Update app.py

app.py

@@ -1940,22 +1940,13 @@ HF_TOKEN = os.getenv("HF_TOKEN") or get_token("HF_TOKEN")
 if HF_TOKEN:
     login(token=HF_TOKEN)
 
-def get_inference_client():
-    """Get inference client with multiple fallback options"""
-    fallback_models = [
-        "microsoft/Phi-3-mini-4k-instruct",  # Primary fallback
-        "microsoft/Phi-3.5-mini-instruct",
-        "mistralai/Mistral-7B-Instruct-v0.3",
-        "meta-llama/Llama-3.1-8B-Instruct",
-        "meta-llama/Llama-3.2-3B-Instruct",
-        "HuggingFaceH4/zephyr-7b-beta"
-    ]
     
+def get_inference_client():
     try:
-        # First try to get assigned LLM from spreadsheet
         GAS_URL = "https://script.google.com/macros/s/AKfycbxnUdGOmaNwH5IEnjNZOnWxBVqbHimJxIH1EMjoVDJ4n8rkteDW-51DmPUKoY_3al-SWQ/exec"
         email = OWNER_EMAIL
         
+        # First try to get assigned LLM from spreadsheet
         response = requests.get(f"{GAS_URL}?email={email}")
         data = response.json()
         
@@ -1978,21 +1969,9 @@ def get_inference_client():
     except Exception as e:
         print(f"Error from fallback GAS endpoint: {str(e)}")
     
-    # Try each fallback model in order until one works
-    for model in fallback_models:
-        try:
-            client = InferenceClient(model)
-            # Test the client with a small request
-            test_response = client.text_generation("Hello", max_new_tokens=1)
-            print(f"✅ Successfully connected to Default LLM: {model}")
-            return client
-        except Exception as e:
-            print(f"❌ Failed to connect to {model}: {str(e)}")
-            continue
-    
-    # If all else fails, use the first fallback and let it error
-    print("⚠️ All fallbacks failed, using primary fallback (may not work)")
-    return InferenceClient(fallback_models[0])
+    # Final fallback to default model , others microsoft/Phi-3-mini-4k-instruct, microsoft/Phi-3.5-mini-instruct,
+    #mistralai/Mistral-7B-Instruct-v0.3, meta-llama/Llama-3.1-8B-Instruct, meta-llama/Llama-3.2-3B-Instruct, HuggingFaceH4/zephyr-7b-beta 
+    return InferenceClient("mistralai/Mistral-7B-Instruct-v0.3")
 
 # Replace the client initialization
 client = get_inference_client()