Update app.py

app.py

@@ -7,11 +7,42 @@ import time
 import re
 from markdownify import markdownify
 from smolagents import Tool, DuckDuckGoSearchTool, CodeAgent, WikipediaSearchTool, LiteLLMModel
+from datetime import datetime, timedelta
+import threading
 
 # (Keep Constants as is)
 # --- Constants ---
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 
+# Rate limiting configuration
+RATE_LIMIT_REQUESTS = 18  # Stay below the 20/min limit
+RATE_LIMIT_WINDOW = 60    # 60 seconds
+REQUEST_DELAY = 4         # Minimum delay between requests (60/18 ≈ 3.33, using 4 for safety)
+
+class RateLimiter:
+    def __init__(self, max_requests=RATE_LIMIT_REQUESTS, window_seconds=RATE_LIMIT_WINDOW):
+        self.max_requests = max_requests
+        self.window_seconds = window_seconds
+        self.requests = []
+        self.lock = threading.Lock()
+    
+    def wait_if_needed(self):
+        with self.lock:
+            now = datetime.now()
+            # Remove requests older than the window
+            self.requests = [req_time for req_time in self.requests 
+                           if now - req_time < timedelta(seconds=self.window_seconds)]
+            
+            if len(self.requests) >= self.max_requests:
+                # Wait until we can make another request
+                oldest_request = min(self.requests)
+                wait_time = (oldest_request + timedelta(seconds=self.window_seconds) - now).total_seconds()
+                if wait_time > 0:
+                    print(f"Rate limit reached. Waiting {wait_time:.1f} seconds...")
+                    time.sleep(wait_time + 1)  # Add 1 second buffer
+            
+            # Record this request
+            self.requests.append(now)
 
 class DownloadTaskAttachmentTool(Tool):
     name = "download_file"
@@ -46,7 +77,6 @@ class DownloadTaskAttachmentTool(Tool):
     def __init__(self, *args, **kwargs):
         self.is_initialized = False
 
-
 class VisitWebpageTool(Tool):
     name = "visit_webpage"
     description = "Visits a webpage at the given url and reads its content as a markdown string. Use this to browse webpages."
@@ -58,25 +88,17 @@ class VisitWebpageTool(Tool):
             import requests
             from markdownify import markdownify
             from requests.exceptions import RequestException
-
             from smolagents.utils import truncate_content
         except ImportError as e:
             raise ImportError(
                 "You must install packages `markdownify` and `requests` to run this tool: for instance run `pip install markdownify requests`."
             ) from e
         try:
-            # Send a GET request to the URL with a 20-second timeout
             response = requests.get(url, timeout=20)
-            response.raise_for_status()  # Raise an exception for bad status codes
-
-            # Convert the HTML content to Markdown
+            response.raise_for_status()
             markdown_content = markdownify(response.text).strip()
-
-            # Remove multiple line breaks
             markdown_content = re.sub(r"\n{3,}", "\n\n", markdown_content)
-
             return truncate_content(markdown_content, 10000)
-
         except requests.exceptions.Timeout:
             return "The request timed out. Please try again later or check the URL."
         except RequestException as e:
@@ -87,11 +109,10 @@ class VisitWebpageTool(Tool):
     def __init__(self, *args, **kwargs):
         self.is_initialized = False
 
-
-# --- Basic Agent Definition ---
-# ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
+# --- Improved Agent Definition ---
 class BasicAgent:
     def __init__(self):
+        self.rate_limiter = RateLimiter()
         self.agent = CodeAgent(
             model=LiteLLMModel(model_id="openrouter/meta-llama/llama-4-maverick:free", api_key=os.getenv("OPENROUTER_KEY")),
             tools=[DuckDuckGoSearchTool(), WikipediaSearchTool(), VisitWebpageTool(), DownloadTaskAttachmentTool()],
@@ -99,11 +120,38 @@ class BasicAgent:
             additional_authorized_imports=['pandas','numpy','csv','subprocess', 'exec']
         )
         print("BasicAgent initialized.")
-    def __call__(self, question: str) -> str:
+    
+    def __call__(self, question: str, max_retries: int = 3) -> str:
         print(f"Agent received question (first 50 chars): {question[:50]}...")
-        agent_answer = self.agent.run(question)
-        print(f"Agent returning answer: {agent_answer}")
-        return agent_answer
+        
+        for attempt in range(max_retries):
+            try:
+                # Apply rate limiting
+                self.rate_limiter.wait_if_needed()
+                
+                # Run the agent
+                agent_answer = self.agent.run(question)
+                print(f"Agent returning answer: {agent_answer}")
+                return agent_answer
+                
+            except Exception as e:
+                error_msg = str(e)
+                print(f"Attempt {attempt + 1} failed: {error_msg}")
+                
+                # Check if it's a rate limit error
+                if "rate limit" in error_msg.lower() or "429" in error_msg:
+                    if attempt < max_retries - 1:
+                        wait_time = (attempt + 1) * 30  # Progressive backoff
+                        print(f"Rate limit hit. Waiting {wait_time} seconds before retry...")
+                        time.sleep(wait_time)
+                        continue
+                    else:
+                        return f"RATE_LIMIT_ERROR: {error_msg}"
+                else:
+                    # For other errors, return immediately
+                    return f"AGENT_ERROR: {error_msg}"
+        
+        return "MAX_RETRIES_EXCEEDED"
 
     def download_file(self, task_id: str) -> str:
         """
@@ -129,16 +177,15 @@ class BasicAgent:
             print(f"Error downloading file for task {task_id}: {e}")
             raise
 
