app.py

import os
from fastapi import FastAPI, HTTPException
from fastapi.responses import StreamingResponse
from openai import AsyncOpenAI
import asyncio

app = FastAPI()

# Initialize OpenAI client
client = AsyncOpenAI(api_key=os.getenv("GITHUB_TOKEN"))

async def generate_ai_response(prompt: str):
    try:
        stream = await client.chat.completions.create(
            model="gpt-3.5-turbo",  # Using 3.5-turbo for better compatibility
            messages=[
                {"role": "system", "content": "You are a helpful assistant."},
                {"role": "user", "content": prompt}
            ],
            temperature=0.7,
            stream=True
        )

        async for chunk in stream:
            if chunk.choices and chunk.choices[0].delta.content:
                yield chunk.choices[0].delta.content

    except Exception as err:
        yield f"Error: {str(err)}"
        raise HTTPException(status_code=500, detail="AI generation failed")

@app.post("/generate")
async def generate_response(prompt: str):
    if not prompt:
        raise HTTPException(status_code=400, detail="Prompt cannot be empty")
    
    return StreamingResponse(
        generate_ai_response(prompt),
        media_type="text/event-stream"
    )

# For Hugging Face Spaces
def get_app():
    return app