Prompty is an asset class and format for LLM prompts designed to enhance observability, understandability, and portability for developers. The primary goal is to accelerate the developer inner loop of prompt engineering and prompt source management in a cross-language and cross-platform implementation.
The file format has a supporting toolchain with a VS Code extension and runtimes in multiple programming languages to simplify and accelerate your AI application development.
The tooling comes together in three ways: the prompty file asset, the VS Code extension tool, and runtimes in multiple programming languges.
The Prompty File Format
Prompty is a language agnostic prompt asset for creating prompts and engineering the responses. Learn more about the format here.
The Prompty VS Code Extension
Run Prompty files directly in VS Code. This Visual Studio Code extension offers an intuitive prompt playground within VS Code to streamline the prompt engineering process. You can find the Prompty extension in the Visual Studio Code Marketplace.
Download the VS Code extension here.
The Prompty Runtimes
To execute a Prompty file asset in code, you can use one of the supporting runtimes such as:
- Prompty Core (python) - The python Prompty core package is the base package needed to run a prompty asset file. Please note this package is preview and under active development.
- Prompty Core (csharp) - Coming soon.
- Promptyflow (python) - Use Prompty with Promptflow as your runtime and logic orchestrator.
- LangChain (python) - Use the experimental LangChain Prompty runtime.
- Semantic Kernal (csharp) - Use the experimental Semantic Kernal Prompty runtime.
**Note: We are continuing to work on the runtimes so watch for frequent updates!
Learn more and get started building applications with Prompty
Quick Start - Coming soon.
Tutorials - Coming soon.
Examples - Check out the AI App templates that were released at Microsoft Build that leverage Prompty for a variety of scenarios.
Contributing - Coming soon.