openui-forge-langchain
installsforks
How to install openui-forge-langchain?
othmanadi/openui-forge/openui-forge-langchain
$npx -y skills add OthmanAdi/openui-forge --skill openui-forge-langchainOpenUI generative UI with LangChain/LangGraph backend. Supports ChatOpenAI and ChatAnthropic.
SKILL.md
| 1 | # OpenUI Forge — LangChain |
| 2 | |
| 3 | Build generative UI apps with OpenUI + LangChain. Stream from ChatOpenAI or ChatAnthropic, convert to OpenAI NDJSON. |
| 4 | |
| 5 | ## Activation Triggers |
| 6 | |
| 7 | - "openui langchain", "openui langgraph", "openui langsmith" |
| 8 | - "generative ui langchain", "langchain streaming ui" |
| 9 | |
| 10 | ## Prerequisites |
| 11 | |
| 12 | - Node.js >= 22 (24 LTS recommended), React >= 18.3.1 (19+ recommended) |
| 13 | - `OPENAI_API_KEY` or `ANTHROPIC_API_KEY` set |
| 14 | - Next.js project (App Router recommended) |
| 15 | |
| 16 | ## Quick Start |
| 17 | |
| 18 | 1. Install dependencies (pick one or both LLM providers): |
| 19 | ```bash |
| 20 | npm install @openuidev/react-ui @openuidev/react-headless @openuidev/react-lang lucide-react zod @langchain/openai @langchain/core |
| 21 | # For Anthropic: npm install @langchain/anthropic |
| 22 | ``` |
| 23 | 2. Add the CSS import to `app/layout.tsx`: |
| 24 | ```tsx |
| 25 | import "@openuidev/react-ui/components.css"; |
| 26 | ``` |
| 27 | 3. Create the API route and frontend page below |
| 28 | 4. Run `npm run dev` and test |
| 29 | |
| 30 | ## Full Code |
| 31 | |
| 32 | ### Backend (OpenAI): `app/api/chat/route.ts` |
| 33 | |
| 34 | ```typescript |
| 35 | import { openuiChatLibrary } from "@openuidev/react-ui/genui-lib"; |
| 36 | import { ChatOpenAI } from "@langchain/openai"; |
| 37 | import { HumanMessage, SystemMessage, AIMessage } from "@langchain/core/messages"; |
| 38 | |
| 39 | const model = new ChatOpenAI({ model: process.env.OPENAI_MODEL ?? "gpt-5.5", streaming: true }); |
| 40 | |
| 41 | export async function POST(req: Request) { |
| 42 | const { messages } = await req.json(); |
| 43 | |
| 44 | const systemPrompt = openuiChatLibrary.prompt({ |
| 45 | preamble: "You are a helpful assistant that generates interactive UIs.", |
| 46 | }); |
| 47 | |
| 48 | const lcMessages = [ |
| 49 | new SystemMessage(systemPrompt), |
| 50 | ...messages.map((m: { role: string; content: string }) => |
| 51 | m.role === "user" ? new HumanMessage(m.content) : new AIMessage(m.content) |
| 52 | ), |
| 53 | ]; |
| 54 | |
| 55 | const stream = await model.stream(lcMessages); |
| 56 | const encoder = new TextEncoder(); |
| 57 | const id = `chatcmpl-${Date.now()}`; |
| 58 | |
| 59 | const readableStream = new ReadableStream({ |
| 60 | async start(controller) { |
| 61 | for await (const chunk of stream) { |
| 62 | const text = typeof chunk.content === "string" ? chunk.content : ""; |
| 63 | if (!text) continue; |
| 64 | const payload = { |
| 65 | id, |
| 66 | object: "chat.completion.chunk", |
| 67 | choices: [{ index: 0, delta: { content: text }, finish_reason: null }], |
| 68 | }; |
| 69 | controller.enqueue(encoder.encode(`data: ${JSON.stringify(payload)}\n\n`)); |
| 70 | } |
| 71 | const done = { |
| 72 | id, |
