Update app.py

app.py

@@ -93,7 +93,7 @@ async def chat(request: ChatRequest):
                     config=GenerateContentConfig(
                         system_instruction=["You are a helpful assistant who is an expert at summarization."],
                         max_output_tokens=250,
-                        temperature=0.8
+                        temperature=0.5
                     ),
                 )
                 request.chat_history = request.chat_history[-(summary_thresh+2):] # keep last k items
@@ -134,11 +134,9 @@ async def chat(request: ChatRequest):
                 model="gemini-2.0-flash",
                 contents=request.chat_history,
                 config=GenerateContentConfig(
-                    system_instruction=[request.system_message]
-                    generation_config={
-                        "temperature": 0.7,
-                        "max_output_tokens": 256, # Set your desired maximum output tokens here
-                    },
+                    system_instruction=[request.system_message],
+                    max_output_tokens=250,
+                    temperature=0.8
                 ),
             )