Download the PHP package fholbrook/php-openrouter-client without Composer

PHP OPENROUTER CLIENT

This package provides an easy-to-use interface for integrating OpenRouter into your PHP applications. OpenRouter is a unified interface for Large Language Models (LLMs) that allows you to interact with various AI models through a single API.

Table of Contents

• Installation
• Requirements
• Configuration
• Usage
  • Understanding ChatRequest DTO
    • LLM Parameters
    • Function-calling
    • Additional Optional Parameters
    • OpenRouter-only Parameters
  • Understanding the Chat DTO
  • Understanding the Message DTO
  • Creating a ChatRequest
  • Maintaining Conversation Continuity
  • Serialization/Deserialization
  • Structured Output
  • Function Calling
• Contributing
• License

Special thanks to Moe Mizrak for his work on laravel-openrouter. This package is a derivative of his work.

Installation

Install via Composer:

Requirements

This is a low dependency package, but you need to ensure that your environment meets the following requirements:

• PHP 8.2 or higher: Use version v0.1.x (latest compatible version)
• ext-json: Required for JSON serialization
• ext-fileinfo: Required for file uploads

Configuration

First, construct your configuration class and pass it to the client class:

If you're using symfony, you can configure the OpenRouterConfig as a service in your services.yaml file:

Usage

This package facilitates several patterns, it's up to you to choose the one that best fits your application. The DTO objects provided the package are used to structure requests to OpenRouter and responses from OpenRouter.

Understanding ChatRequest DTO

The ChatRequest class is used to encapsulate the data required for making chat requests to the OpenRouter API. Here's a breakdown of the key properties:

• chat (Chat|null): The Chat object contains an array of Messages objects representing the chat messages. If chat is provided, prompt is ignored.
• prompt (string|null): A string representing the prompt for the chat request.
• model (string|null): The name of the model to be used for the chat request. If not specified, the user's default model will be used. This field is XOR-gated with the models field.
• response_format (ResponseFormatData|null): An instance of the ResponseFormat class representing the desired format for the response.
• stop (array|string|null): A value specifying the stop sequence for the chat generation.
• stream (bool|null): A boolean indicating whether streaming should be enabled or not.
• include_reasoning (bool|null): Whether to return the model's reasoning.

  LLM Parameters

  These properties control various aspects of the generated response (more info):

• max_tokens (int|null): The maximum number of tokens that can be generated in the completion. Default is 1024.
• temperature (float|null): A value between 0 and 2 controlling the randomness of the output.
• top_p (float|null): A value between 0 and 1 for nucleus sampling, an alternative to temperature sampling.
• top_k (float|null): A value between 1 and infinity for top-k sampling (not available for OpenAI models).
• frequency_penalty (float|null): A value between -2 and 2 for penalizing new tokens based on their existing frequency.
• presence_penalty (float|null): A value between -2 and 2 for penalizing new tokens based on whether they appear in the text so far.
• repetition_penalty (float|null): A value between 0 and 2 for penalizing repetitive tokens.
• seed (int|null): A value for deterministic sampling (OpenAI models only, in beta).

  Function-calling

• tool_choice (string|array|null): A value specifying the tool choice for function calling.
• tools (array|null): An array of ToolCall objects for function calling.

  Additional optional parameters

• logit_bias (array|null): An array for modifying the likelihood of specified tokens appearing in the completion.

  OpenRouter-only parameters

• transforms (array|null): An array for configuring prompt transforms.
• models (array|null): An array of models to automatically try if the primary model is unavailable. This field is XOR-gated with the model field.
• route (string|null): A value specifying the route type (e.g., RouteType::FALLBACK).
• provider (ProviderPreferencesData|null): An instance of the ProviderPreferences DTO object for configuring provider preferences.

Understanding the Chat DTO

The Chat class is used to model a chat conversation between the user and the AI. It contains the following properties:

• messages (Message[]): An array of Message objects representing the chat messages.
• id (string|null): The implementors ID of the chat conversation. This field is here for convenience.

Understanding Message DTO

The Message class is used to model a back-and-forth conversation between the user and the AI. It contains the following properties:

• role (string): The role of the message such as user, assistant, system, tool. See RoleType.
• content (string|array|ImageContent[]|TextContent[]): The content of the message. This can be a string or an array of content parts. See ImageContent.
• name (string|null): The name of the user to enable personalized messages.
• stamps (StampInterface[]): An array of stamps on the message, this is metadata about the message.

Creating a ChatRequest

This is a sample ChatRequest instance:

You can also create a ChatRequest instance using the Chat object:

Maintaining Conversation Continuity

If you want to maintain conversation continuity meaning that historical chat will be remembered and considered for your new chat request, you simply need to pass the Chat object on subsequent calls:

Serialization/Deserialization

At anytime you can store the chat object in whatever durable storage you prefer by serializing/deserializing it:

Structured Output

(Please also refer to OpenRouter Document Structured Output for models supporting structured output, also for more details)

If you want to receive the response in a structured format, you can specify the type property for response_format (ChatData object.

Additionally, it's recommended to set the require_parameters property for provider (ChatData object.

You can also specify the response_format as json_schema to receive the response in a specified schema format (Advisable to set 'strict' => true in json_schema array for strict schema):

[!TIP] You can also use prompt engineering to obtain structured output and control the format of responses.

Function Calling

You can also use the tool_choice and tools properties to allow the LLM to call tools. The tool_choice property can be set to auto or manual to automatically or manually select the tool to use. The tools property is an array of ToolCall objects that specify the tool to call and the parameters to pass to the tool

Here's how to define tools:

Contributing

We welcome contributions! If you'd like to improve this package, simply create a pull request with your changes. Your efforts help enhance its functionality and documentation.

License

PHP OpenRouter Client is an open-sourced software licensed under the MIT license.