Skip to content

README.md

Latest commit

 

History

History
52 lines (37 loc) · 1.54 KB

README.md

File metadata and controls

52 lines (37 loc) · 1.54 KB

Nometa-Bot

Developed by students of the Simulator ML (Karpov.Courses)

Repository structure
  • deployment/ - docker application deployment files
  • docs/ - project documentation folder
  • exploration/ - data mining folder
  • static/ - scripts to launch components
  • src/ - application source folder
    • app/ - telegram bot files
    • metrics/ - files for evaluating the quality of models
    • models/ - folder with training scripts and inference
    • utils/ - folder with util functions and variables
  • test/ - application tests (pytest)

Launch

  1. git clone https://github.com/uberkinder/Nometa-Bot.git
  2. Create a telegram bot and get a token through https://t.me/BotFather

Choose a launch option and continue with the steps

Local

  1. install python version: 3.8

  2. pip install -r requirements.txt

  3. install PyTorch

  4. pip3 install torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/cpu

  5. Add a variable to your environment on ...

    linux: export BOT_TOKEN=<your_token>

    windows (cmd): setx BOT_TOKEN "<your_token>"

  6. run python static/start_bot.py

Docker

from the root of the repository run the commands 3) docker build -t nometa_bot -f deployment/Dockerfile . 4) docker run -e BOT_TOKEN=<your_token> -p 8080:8080 nometa_bot

After launching the bot, add it to the chat and allow it to read messages