openui-forge-ruby

Name: openui-forge-ruby
Author: OthmanAdi

1installs0forks

How to install openui-forge-ruby?

othmanadi/openui-forge/openui-forge-ruby

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

Installs into the current project.

Summary

OpenUI generative UI with a Ruby on Rails backend. SSE streaming via ActionController::Live, forwarding the OpenAI API stream with Net::HTTP.

Files · 1

View on GitHub

SKILL.md

1	# OpenUI Forge — Ruby
2
3	Build generative UI apps with a React frontend + Ruby on Rails backend. Streams OpenAI API responses directly via `ActionController::Live`, forwarding OpenAI's native SSE with `Net::HTTP`.
4
5	## Activation Triggers
6
7	- "openui ruby", "openui rails", "openui ruby backend"
8	- "generative ui ruby", "rails streaming ui backend"
9
10	## Prerequisites
11
12	- Node.js >= 22 (24 LTS recommended) + React >= 18.3.1 (19+ recommended) (frontend)
13	- Ruby >= 3.2 + Rails 8.1.x (backend; run on Puma — `ActionController::Live` needs a threaded server, not WEBrick)
14	- `OPENAI_API_KEY` environment variable set
15
16	## Quick Start
17
18	1. Create the React frontend and install OpenUI deps:
19	```bash
20	npm install @openuidev/react-ui @openuidev/react-headless @openuidev/react-lang lucide-react zod
21	```
22	2. Generate the system prompt into the Rails app:
23	```bash
24	npx @openuidev/cli generate ./src/lib/library.ts --out config/system-prompt.txt
25	```
26	3. Create the Rails backend (see Full Code below)
27	4. Run: `bin/rails server -p 3001` on `:3001`, frontend on `:3000`
28
29	## Full Code
30
31	### Backend: `Gemfile`
32
33	```ruby
34	source "https://rubygems.org"
35
36	gem "rails", "~> 8.1"
37	gem "puma", ">= 6.0"
38	# Net::HTTP is in the standard library — no extra HTTP-client gem required.
39	# Optional: load OPENAI_API_KEY etc. from a .env file in development.
40	gem "dotenv-rails", groups: [:development, :test]
41	```
42
43	### Backend: `app/controllers/chat_controller.rb`
44
45	```ruby
46	require "net/http"
47	require "json"
48	require "uri"
49
50	class ChatController < ApplicationController
51	include ActionController::Live
52
53	skip_forgery_protection
54	before_action :set_cors_headers
55	before_action :handle_preflight, only: :create
56
57	OPENAI_BASE_URL = ENV.fetch("OPENAI_BASE_URL", "https://api.openai.com/v1").freeze
58	OPENAI_MODEL = ENV.fetch("OPENAI_MODEL", "gpt-5.5").freeze
59
60	# Loaded once at boot.
61	SYSTEM_PROMPT = Rails.root.join("config", "system-prompt.txt").read.freeze
62
63	# POST /api/chat { "messages": [{ "role": "...", "content": "..." }] }
64	def create
65	api_key = ENV["OPENAI_API_KEY"]
