chaning to InferenceClientModel

app.py

@@ -1,4 +1,4 @@
-from smolagents import CodeAgent, DuckDuckGoSearchTool, HfApiModel, load_tool, tool
+from smolagents import CodeAgent, load_tool, tool, InferenceClientModel
 import datetime
 import requests
 import pytz
@@ -31,11 +31,12 @@ calories_checker = CaloriesCheckerTool()
 # If the agent does not answer, the model is overloaded, please use another model or the following Hugging Face Endpoint that also contains qwen2.5 coder:
 # model_id='https://pflgm2locj2t89co.us-east-1.aws.endpoints.huggingface.cloud'
 
-model = HfApiModel(
-    max_tokens=2096,
+model = InferenceClientModel(
+    max_tokens=2048,
     temperature=0.5,
     model_id="Qwen/Qwen2.5-Coder-32B-Instruct",  # it is possible that this model may be overloaded
     custom_role_conversions=None,
+    inference_client_url="https://pflgm2locj2t89co.us-east-1.aws.endpoints.huggingface.cloud",
 )