Update app.py

app.py

@@ -2,30 +2,22 @@ import os
 from fastapi import FastAPI, HTTPException
 from fastapi.responses import StreamingResponse
 from openai import AsyncOpenAI
+import asyncio
 
 app = FastAPI()
 
-async def generate_ai_response(prompt: str):
-    # Configuration for unofficial GitHub AI endpoint
-    global token
-    token = os.getenv("GITHUB_TOKEN")
-    if not token:
-        raise HTTPException(status_code=500, detail="GitHub token not configured")
-    
-    endpoint = "https://models.github.ai/inference"
-    model = "openai/gpt-4.1-mini"  # Unofficial model name
-
-    client = AsyncOpenAI(base_url=endpoint, api_key=token)
+# 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}
             ],
-            model=model,
-            temperature=1.0,
-            top_p=1.0,
+            temperature=0.7,
             stream=True
         )
 
@@ -43,14 +35,10 @@ async def generate_response(prompt: str):
         raise HTTPException(status_code=400, detail="Prompt cannot be empty")
     
     return StreamingResponse(
-        response_with_token(),
-        media_type="text/event-stream",
+        generate_ai_response(prompt),
+        media_type="text/event-stream"
     )
 
+# For Hugging Face Spaces
 def get_app():
-    return app
-
-@app.get("/gettoken")
-async def get_token():
-    global token
-    return {"token": token}
+    return app