Skip to content

Latest commit

 

History

History
166 lines (117 loc) · 5.05 KB

README.md

File metadata and controls

166 lines (117 loc) · 5.05 KB
Raw

Deploy on Railway

Telegrambot-with-GPT4free

🤖 A Telegram bot powered by ChatGPT using the Aiogram API.

ℹ️ Note: The Hugging Face token is only required for image captioning.

✨ Features:

  • Supports OCR with Tesseract in addition to salesforce blip image captioning.
  • Easy to translate to your own language with multi-language support.
  • Internet access using duckduckgo_search.
  • Supports voice transcription with speech_recognition
  • Image generation using Stability Diffusion and DALL-E.
  • Plugin support for DuckDuckGo search and news (under testing).

Installation Steps

Linux

Download or clone this repository
Go to the directory

git clone https://github.com/noes14155/Telegrambot-with-GPT4free
cd Telegrambot-with-GPT4free

Copy example.env file to .env

cp example.env .env

Change environment variables in .env file Environment Variables

nano .env

Create virtual environment for this project/directory

python3 -m venv venv
source venv/bin/activate

Install the requirements

apt install -y flac ffmpeg tesseract-ocr
wget https://github.com/tesseract-ocr/tessdata_fast/raw/main/script/Devanagari.traineddata -P /usr/share/tesseract-ocr/4.00/tessdata/script/
EXPORT TESSDATA_PREFIX=/usr/share/tesseract-ocr/4.00/tessdata

pip install -r requirements.txt

Run the bot

python main.py

Windows

  1. Download or clone this repository:
git clone https://github.com/noes14155/Telegrambot-with-GPT4free
cd Telegrambot-with-GPT4free

  1. Copy the example.env file to .env

  2. Change the environment variables in the .env file using a text editor of your choice.

  3. Create a virtual environment for this project/directory:

python -m venv venv
venv\Scripts\activate
  1. Install the required dependencies:
pip install -r requirements.txt
  1. Install additional dependencies:

  • Install Tesseract OCR:

    • Download the Windows installer from the Tesseract OCR GitHub page.
    • Run the installer and make sure to check download Additional script data option in the installation options.
    • Add the Tesseract installation directory to the system's PATH environment variable.

  • Install FFmpeg:

    • Download the latest static build of FFmpeg for Windows from the official FFmpeg website.
    • Extract the downloaded ZIP file to a location of your choice.
    • Add the FFmpeg bin directory to the system's PATH environment variable.
  1. Run the bot:
python main.py

Docker

Build (change environment variables before build)

Uncomment this section (If yu want to use gpt4free)

  g4f_server:
    container_name: g4f_server
    ports:
      - '1337:1337'
    environment:
      - PYTHONUNBUFFERED=1
    build:
      context: ./interference
      dockerfile: Dockerfile
    restart: always

Build containers

docker-compose up --build -d

Environment Variables

To run this project, you will need to create a .env file or rename the existing example.env to .env and add the following environment variables

  • BOT_TOKEN Get this by messaging @botfather Refer to 📖 Telegram Bot Tutorial

  • API_BASE To use GPT4free API_BASE = 'http://g4f_server:1337' (Only working in docker) You can use any provider. I have included Naga AI api base. Use the key for the same.

  • GPT_KEY To use GPT4free GPT_KEY = '' (Only working in docker) Key from the provider (including openai). Whichever api base you want use the key provided. For Naga AI, Get this by messaging run the /key get command in th bot channel in Naga AI Discord , Naga AI Telegram

  • HG_TOKEN Optional(Required for image captioning). Sign up on hugging face and get the token from 🔗 Hugging Face.

  • HG_img2text Required for image captioning. If you wnat to use another model for image captioning. change it here.
    Default value HG_img2text = 'https://api-inference.huggingface.co/models/Salesforce/blip-image-captioning-large'

  • DEFAULT_LANG Change to your language default english. If you want to translate to your own language please do so in the language_files folder make your own language.yml file and add the language to languages.yml file.

  • Plugins Enable or disable plugins. Default value True.

🎉 You're all set! Enjoy using the Telegram bot with ChatGPT!

Contributors