How to Install Neuron AI and Build Your First Agent in a Webman PHP App

This guide walks you through installing the Webman framework, adding the Neuron AI package via Composer, generating a custom Agent class, configuring its provider with an API key, and interacting with the agent through a controller to receive responses from a large language model.

Open Source Tech Hub
Open Source Tech Hub
Open Source Tech Hub
How to Install Neuron AI and Build Your First Agent in a Webman PHP App

Chapter Introduction

This section explains how to install Neuron AI in a Webman application and create an Agent.

Requirements

PHP ^8.4

Composer ^2.0

Installation

Run the following Composer commands to install the latest versions.

Install Webman framework

Official documentation: https://www.workerman.net/doc/webman/install.html

# Default interactive installer
composer create-project workerman/webman:~2.0

# Disable interactive installer (used in this guide)
composer create-project workerman/webman:~2.0 --no-interaction neuron.ai.tinywan.com

Install Neuron framework

composer require neuron-core/neuron-ai

Create an Agent

Use the command below to generate your first Agent class.

./vendor/bin/neuron make:agent app\
euron\\ZaiAgent

The generated class looks like the following:

<?php
/**
 * @desc ZaiAgent
 * @author Tinywan(ShaoBo Wan)
 */
declare(strict_types=1);

namespace app
euron;

use NeuronAI\Agent\Agent;
use NeuronAI\Agent\SystemPrompt;
use NeuronAI\Providers\AIProviderInterface;
use NeuronAI\Providers\ZAI\ZAI;

class ZaiAgent extends Agent
{
    protected function provider(): AIProviderInterface
    {
        return new ZAI(
            key: "sk-xxxx",
            model: "glm-5",
            parameters: [], // Add custom params (temperature, logprobs, etc)
        );
    }

    public function instructions(): string
    {
        return (string) new SystemPrompt(
            background: [
                "你是由开源技术小栈开发的 Agent。",
            ],
        );
    }
}

Obtain an API key at https://bigmodel.cn/usercenter/proj-mgmt/apikeys

Chat with the Agent

Send a prompt to the Agent and retrieve the LLM response:

<?php
/**
 * @desc ZaiAgent
 * @author Tinywan(ShaoBo Wan)
 */
declare(strict_types=1);

namespace app\controller;

use support\Request;
use NeuronAI\Chat\Messages\UserMessage;

class IndexController
{
    public function index(Request $request)
    {
        $message = \app
euron\ZaiAgent::make()
            ->chat(new UserMessage('你是是大模型?'))
            ->getMessage();
        return $message->getContent();
    }
}
LLMAgentPHPComposerWebmanNeuron AI
Open Source Tech Hub
Written by

Open Source Tech Hub

Sharing cutting-edge internet technologies and practical AI resources.

0 followers
Reader feedback

How this landed with the community

Sign in to like

Rate this article

Was this worth your time?

Sign in to rate
Discussion

0 Comments

Thoughtful readers leave field notes, pushback, and hard-won operational detail here.