Download the PHP package jooservices/laravel-embedding without Composer

On this page you can find all versions of the php package jooservices/laravel-embedding. It is possible to download/install these versions without Composer. Possible dependencies are resolved automatically.

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:
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.
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?

Example code of jooservices/laravel-embedding

Informations about the package laravel-embedding

JOOservices Laravel Embedding Library

A Laravel package for text chunking, Ollama-based embedding generation, optional persistence, and PostgreSQL pgvector similarity search.

Current runtime support is intentionally narrow:

Key Features

  1. Smart Context Chunking: Includes DefaultChunker, MarkdownChunker, SentenceChunker, and TokenBudgetChunker.
  2. Native PostgreSQL Vector Search: Uses pgvector cosine-distance operators (<=>) when your embedding store is PostgreSQL.
  3. Background Processing: Ships with queue-aware jobs plus configurable queue connection, queue name, retry/backoff, timeout, and overlap protection.
  4. Safer Re-Embedding: Can skip unchanged targets and replace persisted target sets only after successful generation.
  5. Flexible Targeting: Supports Eloquent-backed targets and non-Eloquent target_type / target_id references.
  6. Search Helpers: Supports metadata-aware filtering and a thin EmbeddingSearch service.

Quick Start

Please read the complete documentation available in the docs/ directory:

Basic Usage

PostgreSQL Notes

This package does not auto-create a pgvector ANN index because index strategy depends on your chosen model dimensions and operational preferences. Treat extension enablement and index creation as deployment decisions in the host application.

If you want the package migration to attempt CREATE EXTENSION vector, enable:

AI Agents & Development

This package contains strict documentation for external AI Agents (Cursor, Cline, Github Copilot). If you are an AI Agent building on top of this package, read the Skill sheet located at .agents/skills/laravel-embedding/SKILL.md.

All versions of laravel-embedding with dependencies

PHP Build Version
Package Version
Requires php Version ^8.5
illuminate/support Version ^11.0|^12.0
illuminate/database Version ^11.0|^12.0
illuminate/http Version ^11.0|^12.0
jooservices/dto Version ^1.0.3
Composer command for our command line client (download client) This client runs in each environment. You don't need a specific PHP version etc. The first 20 API calls are free. Standard composer command

The package jooservices/laravel-embedding contains the following files

Loading the files please wait ...