Introduction
I’m thrilled to announce the release of TransformersPHP, a new library designed to seamlessly integrate machine learning
functionalities into PHP projects. As PHP continues to grow and evolve as a language, it opens up the
opportunity of using it for advanced features and capabilities outside the regular ones. Recognizing this, I’ve
developed TransformersPHP to bridge the gap between PHP and the powerful AI functionalities traditionally reserved for
Python environments.
What is TransformersPHP?
TransformersPHP is a library that aims to make the advanced capabilities of the Python-based Hugging Face’s Transformers
library accessible to PHP developers. It provides a toolkit for implementing machine learning models for tasks such as
text generation, classification, summarization, translation, and more, all within a PHP environment.
At its core, TransformersPHP leverages ONNX Runtime, a high-performance engine for running ONNX (Open Neural Network
Exchange) models. This enables PHP developers to utilize a wide range of pre-trained models across 100+ languages,
previously only available in Python, thus opening up a can of possibilities for PHP-based applications.
Key Features
Familiar API: Leverages a similar API to the Python Transformers and Xenova Transformers.js libraries, making it
easy to follow any previous guides or tutorials written for those libraries.
NLP Task Support: Currently supports all NLP tasks
including text classification, fill mask,
zero-shot classification, question answering,
token classification, feature extraction (embeddings),
translation, summarization,
and text generation.
Pre-trained Model Support: Provides access to a vast collection of pre-trained models from the Hugging Face Hub.
Easy Model Download and Management: Includes command-line tools for downloading and managing pre-trained models.
Custom Model Support: Supports using custom models converted from PyTorch, TensorFlow, or JAX into ONNX format.
Getting Started with TransformersPHP
Prerequisites
Before using TransformersPHP, ensure your system meets the following requirements:
PHP 8.1 or above
Composer (obviously)
PHP FFI extension
JIT compilation (optional, but recommended for performance improvement)
Increased memory limit (for advanced tasks like text generation)
Installation
Installation is straightforward with Composer:
After installation, initialize the package to download the necessary shared libraries for ONNX models:
Remember, the shared libraries are platform-specific so make sure to run the install command on the target platform
where
your code will be executed (eg inside the docker container)
Pre-Download Models
To avoid downloading the model on-the-fly when using it, pre-download the ONNX model weights from the Hugging Face model
hub. Use the command-line tool included with the package:
For example:
Example Usage
Here’s a simple example of how to use TransformersPHP for zero-shot classification:
$classifier = pipeline(‘zero-shot-classification’, ‘Xenova/mobilebert-uncased-mnli’);
$text = ‘I have a problem with my iphone that needs to be resolved asap!’;
$labels = [‘urgent’, ‘not urgent’, ‘phone’, ‘tablet’, ‘computer’];
$result = $classifier($text, $labels, multiLabel: true);
And the output will be this:
“sequence” => “I have a problem with my iphone that needs to be resolved asap!”,
“labels” => [“urgent”, “phone”, “computer”, “tablet”, “not urgent”],
“scores” => [0.99588709563603, 0.9923963400697, 0.0023335396113424, 0.0015134149376, 0.0010699384208377]
]
Example 2
Here’s another example for another task – token classification
$ner = pipeline(‘token-classification’, ‘codewithkyrian/bert-english-uncased-finetuned-pos’);
$output = $ner(‘My name is Kyrian and I live in Onitsha’, aggregationStrategy: ‘max’);
And the output will be:
[“entity_group” => “PRON”, “word” => “my”, “score” => 0.99482086393966],
[“entity_group” => “NOUN”, “word” => “name”, “score” => 0.95769686675798],
[“entity_group” => “AUX”, “word” => “is”, “score” => 0.97602109098715],
[“entity_group” => “PROPN”, “word” => “kyrian”, “score” => 0.96583783664597],
[“entity_group” => “CCONJ”, “word” => “and”, “score” => 0.98444884455349],
[“entity_group” => “PRON”, “word” => “i”, “score” => 0.99566682068677],
[“entity_group” => “VERB”, “word” => “live”, “score” => 0.98391136480035],
[“entity_group” => “ADP”, “word” => “in”, “score” => 0.99580186695928],
[“entity_group” => “PROPN”, “word” => “onitsha”, “score” => 0.91250281394515],
]
Learn More
For detailed information on installation, model conversion, and usage of TransformersPHP, head over to
the comprehensive documentation. You can also check
out the package GitHub repository and leave some stars ⭐️
I’m excited to see how the PHP community uses TransformersPHP to push the boundaries of what’s possible in web
development and beyond.
