LLM Conversation Script

This is a simple Python script that allows two language models (LLMs) to have a conversation based on a seeded topic and saves the output to a text file. The script utilizes the OpenAI GPT-3 API for generating responses from the models.

Installation

Ensure you have the openai library installed. You can do this using pip:

        pip install openai
    

Here’s the Script:

        
import openai

# Set up your API key
openai.api_key = 'your_openai_api_key'

def get_response(prompt):
    response = openai.ChatCompletion.create(
        model="gpt-3.5-turbo",
        messages=[{"role": "user", "content": prompt}]
    )
    return response['choices'][0]['message']['content']

def main(topic):
    # Seed the conversation with a topic
    messages = [
        f"Let's have a hilarious conversation about {topic}!"
    ]
    
    # Initiate two LLMs talking to each other
    for _ in range(5):  # Number of exchanges
        user_message = messages[-1]
        assistant_response = get_response(user_message)
        messages.append(assistant_response)
        # Use the assistant's response as the next user's prompt
        messages.append(f"Assistant: {assistant_response}")

        # Simulate the second LLM responding
        response2 = get_response(assistant_response)
        messages.append(response2)
    
    # Save the conversation to a text file
    with open("llm_conversation.txt", "w") as file:
        for message in messages:
            file.write(message + "\n")

    print("Conversation saved to llm_conversation.txt")

if __name__ == "__main__":
    seed_topic = "the secret life of house cats"
    main(seed_topic)
        
    

How It Works:

1. Setup: The script initializes your OpenAI API key and imports the necessary library.
2. Response Function: It defines a get_response function to interact with the OpenAI API and fetch responses.
3. Main Logic: The main function seeds the conversation with a topic, simulates dialogue between two LLMs, and collects their exchanges.
4. Output: Finally, it writes the conversation to a text file named llm_conversation.txt.

Usage:

• Install the necessary library.
• Replace the API key with your own.
• Adjust the seed topic to any fun or hilarious subject you'd like.
• Run the script and check the output in llm_conversation.txt.

Enjoy your fun and light-hearted exchange between two LLMs!