Update app.py

app.py

@@ -20,19 +20,7 @@ async def root():
 async def health_check():
     return {"status": "OK"}
 
-
-@app.get("/api/fastAI")
-async def fast_ai_endpoint(user: str, model: str = "llama3-70b", system: str = "Answer as concisely as possible."):
-    """Get a response from the Snova AI service."""
-    FastAI.model = model
-    FastAI.system = system
-    try:
-        response = await asyncio.to_thread(FastAI.generate_response, user)
-        return JSONResponse(content={"response": response})
-    except Exception as e:
-        raise HTTPException(status_code=500, detail=f"Error during Snova AI request: {e}")
-
-        
+    
 @app.get("/api/search")
 async def search(
     q: str,
@@ -163,7 +151,21 @@ async def llm_chat(
     except Exception as e:
         raise HTTPException(status_code=500, detail=f"Error during LLM chat: {e}")
 
+fast_ai = FastAI()
+
+@app.get("/api/fastAI")
+async def fast_ai_endpoint(user: str, model: str = "llama3-70b", system: str = "Answer as concisely as possible."):
+    """Get a response from the Snova AI service."""
+    fast_ai.model = model
+    fast_ai.system = system
+    try:
+        # Use asyncio.to_thread to run generate_response in a separate thread
+        response = await asyncio.to_thread(fast_ai.generate_response, user)
+        return JSONResponse(content={"response": response})
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=f"Error during Snova AI request: {e}")
 
+    
 @app.get("/api/answers")
 async def answers(q: str, proxy: Optional[str] = None):
     """Get instant answers for a query."""