Agents

Agents are the foundation of LarAgent. They define how your AI assistant behaves, what tools it can use, and how it processes information.

Creating an Agent

You can create a new agent manually by extending the LarAgent\Agent class. This is the parent class for building your custom AI agent with specific capabilities and behaviors.

Using make:agent command is a recommended way of creating agents.

namespace App\AiAgents;

use LarAgent\Agent;

class MyAgent extends Agent
{
    // Your agent implementation
}

For rapid development, you can use the artisan command to generate a new agent with a basic structure:

php artisan make:agent MyAgent

This will create a new agent class in the App\AiAgents directory with all the necessary boilerplate code:

YourAgentName.php

<?php

namespace App\AiAgents;

use LarAgent\Agent;

class YourAgentName extends Agent
{
    protected $model = 'gpt-4o-mini';

    protected $history = 'in_memory';

    protected $provider = 'default';

    protected $tools = [];

    public function instructions()
    {
        return "Define your agent's instructions here.";
    }

    public function prompt($message)
    {
        return $message;
    }
}

Configuring an Agent

Agents can be configured through various properties and methods to customize their behavior. Here are the core configuration options:

Core methods

The agent also provides several core methods that you can override to customize its behavior:


// Define the agent's system instructions
// This sets the behavior, role, and capabilities of your agent
// For simple textual instructions, use the `instructions` property
// For more complex instructions or dynamic behavior, use the `instructions` method
public function instructions()
{
    return "Define your agent's instructions here.";
}

Properties

Instructions

/** @var string - Define the agent's behavior and role */
protected $instructions;

This property sets the system instructions for your agent, defining its behavior, personality, and capabilities.

// Example
protected $instructions = "You are a helpful assistant specialized in weather forecasting.";

History

/** @var string - Choose from built-in chat history types */
protected $history;

Choose from built-in chat history implementations: “in_memory”, “session”, “cache”, “file”, or “json”.

// Example
protected $history = 'cache';

// Or use a class
protected $history = \LarAgent\History\CacheChatHistory::class;

Driver

/** @var string - Specify which LLM driver to use */
protected $driver;

The driver class that handles communication with the AI provider.

// Example
protected $driver = \LarAgent\Drivers\OpenAi\OpenAiDriver::class;

Provider

/** @var string - Select the AI provider configuration */
protected $provider = 'default';

References a provider configuration from your config file.

// Example
protected $provider = 'openai-gpt4';

Model

/** @var string - Choose which language model to use */
protected $model = 'gpt-4o-mini';

The specific model to use from your chosen provider.

// Example
protected $model = 'gpt-4o';

Other properties

All config properties have relevant setter (chainable methods) you can use to set them at runtime. For example, $maxCompletionTokens -> maxCompletionTokens(int $tokens), $topP -> topP(float $topP) and etc.

All config properties can be defined by config file in provider settings. For example, $maxCompletionTokens -> max_completion_tokens => 2000 and etc.

Tokens

/** @var int - Set the maximum number of tokens in the completion */
protected $maxCompletionTokens;

Limits the length of the AI’s response.

// Example
protected $maxCompletionTokens = 2000;

Temperature

/** @var float - Control response creativity */
protected $temperature;

Controls randomness: 0.0 for focused responses, 2.0 for creative ones.

// Example
protected $temperature = 0.7; // Balanced

Message

/** @var string|null - Current message being processed */
protected $message;

n

/** @var int|null */
protected $n;

How many chat completion choices to generate for each input message. Note that you will be charged based on the number of generated tokens across all of the choices. Keep n as 1 to minimize costs.

In case of $n > 1, the agent will return an array of responses.

top_p

/** @var float|null */
protected $topP;

An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.

We generally recommend altering $topP or $temperature but not both.

frequency_penalty

/** @var float|null */
protected $frequencyPenalty;

Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model’s likelihood to repeat the same line verbatim.

presence_penalty

/** @var float|null */
protected $presencePenalty;

Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model’s likelihood to talk about new topics.

Using an Agent

There are two ways to interact with your agent: direct response or chainable methods.

Direct Response

The simplest way is to use the for() method to specify a chat history name and get an immediate response:

// Using a specific chat history name
echo WeatherAgent::for('test_chat')->respond('What is the weather like?');

Using Chainable Methods

For more control over the interaction, you can use the chainable syntax:

$response = WeatherAgent::for('test_chat')
    ->message('What is the weather like?')  // Set the message
    ->temperature(0.7)                      // Optional: Override temperature
    ->respond();                            // Get the response

Ready made user message

Instead of passing a string as a message, you can build your own UserMessage instance. It allows you to add metadata to the message, such as the user ID or request ID. Also, using different methods associated with UserMessage instance.

