Download the PHP package evoware/ollama-php without Composer
On this page you can find all versions of the php package evoware/ollama-php. It is possible to download/install these versions without Composer. Possible dependencies are resolved automatically.
Download evoware/ollama-php
More information about evoware/ollama-php
Files in evoware/ollama-php
Package ollama-php
Short Description A PHP library for interacting with local Ollama server.
License GPL-3.0-or-later
FAQ
Example:
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 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.
Informations about the package ollama-php
Ollama PHP
A comprehensive PHP library designed for seamless interaction with the Ollama server, facilitating a range of operations from generating text completions to managing models and producing embeddings.
But what's Ollama? Ollama is a tool for running open-source Large Language Models locally. You can find more information about Ollama directly at the project repository or documentation page.
Installation
To integrate the Ollama PHP Adapter into your project, use Composer for a smooth installation process:
Usage:
The Ollama PHP Adapter simplifies the complexity of interacting with the Ollama server, providing intuitive methods for various functionalities.
Generating Text Completions
Generate text completions by providing a prompt to the model. Access the completion text using the getResponse() method:
Interacting with models:
Manage your local models by listing, pulling, and interacting through the provided methods:
To learn more about model file format, please visit Ollama Model File documentation here.
Generating embeddings:
Produce embeddings for a given text, returning an array of embedding data through the EmbeddingsResponse object:
Response Types
The adapter delineates responses into specific object types for clarity and ease of use:
- CompletionResponse: Handles the data from text completion requests.
- ChatCompletionResponse: Manages chat completion data.
- EmbeddingsResponse: Encapsulates embedding data.
- ModelOperationResponse: Represents the outcome of model operations (create, delete, pull, etc.).
Responses provide access to the underlying Guzzle Response via the getHttpResponse() method for further customization and handling.
Roadmap
- Handling streaming responses.
- Introduction of ChatSession class for storing chat context in a styructured manner.
- Laravel facade support
Caution
⚠️ Development Stage: This project is in its early development stages and is not recommended for production environments. It is provided as-is, without any guarantees. Proceed with caution and use at your own risk. ⚠️
