Unlock Bold Innovation with Simplified AI

PromptDesk is 100% free and open-source minimalist tool to facilitate the creation, organization, integration, and evaluation of prompts, prompt-based applications, agents and Large Language Models (LLMs).

Explore the docs »

Features · Walkthroughs · Podcast · Articles · Contributors · Community

Available in: Python - JavaScript

If you like this project, please consider giving this repo a ⭐️ star.

Features

• 🤝 Cross-team Collaboration
• 🔐 Data Privacy and Security
• 🌐 Any model, any scale
• 👨‍💻 Python and Javascript SDK
• 🏠 Local or Proxied Calls
• 📈 Comprehensive Logs
• ♾️ Unlimited Models
• 🚀 Easy to set up and integrate (5 minutes)

🚀 Getting Started

We recommend starting with the Quickstart guide. You can also jump straight to building prompts or start integrating prompts in python or javascript.

Quickstart

Run the following commands to install PromptDesk OS in your CLI:

wget https://raw.githubusercontent.com/promptdesk/promptdesk/main/quickstart/setup.sh
chmod +x setup.sh && ./setup.sh

Please ensure that port 80 and 443 (optional) is available on your system. If you have a web server running, you may need to stop it before running the setup script.

Open your web browser and navigate to http://localhost, the IP address, or the domain name provided to access PromptDesk OS. Initial setup will require a valid OpenAI API key for installation testing purposes.

More installation options are available in the PromptDesk OS GitHub Repository.

Python SDK

To install PromptDesk, use pip:

pip install promptdesk

You can call the prompt you build in the application by using the generate method.

from promptdesk import PromptDesk

pd = PromptDesk(
    api_key = "YOUR_PROMPTDESK_API_KEY", #find in /settings
    service_url = "http://localhost"
)

story = pd.generate("short-story-test", {
    "setting": "dark and stormy night",
    "character": "lonely farmer",
    "plot": "visited by a stranger"
})

print(story)

🔗 Important Links

For more information about PromptDesk, please refer to the following resources:

• Documentation
• Application GitHub Repository
• Python GitHub Repository
• PyPI Package
• npm Package
• Docker Hub
• Official Website