Download the PHP package b7s/neuraphp without Composer
On this page you can find all versions of the php package b7s/neuraphp. It is possible to download/install these versions without Composer. Possible dependencies are resolved automatically.
Vendor b7s
Package neuraphp
Short Description Local text embeddings via PHP FFI, powered by embedding.cpp. No Python, no API calls, no external services at runtime.
License MIT
Package neuraphp
Short Description Local text embeddings via PHP FFI, powered by embedding.cpp. No Python, no API calls, no external services at runtime.
License MIT
FAQ
After the download, you have to make one include require_once('vendor/autoload.php');. After that you have to import the classes with use statements.
Example:
Example:
If you use only one package a project is not needed. But if you use more then one package, without a project it is not possible to import the classes with use statements.
In general, it is recommended to use always a project to download your libraries. In an application normally there is more than one library needed.
In general, it is recommended to use always a project to download your libraries. In an application normally there is more than one library needed.
Some PHP packages are not free to download and because of that hosted in private repositories.
In this case some credentials are needed to access such packages.
Please use the auth.json textarea to insert credentials, if a package is coming from a private repository.
You can look here for more information.
- Some hosting areas are not accessible by a terminal or SSH. Then it is not possible to use Composer.
- To use Composer is sometimes complicated. Especially for beginners.
- Composer needs much resources. Sometimes they are not available on a simple webspace.
- If you are using private repositories you don't need to share your credentials. You can set up everything on our site and then you provide a simple download link to your team member.
- Simplify your Composer build process. Use our own command line tool to download the vendor folder as binary. This makes your build process faster and you don't need to expose your credentials for private repositories.
Please rate this library. Is it a good library?
Informations about the package neuraphp
# NeuraPHP
NeuraPHP brings local AI embeddings to PHP—no APIs, no subscriptions, no external services. Run fast, private, personalized text embeddings directly on your machine, saving money while keeping full control of your data. Simple to install, effortless to use, and built for real‑world PHP apps.
[](https://php.net)
[](LICENSE)
Features
- Local embeddings — No API calls, no network latency, no data leaving your server
- PHP FFI — Direct memory access to a C library, no separate process
- Fluent API —
Neuraphp::make()->model(ModelReference::fromEnum(Model::AllMiniLML12V2))->embed('text') - Multiple models — AllMiniLM-L6-v2, AllMiniLM-L12-v2, Paraphrase, BGE, E5, multilingual; or any BERT-compatible HuggingFace model
- Quantization — F32, F16, Q4_0, Q4_1 for speed/quality tradeoffs
- Vector math — Cosine similarity, dot product, Euclidean distance, L2 normalization
- CLI tools —
neuraphp installfor auto-setup,neuraphp doctorfor diagnostics,neuraphp infofor configuration - Laravel integration — Optional service provider and facade
- Framework-agnostic — Works with any PHP 8.3+ project
Docs: CLI Reference
Add to your project:
Quick Start
For more examples, custom models, batch embedding, and the full API, see the Advanced Guide
⚠️ Prerequisites: embedding.cpp Library & Model
Neuraphp requires
libbert_shared.so(compiled from embedding.cpp) and a GGUF model file to function.
Minimum versions required to compile the library:
| Tool | Min Version | Install |
|---|---|---|
| Git | 2.0+ | git-scm.com |
| CMake | 3.18+ | cmake.org |
| GNU Make | 3.81+ | sudo apt install build-essential / xcode-select --install |
| C++ compiler (g++/clang++) | GCC 10+ / Clang 10+ (C++20) | sudo apt install g++ / xcode-select --install |
| Rust (cargo) | 1.75+ | rustup.rs |
| Git LFS | 2.0+ | sudo apt install git-lfs / brew install git-lfs |
| Python | 3.8+ | (model conversion only) |
There are two ways to set these up:
Option A: Automatic Installation (Recommended)
Run the installation command - it clones, compiles, and downloads everything for you:
You need to run this command just once for each model you want to use. If you don't change the model, you don't need to re-run it.
This will:
- Check prerequisites (git, cmake, make, C++ compiler, Rust, git-lfs)
- Clone embedding.cpp into a temp directory and compile
libbert_shared.so - Download the default model (all-MiniLM-L6-v2) from HuggingFace
- Convert the model to GGUF format (requires Python 3.8+, torch, transformers)
- Copy only final artifacts to
bin/neuraphp-data/in your project root- Clean up temp files and create
bin/neuraphp-data/.gitignoreso artifacts are never committed
- Clean up temp files and create
Options:
Testing
License
MIT
All versions of neuraphp with dependencies
PHP Build Version
Package Version
The package b7s/neuraphp contains the following files
Loading the files please wait ...