PHP download

Download the PHP package tenqz/ollama without Composer

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

Table of contents
Download tenqz/ollama
More information about tenqz/ollama
Files in tenqz/ollama

Vendor tenqz
Package ollama
Short Description Php library for working with Ollama server.
License MIT

Keywords php api client ai llm ollama large-language-models

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 tenqz/ollama

Informations about the package ollama

Ollama PHP Client Library

Documentation for version v0.6.0

About

Ollama PHP Client Library is a robust, well-designed PHP client for interacting with the Ollama API. This library allows PHP developers to easily integrate large language models (LLMs) into their applications using the Ollama server.

Features

Clean, domain-driven architecture with clear separation of concerns
Comprehensive Ollama API support including text generation and embeddings
Type-safe request and response handling with full DTO support
Text generation with advanced options (temperature, top-k, top-p, repetition penalty, and more)
Text embeddings for semantic search, similarity, and vector operations
Multimodal support for image inputs with base64-encoded images
Streaming support for real-time text generation
Flexible configuration with customizable timeouts and connection settings
PSR standards compliance with proper interfaces and abstractions
Comprehensive test coverage with 97+ unit tests for embeddings alone

Installation

You can install the package via composer:

Requirements

PHP 7.2 or higher (supports PHP 8.0+ features)
cURL extension for HTTP communication
JSON extension for data serialization
Ollama server running locally or remotely

Usage

Text Generation

Text Embeddings

Architecture

The library follows Domain-Driven Design principles with a clear separation of concerns across multiple layers:

Transport Layer

TransportClientInterface - Interface for HTTP clients with GET/POST methods
ResponseInterface - Interface for API responses with status and data access
CurlTransportClient - cURL implementation with configurable timeouts and headers
JsonResponse - JSON response implementation with data parsing

Generation Layer (Text Generation)

GenerationRequest - Request DTO with prompts, options, images, streaming, templates
GenerationOptions - Fine-grained control (temperature, top-k, top-p, repetition penalty, etc.)
GenerationResponse - Response DTO with generated text and metadata
GenerationClientInterface - Client interface for generation operations
OllamaGenerationClient - Implementation with error handling and response transformation
GenerationException - Domain-specific exception for generation errors

Embedding Layer (Text Embeddings)

EmbeddingRequest - Request DTO with model and input text
EmbeddingResponse - Response DTO with embedding vectors (supports batch processing)
EmbeddingClientInterface - Client interface for embedding operations
OllamaEmbeddingClient - Implementation with error handling and vector processing
EmbeddingException - Domain-specific exception for embedding errors

Shared Layer

OllamaServerConfig - Server configuration with host, port, and URL building
OllamaApiEndpoints - API endpoint constants (/api/generate, /api/embed)
Cross-cutting concerns and utilities used across domains

Advanced Features

Generation Options

The library supports comprehensive generation options for fine-tuning model behavior:

Sampling Parameters:

temperature (0.0-1.0) - Controls randomness (higher = more creative)
top_k (1-100) - Limits vocabulary diversity
top_p (0.0-1.0) - Nucleus sampling for focused responses
seed (integer) - Deterministic outputs for reproducible results

Generation Control:

num_predict (integer) - Maximum tokens to generate
repeat_penalty (float) - Penalty for repetition
stop (array) - Stop sequences to end generation

Advanced:

stream (boolean) - Real-time streaming responses
format (string) - Output format (e.g., 'json')
system (string) - System message for role definition
images (array) - Base64-encoded images for multimodal models
keep_alive (string/int) - Model persistence duration

Embedding Features

The Embedding layer supports:

Request Options:

model (string) - Embedding model name (e.g., nomic-embed-text:latest)
input (string) - Text to generate embeddings for
options (array) - Additional model parameters
keep_alive (string/int) - Model persistence duration

Response Data:

embeddings (array) - Array of embedding vectors (supports batch processing)
dimension (int) - Vector dimension (e.g., 768)
model (string) - Model name used
Performance metrics: total_duration, load_duration, prompt_eval_count

Methods:

getEmbedding() - Get first embedding vector (single text)
getEmbeddings() - Get all embedding vectors (batch processing)
getDimension() - Get vector dimension
getCount() - Get number of embeddings

Development

The library includes comprehensive development tools:

License

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

All versions of ollama with dependencies

PHP Build Version

Package Version

Version v0.6.0 Release 07. Oct 2025
create-project require 0 people chose require and
0 people chose create-project.

Download

Download latest version of ollama from vendor tenqz

Requires php Version ^7.2|^8.0
ext-curl Version *
ext-json Version *

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 tenqz/ollama contains the following files

Loading the files please wait ...