Create app.py

app.py

@@ -464,145 +464,34 @@ Answer:"""
             return fixed_answer
 
 
-def run_and_submit_all( profile: gr.OAuthProfile | None, other_arg=None): # Modified to accept 2 arguments
-    """
-    Fetches all questions, runs the BasicAgent on them, submits all answers,
-    and displays the results.
-    """
-    print("run_and_submit_all function started.") # Debugging print at function start
-    # --- 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.")
-        # --- SIMULAÇÃO PARA COLAB ---
-        username = "colab_test_user" # <--- Adicione esta linha para simular um usuário no Colab
-        print(f"User not logged in, simulating for Colab: {username}")
-        # return "Please Login to Hugging Face with the button.", None # Comente esta linha para testar no Colab
-
-    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)
-    print("Attempting to instantiate BasicAgent...") # Debugging print before instantiation
-    try:
-        agent = BasicAgent()
-        print("BasicAgent instantiated successfully.") # Debugging print after instantiation
-    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" if space_id else "No SPACE_ID found, cannot generate agent_code URL."
-    print(agent_code)
-
-    # 2. Fetch Questions
-    print(f"Fetching questions from: {questions_url}")
-    questions_data = None # Initialize to None
-    try:
-        response = requests.get(questions_url, timeout=15)
-        response.raise_for_status()
-        questions_data = response.json()
-        # Add check for empty or non-list questions_data immediately after fetching
-        if not isinstance(questions_data, list) or not questions_data:
-             print(f"Fetched questions_data is empty or not a list. Type: {type(questions_data)}")
-             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 the response text for debugging if JSON decoding fails
-         print(f"Response text: {response.text[:500] if 'response' in locals() else 'No response object'}")
-         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 your Agent
-    results_log = []
-    answers_payload = []
-    print(f"Running agent on {len(questions_data)} questions...")
-    # The check that questions_data is a list is now done immediately after fetching
-    for item in questions_data:
-        # Add check for None or non-dict item before accessing keys
-        if item is None or not isinstance(item, dict):
-            print(f"Skipping invalid item in questions_data: {item}")
-            continue
-        task_id = item.get("task_id")
-        question_text = item.get("question")
-        if not task_id or not isinstance(task_id, (str, int)) or not question_text or not isinstance(question_text, str):
-            print(f"Skipping item with missing or invalid task_id or question: {item}")
-            continue
-        print(f"Processing Task ID: {task_id}") # Debugging task ID
-        try:
-            # Here, we only pass the question text for now, as the API doesn't support video input
-            # The video processing logic is added but not triggered by this function
-            submitted_answer = agent(question_text)
-            print(f"Agent returned answer for {task_id}: {submitted_answer[:50]}...") # Debugging returned answer
-            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()
-        result_data = response.json()
-        final_status = (
-            f"Submission Successful!\n"
-            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"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)}"
-            status_message = f"Submission Failed: {error_detail}"
-            print(status_message)
-            # If submission fails, also return the results log so the user can see what was attempted
-            results_df = pd.DataFrame(results_log)
-            return status_message, results_df
-        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
-        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
+# --- Gradio Interface Setup ---
+# Define the Gradio interface
+with gr.Blocks() as demo:
+    gr.Markdown(
+        """
+        # Agente de IA para o Desafio Hugging Face
+        Este agente usa o Google Gemini para responder perguntas e a SerpAPI para realizar buscas na web.
+        Ele também tem uma funcionalidade (não ativada pelo desafio) para processar vídeos.
+        """
+    )
+
+    with gr.Row():
+        with gr.Column():
+            question_input = gr.Textbox(label="Sua Pergunta", placeholder="Ex: O que é inteligência artificial?")
+            # Não incluímos o input de vídeo aqui, pois o desafio não o usa diretamente
+            # video_input = gr.Video(label="Upload de Vídeo (Opcional)", type="filepath")
+            submit_button = gr.Button("Executar Agente e Submeter Respostas")
+        with gr.Column():
+            status_output = gr.Textbox(label="Status da Execução", interactive=False)
+            results_dataframe = gr.Dataframe(label="Resultados Detalhados", interactive=False, headers=["Task ID", "Question", "Submitted Answer"])
+
+    # Conectar o botão à função run_and_submit_all
+    # O componente gr.Login() fornece o 'profile' automaticamente quando o usuário faz login
+    submit_button.click(
+        fn=run_and_submit_all,
+        inputs=[gr.Login(every=None), None], # 'None' para o 'other_arg' que não estamos usando
+        outputs=[status_output, results_dataframe]
+    )
+
+# Lançar o aplicativo Gradio
+demo.launch(share=True) # share=True gera um link público para o seu Space (útil para testes)