Update app.py

app.py

@@ -3,141 +3,135 @@ import gradio as gr
 import requests
 import inspect 
 import pandas as pd
-# ECCO LA MODIFICA QUI SOTTO:
-from smolagents import CodeAgent, DuckDuckGoSearchTool, InferenceClientModel
+from smolagents import CodeAgent, DuckDuckGoSearchTool, InferenceClientModel, tool
 
 # --- Constants ---
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 
+# ==========================================
+# 🚀 NUOVO TOOL: LETTORE DI PAGINE WEB
+# ==========================================
+@tool
+def visit_webpage(url: str) -> str:
+    """Visits a webpage and returns its text content. Use this to read articles or Wikipedia pages.
+    Args:
+        url: The URL of the webpage to visit.
+    """
+    try:
+        import requests
+        from bs4 import BeautifulSoup
+        headers = {'User-Agent': 'Mozilla/5.0'}
+        response = requests.get(url, headers=headers, timeout=10)
+        response.raise_for_status()
+        soup = BeautifulSoup(response.text, 'html.parser')
+        # Rimuove script e stili per pulire il testo
+        for script in soup(["script", "style"]):
+            script.extract()
+        text = soup.get_text(separator='\n', strip=True)
+        # Restituisce i primi 10000 caratteri per non intasare la memoria dell'agente
+        return text[:10000] 
+    except Exception as e:
+        return f"Error reading the webpage: {str(e)}"
+
 # --- Basic Agent Definition ---
-# ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
 class BasicAgent:
     def __init__(self):
-        print("Inizializzazione del VERO Agente AI...")
+        print("Inizializzazione dell'Agente AI POTENZIATO...")
         
-        # 1. Definisci il modello (usiamo Qwen su HF) - ECCO LA MODIFICA QUI SOTTO:
+        # 1. Definisci il modello
         self.model = InferenceClientModel(model_id="Qwen/Qwen2.5-Coder-32B-Instruct")
         
-        # 2. Fornisci all'agente gli strumenti per cercare su internet
-        self.tools = [DuckDuckGoSearchTool()]
+        # 2. Strumenti: Ricerca + Lettura Web
+        self.tools = [DuckDuckGoSearchTool(), visit_webpage]
         
-        # 3. Crea l'agente
+        # 3. Crea l'agente (aumentati i max_steps a 15 per farlo pensare di più)
         self.agent = CodeAgent(
             tools=self.tools,
             model=self.model,
-            max_steps=10,
-            additional_authorized_imports=["requests", "bs4", "json", "time"]
+            max_steps=15,
+            additional_authorized_imports=["requests", "bs4", "json", "time", "math", "datetime"]
         )
         
-        # 4. IL TRUCCO PER L'EXACT MATCH: Istruzioni severissime
+        # 4. PROMPT CORAZZATO PER EXACT MATCH
         self.prompt_template = """
-        You must answer the following question.
+        You are an expert AI solving the GAIA benchmark. You must answer the following question.
         
-        CRITICAL RULE (EXACT MATCH): 
-        You must output ONLY the exact requested answer. 
-        Absolutely NO introductory phrases, no "The answer is...", no "FINAL ANSWER:". 
-        Just return the raw data, word, or number.
+        CRITICAL RULES:
+        1. If you need information, use DuckDuckGoSearchTool to find URLs, then use the visit_webpage tool to read the content of those URLs.
+        2. EXACT MATCH ONLY: You must output ONLY the exact requested answer. 
+        3. Absolutely NO introductory phrases, no "The answer is...", no "FINAL ANSWER:". 
+        4. If the question asks for a number, return JUST the number. If it asks for a name, return JUST the name.
         
         Question to solve: {question}
         """
 
     def __call__(self, question: str) -> str:
-        print(f"Agent received question (first 50 chars): {question[:50]}...")
+        print(f"Agent received question: {question[:50]}...")
         try:
-            # Combina la domanda con le nostre istruzioni severe
             formatted_prompt = self.prompt_template.format(question=question)
-            
-            # Fai ragionare e agire il tuo agente!
             answer = self.agent.run(formatted_prompt)
-            
-            # Pulisce la stringa da eventuali spazi extra
             final_answer = str(answer).strip() 
+            
+            # Un'ultima pulizia di sicurezza se l'LLM fa di testa sua
+            if "FINAL ANSWER:" in final_answer:
+                final_answer = final_answer.split("FINAL ANSWER:")[-1].strip()
+                
             print(f"L'agente ha trovato la risposta: {final_answer}")
             return final_answer
         except Exception as e:
-            print(f"Errore durante l'esecuzione dell'agente: {e}")
+            print(f"Errore: {e}")
             return "Error"
 
 
 def run_and_submit_all( profile: gr.OAuthProfile | None):
-    """
-    Fetches all questions, runs the BasicAgent on them, submits all answers,
-    and displays the results.
-    """
-    # --- 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}"
         print(f"User logged in: {username}")
     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"
 
-    # 1. Instantiate Agent ( modify this part to create your 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
-    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(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
     except Exception as e:
-        print(f"An unexpected error occurred fetching questions: {e}")
-        return f"An unexpected error occurred fetching questions: {e}", None
+        return f"Error fetching questions: {e}", None
 
-    # 3. Run your Agent
     results_log = []
     answers_payload = []
-    print(f"Running agent on {len(questions_data)} questions...")
+    
     for item in questions_data:
         task_id = item.get("task_id")
         question_text = item.get("question")
         if not task_id or question_text is None:
-            print(f"Skipping item with missing task_id or question: {item}")
             continue
         try:
             submitted_answer = agent(question_text)
             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})
         except Exception as 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}"})
 
     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)
 
-    # 4. Prepare Submission 
     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)
-
-    # 5. Submit
-    print(f"Submitting {len(answers_payload)} answers to: {submit_url}")
+    
     try:
         response = requests.post(submit_url, json=submission_data, timeout=60)
         response.raise_for_status()
@@ -149,61 +143,17 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
             f"({result_data.get('correct_count', '?')}/{result_data.get('total_attempted', '?')} correct)\n"
             f"Message: {result_data.get('message', 'No message received.')}"
         )
-        print("Submission successful.")
-        results_df = pd.DataFrame(results_log)
-        return final_status, results_df
-    except requests.exceptions.HTTPError as e:
-        error_detail = f"Server responded with status {e.response.status_code}."
-        try:
-            error_json = e.response.json()
-            error_detail += f" Detail: {error_json.get('detail', e.response.text)}"
-        except requests.exceptions.JSONDecodeError:
-            error_detail += f" Response: {e.response.text[:500]}"
-        status_message = f"Submission Failed: {error_detail}"
-        print(status_message)
-        results_df = pd.DataFrame(results_log)
-        return status_message, results_df
-    except requests.exceptions.Timeout:
-        status_message = "Submission Failed: The request timed out."
-        print(status_message)
-        results_df = pd.DataFrame(results_log)
-        return status_message, results_df
-    except requests.exceptions.RequestException as e:
-        status_message = f"Submission Failed: Network error - {e}"
-        print(status_message)
-        results_df = pd.DataFrame(results_log)
-        return status_message, results_df
+        return final_status, pd.DataFrame(results_log)
     except Exception as e:
-        status_message = f"An unexpected error occurred during submission: {e}"
-        print(status_message)
-        results_df = pd.DataFrame(results_log)
-        return status_message, results_df
-
+        status_message = f"Submission Failed: {e}"
+        return status_message, pd.DataFrame(results_log)
 
 # --- Build Gradio Interface using Blocks ---
 with gr.Blocks() as demo:
     gr.Markdown("# Basic Agent Evaluation Runner")
-    gr.Markdown(
-        """
-        **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.
-
-        ---
-        **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.
-        """
-    )
-
     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(
@@ -212,25 +162,6 @@ with gr.Blocks() as demo:
     )
 
 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
-
-    if space_host_startup:
-        print(f"✅ SPACE_HOST found: {space_host_startup}")
-        print(f"   Runtime URL should be: https://{space_host_startup}.hf.space")
-    else:
-        print("ℹ️  SPACE_HOST environment variable not found (running locally?).")
-
-    if space_id_startup: # Print repo URLs if SPACE_ID is found
-        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")
-    else:
-        print("ℹ️  SPACE_ID environment variable not found (running locally?). Repo URL cannot be determined.")
-
-    print("-"*(60 + len(" App Starting ")) + "\n")
-
-    print("Launching Gradio Interface for Basic Agent Evaluation...")
+    space_id_startup = os.getenv("SPACE_ID")
     demo.launch(debug=True, share=False)