-def run_and_submit_all( profile: gr.OAuthProfile | None):
+def run_and_submit_all(profile: gr.OAuthProfile | None, progress=gr.Progress()):
     """
     Fetches all questions, runs the BasicAgent on them, submits all answers,
-    and displays the results.
+    and displays the results with progress tracking.
     """
-    # --- Determine HF Space Runtime URL and Repo URL ---
-    space_id = os.getenv("SPACE_ID") # Get the SPACE_ID for sending link to the code
+    space_id = os.getenv("SPACE_ID")
 
     if profile:
-        username= f"{profile.username}"
+        username = f"{profile.username}"
         print(f"User logged in: {username}")
     else:
         print("User not logged in.")
@@ -148,33 +195,34 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
     questions_url = f"{api_url}/questions"
     submit_url = f"{api_url}/submit"
 
-    # 1. Instantiate Agent ( modify this part to create your agent)
+    # 1. Instantiate Agent
+    progress(0, desc="Initializing agent...")
     try:
         agent = BasicAgent()
     except Exception as e:
         print(f"Error instantiating agent: {e}")
         return f"Error initializing agent: {e}", None
-    # In the case of an app running as a hugging Face space, this link points toward your codebase ( usefull for others so please keep it public)
+    
     agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
     print(agent_code)
 
     # 2. Fetch Questions
+    progress(0.1, desc="Fetching questions...")
     print(f"Fetching questions from: {questions_url}")
     try:
         response = requests.get(questions_url, timeout=15)
         response.raise_for_status()
         questions_data = response.json()
         if not questions_data:
-             print("Fetched questions list is empty.")
-             return "Fetched questions list is empty or invalid format.", None
+            print("Fetched questions list is empty.")
+            return "Fetched questions list is empty or invalid format.", None
         print(f"Fetched {len(questions_data)} questions.")
     except requests.exceptions.RequestException as e:
         print(f"Error fetching questions: {e}")
         return f"Error fetching questions: {e}", None
     except requests.exceptions.JSONDecodeError as e:
-         print(f"Error decoding JSON response from questions endpoint: {e}")
-         print(f"Response text: {response.text[:500]}")
-         return f"Error decoding server response for questions: {e}", None
+        print(f"Error decoding JSON response from questions endpoint: {e}")
+        return f"Error decoding server response for questions: {e}", None
     except Exception as e:
         print(f"An unexpected error occurred fetching questions: {e}")
         return f"An unexpected error occurred fetching questions: {e}", None
@@ -182,8 +230,12 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
     # 3. Run your Agent
     results_log = []
     answers_payload = []
-    print(f"Running agent on {len(questions_data)} questions...")
-    for item in questions_data:
+    total_questions = len(questions_data)
+    print(f"Running agent on {total_questions} questions...")
+    
+    for i, item in enumerate(questions_data):
+        progress((0.1 + 0.8 * i / total_questions), desc=f"Processing question {i+1}/{total_questions}")
+        
         task_id = item.get("task_id")
         question_text = item.get("question")
         requires_file = item.get("requires_file", False)
@@ -192,29 +244,41 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
             print(f"Skipping item with missing task_id or question: {item}")
             continue
 
+        print(f"Processing task {task_id} ({i+1}/{total_questions})")
+        
         try:
             # Download file if required
             if requires_file:
                 file_path = agent.download_file(task_id)
                 print(f"File for task {task_id} saved at: {file_path}")
-                # Optionally, pass the file path to the agent if needed
                 submitted_answer = agent(f"{question_text} (File: {file_path})")
             else:
                 submitted_answer = agent(question_text)
 
+            # Check if the answer indicates an error
+            if submitted_answer.startswith(("RATE_LIMIT_ERROR", "AGENT_ERROR", "MAX_RETRIES_EXCEEDED")):
+                print(f"Error processing task {task_id}: {submitted_answer}")
+                results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": submitted_answer})
+                # Don't add to answers_payload for submission if it's an error
+                continue
+            
             answers_payload.append({"task_id": task_id, "submitted_answer": submitted_answer})
             results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": submitted_answer})
-            time.sleep(2)
+            
+            # Add delay between requests
+            time.sleep(REQUEST_DELAY)
+            
         except Exception as e:
+            error_msg = f"PROCESSING_ERROR: {e}"
             print(f"Error running agent on task {task_id}: {e}")
-            results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": f"AGENT ERROR: {e}"})
-
+            results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": error_msg})
 
     if not answers_payload:
-        print("Agent did not produce any answers to submit.")
-        return "Agent did not produce any answers to submit.", pd.DataFrame(results_log)
+        print("Agent did not produce any valid answers to submit.")
+        return "Agent did not produce any valid answers to submit. Check the results table for errors.", pd.DataFrame(results_log)
 
