Coder Social home page Coder Social logo

ruiduobao / chatgpt-telegram-bot Goto Github PK

View Code? Open in Web Editor NEW

This project forked from altryne/chatgpt-telegram-bot

0.0 1.0 0.0 799 KB

This is a very early attempt at having chatGPT work within a telegram bot

License: MIT License

Shell 0.94% Python 98.60% Dockerfile 0.47%

chatgpt-telegram-bot's Introduction

Deprecated - folks this repo will be unmaintaned until / if open AI releases a proper chatGPT API.

ChatGPT Telegram Bot

CleanShot 2022-12-02 at 16 08 27

This is a Telegram bot that lets you chat with the chatGPT language model using your local browser. The bot uses Playwright to run chatGPT in Chromium, and can parse code and text, as well as send messages. It also includes a /draw command that allows you to generate pictures using stable diffusion. More features are coming soon.

Features

  • Chat with chatGPT from your Telegram on the go
  • /draw pictures using stable diffusion (version 0.0.2)
  • /browse give chatGPT access to Google (version 0.0.3)

How to Install

Step 1: Install Python and Miniconda

  1. Go to the Miniconda download page.
  2. Click on the appropriate installer for your operating system.
  3. Follow the prompts to complete the installation.

Step 2: Create a conda environment

  1. Open a terminal or command prompt.
  2. Navigate to the directory where you want to create the environment.
  3. Run conda env create -f environment.yml to create the environment.
  4. Activate the newly created environment conda activate chat

Step 3: Install Playwright

  1. Open a terminal or command prompt.
  2. Navigate to the directory where you installed Miniconda.
  3. Run playwright install to download the necessary Chromium software.
  4. Run playwright install-deps to download the necessary dependencies

Step 4: Set up your Telegram bot

  1. Set up your Telegram bot token and user ID in the .env file. See these instructions for more information on how to do this.

How to obtain telegram user id? Add telegram userinfobot to your telegram contacts

  1. Edit the .env.example file, rename it to .env, and place your values in the appropriate fields.

Step 5: Set up your API keys

  1. Copy the .env.example file and rename the copy to .env.
  2. To use the /draw command, you will need to obtain an API key for stable diffusion. To do this, go to Dream Studio Beta and sign up for a free membership.
  3. SERP_API_KEY is optional. If you want to use the /browse command, you will need to obtain an API key for SERP. To do this, go to SERP API and sign up for a free account.

Step 5: Run the server

  1. Open a terminal or command prompt.
  2. Navigate to the directory where you installed the ChatGPT Telegram bot.
  3. Run python server.py to start the server.

Step 6: Chat with your bot in Telegram

  1. Open the Telegram app on your device.
  2. Find your bot in the list of contacts (you should have already created it with @botfather).
  3. Start chatting with your bot.

If you're using Docker inside a server (headless mode)

You can use the docker image to launch your bot in a server (using playwright headless mode)

docker-compose example

services:
  chatgpt-telegram-bot:
    image: ghcr.io/altryne/chatgpt-telegram-bot
    container_name: chatgpt-telegram-bot
    environment:
      - TELEGRAM_API_KEY=
      - TELEGRAM_USER_ID= #Use this with your user ID to restrict usage only to your account
      - STABILITY_API_KEY= #use this if you want the bot to draw things with stability AI as well
      - SERP_API_KEY= #add this from serpapi if you want to enable the google search feature
      - OPEN_AI_EMAIL= #openai login email. Needed for autologin in headless mode
      - OPEN_AI_PASSWORD= #openai password. Needed for autologin in headless mode

Credits

chatgpt-telegram-bot's People

Contributors

altryne avatar stjohn96 avatar thibauld avatar sebaplaza avatar egemengol avatar

Watchers

 avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.