openui-forge-python

OpenUI Forge — Python

Build generative UI apps with a React frontend + Python FastAPI backend. Streams OpenAI-compatible NDJSON.

Activation Triggers

• "openui python", "openui fastapi", "openui flask"
• "generative ui python", "python streaming ui backend"

Prerequisites

• Node.js >= 22 (24 LTS recommended) + React >= 18.3.1 (19+ recommended) (frontend)
• Python >= 3.10 (backend)
• OPENAI_API_KEY or ANTHROPIC_API_KEY set

Quick Start

1. Create the React frontend and install OpenUI deps:

npm install @openuidev/react-ui @openuidev/react-headless @openuidev/react-lang lucide-react zod

1. Generate the system prompt from your component library:

npx @openuidev/cli generate ./src/lib/library.ts --out backend/system-prompt.txt

1. Set up the Python backend (see Full Code below)
2. Run both: frontend on :3000, backend on :8000

Full Code

Backend: backend/requirements.txt

fastapi>=0.115.0
uvicorn>=0.24.0
openai>=2.0
anthropic>=0.111.0
python-dotenv>=1.0.0

The Python >= 3.10 floor comes from fastapi/uvicorn/python-dotenv; openai and anthropic themselves need only Python 3.9.

Backend (OpenAI): backend/main.py

import os
from pathlib import Path
from dotenv import load_dotenv
from fastapi import FastAPI, Request
from fastapi.middleware.cors import CORSMiddleware
from fastapi.responses import StreamingResponse
from openai import AsyncOpenAI

load_dotenv()
app = FastAPI()
app.add_middleware(
    CORSMiddleware,
    allow_origins=["http://localhost:3000"],
    allow_methods=["POST"],
    allow_headers=["*"],
)

# AsyncOpenAI keeps the request from blocking the event loop during streaming.
client = AsyncOpenAI()
SYSTEM_PROMPT = Path("system-prompt.txt").read_text()

@app.post("/api/chat")
async def chat(request: Request):
    body = await request.json()
    messages = [{"role": "system", "content": SYSTEM_PROMPT}] + body["messages"]

    async def generate():
        response = await client.chat.completions.create(
            model=os.getenv("OPENAI_MODEL", "gpt-5.5"),
            stream=True,
            messages=messages,
        )
        async for chunk in response:
            data = chunk.model_dump_json()
            yield f"data: {data}\n\n"
        yield "data: [DONE]\n\n"

    return StreamingResponse(generate(), media_type="text/event-stream")