Introduction

Welcome! This beginner-friendly guide will walk you through building a simple LLM app in Lexica using an existing template. We'll create the application, engineer a prompt, and deploy it as an API—all

Prerequisites

This guide assumes you are using lexica cloud. If you would like to self-host the lexica platform, please refer to the self-hosting guide for deployment instructions.

In case you are self-hosting Lexica

Step 0: Add your OpenAI API keys

1. Access the agenta in your webbrowser.

2. Select "Settings" from the left sidebar.

3. Select "LLM Keys" from the top menu.

4. Add your OpenAI API key.

Your OpenAI API keys are saved locally on your browser and are sent to the Agenta server only when you create a new application (as an environment variable in the Docker container).

Step 1: Create a New LLM App

1. Click on the "Create New App" button.

2. Select "Create from Template" and choose the "Single Prompt Template"; then name the application "get_capital."

Step 2: Test the Application

The provided application template already includes a prompt that states the capital of a country. Let's test it:

• Go to the playground.

• Type "France."

• Click the "Run" button.

• The result should read, "The capital of France is Paris." If you only want to return "Paris," we'll adjust this with prompt engineering in the next step.

Step 3: Deploy the application

To deploy the application as an API. You need to click on the button "Publish" in the playground and select an environemnt.

You can now find the API endpoint in the "Endpoints" menu. Copy and paste the code from the "Endpoints" menu to use it in your software.

INFO

Congratulations! You've created your first LLM application. Feel free to modify it, explore its parameters, and discover Lexica's features. Your next steps could include fetching prompts from Lexica, building a custom workflow, or running an evaluation.