Multi-LLM-Chat-Playground

Welcome to the Multi-LLM Chat Playground! 🎉 This interactive app lets you compare responses from multiple Large Language Models (LLMs) in real-time using LiteLLM — a lightweight, unified API for interacting with different LLM providers.

✨ Supported Models

• GPT-4o
• Claude 3.5 Sonnet
• Cohere Command R Plus

Whether you’re experimenting with creative prompts or exploring the models' different styles, this app provides a fun, easy way to see how each model handles the same input.

Why Use This? 🤔

• Instantly compare responses from GPT-4o, Claude 3.5 Sonnet, and Cohere Command R Plus.

• Explore how different prompts shape model responses.

• Test different types of prompts, from technical to creative.

• Gain insights into how models interpret the same input differently.

Key Features

🤖 Multi-Model Comparison: Compare responses from multiple LLMs in real time.

🔧 Custom Prompts: Define your own prompts to tailor responses.

👀 Side-by-Side View: Instantly see how each model interprets and responds to the same input.

🔌 Powered by LiteLLM: A simple, unified interface to access multiple LLMs with ease.

🎨 Creative Experimentation: Test various prompts, from simple questions to creative tasks like writing poetry.

How It Works

1. Enter your API Keys 🔑

   Provide API keys for OpenAI, Anthropic, and Cohere to access the models.

2. Test Your Prompts ✍️

   Enter a custom prompt or use the default one to see how it shapes the models' responses.

3. Enter Your Message 💬

   Type a message or question you’d like to send to all models.

4. View Responses 👀

   See how each model responds side-by-side!

Getting Started

1. Clone this repository.
2. Install the required dependencies:

   pip install -r requirements.txt
   

3. Start the app:

   streamlit run multi-llm-pg.py
   

4. Begin experimenting and have fun! 🎉

🎮 Demo

Here’s a quick look at how the Multi-LLM Chat Playground works!

Screenshots

Enter API Keys

Enter a Prompt & Message

🌍 Explore and Share!

Feel free to explore and test various creative prompts, compare model behaviors, and see how different instructions impact the outputs. Share your experiences and discoveries with the community! 🚀

📝 Contributing:

Want to improve the app? Fork the repo, submit a PR, or open an issue. All contributions are welcome! 🤝

Happy experimenting! 🎉✨