optimus-prompt 0.1.0

Compare responses from different LLMs to the same prompt

Optimus Prompt 🤖

Compare responses from different Language Learning Models (LLMs) to the same prompt.

Features

• Support for multiple LLM providers:
  • OpenAI (GPT-3.5, GPT-4)
  • Anthropic (Claude)
• Simple prompt input via text file
• Human-readable output format
• Easy to extend with new providers

Installation

pip install optimus-prompt

Quick Start

1. Create a prompt.txt file with your prompt:

Explain quantum computing in simple terms

2. Set up your API keys in a .env file:

OPENAI_API_KEY=your_openai_key_here
ANTHROPIC_API_KEY=your_anthropic_key_here

3. Run Prompt Prism:

from optimus_prompt.core import Prompt
from optimus_prompt.providers import OpenAIProvider, AnthropicProvider
from optimus_prompt.core import ResponseWriter

# Initialize providers
providers = [
    OpenAIProvider(model="gpt-4"),
    AnthropicProvider(model="claude-3")
]

# Read prompt from file
with open("prompt.txt", "r") as f:
    prompt_text = f.read().strip()
prompt = Prompt(prompt_text)

# Collect responses
responses = []
for provider in providers:
    response = provider.generate(prompt)
    responses.append(response)

# Write responses to file
writer = ResponseWriter("output.txt")
writer.write(prompt, responses)

Development

Setup

1. Clone the repository:

git clone https://github.com/yourusername/optimus-prompt.git
cd optimus-prompt

2. Install Poetry (if not already installed):

pip install poetry

3. Install dependencies:

poetry install

Running Tests

poetry run pytest

Contributing

We welcome contributions! Please see our Contributing Guide for details.

License

This project is licensed under the MIT License - see the LICENSE file for details.