Update app.py

app.py

@@ -13,7 +13,7 @@ client = OpenAI(
   api_key=os.environ.get('YOUR_API_TOKEN')
 ) 
 
-def predict(message, history):
+def predict(message, history, test=""):
     history_openai_format = []
     for human, assistant in history:
         history_openai_format.append({"role": "user", "content": human })
@@ -23,7 +23,8 @@ def predict(message, history):
     response = client.chat.completions.create(model='google/gemma-1.1-7b-it',
     messages= history_openai_format,
     temperature=0.7,
-    stream=True)
+    stream=True,
+    max_tokens=3000)
 
     partial_message = ""
     for chunk in response: