openui-forge-openai
installsforks
How to install openui-forge-openai?
othmanadi/openui-forge/openui-forge-openai
$npx -y skills add OthmanAdi/openui-forge --skill openui-forge-openaiOpenUI generative UI with OpenAI SDK backend. Streaming chat completions with gpt-5.5 (or any current OpenAI-compatible model).
SKILL.md
| 1 | # OpenUI Forge — OpenAI |
| 2 | |
| 3 | Build generative UI apps with OpenUI + OpenAI SDK. One backend, one adapter, streaming out of the box. |
| 4 | |
| 5 | ## Activation Triggers |
| 6 | |
| 7 | - "openui openai", "openui gpt", "openui chatgpt" |
| 8 | - "generative ui openai", "openai streaming ui" |
| 9 | |
| 10 | ## Prerequisites |
| 11 | |
| 12 | - Node.js >= 22 (24 LTS recommended), React >= 18.3.1 (19+ recommended) |
| 13 | - `OPENAI_API_KEY` environment variable set |
| 14 | - Optional: `OPENAI_BASE_URL` to route via an OpenAI-compatible provider (Gemini, OpenRouter, xAI, DeepSeek, etc.) without code changes. `OPENAI_BASE_URL` is the correct env var; the legacy `OPENAI_API_BASE` was removed in openai v6. See [Provider Routing](#provider-routing) below. |
| 15 | - Optional: `OPENAI_MODEL` to pin a specific model (defaults to `gpt-5.5`) |
| 16 | - Next.js project (App Router recommended) |
| 17 | |
| 18 | ## Provider Routing |
| 19 | |
| 20 | This is the OpenAI-compatible variant: the same `OpenAI` client and `chat.completions.create` code talks to any provider below by setting `OPENAI_BASE_URL` (and `OPENAI_MODEL`). No code changes. `OPENAI_BASE_URL` is the correct env var; the old `OPENAI_API_BASE` was removed in openai v6. |
| 21 | |
| 22 | | Provider | `OPENAI_BASE_URL` | Example `OPENAI_MODEL` | |
| 23 | |----------|-------------------|------------------------| |
| 24 | | Gemini | `https://generativelanguage.googleapis.com/v1beta/openai/` | `gemini-3.5-flash` | |
| 25 | | OpenRouter | `https://openrouter.ai/api/v1` | `anthropic/claude-opus-4.7` | |
| 26 | | xAI (Grok) | `https://api.x.ai/v1` | `grok-4.3` | |
| 27 | | DeepSeek | `https://api.deepseek.com` | `deepseek-v4-pro` | |
| 28 | | Groq | `https://api.groq.com/openai/v1` | `llama-3.3-70b-versatile` | |
| 29 | | Mistral | `https://api.mistral.ai/v1` | `mistral-large-latest` | |
| 30 | | Together | `https://api.together.ai/v1` | `openai/gpt-oss-20b` | |
| 31 | | Fireworks | `https://api.fireworks.ai/inference/v1` | `accounts/fireworks/models/glm-5` | |
| 32 | | Ollama (local) | `http://localhost:11434/v1/` | `llama3.3` (any placeholder API key) | |
| 33 | | LM Studio (local) | `http://localhost:1234/v1` | loaded model id (any placeholder API key) | |
| 34 | |
| 35 | Model ids drift; check each provider's current catalog. Base-url routing covers chat completions only, not full OpenAI API parity. |
| 36 | |
| 37 | > **Azure OpenAI is not a generic drop-in.** Use `OPENAI_BASE_URL=https://YOUR-RESOURCE.openai.azure.com/openai/v1/`, set `OPENAI_MODEL` to your *deployment name* (not a catalog id like `gpt-5.5`), and prefer the `AzureOpenAI` client. The legacy data-plane path also needs an `?api-version=` query param. |
| 38 | |
| 39 | ## Quick Start |
| 40 | |
| 41 | 1. Install dependencies: |
| 42 | ```bash |
| 43 | npm install @openuidev/react-ui @openuidev/react-headless @openuidev/react-lang lucide-react zod openai |
| 44 | ``` |
