Making Your First LLM Call | CodeSignal Learn

Making Your First LLM Call | CodeSignal Learn

Introduction to LLM Calls

Welcome to the first lesson of our course on building your own AI Cooking Helper . In this lesson, we will explore the concept of making basic LLM (Large Language Model) calls. LLMs, such as OpenAI's models, are powerful tools that can generate human-like text responses. They are integral to AI applications, enabling them to understand and respond to user inputs naturally. By the end of this lesson, you will understand how to make a basic LLM call and interpret its output.

Understanding the Code Structure

Let's start by understanding the structure of the code used to make an LLM call. We'll build this step by step. First, we need to import the necessary library and set up the OpenAI client. This client will allow us to interact with the OpenAI API. TypeScriptimport OpenAI from "openai"; const client = new OpenAI({ apiKey: process.env.OPENAI_API_KEY }); Here, we import the OpenAI class from the openai library. We then create an OpenAI client using the API key stored in an environment variable. This client is essential for making requests to the OpenAI API. In the Codesignal environment, this variables are already configured!

Creating System and User Prompts

Next, we need to define the prompts that will guide the model's behavior. There are two types of prompts: system prompts and user prompts . TypeScript const system_prompt = "You are a cooking assistant that talks like a pirate."; const user_prompt = "What is the best cooking recipe in the world?"; System Prompt : This sets the context for the model. In our example, the system prompt instructs the model to respond like a pirate. User Prompt : This is the input from the user. Here, the user is asking what the best cooking recipe is. These prompts are crucial, as they shape the model's responses, ensuring they are relevant and contextually appropriate.

Configuring the Model Parameters

To control the model's output, we configure certain parameters, such as temperature and the model used. TypeScript const temperature = 0.7; const model = "gpt-4o-mini"; Temperature : This parameter controls the randomness of the model's output. A lower temperature (e.g., 0.2) makes the output more deterministic, while a higher temperature (e.g., 0.8) introduces more randomness and creativity. In our example, a temperature of 0.7 strikes a balance between creativity and coherence. Model : This parameter controls the model that will be used to generate the response. You can find a list of available models on the OpenAI website . For this course, we will use gpt-4o-mini, but you are free to change this parameter to your preferred model.

Sign up

Join the 1M+ learners on CodeSignal

Be a part of our community of 1M+ users who develop and demonstrate their skills on CodeSignal

Executing the LLM Call

Now, let's execute the LLM call using the client.chat.completions.create method. Since this is an asynchronous operation, we will use an async function and the await keyword. async function demo() { const completion = await client.chat.completions.create({ model: model, messages: [ { role: "system", content: system_prompt }, { role: "user", content: user_prompt }, ], temperature: temperature, }); console.log(completion.choices[0]?.message?.content?.trim()); } demo(); Model: We specify the model to use, in this case, "gpt-4o-mini". Messages: This is an array of messages that includes both the system and user prompts. Temperature: We pass the temperature parameter to control the output's randomness. The response will look something like this: { "choices": [ { "message": { "role": "assistant", "content": "Arrr! The best recipe be a hearty seafood stew, fit for any pirate crew!" } // ...other properties } // ...other choices (if any) ] // ...other properties } The create method sends the request to the OpenAI API, and the response is stored in the completion variable. We then print the model's response, which is accessed through completion.choices[0]?.message?.content?.trim().

TypeScript

async function demo() {
  const completion = await client.chat.completions.create({
    model: model,
    messages: [
      { role: "system", content: system_prompt },
      { role: "user", content: user_prompt },
    ],
    temperature: temperature,
  });

  console.log(completion.choices[0]?.message?.content?.trim());
}

demo();

JSON

{
  "choices": [
    {
      "message": {
        "role": "assistant",
        "content": "Arrr! The best recipe be a hearty seafood stew, fit for any pirate crew!"
      }
      // ...other properties
    }
    // ...other choices (if any)
  ]
  // ...other properties
}