Skip to content

promptdesk/promptdesk

Repository files navigation


pypi npm docker docker pulls AGPLv3

Bold Innovation, 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).

Quickstart Guide »

Features · Podcast · Articles · Contributors · Community

Available in: Python - JavaScript

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

Alt Text

Features

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

🚀 Getting Started and Installation

To get started with PromptDesk OS, visit promptdesk.ai/docs/quickstart for the installation script. It's a simple, two-line install process that takes an average of just 5 minutes from start to finish.

PromptDesk OS is a self-hosted, 100% free and open-source Docker container that can be deployed anywhere.

You can also jump straight to building prompts or start integrating prompts in python or javascript.

Python SDK

Using the PromptDesk Python SDK, you can easily integrate your prompts into your Python applications.

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)

JavaScript SDK

Using the PromptDesk JavaScript SDK, you can easily integrate your prompts into your Python applications.

npm install promptdesk

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

import { PromptDesk } from 'promptdesk'; //ES6
//const { PromptDesk } = require('promptdesk'); //CommonJS

var pd = new PromptDesk({
    apiKey: "YOUR_PROMPTDESK_API_KEY", //find in /settings
    serviceUrl: "http://localhost"
})

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

console.log(story)

🔗 Important Links

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