Update app.py

app.py

@@ -50,7 +50,7 @@ async def lifespan(app: FastAPI):
         
         # Faster LLM with constrained output
         ml_models["llm"] = ChatGoogleGenerativeAI(
-            model="gemini-1.0-pro",
+            model="gemini-1.5-pro",
             api_key=GOOGLE_API_KEY,
             temperature=0.1,
             max_output_tokens=300