     # 4. Prepare Submission 
+    progress(0.9, desc="Submitting answers...")
     submission_data = {"username": username.strip(), "agent_code": agent_code, "answers": answers_payload}
     status_update = f"Agent finished. Submitting {len(answers_payload)} answers for user '{username}'..."
     print(status_update)
@@ -230,9 +294,12 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
             f"User: {result_data.get('username')}\n"
             f"Overall Score: {result_data.get('score', 'N/A')}% "
             f"({result_data.get('correct_count', '?')}/{result_data.get('total_attempted', '?')} correct)\n"
+            f"Processed: {len(results_log)} questions\n"
+            f"Successfully submitted: {len(answers_payload)} answers\n"
             f"Message: {result_data.get('message', 'No message received.')}"
         )
         print("Submission successful.")
+        progress(1.0, desc="Complete!")
         results_df = pd.DataFrame(results_log)
         return final_status, results_df
     except requests.exceptions.HTTPError as e:
@@ -262,7 +329,6 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
         results_df = pd.DataFrame(results_log)
         return status_message, results_df
 
-
 # --- Build Gradio Interface using Blocks ---
 with gr.Blocks() as demo:
     gr.Markdown("# Basic Agent Evaluation Runner")
@@ -270,14 +336,19 @@ with gr.Blocks() as demo:
         """
         **Instructions:**
 
-        1.  Please clone this space, then modify the code to define your agent's logic, the tools, the necessary packages, etc ...
-        2.  Log in to your Hugging Face account using the button below. This uses your HF username for submission.
-        3.  Click 'Run Evaluation & Submit All Answers' to fetch questions, run your agent, submit answers, and see the score.
+        1. Please clone this space, then modify the code to define your agent's logic, the tools, the necessary packages, etc.
+        2. Log in to your Hugging Face account using the button below. This uses your HF username for submission.
+        3. Click 'Run Evaluation & Submit All Answers' to fetch questions, run your agent, submit answers, and see the score.
 
         ---
-        **Disclaimers:**
-        Once clicking on the "submit button, it can take quite some time ( this is the time for the agent to go through all the questions).
-        This space provides a basic setup and is intentionally sub-optimal to encourage you to develop your own, more robust solution. For instance for the delay process of the submit button, a solution could be to cache the answers and submit in a seperate action or even to answer the questions in async.
+        **Improvements:**
+        - ✅ Rate limiting to prevent API errors
+        - ✅ Progressive retry logic with backoff
+        - ✅ Better error handling and categorization
+        - ✅ Progress tracking during execution
+        - ✅ Detailed status reporting
+        
+        **Note:** This improved version includes rate limiting to stay within the free tier limits of 20 requests per minute.
         """
     )
 
@@ -285,20 +356,19 @@ with gr.Blocks() as demo:
 
     run_button = gr.Button("Run Evaluation & Submit All Answers")
 
-    status_output = gr.Textbox(label="Run Status / Submission Result", lines=5, interactive=False)
-    # Removed max_rows=10 from DataFrame constructor
+    status_output = gr.Textbox(label="Run Status / Submission Result", lines=8, 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]
+        outputs=[status_output, results_table],
+        show_progress=True
     )
 
 if __name__ == "__main__":
     print("\n" + "-"*30 + " App Starting " + "-"*30)
-    # Check for SPACE_HOST and SPACE_ID at startup for information
     space_host_startup = os.getenv("SPACE_HOST")
-    space_id_startup = os.getenv("SPACE_ID") # Get SPACE_ID at startup
+    space_id_startup = os.getenv("SPACE_ID")
 
     if space_host_startup:
         print(f"✅ SPACE_HOST found: {space_host_startup}")
@@ -306,7 +376,7 @@ if __name__ == "__main__":
     else:
         print("ℹ️  SPACE_HOST environment variable not found (running locally?).")
 
-    if space_id_startup: # Print repo URLs if SPACE_ID is found
+    if space_id_startup:
         print(f"✅ SPACE_ID found: {space_id_startup}")
         print(f"   Repo URL: https://huggingface.co/spaces/{space_id_startup}")
         print(f"   Repo Tree URL: https://huggingface.co/spaces/{space_id_startup}/tree/main")
@@ -316,4 +386,4 @@ if __name__ == "__main__":
     print("-"*(60 + len(" App Starting ")) + "\n")
 
     print("Launching Gradio Interface for Basic Agent Evaluation...")
-    demo.launch(debug=True, share=False) 
+    demo.launch(debug=True, share=False)