$userMessage = Message::user($finalPrompt, ['userRequest' => $userRequestId]);

$response = WeatherAgent::for('test_chat')->message($userMessage)->respond();

If you use UserMessage instance instead string, it will bypass the prompt method.

Return message

By default, respond method returns:

string with regular request
array of string if $n is greater than 1.
array Associative array of defined structured output schema.

You can change the return type by using returnMessage method or setting $returnMessage property to true, which will enforce respond method to return MessageInterface instance.

// Returns MessageInterface -> AssistantMessage instance
$response = WeatherAgent::for('test_chat')->returnMessage()->respond();

If returnMessage is true and structured output is defined, beforeStructuredOutput hook will not happen, because structured output is not processed to array.

Image input

You can pass publicly accessible image URLs to the agent as an array of strings.

$images = [
    'https://example.com/image.jpg',
    'https://example.com/image2.jpg',
];

$response = WeatherAgent::for('test_chat')->withImages($images)->respond();

Alternative way to pass images is to use base64 encoded data.

$imageUrls = [
    'data:image/jpeg;base64,' . base64_encode($img)
];

$response = ImageAgent::for('test')->withImages($imageUrls)->respond("Analyze images");

Base64 image input Contributed by havspect in issue #74.

Audio input

You can pass base64 encoded audio data to the agent as an array of arrays containing the format and data. Supported formats by OpenAI: “wav”, “mp3”, “ogg”, “flac”, “m4a”, “webm”

$audios = [
    [
        'format' => 'mp3',
        'data' => $base64Audio
    ]
];

echo WeatherAgent::for('test_chat')->withAudios($audios)->respond();

Agent Mutators Reference

Here are some chainable methods to modify the agent’s behavior on the fly:

message() - Set the message

/**
 * Set the message for the agent to process
 */
public function message(string|UserMessage $message);

Sets the message that will be sent to the AI model.

// Example
$agent = WeatherAgent::for('test_chat');
$agent->message('What is the weather like today?')->respond();

withImages() - Add images

/**
 * Add images to the agent's input (message)
 * @param array $imageUrls Array of image URLs
 */
public function withImages(array $imageUrls);

Adds images to the message for multimodal models.

// Example
$agent->message('What's in this image?')
      ->withImages(['https://example.com/image.jpg'])
      ->respond();

withAudios() - Add audios

/**
 * Add audios to the agent's input (message)
 * Array of arrays: ['data' => 'base64', 'format' => 'wav']
 * Possible formats: "wav", "mp3", "ogg", "flac", "m4a", "webm"
 * @param array $audioStrings Array of audio data
 */
public function withAudios(array $audioStrings);

Adds audios to the message, use for multimodal models.

// Example
  $audios = [
      [
          'format' => 'mp3',
          'data' => $base64Audio
      ]
  ];
$agent->message('What's in this audio?')
      ->withAudios($audios)
      ->respond();

withModel() - Change model

/**
 * Decide model dynamically in your controller
 * @param string $model Model identifier (e.g., 'gpt-4o', 'gpt-3.5-turbo')
 */
public function withModel(string $model);

Overrides the default model for this specific call.

// Example
$agent->message('Complex question')
      ->withModel('gpt-4o')
      ->respond();

addMessage() - Add custom message

/**
 * @param MessageInterface 
 */
public function addMessage(MessageInterface $message);

Adds a custom message to the chat history. MessageInterface: Easily created with Message class: Message::system('Your message here') Use with caution, as it is added directly to the chat history and keep in mind that history needs to keep certain structure defined by openai.

// Example
use LarAgent\Message;

$agent->addMessage(Message::system('Remember to be concise'))
      ->message('Explain quantum computing')
      ->respond();

clear() - Clear history

setChatHistory() - Change history

/**
 * Set other chat history instance
 */
public function setChatHistory(ChatHistoryInterface $chatHistory);

Replaces the current chat history with a different instance.

// Example
$newHistory = new CacheChatHistory('backup-chat');
$agent->setChatHistory($newHistory)->respond('Continue from backup');

withTool() - Add tool

/**
 * Add tool to the agent's registered tools
 */
public function withTool(ToolInterface $tool);

Adds a tool for this specific call.

// Example
$weatherTool = new WeatherTool();
$agent->withTool($weatherTool)
      ->message("What's the weather in New York?")
      ->respond();

removeTool() - Remove tool

/**
 * Remove tool for this specific call
 */
public function removeTool(string $name);

Removes a tool for this specific call.

// Example
$agent->removeTool('get_weather')
      ->message('Tell me a story without checking the weather')
      ->respond();

temperature() - Adjust creativity

/**
 * Override the temperature for this specific call
 */
public function temperature(float $temp);

Controls the randomness of the response (0.0 for focused, 2.0 for creative).

