Update app.py

app.py

@@ -1,11 +1,12 @@
 import gradio as gr
+import os
 import requests
 from cachetools import TTLCache
 
 # Configuration
 API_URL = "https://api-inference.huggingface.co/models/mistralai/Mistral-7B-Instruct-v0.3"
-API_TOKEN = "hf_yourtokenhere"  # Replace with your token
-MAX_TOKENS = 256
+API_TOKEN = os.environ.get("HF_TOKEN")  # Get from environment # Replace with your token
+MAX_TOKENS = 150
 CACHE_TTL = 3600  # 1 hour cache
 
 # Initialize response cache