update the final code to fix the too many request error

app.py

@@ -6,20 +6,17 @@ import inspect
 import pandas as pd
 from smolagents import (
     CodeAgent,
-    LiteLLMModel,
+    HfApiModel,
     DuckDuckGoSearchTool,
     WikipediaSearchTool,
     PythonInterpreterTool,
     tool,
 )
 
-# (Keep Constants as is)
 # --- Constants ---
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 
 # --- Basic Agent Definition ---
-# --- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
-
 @tool
 def get_current_date_time() -> str:
     """Returns the current date and time in ISO format."""
@@ -29,26 +26,27 @@ def get_current_date_time() -> str:
 class BasicAgent:
     def __init__(self):
         print("BasicAgent initialized.")
-        gemini_api_key = os.getenv("GEMINI_API_KEY")
-        if not gemini_api_key:
-            raise ValueError("GEMINI_API_KEY environment variable not set")
-        self.model = LiteLLMModel(
-            model_id="gemini/gemini-2.0-flash-lite",
-            api_key=gemini_api_key,
+        
+        # Using Hugging Face's free Serverless Inference API
+        # Qwen2.5-Coder-32B-Instruct is the default and highly recommended for this course
+        self.model = HfApiModel(
+            model_id="Qwen/Qwen2.5-Coder-32B-Instruct",
         )
+        
         self.tools = [
             DuckDuckGoSearchTool(),
             WikipediaSearchTool(),
             PythonInterpreterTool(),
             get_current_date_time,
         ]
+        
         self.agent = CodeAgent(
             tools=self.tools,
             model=self.model,
             max_steps=8,
             additional_authorized_imports=["datetime", "re", "json", "math", "collections"],
         )
-        print("BasicAgent ready with Gemini 2.0 Flash-Lite (CodeAgent).")
+        print("BasicAgent ready with Qwen2.5-Coder-32B-Instruct (CodeAgent).")
 
     def __call__(self, question: str) -> str:
         print(f"Agent received question: {question[:80]}...")
@@ -69,8 +67,7 @@ class BasicAgent:
                     return f"Error: {err}"
         return "Error: Rate limit exceeded after retries"
 
-
-# --- The rest of the code (keep as-is) ---
+# --- The rest of the code ---
 def run_and_submit_all(profile: gr.OAuthProfile | None):
     space_id = os.getenv("SPACE_ID")
     if profile:
@@ -79,17 +76,21 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
     else:
         print("User not logged in.")
         return "Please Login to Hugging Face with the button.", None
+        
     api_url = DEFAULT_API_URL
     questions_url = f"{api_url}/questions"
     submit_url = f"{api_url}/submit"
+    
     try:
         agent = BasicAgent()
     except Exception as e:
         print(f"Error instantiating agent: {e}")
         return f"Error initializing agent: {e}", None
+        
     agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
     print(f"Agent code: {agent_code}")
     print(f"Fetching questions from: {questions_url}")
+    
     try:
         response = requests.get(questions_url, timeout=15)
         response.raise_for_status()
@@ -100,14 +101,17 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
     except Exception as e:
         print(f"Error fetching questions: {e}")
         return f"Error fetching questions: {e}", None
+        
     results_log = []
     answers_payload = []
     print(f"Running agent on {len(questions_data)} questions...")
+    
     for i, item in enumerate(questions_data):
         task_id = item.get("task_id")
         question_text = item.get("question")
         if not task_id or not question_text:
             continue
+            
         try:
             submitted_answer = agent(question_text)
             answers_payload.append({"task_id": task_id, "submitted_answer": submitted_answer})
@@ -115,11 +119,16 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
         except Exception as e:
             print(f"Error on task {task_id}: {e}")
             results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": f"ERROR: {e}"})
-        time.sleep(3)
+            
+        # Wait 10 seconds between questions to play nicely with HF inference servers
+        time.sleep(10)
+        
     if not answers_payload:
         return "No answers.", pd.DataFrame(results_log)
+        
     submission_data = {"username": username.strip(), "agent_code": agent_code, "answers": answers_payload}
     print(f"Submitting {len(answers_payload)} answers...")
+    
     try:
         response = requests.post(submit_url, json=submission_data, timeout=60)
         response.raise_for_status()
@@ -137,22 +146,22 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
         print(f"Submission error: {e}")
         return f"Submission failed: {e}", pd.DataFrame(results_log)
 
-
 # --- Build Gradio UI ---
 with gr.Blocks() as demo:
     gr.Markdown("# Basic Agent Evaluation Runner")
     gr.Markdown(
         """
         **Instructions:**
-        1. Clone this space and set `GEMINI_API_KEY` in your Space secrets.
+        1. Ensure you have your `HF_TOKEN` in your Space secrets (Settings -> Secrets).
         2. Log in with your Hugging Face account below.
-        3. Click 'Run Evaluation & Submit' to start.
+        3. Click 'Run Evaluation & Submit' to start. Please be patient, as inference will take a few minutes to process 20 questions securely.
         """
     )
     gr.LoginButton()
     run_button = gr.Button("Run Evaluation & Submit All Answers")
     status_output = gr.Textbox(label="Run Status / Submission Result", lines=5, interactive=False)
     results_table = gr.DataFrame(label="Questions and Agent Answers", wrap=True)
+    
     run_button.click(
         fn=run_and_submit_all,
         outputs=[status_output, results_table]
@@ -160,4 +169,4 @@ with gr.Blocks() as demo:
 
 if __name__ == "__main__":
     print("Starting Gradio app...")
-    demo.launch(debug=True, share=False)
+    demo.launch(debug=True, share=False)