Update app.py

app.py

@@ -365,7 +365,7 @@ class GAIAAgent:
         # Initialize the model with fallback options
         try:
             # Try powerful model first - but use one that's more widely available
-            model_id = "meta-llama/Llama-3.1-8B-Instruct"
+            model_id = "meta-llama/Llama-3.3-70B-Instruct"
             self.model = InferenceClientModel(model_id=model_id)
             print(f"✅ Model initialized successfully: {model_id}")
         except Exception as e:
@@ -494,247 +494,7 @@ Think step by step, use the appropriate tools, and provide only the final answer
                     result = result[1:-1]
                 
                 # Clean up decimal numbers (e.g., "42.0" -> "42")
-                if re.match(r'^\d+\.0+
-
-def run_and_submit_all(profile: gr.OAuthProfile | None):
-    """
-    Fetches all questions, runs the GAIAAgent 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
-
-    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 Enhanced Agent
-    try:
-        print("🚀 Initializing GAIA Agent with smolagents...")
-        agent = GAIAAgent()
-        print("✅ Enhanced agent ready for GAIA benchmark!")
-    except Exception as e:
-        error_msg = f"Error initializing agent: {e}"
-        print(f"❌ {error_msg}")
-        return error_msg, None
-    
-    # In the case of an app running as a hugging Face space, this link points toward your codebase
-    agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
-    print(f"Agent code link: {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 from GAIA benchmark.")
-    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
-
-    # 3. Run Enhanced Agent
-    results_log = []
-    answers_payload = []
-    print(f"🤖 Running enhanced GAIA agent on {len(questions_data)} questions...")
-    
-    for i, item in enumerate(questions_data, 1):
-        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
-        
-        print(f"\n📝 Processing question {i}/{len(questions_data)} (ID: {task_id})")
-        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[:100] + "..." if len(question_text) > 100 else question_text, 
-                "Submitted Answer": submitted_answer
-            })
-            print(f"✅ Answer for {task_id}: {submitted_answer}")
-        except Exception as e:
-             error_msg = f"AGENT ERROR: {e}"
-             print(f"❌ Error running agent on task {task_id}: {e}")
-             answers_payload.append({"task_id": task_id, "submitted_answer": error_msg})
-             results_log.append({
-                 "Task ID": task_id, 
-                 "Question": question_text[:100] + "..." if len(question_text) > 100 else 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)
-
-    # 4. Prepare Submission 
-    submission_data = {"username": username.strip(), "agent_code": agent_code, "answers": answers_payload}
-    status_update = f"🚀 Agent finished processing. 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()
-        result_data = response.json()
-        
-        score = result_data.get('score', 'N/A')
-        correct_count = result_data.get('correct_count', '?')
-        total_attempted = result_data.get('total_attempted', '?')
-        
-        final_status = (
-            f"🎉 Submission Successful!\n"
-            f"👤 User: {result_data.get('username')}\n"
-            f"📊 Overall Score: {score}% ({correct_count}/{total_attempted} correct)\n"
-            f"🎯 Target: >30% for certification\n"
-            f"💬 Message: {result_data.get('message', 'No message received.')}"
-        )
-        
-        if isinstance(score, (int, float)) and score >= 30:
-            final_status += f"\n🏆 CONGRATULATIONS! You've achieved the target score of 30%!"
-        elif isinstance(score, (int, float)):
-            final_status += f"\n📈 Keep improving! You need {30-score:.1f}% more to reach the target."
-        
-        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
-    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
-
-
-# --- Build Gradio Interface using Blocks ---
