main.py

from fastapi import FastAPI
from pydantic import BaseModel
from fastapi.middleware.cors import CORSMiddleware
from fastapi.responses import StreamingResponse
import httpx
import asyncio
import json

# FastAPI app
app = FastAPI()

# CORS Middleware
app.add_middleware(
    CORSMiddleware,
    allow_origins=["*"],
    allow_credentials=True,
    allow_methods=["*"],
    allow_headers=["*"],
)

# Request body model
class Question(BaseModel):
    question: str

# Your OWN Hosted HuggingFace Space URL
YOUR_SPACE_URL = "https://abdullahalioo-aiapp.hf.space"  # 🔥 change this!

async def generate_response_chunks(prompt: str):
    payload = {
        "messages": [
            {"role": "system", "content": "You are an Orion AI assistant created by Abdullah Ali who is very intelligent, 13 years old, and lives in Lahore."},
            {"role": "user", "content": prompt}
        ],
        "temperature": 0.7,
        "max_tokens": 512,
        "stream": True  # Tell your server to stream output
    }

    async with httpx.AsyncClient(timeout=None) as client:
        async with client.stream("POST", f"{YOUR_SPACE_URL}/v1/chat/completions", json=payload) as response:
            async for line in response.aiter_lines():
                if line.strip():
                    try:
                        # The server sends stream chunks, decode them
                        data = json.loads(line)
                        content = data['choices'][0]['delta']['content']
                        if content:
                            for letter in content:
                                yield letter
                                await asyncio.sleep(0.01)  # simulate typing
                    except Exception as e:
                        yield f"Error decoding stream: {e}"

@app.post("/ask")
async def ask(question: Question):
    return StreamingResponse(
        generate_response_chunks(question.question),
        media_type="text/plain"
    )