README

This package simplifies your interaction with various GPT models, eliminating the need for tokens or other methods to access GPT. It also allows you to use three artificial intelligences to generate images: DALL·E, Prodia, and more, some of which are premium while others are free, all of this without restrictions or limits.

Installation

You can install the package via Composer

  composer require yandricr/gpti-php

Available Models

GPTI provides access to a variety of artificial intelligence models to meet various needs. Currently, the available models include:

ChatGPT
GPT-3.5-Turbo
ChatGPT Web
GPT-4o
Bing
LLaMA-3.1
Blackbox
AI Images

Api key

If you want to access the premium models, enter your credentials. You can obtain them by clicking here.

require "./vendor/autoload.php";

use gpti\...; // select model

$res = new ...();
$res->setAPI(user:"user-xxxxxxxx", secret:"nx-xxxxxxx-xxxxx-xxxxx");

Usage GPT

require "./vendor/autoload.php";

use gpti\gpt;

$res = new gpt(messages:array(
    [
        "role" => "assistant",
        "content" => "Hello! How are you today?"
    ],
    [
        "role" => "user",
        "content" => "Hello, my name is Yandri."
    ],
    [
        "role" => "assistant",
        "content" => "Hello, Yandri! How are you today?"
    ]
), prompt:"Can you repeat my name?", model:"GPT-4", markdown:false);
$res->execute();

if($res->error() != null){
    print(json_encode($res->error()));
} else {
    print(json_encode($res->result()));
}

Models

Select one of these available models in the API to enhance your experience.

gpt-4
gpt-4-0613
gpt-4-32k
gpt-4-0314
gpt-4-32k-0314
gpt-3.5-turbo
gpt-3.5-turbo-16k
gpt-3.5-turbo-0613
gpt-3.5-turbo-16k-0613
gpt-3.5-turbo-0301
text-davinci-003
text-davinci-002
code-davinci-002
gpt-3
text-curie-001
text-babbage-001
text-ada-001
davinci
curie
babbage
ada
babbage-002
davinci-002

Usage GPT v2

It's quite similar, with the difference that it has the capability to generate real-time responses via streaming using gpt-3.5-turbo.

require "./vendor/autoload.php";

use gpti\gptturbo;

$res = new gptturbo(messages:array(
    [
        "role" => "assistant",
        "content" => "Hello! How are you today?"
    ],
    [
        "role" => "user",
        "content" => "Hello, my name is Yandri."
    ],
    [
        "role" => "assistant",
        "content" => "Hello, Yandri! How are you today?"
    ],
    [
        "role" => "user",
        "content" => "Can you repeat my name?"
    ]
), markdown:false, stream:false);
$res->execute();

if($res->error() != null){
    print(json_encode($res->error()));
} else {
    print(json_encode($res->result()));
}

Usage GPT v2 Streaming

require "./vendor/autoload.php";

use gpti\gptturbo;

$res = new gptturbo(messages:array(
    [
        "role" => "assistant",
        "content" => "Hello! How are you today?"
    ],
    [
        "role" => "user",
        "content" => "Hello, my name is Yandri."
    ],
    [
        "role" => "assistant",
        "content" => "Hello, Yandri! How are you today?"
    ],
    [
        "role" => "user",
        "content" => "Can you repeat my name?"
    ]
), markdown:false, stream:true);
$res->execute();

if($res->error() != null){
    print(json_encode($res->error()));
} else {
    foreach($res->stream() as $data){
        print(json_encode($data));
    }
}

Usage GPT Web

GPT-4 has been enhanced by me, but errors may arise due to technological complexity. It is advisable to exercise caution when relying entirely on its accuracy for online queries.

require "./vendor/autoload.php";

use gpti\gptweb;

$res = new gptweb(prompt:"Are you familiar with the movie Wonka released in 2023?", markdown:false);
$res->execute();

if($res->error() != null){
    print(json_encode($res->error()));
} else {
    print(json_encode($res->result()));
}

Usage GPT-4o

require "./vendor/autoload.php";

use gpti\gpt4o;