66	if api_key.nil? \|\| api_key.empty?
67	render(json: { error: "OPENAI_API_KEY not set" }, status: :internal_server_error)
68	return
69	end
70
71	body = JSON.parse(request.body.read) rescue {}
72	incoming = body["messages"]
73	unless incoming.is_a?(Array) && !incoming.empty?
74	render(json: { error: "messages must be a non-empty array" }, status: :bad_request)
75	return
76	end
77
78	# Prepend the server-side system prompt; never trust a client-sent one.
79	messages = [{ "role" => "system", "content" => SYSTEM_PROMPT }]
80	incoming.each do \|m\|
81	next unless m.is_a?(Hash)
82	messages << { "role" => m["role"].to_s, "content" => m["content"].to_s }
83	end
84
85	# Headers MUST be set before the first write (the response commits on write).
86	response.headers["Content-Type"] = "text/event-stream"
87	response.headers["Cache-Control"] = "no-cache"
88	# Rails inserts Rack::ETag, which buffers the whole body and breaks
89	# streaming. Setting Last-Modified makes Rack::ETag pass the body through.
90	response.headers["Last-Modified"] = Time.now.httpdate
91	# Defeat proxy buffering (nginx) so chunks reach the browser immediately.
92	response.headers["X-Accel-Buffering"] = "no"
93
94	uri = URI.parse("#{OPENAI_BASE_URL}/chat/completions")
95	payload = JSON.generate(
96	model: OPENAI_MODEL,
97	stream: true,
98	messages: messages,
99	)
100
101	# read_timeout: nil disables the default 60s per-read timeout; a streaming
102	# completion can pause longer than 60s between chunks and would otherwise
103	# raise Net::ReadTimeout and cut the response off mid-stream.
104	Net::HTTP.start(uri.host, uri.port, use_ssl: uri.scheme == "https", read_timeout: nil) do \|http\|
105	upstream = Net::HTTP::Post.new(uri)
106	upstream["Content-Type"] = "application/json"
107	upstream["Authorization"] = "Bearer #{api_key}"
108	upstream["Accept"] = "text/event-stream"
109	upstream.body = payload
110
111	http.request(upstream) do \|res\|
112	unless res.code.to_i == 200
113	err = +""
114	res.read_body { \|c\| err << c }
115	response.stream.write("data: #{JSON.generate(error: "OpenAI returned #{res.code}: #{err}")}\n\n")
116	response.stream.write("data: [DONE]\n\n")
117	next
118	end
119
120	# Forward OpenAI's native SSE bytes verbatim. The upstream already emits
121	# `data: {chunk}\n\n` frames terminated by `data: [DONE]`, so we just
122	# write each chunk through and flush — no buffering, no reframing. This
123	# avoids splitting a frame that straddles a TCP read boundary, because
124	# the browser's adapter reassembles SSE frames itself.
125	res.read_body do \|chunk\|
126	response.stream.write(chunk)
127	end
128	end

