Documentation
Getting Started
Tutorials
Prompty File Spec
Contributing
Getting Started
sethjuarezwayliumscassiebreviubethanyjep
8/14/2024

Quick Start

In this Quick Start, we will cover how you can get started to build your first Prompty. At the end of the Quick start you should know how to:

  • Setup and configure your Prompty.
  • Create and run a Prompty.
  • Load and execute a Prompty in your code.

Prerequisites

To make the most of this Quick start, ensure you have:

  • Azure OpenAI or OpenAI resource

Installation

Install the Prompty Extension

To get started with Prompty, first, install the Prompty extension in the Visual Studio Code Marketplace.

Create a Prompty file

Once the extension is installed, go to your Explorer, right click and select New Prompty. It will create a new file with the .prompty extension. We will update our Prompty file to get a response from an LLM.

---
name: Shakespearean Writing Prompty
description: A prompt that answers questions in Shakespearean style using GPT-4
authors:
  - Bethany Jepchumba
model:
  api: chat
  configuration:
    type: azure_openai
    azure_endpoint: ${env:AZURE_OPENAI_ENDPOINT}
    azure_deployment: gpt-4
  parameters:
    max_tokens: 3000
sample:
  question: Please write a short text inviting friends to a Game Night.
---

system:
You are a Shakespearean writing assistant who speaks in a Shakespearean style. You help people come up with creative ideas and content like stories, poems, and songs that use Shakespearean style of writing style, including words like "thou" and "hath”.
Here are some example of Shakespeare's style:
- Romeo, Romeo! Wherefore art thou Romeo?
- Love looks not with the eyes, but with the mind; and therefore is winged Cupid painted blind.
- Shall I compare thee to a summer's day? Thou art more lovely and more temperate.

example:
user: Please write a short text turning down an invitation to dinner.
assistant: Dearest,
  Regretfully, I must decline thy invitation.
  Prior engagements call me hence. Apologies.

user:
{{question}}

The Prompty Specification

Prompty is an asset class not tied to any language as it uses markdown format with YAML to specify your metadata. It unifies the prompt and its execution in a single package to quickly get started. The front matter is structured in YAML which provides the model configuration and Prompty inputs. Below the front matter is the prompt template in Jinja which allows for dynamic inputs to the Prompty.

Model Cofigurations

You can define and configure your model directly in Visual Studio Code. To configure your model, navigate to and edit your settings.json file. You can edit this by navigating to settings > Extensions > Prompty > Edit in settings.json

Once in settings.json, update your model name, type, api_version, endpoint and deployment. You can update this at user level for use across different Prompty files or at workspace level to share with your team members.

[TIP!] Login to Azure Active Directory to authenticate your Azure OpenAI models for enhanced security. In your model configurations, leave the api_key empty to trigger Azure Active Directory authentication.

Environment Variables

When using OpenAI, you can store your keys in a .env file in the same directory as the Prompty file or the root folder. In your Prompty file, you can reference your keys using ${env:OPENAI_xxx}

Run your Prompty

Run the Prompty file by either click the Run button at the top or clicking f5 button. The Output will be in two formats:

  • Prompty Output: a brief response with just the model output.

  • Prompty Output (verbose): a detailed response with both the requests sent and response received including the tokens used in the process.

Next Steps

The following resources: