app.py

import os
import logging
from fastapi import FastAPI, HTTPException, Query
from fastapi.responses import StreamingResponse
from pydantic import BaseModel
from openai import AsyncOpenAI
from typing import Optional

# Configure logging
logging.basicConfig(level=logging.DEBUG)
logger = logging.getLogger(__name__)

app = FastAPI()

class GenerateRequest(BaseModel):
    prompt: str

async def generate_ai_response(prompt: str, model: str):
    logger.debug(f"Received prompt: {prompt}, model: {model}")
    token = os.getenv("GITHUB_TOKEN")
    endpoint = os.getenv("AI_SERVER_URL", "https://models.github.ai/inference")
    
    if not token:
        logger.error("GitHub token not configured")
        raise HTTPException(status_code=500, detail="GitHub token not configured")

    logger.debug(f"Using endpoint: {endpoint}")
    client = AsyncOpenAI(base_url=endpoint, api_key=token)

    try:
        stream = await client.chat.completions.create(
            messages=[
                {"role": "system", "content": "You are a helpful assistant named Orion, created by Abdullah Ali"},
                {"role": "user", "content": prompt}
            ],
            model=model,
            temperature=1.0,
            top_p=1.0,
            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:
        logger.error(f"AI generation failed: {str(err)}")
        yield f"Error: {str(err)}"
        raise HTTPException(status_code=500, detail=f"AI generation failed: {str(err)}")

@app.post("/generate", summary="Generate AI response", response_description="Streaming AI response")
async def generate_response(
    model: str = Query("default-model", description="The AI model to use"),
    prompt: Optional[str] = Query(None, description="The input text prompt for the AI"),
    request: Optional[GenerateRequest] = None
):
    logger.debug(f"Request received - model: {model}, prompt: {prompt}, body: {request}")
    final_prompt = prompt if prompt is not None else (request.prompt if request is not None else None)
    
    if not final_prompt or not final_prompt.strip():
        logger.error("Prompt cannot be empty")
        raise HTTPException(status_code=400, detail="Prompt cannot be empty")
    
    if not model or not model.strip():
        logger.error("Model cannot be empty")
        raise HTTPException(status_code=400, detail="Model cannot be empty")
    
    return StreamingResponse(
        generate_ai_response(final_prompt, model),
        media_type="text/event-stream"
    )

def get_app():
    return app