// Example
$agent->temperature(1.5)  // More creative response
      ->message('Write a poem about AI')
      ->respond();

Agent Accessors Reference

You can access the agent’s properties using these methods on an instance of the agent:

getChatSessionId() - Get session ID

/**
 * Get the current chat session ID
 * String like "[AGENT_NAME]_[MODEL_NAME]_[CHAT_NAME]"
 * CHAT_NAME is defined by "for" method
 * Example: WeatherAgent_gtp-4o-mini_test-chat
 */
public function getChatSessionId(): string;

Returns the unique identifier for the current chat session.

// Example
$sessionId = $agent->getChatSessionId();
// Returns: "WeatherAgent_gtp-4o-mini_user-123"

getProviderName() - Get provider

/**
 * Returns the provider name
 */
public function getProviderName(): string;

Returns the name of the AI provider being used.

// Example
$provider = $agent->getProviderName();
// Returns: "openai" or other provider name

getTools() - Get tools

/**
 * Returns an array of registered tools
 */
public function getTools(): array;

Returns all tools registered with the agent.

// Example
$tools = $agent->getTools();
foreach ($tools as $tool) {
    echo $tool->getName() . "\n";
}

chatHistory() - Get history

/**
 * Returns current chat history instance
 */
public function chatHistory(): ChatHistoryInterface;

Returns the current chat history instance.

// Example
$history = $agent->chatHistory();
$messageCount = $history->count();

currentMessage() - Get current message

/**
 * Returns the current message
 */
public function currentMessage(): ?string;

Returns the message currently being processed.

// Example
$message = $agent->currentMessage();
if ($message) {
    echo "Processing: " . $message;
}

lastMessage() - Get last message

/**
 * Returns the last message
 */
public function lastMessage(): ?MessageInterface;

Returns the last message in the chat history.

// Example
$lastMessage = $agent->lastMessage();
if ($lastMessage) {
    echo "Last message role: " . $lastMessage->getRole();
    echo "Last message content: " . $lastMessage->getContent();
}

getChatKeys() - Get all chat keys

/**
 * Get all chat keys associated with this agent class
 */
public function getChatKeys(): array;

Returns all chat keys associated with this agent class.

// Example
$chatKeys = $agent->getChatKeys();
// Returns: ["user_1_chat", "user_2_chat", ...]

// You can use this to list all active conversations
foreach ($chatKeys as $key) {
    echo "Active chat: " . $key . "\n";
}

getModalities() - Get modalities

/**
 * Get all modalities associated with this agent class
 */
public function getModalities(): array;

Returns all modalities associated with this agent class.

// Example
$modalities = $agent->getModalities();
// Returns: ["text", "image", "audio"]

getAudio() - Get audio

/**
 * Get all audio associated with this agent class
 */
public function getAudio(): ?array;

Returns all audio associated with this agent class.

// Example
$audio = $agent->getAudio();
// Returns: null or array of audio data containing arrays of format and data
// [
//     [
//         'format' => 'mp3',
//         'data' => $base64Audio
//     ]
// ]

Example Configuration

class WeatherAgent extends Agent
{
    protected $model = 'gpt-4o';
    protected $history = 'session';
    protected $temperature = 0.7;
    
    public function instructions()
    {
        return "You are a weather expert assistant. Provide accurate weather information.";
    }
    
    public function prompt(string $message)
    {
        return "Weather query: " . $message;
    }
}

Get Started

Core concepts

Extensibility & Customization

Creating an Agent

Configuring an Agent

Core methods

Properties

Instructions

History

Driver

Provider

Model

Other properties

Tokens

Temperature

Message

n

top_p

frequency_penalty

presence_penalty

Using an Agent

Direct Response

Using Chainable Methods

Ready made user message

Return message

Image input

Audio input

Agent Mutators Reference

Agent Accessors Reference

Example Configuration

Get Started

Core concepts

Extensibility & Customization

​Creating an Agent

​Configuring an Agent

​Core methods

​Properties

​Instructions

​History

​Driver

​Provider

​Model

​Other properties

Tokens

Temperature

Message

n

top_p

frequency_penalty

presence_penalty

​Using an Agent

​Direct Response

​Using Chainable Methods

​Ready made user message

​Return message

​Image input

​Audio input

​Agent Mutators Reference

​Agent Accessors Reference

​Example Configuration

Creating an Agent

Configuring an Agent

Core methods

Properties

Instructions

History

Driver

Provider

Model

Other properties

Using an Agent

Direct Response

Using Chainable Methods

Ready made user message

Return message

Image input

Audio input

Agent Mutators Reference

Agent Accessors Reference

Example Configuration