1

Deploy

Click the “Deploy” button in the prompt editor to deploy your prompt to the production environment.

2

Create API Key

Navigate to the “API Keys” section in your organization settings and create a new API key. Be sure to save it as a secure environment variable or in a secret manager before closing the tab, as you will not have access to it again.

3

Install SDK

Now, install the PromptFoundry SDK in your application.

npm install @prompt-foundry/typescript-sdk

4

Integrate into your provider call

Integrate the SDK into your provider call to start using your deployed prompt.

Option 1 - Completion Proxy
Option 2 - Direct Provider Integration

Initiates a completion request to the configured LLM provider using specified parameters and provided variables. This endpoint abstracts the integration with different model providers, enabling seamless switching between models while maintaining a consistent data model for your application.

This option requires you to add a provider API key in your organization settings.

  import PromptFoundry from '@prompt-foundry/typescript-sdk';

  // Initialize Prompt Foundry SDK with your API key
  const promptFoundry = new PromptFoundry({
    apiKey: process.env['PROMPT_FOUNDRY_API_KEY'],
  });

  async function main() {
    // Retrieve model parameters for the prompt
    const completionCreateResponse = await client.completion.create('637ae1aa8f4aa6fad144ccbd', {
      // Optionally append additional messages to the converstation thread on top of your configured prompt messages
      appendMessages: [
        { role: 'user', content: [{ type: 'TEXT', text: 'What is the weather in Seattle, WA?' }] },
      ],
      // Supports prompt template variables
      variables: {},
    });
    // completion response
    console.log(completionCreateResponse.message);
  }

  main().catch(console.error);

Fetches the configured model parameters and messages rendered with the provided variables mapped to the set LLM provider. This endpoint abstracts the need to handle mapping between different providers, while still allowing direct calls to the providers.

import PromptFoundry from "@prompt-foundry/typescript-sdk";
import { Configuration, OpenAIApi } from "openai";

// Initialize Prompt Foundry SDK with your API key
const promptFoundry = new PromptFoundry({
  apiKey: process.env["PROMPT_FOUNDRY_API_KEY"],
});

// Initialize OpenAI SDK with your API key
const configuration = new Configuration({
  apiKey: process.env["OPENAI_API_KEY"],
});

const openai = new OpenAIApi(configuration);

async function main() {
// Retrieve model parameters for the prompt
  const modelParameters = await promptFoundry.prompts.getParameters("66abc31c93546b6b73414840", {
    variables: { hello: "world" },
  });

  // check if provider is Open AI
  if (modelParameters.provider === "openai") {
  // Use the retrieved parameters to create a chat completion request
    const modelResponse = await openai.chat.completions.create(
      modelParameters.parameters
    );

    // Print the response from OpenAI
    console.log(modelResponse.data);

  }
}

Deploying

Node Quickstart

Python Quickstart