| 73 | object: "chat.completion.chunk", |
| 74 | choices: [{ index: 0, delta: {}, finish_reason: "stop" }], |
| 75 | }; |
| 76 | controller.enqueue(encoder.encode(`data: ${JSON.stringify(done)}\n\n`)); |
| 77 | controller.enqueue(encoder.encode("data: [DONE]\n\n")); |
| 78 | controller.close(); |
| 79 | }, |
| 80 | }); |
| 81 | |
| 82 | return new Response(readableStream, { |
| 83 | headers: { "Content-Type": "text/event-stream" }, |
| 84 | }); |
| 85 | } |
| 86 | ``` |
| 87 | |
| 88 | ### Backend (Anthropic variant): `app/api/chat/route.ts` |
| 89 | |
| 90 | Replace the model initialization and import: |
| 91 | |
| 92 | ```typescript |
| 93 | import { ChatAnthropic } from "@langchain/anthropic"; |
| 94 | |
| 95 | const model = new ChatAnthropic({ |
| 96 | model: process.env.ANTHROPIC_MODEL ?? "claude-sonnet-4-6", |
| 97 | maxTokens: 4096, |
| 98 | streaming: true, |
| 99 | }); |
| 100 | ``` |
| 101 | |
| 102 | Everything else (message mapping, stream conversion, response) stays identical. |
| 103 | |
| 104 | ### Frontend: `app/chat/page.tsx` |
| 105 | |
| 106 | ```tsx |
| 107 | "use client"; |
| 108 | import { FullScreen } from "@openuidev/react-ui"; |
| 109 | import { openuiChatLibrary } from "@openuidev/react-ui/genui-lib"; |
| 110 | import { |
| 111 | openAIAdapter, |
| 112 | openAIMessageFormat, |
| 113 | } from "@openuidev/react-headless"; |
| 114 | |
| 115 | export default function ChatPage() { |
| 116 | return ( |
| 117 | <FullScreen |
| 118 | componentLibrary={openuiChatLibrary} |
| 119 | streamProtocol={openAIAdapter()} |
| 120 | messageFormat={openAIMessageFormat} |
| 121 | apiUrl="/api/chat" |
| 122 | /> |
| 123 | ); |
| 124 | } |
| 125 | ``` |
| 126 | |
| 127 | > The backend emits SSE (`data: {json}\n\n`). Pair it with `openAIAdapter()` on the frontend. (`langGraphAdapter` is also exported from `@openuidev/react-headless` if you stream LangGraph events natively rather than converting to OpenAI shape.) |
| 128 | |
| 129 | ## Component Creation |
| 130 | |
| 131 | ```tsx |
| 132 | import { defineComponent } from "@openuidev/react-lang"; |
| 133 | import { z } from "zod"; |
| 134 | |
| 135 | export const MetricCard = defineComponent({ |
| 136 | name: "MetricCard", |
| 137 | description: "Displays a metric with label, value, and optional trend", |
| 138 | props: z.object({ |
| 139 | label: z.string().describe("Metric name"), |
| 140 | value: z.number().describe("Current metric value"), |
| 141 | trend: z.enum(["up", "down", "flat"]).optional().describe("Trend direction"), |
| 142 | }), |
| 143 | component: ({ props }) => ( |
| 144 | <div style={{ padding: 16, border: "1px solid #e5e7eb", borderRadius: 8 }}> |
| 145 | <div style={{ fontSize: 14, color: "#6b7280" }}>{props.label}</div> |
| 146 | <div style={{ fontSize: 24, fontWeight: 700 }}>{props.value}</div> |
| 147 | {props.trend && <span>{props.trend === "up" ? "+" : props.trend === "down" ? "-" : "="}</span>} |
| 148 | </div> |
| 149 | ), |
| 150 | }); |
| 151 | ``` |
| 152 | |
| 153 | ## System Prompt Generation |
| 154 | |
| 155 | ```bash |
| 156 | npx @openuidev/cli generate ./ |
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
