kingozorg / open-ai

A PHP SDK for accessing the OpenAI GPT-3 API

Home Page:https://packagist.org/packages/orhanerday/open-ai

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

OpenAI GPT-3 Api Client in PHP

Latest Version on Packagist Total Downloads



orhanerday-open-ai-logo




For more information, you can read laravel news blog post.

To get started with this package, you'll first want to be familiar with the OpenAI API documentation and examples.

News

orhanerday/open-ai added to community libraries php section.

Installation

You can install the package via composer:

composer require orhanerday/open-ai

Quick Start

<?php

require __DIR__ . '/vendor/autoload.php'; // remove this line if you use a PHP Framework.

use Orhanerday\OpenAi\OpenAi;

$open_ai = new OpenAi('sk-gjtv.....');

$complete = $open_ai->complete([
    'engine' => 'davinci',
    'prompt' => 'Hello',
    'temperature' => 0.9,
    'max_tokens' => 150,
    'frequency_penalty' => 0,
    'presence_penalty' => 0.6,
]);

var_dump($complete);

Usage

Load your key from an environment variable.

According to the following code $open_ai is the base variable for all open-ai operations.

use Orhanerday\OpenAi\OpenAi;

$open_ai = new OpenAi(env('OPEN_AI_API_KEY'));

Completions

Given a prompt, the model will return one or more predicted completions, and can also return the probabilities of alternative tokens at each position.

$complete = $open_ai->complete([
   'engine' => 'davinci',
   'prompt' => 'Hello',
   'temperature' => 0.9,
   'max_tokens' => 150,
   'frequency_penalty' => 0,
   'presence_penalty' => 0.6,
]);

Searches

Given a query and a set of documents or labels, the model ranks each document based on its semantic similarity to the provided query.

$search = $open_ai->search([
    'engine' => 'ada',
    'documents' => ['White House', 'hospital', 'school'],
    'query' => 'the president',
]);

Answers

Given a question, a set of documents, and some examples, the API generates an answer to the question based on the information in the set of documents. This is useful for question-answering applications on sources of truth, like company documentation or a knowledge base.

$answer = $open_ai->answer([
  'documents' => ['Puppy A is happy.', 'Puppy B is sad.'],
  'question' => 'which puppy is happy?',
  'search_model' => 'ada',
  'model' => 'curie',
  'examples_context' => 'In 2017, U.S. life expectancy was 78.6 years.',
  'examples' => [['What is human life expectancy in the United States?', '78 years.']],
  'max_tokens' => 5,
  'stop' => ["\n", '<|endoftext|>'],
]);

Classifications

Given a query and a set of labeled examples, the model will predict the most likely label for the query. Useful as a drop-in replacement for any ML classification or text-to-label task.

$classification = $open_ai->classification([
   'examples' => [
       ['A happy moment', 'Positive'],
       ['I am sad.', 'Negative'],
       ['I am feeling awesome', 'Positive'],
   ],
   'labels' => ['Positive', 'Negative', 'Neutral'],
   'query' => 'It is a raining day =>(',
   'search_model' => 'ada',
   'model' => 'curie',
]);

Content Moderations

Given a input text, outputs if the model classifies it as violating OpenAI's content policy.

$flags = $open_ai->moderation([
    'input' => 'I want to kill them.'
]);

Know more about Content Moderations here: OpenAI Moderations

List engines

Lists the currently available engines, and provides basic information about each one such as the owner and availability.

$engines = $open_ai->engines();

Files

Files are used to upload documents that can be used across features like Answers, Search, and Classifications

List files

Returns a list of files that belong to the user's organization.

$files = $open_ai->listFiles();

Upload file

Upload a file that contains document(s) to be used across various endpoints/features. Currently, the size of all the files uploaded by one organization can be up to 1 GB. Please contact OpenAI if you need to increase the storage limit.

$c_file = curl_file_create(__DIR__ . 'files/sample_file_1.jsonl');
$result = $open_ai->uploadFile([
            "purpose" => "answers",
            "file" => $c_file,
]);

Upload file with HTML Form

<form action="index.php" method="post" enctype="multipart/form-data">
    Select file to upload:
    <input type="file" name="fileToUpload" id="fileToUpload">
    <input type="submit" value="Upload File" name="submit">
</form>
<?php
require __DIR__ . '/vendor/autoload.php';

use Orhanerday\OpenAi\OpenAi;

if ($_SERVER['REQUEST_METHOD'] == 'POST') {
    ob_clean();
    $open_ai = new OpenAi('YOUR_API_KEY');
    $tmp_file = $_FILES['fileToUpload']['tmp_name'];
    $file_name = basename($_FILES['fileToUpload']['name']);
    $c_file = curl_file_create($tmp_file, $_FILES['fileToUpload']['type'], $file_name);

    echo "[";
    echo $open_ai->uploadFile(
        [
            "purpose" => "answers",
            "file" => $c_file,
        ]
    );
    echo ",";
    echo $open_ai->listFiles();
    echo "]";

}

Delete file

$result = $open_ai->deleteFile('file-xxxxxxxx');

Retrieve file

$file = $open_ai->retrieveFile('file-xxxxxxxx');

Fine-tunes

Manage fine-tuning jobs to tailor a model to your specific training data.

Create fine-tune

$result = $open_ai->createFineTune([
       "training_file" => "file-U3KoAAtGsjUKSPXwEUDdtw86",
]);

List fine-tune

$fine_tunes = $open_ai->listFineTunes();

Retrieve fine-tune

$fine_tune = $open_ai->retrieveFineTune('ft-AF1WoRqd3aJAHsqc9NY7iL8F');

Cancel fine-tune

$result = $open_ai->cancelFineTune('ft-AF1WoRqd3aJAHsqc9NY7iL8F');

List fine-tune events

$fine_tune_events = $open_ai->listFineTuneEvents('ft-AF1WoRqd3aJAHsqc9NY7iL8F');

Delete fine-tune model

$result = $open_ai->deleteFineTune('curie:ft-acmeco-2021-03-03-21-44-20');

Retrieve engine

Retrieves an engine instance, providing basic information about the engine such as the owner and availability.

$engine = $open_ai->engine('davinci');

Printing results i.e. $search

echo $search;

Testing

composer test

Changelog

Please see CHANGELOG for more information on what has changed recently.

Contributing

Please see CONTRIBUTING for details.

Security Vulnerabilities

Please report security vulnerabilities to orhanerday@gmail.com

Credits

License

The MIT License (MIT). Please see License File for more information.

Donation

Buy Me A Coffee

About

A PHP SDK for accessing the OpenAI GPT-3 API

https://packagist.org/packages/orhanerday/open-ai

License:MIT License


Languages

Language:PHP 100.0%