| 45 | 2. Add the CSS import to `app/layout.tsx`: |
| 46 | ```tsx |
| 47 | import "@openuidev/react-ui/components.css"; |
| 48 | ``` |
| 49 | 3. Create the API route (Step 4 below) |
| 50 | 4. Create the frontend page (Step 5 below) |
| 51 | 5. Run `npm run dev` and test |
| 52 | |
| 53 | ## Full Code |
| 54 | |
| 55 | ### Backend: `app/api/chat/route.ts` |
| 56 | |
| 57 | ```typescript |
| 58 | import { openuiChatLibrary } from "@openuidev/react-ui/genui-lib"; |
| 59 | import OpenAI from "openai"; |
| 60 | |
| 61 | const client = new OpenAI(); |
| 62 | |
| 63 | export async function POST(req: Request) { |
| 64 | const { messages } = await req.json(); |
| 65 | |
| 66 | const systemPrompt = openuiChatLibrary.prompt({ |
| 67 | preamble: "You are a helpful assistant that generates interactive UIs.", |
| 68 | additionalRules: ["Always use Stack as root when combining multiple components."], |
| 69 | }); |
| 70 | |
| 71 | const response = await client.chat.completions.create({ |
| 72 | model: process.env.OPENAI_MODEL ?? "gpt-5.5", |
| 73 | stream: true, |
| 74 | messages: [{ role: "system", content: systemPrompt }, ...messages], |
| 75 | }); |
| 76 | |
| 77 | // response.toReadableStream() produces NDJSON (one JSON object per line, no SSE `data:` prefix). |
| 78 | // Pair with openAIReadableStreamAdapter() on the frontend. |
| 79 | return new Response(response.toReadableStream(), { |
| 80 | headers: { "Content-Type": "application/x-ndjson" }, |
| 81 | }); |
| 82 | } |
| 83 | ``` |
| 84 | |
| 85 | ### Frontend: `app/chat/page.tsx` |
| 86 | |
| 87 | ```tsx |
| 88 | "use client"; |
| 89 | import { FullScreen } from "@openuidev/react-ui"; |
| 90 | import { openuiChatLibrary } from "@openuidev/react-ui/genui-lib"; |
| 91 | import { |
| 92 | openAIReadableStreamAdapter, |
| 93 | openAIMessageFormat, |
| 94 | } from "@openuidev/react-headless"; |
| 95 | |
| 96 | export default function ChatPage() { |
| 97 | return ( |
| 98 | <FullScreen |
| 99 | componentLibrary={openuiChatLibrary} |
| 100 | streamProtocol={openAIReadableStreamAdapter()} |
| 101 | messageFormat={openAIMessageFormat} |
| 102 | apiUrl="/api/chat" |
| 103 | /> |
| 104 | ); |
| 105 | } |
| 106 | ``` |
| 107 | |
| 108 | ## Component Creation |
| 109 | |
| 110 | ```tsx |
| 111 | import { defineComponent } from "@openuidev/react-lang"; |
| 112 | import { z } from "zod"; |
| 113 | |
| 114 | export const MyCard = defineComponent({ |
| 115 | name: "MyCard", |
| 116 | description: "A card displaying a title and body text", |
| 117 | props: z.object({ |
| 118 | title: z.string().describe("The card heading"), |
| 119 | body: z.string().describe("The card body content"), |
| 120 | }), |
| 121 | component: ({ props }) => ( |
| 122 | <div style={{ border: "1px solid #ddd", borderRadius: 8, padding: 16 }}> |
| 123 | <h3>{props.title} |
People who liked this also viewed
6 picksType
- 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 2026
- 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 2026
- design-taste-frontendTaste-Skill - gives your AI good taste. stops the AI from generating boring, generic slop SkillsJul 2026
- 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 2026
- 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 2026
- 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 2026
