README

This library provides a single, unified, framework-independent library for integration with several popular AI platforms and large language models.

Installation

Install the library using Composer:

composer require 1tomany/llm-sdk

Usage

There are two ways to use this library:

Direct Instantiate the AI client you wish to use and send a request object to it. This method is easier to use, but comes with the cost that your application will be less flexible and testable.
Actions Register the clients you wish to use with a OneToMany\LlmSdk\Factory\ClientFactory instance, inject that instance into each action you wish to take, and interact with the action instead of through the client.

Note: A Symfony bundle is available if you wish to integrate this library into your Symfony applications with autowiring and configuration support.

I learn best by looking at actual code samples, so lets take a look at the two methods first.

Examples

examples/files/upload.php Uploads a file to an LLM vendor
examples/queries/embed.php Embeds content to a high dimensionality vector
examples/queries/generate.php Generates output from a prompt sent to an LLM

Supported platforms

Anthropic
Gemini
Mock
OpenAI

Platform feature support

Note: Each platform refers to running model inference differently; OpenAI uses the word "Responses" while Gemini uses the word "Content". I've decided the word "Query" is the most succinct term to describe interacting with an LLM. The "Embeddings" and "Queries" sections below refers to the ability to compile a query and use it to generate output from an LLM.

Feature	Anthropic	Gemini	Mock	OpenAI
Batches
Create	❌	✅	✅	✅
Read	❌	✅	✅	✅
Cancel	❌	❌	❌	❌
Embeddings
Compile	❌	✅	✅	✅
Embed Content	❌	✅	✅	✅
Files
Upload	✅	✅	✅	✅
Read	❌	❌	❌	❌
List	❌	❌	❌	❌
Download	❌	❌	❌	❌
Delete	✅	✅	✅	✅
Queries
Compile	❌	✅	✅	✅
Generate Output	❌	✅	✅	✅

Credits

Vic Cherubini, 1:N Labs, LLC

License

The MIT License

1tomany / llm-sdk

Maintainers

Package info

Statistics

Security