Skip to content

Latest commit

 

History

History
201 lines (139 loc) · 9.33 KB

README.md

File metadata and controls

201 lines (139 loc) · 9.33 KB
Raw

ChatGPT Telegram Bot

badge:version docker image size license

English ｜ 中文

A ChatGPT bot for Telegram based on Node.js. Support both browserless and browser-based APIs.

Updates

🎉 v2 has been released!

🔔 Apr. 3, 2023 (v2.5.0)
  • Support per-chat conversation by @Vadko.
  • Support setting message queue as optional by @Vadko.
Previous Updates
🔔 Mar. 10, 2023 (v2.4.0)
  • Add a timeout mechanism to prevent the message queue from getting stuck. You can override the default timeout in the config file.
🔔 Mar. 07, 2023 (v2.3.2)
🔔 Mar. 02, 2023 (v2.3.0)

We strongly advice you to use the official API. There are rumors that OpenAI may ban your account if you continue to use the unofficial and browser API.

🔔 Feb. 28, 2023 (v2.2.0)
  • Support message queue to avoid rate limit.
  • Improve Markdown parsing.
🔔 Feb. 22, 2023 (v2.1.1)
  • Support custom prompt prefix and suffix (allowing you to customize the bot's identity and behavior).
  • Support Node.js v19.
🔔 Feb. 19, 2023 (v2.1.0)

We have added support for the unofficial proxy API by @acheong08. This API uses a proxy server that allows users to bypass Cloudflare protection and use the real ChatGPT. Please see Usage for more details.

For previous users, we've updated our API options. api.version is now api.type, with options browser (previously v3), official (previously v4), and unofficial. Please update your config file accordingly.

🔔 Feb. 17, 2023

According to one of the maintainers of the reverse proxy servers, OpenAI has patched this method. So you have to either use the browserless Official API with official models (which costs money), or use the browser-based solution.

🔔 Feb. 15, 2023

We have release the v2.0.0 of this bot, which supports both browserless and browser-based APIs. You can switch between the two APIs at any time using the config file. Additionally, we have refactored the codebase to make it more maintainable and easier to extend.

For old users, you will need to switch from the .env file to json files under the config/ folder.

Features

Private Chat Group Chat
  • Support for both browserless (official, unofficial) and browser-based APIs
  • Support for both private and group chats
  • Work in privacy mode (the bot can only see specific messages)
  • Bot access control based on user and group IDs
  • Reset chat thread and refresh session with command
  • Queue messages to avoid rate limit
  • Typing indicator, Markdown formatting, ...
  • Cloudflare bypassing and CAPTCHA automation (for the browser-based API)
  • Customize bot identity and behavior (by setting api.official.systemMessage)
  • User-friendly logging

Usage

Differences between the three types of APIs

Thank @transitive-bullshit for making this easy-to-understand table!

Type Free? Robust? Quality?
official ❌ No ✅ Yes ✅ Real ChatGPT models
unofficial ✅ Yes ☑️ Maybe ✅ Real ChatGPT
browser ✅ Yes ❌ No ✅ Real ChatGPT
  • official: Uses the gpt-3.5-turbo model by default with the official OpenAI chat completions API (official, robust approach, but it's not free)
  • unofficial: Uses an unofficial proxy server to access ChatGPT's backend API in a way that circumvents Cloudflare (uses the real ChatGPT and is pretty lightweight, but relies on a third-party server and is rate-limited)
  • browser (not recommended): Uses Puppeteer to access the official ChatGPT webapp (uses the real ChatGPT, but very flaky, heavyweight, and error prone)

Warning

There are rumors that OpenAI may ban your account if you continue to use the unofficial and browser API. Use it at your own risk.

Start the server

Option 1: Node

To get started, follow these steps:

  1. Clone this project.
  2. Create local.json under the config/ folder. You can copy the config/default.json as a template.
  3. Modify the local.json following the instructions in the file. The settings in local.json will override the default settings in default.json.
  • Set api.type to official if you want to use the browserless official API. Then provide your OpenAI API Key and other settings. You can refer to this for more details. Note that this will cost your credits.
  • Set api.type to unofficial if you want to use the browserless unofficial API. Then provide your OpenAI access token (how to get your access token?) and other settings. You can refer to this for more details.
  • Set api.type to browser if you want to use the browser-based API (not recommended). Then provide the OpenAI / Google / Microsoft credentials and other settings. You can refer to this and this for more details. Make sure you have a Chromium-based browser installed.

Then you can start the bot with:

pnpm install
pnpm build && pnpm start

Option 2: Docker

To get started, follow these steps:

  1. Create a folder named config and create a local.json file in it. You can follow the instructions in the "Choice #1: Node" section to customize the settings.

  2. Run the following command to start the bot:

    docker run -d -v ./config:/app/config raineggplant/chatgpt-telegram-bot:latest

    This will pull the latest image that only supports the browserless API. If you want to use the browser-based API, you can add a -browser suffix to the tag, e.g., raineggplant/chatgpt-telegram-bot:latest-browser.

Chat with the bot in Telegram

To chat with the bot in Telegram, you can:

  • Send direct messages to the bot (this is not supported in groups)
  • Send messages that start with the specified command (e.g., /chat or the command you specified in the json config file)
  • Reply to the bot's last message

Note Make sure you have enabled the privacy mode of your bot before adding it to a group, or it will reply to every message in the group.

The bot also has several commands.

  • /help: Show help information.
  • /reset: Reset the current chat thread and start a new one.
  • /reload (admin required, browser-based API only): Refresh the ChatGPT session.

Note When using a command in a group, make sure to include a mention after the command, like /help@chatgpt_bot.

Advanced

Running the bot using browser-based API on a headless server

You can use Xvfb to create a virtual framebuffer on a headless server and run this program:

xvfb-run -a --server-args="-screen 0 1280x800x24 -nolisten tcp -dpi 96 +extension RANDR" pnpm start

We recommend you to use Google auth to avoid the complicated login Recaptchas. If you use a OpenAI account, you may have to use nopecha or 2captcha or manually solve the Recaptcha (by connecting to the display server using x11vnc). For more details about CAPTCHA solving, please refer to the api repository.

Credits

LICENSE

MIT License.

Leave a star ⭐ if you find this project useful.