smaranjitghose / AIEmailGenerator

A minimalistic application to generate custom email templates built using Python and GPT-3

AI Email Generator

A minimalistic application to generate custom email templates built using Python and GPT-3

Set-Up ⚒️

• Ensure you have the latest stable version of Python in your system

• Open your terminal / command prompt.

• Clone the repository

  git clone https://github.com/smaranjitghose/AIEmailGenerator.git
  

• Change the directory to the cloned project

  cd AIEmailGenerator
  

• Create a virtual environment

  python -m venv env
  

• Activate the virtual environment

  • Windows

     env/Scripts/Activate.ps1
    

  • Linux/Mac

    source env/bin/activate
    

• Check if the virtual environment in the concerned repository is used for python shell

  which python
  

• Upgrage Pip Installer

  python -m pip install --upgrade pip
  

• Install the dependencies

  pip install -r requirements.txt
  

• Load the application

  streamlit run .\Home.py
  

• If the app does not load by itself in your default browser, open a browser of your choice and navigate to http://localhost:8501

• To stop the application, press CTRL + C in your terminal

• To deactive the python environment, type in your terminal

  deactivate
  

Demo 👇

v.0.0.1

v.0.0.1 (Sample Email)

Note ✏️

• For Streamlit Sharing, mentioning versions of the modules in requirements throws error at times

Future Work 🏗️

• Chrome Plugin
• Better Prompting
• Editable
• Sample Templats: 10
• Add to Email

Deployment Options 🥊

• Streamlit Cloud

• HuggingFace Spaces

• Fly

• Railway

• Render

• Cyclic

• Heroku

• Digital Ocean

• Google App Engine

• Amazon EC2 Instance

• Azure App

(Using Google Colab/Kaggle as temporary MVP server)

• pyngrok

  • Step 1: Install pyngrok in Google Colab

    ! pip install pyngrok
    

  • Step 2: Sign-up in ngrok and get Authentication Token

  • Step 3: Authenticate

       from pyngrok import ngrok
       ngrok.set_auth_token("xxx")

  • Step 4: Load the Streamlit App at port 8051, create a tunnel for it and reveal the public URL for the tunnel

       !nohup streamlit run app.py --server.port 8051 &
       url = ngrok.connect(8051).public_url
       print(url)

  • Step 5: Share URL with client

• localtunnel

  • Step 1: Install localtunnel

    npm install -g localtunnel
    

  • Step 2

    streamlit run Home.py & npx localtunnel --port 8501
    

  • Step 3: Share URL with client

Acknowledgements 🙏

• Text to Text Generator Model: OpenAI GPT3
  • Documentation
  • Playground
• Animations: LottieFiles