ChatGPT CLI [Python App]

gpt_cli.py

"""
Author: @jatinkrmalik
This script creates a chat interface between the user and OpenAI's GPT model.
Instructions to run the program:
1. Set your OpenAI API key as an environment variable in your terminal session. You can do this by running the following command:
    export OPENAI_API_KEY='your-api-key-here'
    Remember to replace 'your-api-key-here' with your actual OpenAI API key.
2. After setting the API key, you can run the script with the following command:
    python gpt_cli.py
3. Once the script is running, you can start typing your messages into the terminal. The model's responses will be printed out. You can keep the conversation going for as long as you like.
    
4. If you wish to stop the program, simply type 'quit' or 'exit'.
"""

import argparse
import openai
import os

# Fetch the OpenAI API key from the environment variables
openai_api_key = os.getenv('OPENAI_API_KEY')

if openai_api_key is None:
    raise ValueError("The environment variable OPENAI_API_KEY is not set. Please set this variable with your OpenAI API key.")

# Set the OpenAI API key
openai.api_key = openai_api_key

# Initialize conversation with a system message
conversation = [
    {
        "role": "system",
        "content": "You are a helpful assistant."
    }
]

def chat_with_model(message):
    conversation.append({
        "role": "user",
        "content": message
    })
    response = openai.ChatCompletion.create(
        model="gpt-4-0613", # update this to newer model if it's available, such as gpt-3.5-turbo-16k
        messages=conversation
    )
    conversation.append({
        "role": "assistant",
        "content": response['choices'][0]['message']['content']
    })
    return response['choices'][0]['message']['content']

# Interactive conversation loop
print("You are now chatting with OpenAI gpt-4-0613  model. Type 'quit' or 'exit' to end the program.")
print()
while True:
    user_message = input("👨 User: ")
    if user_message.lower() in ['quit', 'exit']:
        break
    else:
        print("🤖 Assistant: ", chat_with_model(user_message))
        print()

Here's a preview: