openui-forge-php

Name: openui-forge-php
Author: OthmanAdi

1installs0forks

How to install openui-forge-php?

othmanadi/openui-forge/openui-forge-php

$npx -y skills add OthmanAdi/openui-forge --skill openui-forge-php

Installs into the current project.

Summary

OpenUI generative UI with a PHP (Laravel 13.x) backend. Forwards OpenAI's SSE stream verbatim via response()->stream().

Files · 1

View on GitHub

SKILL.md

1	# OpenUI Forge — PHP
2
3	Build generative UI apps with a React frontend + Laravel backend. Streams the OpenAI API's native SSE response straight through `response()->stream()`.
4
5	## Activation Triggers
6
7	- "openui php", "openui laravel", "openui php backend"
8	- "generative ui php", "laravel streaming ui backend"
9
10	## Prerequisites
11
12	- Node.js >= 22 (24 LTS recommended) + React >= 18.3.1 (19+ recommended) (frontend)
13	- PHP >= 8.3 + Laravel 13.x (backend; Laravel 13 requires PHP 8.3 minimum and supports 8.3 through 8.5)
14	- Composer; `guzzlehttp/guzzle` ships with Laravel and backs the `Http` facade (no extra dependency to call OpenAI)
15	- `OPENAI_API_KEY` environment variable set
16
17	## Quick Start
18
19	1. Create the React frontend and install OpenUI deps:
20	```bash
21	npm install @openuidev/react-ui @openuidev/react-headless @openuidev/react-lang lucide-react zod
22	```
23	2. Generate the system prompt:
24	```bash
25	npx @openuidev/cli generate ./src/lib/library.ts --out backend/storage/app/system-prompt.txt
26	```
27	3. Create the Laravel backend (see Full Code below). On a fresh app, enable API routes once with `php artisan install:api`.
28	4. Run: `php artisan serve` on `:8000`, frontend on `:3000`
29
30	## Full Code
31
32	### Backend: `composer.json` (require block)
33
34	```json
35	{
36	"require": {
37	"php": "^8.3",
38	"laravel/framework": "^13.0"
39	}
40	}
41	```
42
43	> Laravel bundles `guzzlehttp/guzzle`, so the `Http` facade can call OpenAI with no extra package. The OpenAI SSE passthrough below needs nothing beyond the framework.
44
45	### Backend: `routes/api.php`
46
47	```php
48	<?php
49
50	use App\Http\Controllers\ChatController;
51	use Illuminate\Support\Facades\Route;
52
53	// `php artisan install:api` creates this file and prefixes it with /api,
54	// so this route is reachable at POST /api/chat.
55	Route::post('/chat', [ChatController::class, 'chat']);
56	```
57
58	### Backend: `app/Http/Controllers/ChatController.php`
59
60	```php
61	<?php
62
63	namespace App\Http\Controllers;
64
65	use Illuminate\Http\Request;
66	use Illuminate\Support\Facades\Http;
67	use Symfony\Component\HttpFoundation\StreamedResponse;
68
69	class ChatController extends Controller
70	{
71	// Loaded once per worker process, then reused across requests.
72	private static ?string $systemPrompt = null;
73
74	private function systemPrompt(): string
75	{
76	if (self::$systemPrompt === null) {
77	$path = storage_path('app/system-prompt.txt');
78	if (! is_file($path)) {
79	abort(500, 'system-prompt.txt not found at ' . $path);
80	}
81	self::$systemPrompt = (string) file_get_contents($path);
82	}
83
84	return self::$systemPrompt;
85	}
86
87	public function chat(Request $request): StreamedResponse
88	{
89	// Read config(), never env(), in a controller: after `php artisan
90	// config:cache` (standard in production) env() returns null outside
91	// config files. See the config/services.php block below.
92	$apiKey = config('services.openai.key');
93	if (! $apiKey) {
94	abort(500, 'OPENAI_API_KEY not set');
95	}
96
97	$incoming = $request->validate([
98	'messages' => 'required\|array\|min:1',
99	'messages.*.role' => 'required\|string',
100	'messages.*.content' => 'required\|string',
101	])['messages'];
102
103	// Prepend the system prompt; never trust a client-sent system message.
104	$messages = array_merge(
105	[['role' => 'system', 'content' => $this->systemPrompt()]],
106	array_map(
107	fn (array $m) => ['role' => $m['role'], 'content' => $m['content']],
108	$incoming,
109	),
110	);
111
112	$baseUrl = rtrim(config('services.openai.base_url'), '/');
113	$model = config('services.openai.model');
114
115	// stream => true returns the Guzzle PSR-7 response with its body still
116	// on the wire, so we read it chunk-by-chunk instead of buffering the
117	// whole completion in memory.
118	$upstream = Http::withToken($apiKey)
119	->withOptions(['stream' => true])
120	->acceptJson()
121	->post("{$baseUrl}/chat/completions", [
122	'model' => $model,
123	'stream' => true,
124	'messages' => $messages,
125	]);
126
127	if ($upstream->failed()) {
128	abort($upstream->status(), 'OpenAI request failed: ' . $upstream->body());
129	}
130
131	$body = $upstream->toPsrResponse()->getBody();
132
133	return response()->stream(function () use ($body): void {
134	// Forward OpenAI's SSE bytes verbatim. OpenAI already emits
135	// `data: {chunk}\n\n` frames plus a final `data: [DONE]`, which is
136	// exactly what openAIAdapter() parses, so no re-framing is needed.
137	while (! $body->eof()) {
138	$chunk = $body->read(8192);

People who liked this also viewed

6 picks

Type

web-design-guidelinesReview UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".SkillsJul 2026483k29k
lark-slides飞书幻灯片：创建和编辑幻灯片。创建演示文稿、读取幻灯片内容、管理幻灯片页面（创建、删除、读取、局部替换）。当用户需要创建或编辑幻灯片、读取或修改单个页面时使用。当用户给出 doubao.com 的 /slides/ URL/token 时，也应直接使用本 skill，不要因为域名不是飞书而回退到 WebFetch；路由依据是 URL 路径模式和 token，而不是域名。不负责：云文档内容编辑（走 SkillsJul 2026332k16k
design-taste-frontendTaste-Skill - gives your AI good taste. stops the AI from generating boring, generic slop SkillsJul 2026280k66k
ui-ux-pro-maxUI/UX design intelligence for web and mobile. Searchable local database with 84 styles, 192 color palettes, 74 font pairings, 192 product types, 98 UX guidelines, 104 icon entries, 16 GSAP motion presSkillsJul 2026280k109k
caveman-helpQuick-reference card for all caveman modes, skills, and commands. One-shot display, not a persistent mode. Trigger: /caveman-help, "caveman help", "what caveman commands", "how do I use caveman".SkillsJul 2026249k92k
codebase-designShared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-nSkillsJul 2026225k182k

openui-forge-php

1installs0forks

View on GitHub

How to install openui-forge-php?

othmanadi/openui-forge/openui-forge-php

$npx -y skills add OthmanAdi/openui-forge --skill openui-forge-php

Installs into the current project.

Summary

OpenUI generative UI with a PHP (Laravel 13.x) backend. Forwards OpenAI's SSE stream verbatim via response()->stream().

Files · 1

View on GitHub

SKILL.md

1	# OpenUI Forge — PHP
2
3	Build generative UI apps with a React frontend + Laravel backend. Streams the OpenAI API's native SSE response straight through `response()->stream()`.
4
5	## Activation Triggers
6
7	- "openui php", "openui laravel", "openui php backend"
8	- "generative ui php", "laravel streaming ui backend"
9
10	## Prerequisites
11
12	- Node.js >= 22 (24 LTS recommended) + React >= 18.3.1 (19+ recommended) (frontend)
13	- PHP >= 8.3 + Laravel 13.x (backend; Laravel 13 requires PHP 8.3 minimum and supports 8.3 through 8.5)
14	- Composer; `guzzlehttp/guzzle` ships with Laravel and backs the `Http` facade (no extra dependency to call OpenAI)
15	- `OPENAI_API_KEY` environment variable set
16
17	## Quick Start
18
19	1. Create the React frontend and install OpenUI deps:
20	```bash
21	npm install @openuidev/react-ui @openuidev/react-headless @openuidev/react-lang lucide-react zod
22	```
23	2. Generate the system prompt:
24	```bash
25	npx @openuidev/cli generate ./src/lib/library.ts --out backend/storage/app/system-prompt.txt
26	```
27	3. Create the Laravel backend (see Full Code below). On a fresh app, enable API routes once with `php artisan install:api`.
28	4. Run: `php artisan serve` on `:8000`, frontend on `:3000`
29
30	## Full Code
31
32	### Backend: `composer.json` (require block)
33
34	```json
35	{
36	"require": {
37	"php": "^8.3",
38	"laravel/framework": "^13.0"
39	}
40	}
41	```
42
43	> Laravel bundles `guzzlehttp/guzzle`, so the `Http` facade can call OpenAI with no extra package. The OpenAI SSE passthrough below needs nothing beyond the framework.
44
45	### Backend: `routes/api.php`
46
47	```php
48	<?php
49
50	use App\Http\Controllers\ChatController;
51	use Illuminate\Support\Facades\Route;
52
53	// `php artisan install:api` creates this file and prefixes it with /api,
54	// so this route is reachable at POST /api/chat.
55	Route::post('/chat', [ChatController::class, 'chat']);
56	```
57
58	### Backend: `app/Http/Controllers/ChatController.php`
59
60	```php
61	<?php
62
63	namespace App\Http\Controllers;
64
65	use Illuminate\Http\Request;
66	use Illuminate\Support\Facades\Http;
67	use Symfony\Component\HttpFoundation\StreamedResponse;
68
69	class ChatController extends Controller
70	{
71	// Loaded once per worker process, then reused across requests.
72	private static ?string $systemPrompt = null;
73
74	private function systemPrompt(): string
75	{
76	if (self::$systemPrompt === null) {
77	$path = storage_path('app/system-prompt.txt');
78	if (! is_file($path)) {
79	abort(500, 'system-prompt.txt not found at ' . $path);
80	}
81	self::$systemPrompt = (string) file_get_contents($path);
82	}
83
84	return self::$systemPrompt;
85	}
86
87	public function chat(Request $request): StreamedResponse
88	{
89	// Read config(), never env(), in a controller: after `php artisan
90	// config:cache` (standard in production) env() returns null outside
91	// config files. See the config/services.php block below.
92	$apiKey = config('services.openai.key');
93	if (! $apiKey) {
94	abort(500, 'OPENAI_API_KEY not set');
95	}
96
97	$incoming = $request->validate([
98	'messages' => 'required\|array\|min:1',
99	'messages.*.role' => 'required\|string',
100	'messages.*.content' => 'required\|string',
101	])['messages'];
102
103	// Prepend the system prompt; never trust a client-sent system message.
104	$messages = array_merge(
105	[['role' => 'system', 'content' => $this->systemPrompt()]],
106	array_map(
107	fn (array $m) => ['role' => $m['role'], 'content' => $m['content']],
108	$incoming,
109	),
110	);
111
112	$baseUrl = rtrim(config('services.openai.base_url'), '/');
113	$model = config('services.openai.model');
114
115	// stream => true returns the Guzzle PSR-7 response with its body still
116	// on the wire, so we read it chunk-by-chunk instead of buffering the
117	// whole completion in memory.
118	$upstream = Http::withToken($apiKey)
119	->withOptions(['stream' => true])
120	->acceptJson()
121	->post("{$baseUrl}/chat/completions", [
122	'model' => $model,
123	'stream' => true,
124	'messages' => $messages,
125	]);
126
127	if ($upstream->failed()) {
128	abort($upstream->status(), 'OpenAI request failed: ' . $upstream->body());
129	}
130
131	$body = $upstream->toPsrResponse()->getBody();
132
133	return response()->stream(function () use ($body): void {
134	// Forward OpenAI's SSE bytes verbatim. OpenAI already emits
135	// `data: {chunk}\n\n` frames plus a final `data: [DONE]`, which is
136	// exactly what openAIAdapter() parses, so no re-framing is needed.
137	while (! $body->eof()) {
138	$chunk = $body->read(8192);

People who liked this also viewed

6 picks

Type