-with gr.Blocks(title="GAIA Agent Evaluation") as demo:
-    gr.Markdown("# 🤖 Enhanced GAIA Agent Evaluation Runner")
-    gr.Markdown(
-        """
-        **Enhanced Agent for GAIA Benchmark Certification**
-
-        This enhanced agent uses Hugging Face's **smolagents** framework with multiple specialized tools:
-        - 🔍 **Web Search**: DuckDuckGoSearchTool (from base toolkit) for finding information
-        - 🐍 **Python Interpreter**: Code execution capabilities (from base toolkit)
-        - 🌐 **Web Scraping**: Custom webpage visitor for content extraction  
-        - 🧮 **Mathematics**: Advanced calculation capabilities
-        - 📊 **Data Analysis**: Statistical analysis of numerical data
-        - 🔢 **Number Extraction**: Intelligent number parsing from text
-        - 📝 **Text Analysis**: Counting and text processing utilities
-        - 🤖 **LLM Model**: Llama-3.1-8B-Instruct for advanced reasoning
-
-        **Instructions:**
-        1. 🔄 **Clone this space** and customize the agent as needed
-        2. 🔑 **Log in** to your Hugging Face account using the button below
-        3. 🚀 **Click 'Run Evaluation'** to test your agent on GAIA benchmark questions
-        4. 🎯 **Target**: Score >30% for course certification
-
-        **Goal**: Answer GAIA level 1 validation questions with exact match precision.
-        
-        ---
-        ⚠️ **Note**: Processing all questions may take several minutes due to the complexity of reasoning required.
-        """
-    )
-
-    gr.LoginButton()
-
-    run_button = gr.Button("🚀 Run Evaluation & Submit All Answers", variant="primary", size="lg")
-
-    status_output = gr.Textbox(
-        label="📊 Evaluation Status & Results", 
-        lines=8, 
-        interactive=False,
-        placeholder="Click the button above to start the evaluation..."
-    )
-    
-    results_table = gr.DataFrame(
-        label="📋 Questions and Agent Responses", 
-        wrap=True,
-        headers=["Task ID", "Question", "Submitted Answer"]
-    )
-
-    run_button.click(
-        fn=run_and_submit_all,
-        outputs=[status_output, results_table]
-    )
-
-if __name__ == "__main__":
-    print("\n" + "="*60)
-    print("🤖 ENHANCED GAIA AGENT STARTING UP")
-    print("="*60)
-    
-    # Setup authentication
-    print("🔐 Setting up HuggingFace authentication...")
-    auth_success = setup_authentication()
-    
-    # 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")
-
-    if space_host_startup:
-        print(f"✅ SPACE_HOST found: {space_host_startup}")
-        print(f"   🌐 Runtime URL: https://{space_host_startup}.hf.space")
-    else:
-        print("ℹ️  SPACE_HOST environment variable not found (running locally?).")
-        if not auth_success:
-            print("💡 For local testing, you may need to run:")
-            print("   from huggingface_hub import notebook_login")
-            print("   notebook_login()")
-
-    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"   🔗 Code URL: https://huggingface.co/spaces/{space_id_startup}/tree/main")
-    else:
-        print("ℹ️  SPACE_ID environment variable not found (running locally?).")
-
-    print("="*60)
-    print("🚀 Launching Enhanced GAIA Agent Interface...")
-    print("🎯 Target: >30% score on GAIA benchmark")
-    print("="*60 + "\n")
-
-    demo.launch(debug=True, share=False), result):
+                if re.match(r'^\d+\.0+$', result):
                     result = str(int(float(result)))
                 
                 result = result.strip()
@@ -916,7 +676,7 @@ with gr.Blocks(title="GAIA Agent Evaluation") as demo:
         - 📊 **Data Analysis**: Statistical analysis of numerical data
         - 🔢 **Number Extraction**: Intelligent number parsing from text
         - 📝 **Text Analysis**: Counting and text processing utilities
-        - 🤖 **LLM Model**: Llama-3.1-8B-Instruct for advanced reasoning
+        - 🤖 **LLM Model**: Llama-3.3-70B-Instruct for advanced reasoning
 
         **Instructions:**
         1. 🔄 **Clone this space** and customize the agent as needed