avoiding questions about its right to the name.

By Sarah Gooding  -  Feb 07, 2025
SocketSocket SOC 2 Logo

Product

  • Package Alerts
  • Integrations
  • Docs
  • Pricing
  • FAQ
  • Roadmap
  • Changelog

About

Packages

npm

Go

Maven

PyPI

Rubygems

Stay in touch

Get open source security insights delivered straight into your inbox.

  • Terms
  • Privacy
  • Security

Made with ⚡️ by Socket Inc