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-ruby

1installs0forks

View on GitHub

How to install openui-forge-ruby?

othmanadi/openui-forge/openui-forge-ruby

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

Installs into the current project.

Summary

OpenUI generative UI with a Ruby on Rails backend. SSE streaming via ActionController::Live, forwarding the OpenAI API stream with Net::HTTP.

Files · 1

View on GitHub

SKILL.md

1	# OpenUI Forge — Ruby
2
3	Build generative UI apps with a React frontend + Ruby on Rails backend. Streams OpenAI API responses directly via `ActionController::Live`, forwarding OpenAI's native SSE with `Net::HTTP`.
4
5	## Activation Triggers
6
7	- "openui ruby", "openui rails", "openui ruby backend"
8	- "generative ui ruby", "rails streaming ui backend"
9
10	## Prerequisites
11
12	- Node.js >= 22 (24 LTS recommended) + React >= 18.3.1 (19+ recommended) (frontend)
13	- Ruby >= 3.2 + Rails 8.1.x (backend; run on Puma — `ActionController::Live` needs a threaded server, not WEBrick)
14	- `OPENAI_API_KEY` environment variable set
15
16	## Quick Start
17
18	1. Create the React frontend and install OpenUI deps:
19	```bash
20	npm install @openuidev/react-ui @openuidev/react-headless @openuidev/react-lang lucide-react zod
21	```
22	2. Generate the system prompt into the Rails app:
23	```bash
24	npx @openuidev/cli generate ./src/lib/library.ts --out config/system-prompt.txt
25	```
26	3. Create the Rails backend (see Full Code below)
27	4. Run: `bin/rails server -p 3001` on `:3001`, frontend on `:3000`
28
29	## Full Code
30
31	### Backend: `Gemfile`
32
33	```ruby
34	source "https://rubygems.org"
35
36	gem "rails", "~> 8.1"
37	gem "puma", ">= 6.0"
38	# Net::HTTP is in the standard library — no extra HTTP-client gem required.
39	# Optional: load OPENAI_API_KEY etc. from a .env file in development.
40	gem "dotenv-rails", groups: [:development, :test]
41	```
42
43	### Backend: `app/controllers/chat_controller.rb`
44
45	```ruby
46	require "net/http"
47	require "json"
48	require "uri"
49
50	class ChatController < ApplicationController
51	include ActionController::Live
52
53	skip_forgery_protection
54	before_action :set_cors_headers
55	before_action :handle_preflight, only: :create
56
57	OPENAI_BASE_URL = ENV.fetch("OPENAI_BASE_URL", "https://api.openai.com/v1").freeze
58	OPENAI_MODEL = ENV.fetch("OPENAI_MODEL", "gpt-5.5").freeze
59
60	# Loaded once at boot.
61	SYSTEM_PROMPT = Rails.root.join("config", "system-prompt.txt").read.freeze
62
63	# POST /api/chat { "messages": [{ "role": "...", "content": "..." }] }
64	def create
65	api_key = ENV["OPENAI_API_KEY"]
66	if api_key.nil? \|\| api_key.empty?
67	render(json: { error: "OPENAI_API_KEY not set" }, status: :internal_server_error)
68	return
69	end
70
71	body = JSON.parse(request.body.read) rescue {}
72	incoming = body["messages"]
73	unless incoming.is_a?(Array) && !incoming.empty?
74	render(json: { error: "messages must be a non-empty array" }, status: :bad_request)
75	return
76	end
77
78	# Prepend the server-side system prompt; never trust a client-sent one.
79	messages = [{ "role" => "system", "content" => SYSTEM_PROMPT }]
80	incoming.each do \|m\|
81	next unless m.is_a?(Hash)
82	messages << { "role" => m["role"].to_s, "content" => m["content"].to_s }
83	end
84
85	# Headers MUST be set before the first write (the response commits on write).
86	response.headers["Content-Type"] = "text/event-stream"
87	response.headers["Cache-Control"] = "no-cache"
88	# Rails inserts Rack::ETag, which buffers the whole body and breaks
89	# streaming. Setting Last-Modified makes Rack::ETag pass the body through.
90	response.headers["Last-Modified"] = Time.now.httpdate
91	# Defeat proxy buffering (nginx) so chunks reach the browser immediately.
92	response.headers["X-Accel-Buffering"] = "no"
93
94	uri = URI.parse("#{OPENAI_BASE_URL}/chat/completions")
95	payload = JSON.generate(
96	model: OPENAI_MODEL,
97	stream: true,
98	messages: messages,
99	)
100
101	# read_timeout: nil disables the default 60s per-read timeout; a streaming
102	# completion can pause longer than 60s between chunks and would otherwise
103	# raise Net::ReadTimeout and cut the response off mid-stream.
104	Net::HTTP.start(uri.host, uri.port, use_ssl: uri.scheme == "https", read_timeout: nil) do \|http\|
105	upstream = Net::HTTP::Post.new(uri)
106	upstream["Content-Type"] = "application/json"
107	upstream["Authorization"] = "Bearer #{api_key}"
108	upstream["Accept"] = "text/event-stream"
109	upstream.body = payload
110
111	http.request(upstream) do \|res\|
112	unless res.code.to_i == 200
113	err = +""
114	res.read_body { \|c\| err << c }
115	response.stream.write("data: #{JSON.generate(error: "OpenAI returned #{res.code}: #{err}")}\n\n")
116	response.stream.write("data: [DONE]\n\n")
117	next
118	end
119
120	# Forward OpenAI's native SSE bytes verbatim. The upstream already emits
121	# `data: {chunk}\n\n` frames terminated by `data: [DONE]`, so we just
122	# write each chunk through and flush — no buffering, no reframing. This
123	# avoids splitting a frame that straddles a TCP read boundary, because
124	# the browser's adapter reassembles SSE frames itself.
125	res.read_body do \|chunk\|
126	response.stream.write(chunk)
127	end
128	end

People who liked this also viewed

6 picks

Type