$res = new gpt4o(messages:array(
    [
        "role" => "assistant",
        "content" => "Hello! How are you today?"
    ],
    [
        "role" => "user",
        "content" => "Hello, my name is Yandri."
    ],
    [
        "role" => "assistant",
        "content" => "Hello, Yandri! How are you today?"
    ],
    [
        "role" => "user",
        "content" => "Can you repeat my name?"
    ]
), markdown:false, stream:false);
$res->execute();

if($res->error() != null){
    print(json_encode($res->error()));
} else {
    print(json_encode($res->result()));
}

Usage GPT-4o Streaming

require "./vendor/autoload.php";

use gpti\gpt4o;

$res = new gpt4o(messages:array(
    [
        "role" => "assistant",
        "content" => "Hello! How are you today?"
    ],
    [
        "role" => "user",
        "content" => "Hello, my name is Yandri."
    ],
    [
        "role" => "assistant",
        "content" => "Hello, Yandri! How are you today?"
    ],
    [
        "role" => "user",
        "content" => "Can you repeat my name?"
    ]
), markdown:false, stream:true);
$res->execute();

if($res->error() != null){
    print(json_encode($res->error()));
} else {
    foreach($res->stream() as $data){
        print(json_encode($data));
    }
}

Usage Bing

require "./vendor/autoload.php";

use gpti\bing;

$res = new bing(messages:array(
    [
        "role" => "assistant",
        "content" => "Hello! How can I help you today? 😊"
    ],
    [
        "role" => "user",
        "content" => "Hi, tell me the names of the movies released in 2023."
    ]
), conversation_style:"Balanced", markdown:false, stream:false);
$res->execute();

if($res->error() != null){
    print(json_encode($res->error()));
} else {
    print(json_encode($res->result()));
}

Usage Bing Streaming

require "./vendor/autoload.php";

use gpti\bing;

$res = new bing(messages:array(
    [
        "role" => "assistant",
        "content" => "Hello! How can I help you today? 😊"
    ],
    [
        "role" => "user",
        "content" => "Hi, tell me the names of the movies released in 2023."
    ]
), markdown:false, stream:true);
$res->execute();

if($res->error() != null){
    print(json_encode($res->error()));
} else {
    foreach($res->stream() as $data){
        print(json_encode($data));
    }
}

Parameters

Usage LLaMA 3.1

require "./vendor/autoload.php";

use gpti\llama;

$res = new llama(messages:array(
    [
        "role" => "user",
        "content" => "Hello, my name is Yandri."
    ]
), conversation_style:"Balanced", markdown:false, stream:false);
$res->execute();

if($res->error() != null){
    print(json_encode($res->error()));
} else {
    print(json_encode($res->result()));
}

Usage LLaMA 3.1 Streaming

require "./vendor/autoload.php";

use gpti\llama;

$res = new llama(messages:array(
    [
        "role" => "user",
        "content" => "Hello, my name is Yandri."
    ]
), markdown:false, stream:true);
$res->execute();

if($res->error() != null){
    print(json_encode($res->error()));
} else {
    foreach($res->stream() as $data){
        print(json_encode($data));
    }
}

Usage blackbox

require "./vendor/autoload.php";

use gpti\blackbox;

$res = new blackbox(messages:array(
    [
        "role" => "user",
        "content" => "Hello, my name is Yandri."
    ]
), conversation_style:"Balanced", markdown:false, stream:false);
$res->execute();

if($res->error() != null){
    print(json_encode($res->error()));
} else {
    print(json_encode($res->result()));
}

Usage Blackbox Streaming

require "./vendor/autoload.php";

use gpti\blackbox;

$res = new blackbox(messages:array(
    [
        "role" => "user",
        "content" => "Hello, my name is Yandri."
    ]
), markdown:false, stream:true);
$res->execute();

if($res->error() != null){
    print(json_encode($res->error()));
} else {
    foreach($res->stream() as $data){
        print(json_encode($data));
    }
}

AI Images

Check the documentation here to learn how to use the different image generation models.

require "./vendor/autoload.php";

use gpti\imageai;

$res = new imageai(prompt:"cat color red", model:"dalle", response:"url", data:[]);
$res->execute();

if($res->error() != null){
    print(json_encode($res->error()));
} else {
    print(json_encode($res->result()));
}

API Reference

Currently, some models require your credentials to access them, while others are free. For more details and examples, please refer to the complete documentation.

Code Errors

These are the error codes that will be presented in case the API fails.

yandricr / gpti-php

Maintainers

Details