Exploring Model Parameters in PHP | CodeSignal Learn

Exploring Model Parameters in PHP | CodeSignal Learn

The max_tokens parameter sets a hard limit on the number of tokens the AI can generate in its response. A "token" can be a whole word or just part of a word. For example, "chatbot" might be one token, while "hello" could be split into two tokens: "hel" and "lo." It's important to note that token counts vary across different models, words, and languages — so the same text might have a different token count depending on these factors.

When you set max_tokens, you specify the maximum number of tokens the AI can produce. This is a strict limit, meaning the model will stop generating text once it reaches this count, even if it results in an incomplete sentence or word.

Here's an example where we set max_tokens to 100:

PHP

$response = $client->chat()->create([
    'model' => 'gpt-4',
    'messages' => [['role' => 'user', 'content' => $prompt]],
    'max_tokens' => 100
]);

By setting max_tokens to 100, you impose a hard limit on the number of tokens the AI can generate in its response. This may result in responses being abruptly cut off if the model hasn't completed its intended thought. Importantly, the max_tokens parameter doesn't make the model inherently more concise or brief — it simply restricts response length. The model isn't consciously summarizing or adjusting content to fit within this limit; rather, it continues generating text until reaching the token limit. Primarily, this parameter is valuable for managing usage rates and controlling the cost of API requests.

The temperature parameter is a fascinating aspect of AI interaction. It controls the randomness or creativity of the AI's responses. This parameter typically ranges from 0 to 2. A lower temperature value, such as 0.2, makes the AI's output more deterministic and focused, often resulting in more predictable responses. Conversely, a higher temperature value, like 0.8, encourages the AI to generate more diverse and creative responses, which can be useful for tasks requiring imaginative outputs.

For example, consider the following code snippet where we set the temperature to 0.7:

PHP

$response = $client->chat()->create([
    'model' => 'gpt-4',
    'messages' => [['role' => 'user', 'content' => $prompt]],
    'temperature' => 0.7
]);

With a temperature of 0.7, the AI is likely to provide a response that balances creativity and coherence. Experimenting with different temperature values will help you find the right balance for your specific use case.

The presence_penalty parameter is a powerful tool for encouraging the AI to introduce new topics in its responses. It works by penalizing the AI for using words that have already appeared in the conversation, thus promoting diversity in the dialogue. This parameter ranges from -2.0 to 2.0. A negative value like -1.0 actually encourages the model to repeat content, while a value of 0.0 means the AI is neither encouraged nor discouraged from repeating words. A positive value such as 1.0 or 2.0 strongly encourages the AI to explore new topics, resulting in more varied and diverse responses.

Consider the following code where we set the presence_penalty to 0.6:

PHP

$response = $client->chat()->create([
    'model' => 'gpt-4',
    'messages' => [['role' => 'user', 'content' => $prompt]],
    'presence_penalty' => 0.6
]);

With a presence_penalty of 0.6, the AI is more likely to explore new topics and provide varied responses. This can be particularly useful in scenarios where you want to keep the conversation fresh and engaging.

The frequency_penalty parameter helps reduce repetition in the AI's responses by penalizing the AI for using the same words or phrases multiple times within its response. Like the presence penalty, this parameter ranges from -2.0 to 2.0. A negative value such as -1.0 increases the likelihood of repetition, a value of 0.0 applies no penalty for repetition, and positive values like 1.0 or 2.0 increasingly discourage repetition, promoting a more dynamic and varied dialogue.

While presence_penalty encourages the AI to introduce new topics by penalizing the use of words that have already appeared in the conversation, frequency_penalty focuses on reducing repetition by penalizing the AI for using the same words or phrases multiple times within its response. This distinction allows you to manage both the diversity of topics and the variety of language in the AI's outputs.

In the following example, we set the frequency_penalty to 0.8:

PHP

$response = $client->chat()->create([
    'model' => 'gpt-4',
    'messages' => [['role' => 'user', 'content' => $prompt]],
    'frequency_penalty' => 0.8
]);

By applying a frequency_penalty of 0.8, you can minimize repetitive content in the AI's responses, making the conversation more dynamic and engaging. This parameter is particularly useful when you want to maintain a lively and varied dialogue.

Let's bring it all together with a complete code example that incorporates all the parameters we've discussed:

PHP

<?php
require 'vendor/autoload.php';

// Fetch the api key
$apiKey = $_ENV['OPENAI_API_KEY'] ?? getenv('OPENAI_API_KEY');
$baseUrl = $_ENV['OPENAI_BASE_URL'] ?? getenv('OPENAI_BASE_URL');
$baseUrl = rtrim($baseUrl, '/');
if (!str_ends_with($baseUrl, '/v1')) {
    $baseUrl .= '/v1';
}

// Initialize the OpenAI client
$client = \OpenAI::factory()
    ->withApiKey($apiKey)
    ->withBaseUri($baseUrl)
    ->make();

// Define a simple user message to test the API
$prompt = "Describe a sunset over the ocean";

// Get response with specific parameters
$response = $client->chat()->create([
    'model' => 'gpt-4',
    'messages' => [['role' => 'user', 'content' => $prompt]],
    'temperature' => 0.7,  // Controls response creativity
    'max_tokens' => 100,   // Limits response length
    'presence_penalty' => 0.6,  // Encourages new topics
    'frequency_penalty' => 0.8  // Reduces repetition
]);

// Extract the AI's response from the API result
$reply = trim($response->choices[0]->message->content);

// Show both sides of the conversation
echo "Prompt: $prompt" . PHP_EOL;
echo "Response: $reply" . PHP_EOL;
?>

In this example, we use all four parameters to customize the AI's response. By adjusting these parameters, you can fine-tune the chatbot's behavior to meet your specific requirements. When you run this code, you should see a response that reflects the balance of creativity, length, and content diversity that you've set.