Added auto-check for model choice

app.py

@@ -78,12 +78,42 @@ def get_current_time_in_timezone(timezone: str) -> str:
 
 final_answer = FinalAnswerTool()
 
+MODEL_IDS = [
+    'https://wxknx1kg971u7k1n.us-east-1.aws.endpoints.huggingface.cloud/',
+    'https://jc26mwg228mkj8dw.us-east-1.aws.endpoints.huggingface.cloud/', 
+    'meta-llama/Llama-3.2-1B-Instruct',
+    'Qwen/Qwen2.5-Coder-32B-Instruct',
+    'Qwen/Qwen2.5-Coder-1.5B-Instruct'
+    # Add here wherever model is working for you
+]
+
+def is_model_overloaded(model_url):
+    """Verify if the model is overloaded doing a test call."""
+    try:
+        response = requests.post(model_url, json={"inputs": "Test"})
+        if response.status_code == 503:  # 503 Service Unavailable = Overloaded
+            return True
+        return False
+    except requests.RequestException:
+        return True  # if there are an error is overloaded
+
+def get_available_model():
+    """Select the first model available from the list."""
+    for model_url in MODEL_IDS:
+        print("trying model_url\n")
+        if not is_model_overloaded(model_url):
+            return model_url
+    return MODEL_IDS[0]  # if all are failing, use the first model by dfault
+
+selected_model_id = get_available_model()
+
 model = HfApiModel(
     max_tokens=1048,
     temperature=0.5,
     #model_id='meta-llama/Llama-3.2-1B-Instruct',
     #model_id='Qwen/Qwen2.5-Coder-32B-Instruct',
-    model_id = 'Qwen/Qwen2.5-Coder-1.5B-Instruct',    
+    #model_id = 'Qwen/Qwen2.5-Coder-1.5B-Instruct',    
+    model_id = selected_model_id # model available selected from the list automatically
     custom_role_conversions=None,
 )