Update app.py

app.py

@@ -4,6 +4,8 @@ import requests
 import pytz
 import yaml
 from tools.final_answer import FinalAnswerTool
+from smolagents import LiteLLMModel
+from dotenv import load_dotenv
 
 from Gradio_UI import GradioUI
 
@@ -39,13 +41,14 @@ final_answer = FinalAnswerTool()
 # 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,
-temperature=0.5,
-model_id='https://generativelanguage.googleapis.com/v1beta/models/gemini-2.0-flash:generateContent?key=AIzaSyDuxgug177abEYu49axKHvHdm3mecg2-II',# it is possible that this model may be overloaded
-custom_role_conversions=None,
-)
+load_dotenv()
 
+# Replace all calls to HfApiModel
+llm_model = LiteLLMModel(
+    model_id="gemini/gemini-2.0-flash", # you can see other model names here: https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models. It is important to prefix the name with "gemini/"
+    api_key=os.getenv("AIzaSyDuxgug177abEYu49axKHvHdm3mecg2-II"),
+    max_tokens=8192
+)
 
 # Import tool from Hub
 image_generation_tool = load_tool("agents-course/text-to-image", trust_remote_code=True)
@@ -54,7 +57,7 @@ with open("prompts.yaml", 'r') as stream:
     prompt_templates = yaml.safe_load(stream)
     
 agent = CodeAgent(
-    model=model,
+    model=llm_model,
     tools=[final_answer], ## add your tools here (don't remove final answer)
     max_steps=6,
     verbosity_level=1,