Update app.py

app.py

@@ -18,6 +18,11 @@ from langchain_community.tools.tavily_research import TavilySearchResults
 # Para manejar variables de entorno (opcional si solo usas secretos de HF)
 from dotenv import load_dotenv
 
+# Para extraer el Task ID de la pregunta
+import re
+# Para leer PDFs
+import pymupdf # Asegúrate de que este import esté aquí si lo usas en download_and_read_task_file
+
 # Cargar variables de entorno si estás desarrollando localmente
 # load_dotenv() # Descomenta si desarrollas localmente y tienes .env
 
@@ -31,7 +36,6 @@ class BasicAgent:
         print("BasicAgent initialized.")
 
         # --- 1. Configuración de las Claves API ---
-        # Se leerán automáticamente de los secretos del Space de HF o de .env si load_dotenv() se usa.
         google_api_key = os.getenv("GOOGLE_API_KEY")
         tavily_api_key = os.getenv("TAVILY_API_KEY")
 
@@ -41,49 +45,41 @@ class BasicAgent:
             raise ValueError("TAVILY_API_KEY environment variable not set. Please add it to your Hugging Face Space secrets.")
 
         # --- 2. Inicialización del LLM (Gemini Pro) ---
-        # Puedes probar con "gemini-pro" o "gemini-1.5-pro" si tienes acceso y tu Space lo soporta.
         self.llm = ChatGoogleGenerativeAI(
             model="gemini-pro",
             google_api_key=google_api_key,
-            temperature=0.1, # Más bajo para respuestas más consistentes y precisas
-            max_tokens=2048 # Aumenta si necesitas respuestas más largas
+            temperature=0.1,
+            max_tokens=2048
         )
         print("LLM (Gemini Pro) initialized.")
 
         # --- 3. Definición de Herramientas ---
-        # a) Tavily Search (MUY IMPORTANTE para GAIA)
-        self.tavily_search_tool = TavilySearchResults(api_key=tavily_api_key, max_results=5) # max_results limita los resultados
+        # a) Tavily Search
+        self.tavily_search_tool = TavilySearchResults(api_key=tavily_api_key, max_results=5)
 
-        # b) Herramienta para descargar y leer archivos (adaptada de nuestra conversación anterior)
-        # Asegúrate de que DEFAULT_API_URL esté accesible en el scope de la clase
+        # b) Herramienta para descargar y leer archivos
         self.api_url = DEFAULT_API_URL
 
         def download_and_read_task_file(task_id: str, filename: str) -> str:
             """
             Downloads a file associated with a task_id from the API and returns its content.
             Supports text, CSV, JSON, and PDF files.
-            Args:
-                task_id (str): The ID of the task associated with the file.
-                filename (str): The name of the file to download (e.g., "document.pdf", "data.csv").
-            Returns:
-                str: The content of the file as a string.
             """
             file_url = f"{self.api_url}/files/{task_id}"
             print(f"DEBUG: Attempting to download file from: {file_url} (filename: {filename})")
             try:
                 response = requests.get(file_url, timeout=30, stream=True)
-                response.raise_for_status() # Raise an exception for bad status codes
+                response.raise_for_status()
 
-                temp_filepath = f"/tmp/{filename}" # Use /tmp for ephemeral storage in Space
+                temp_filepath = f"/tmp/{filename}"
                 with open(temp_filepath, 'wb') as f:
                     for chunk in response.iter_content(chunk_size=8192):
                         f.write(chunk)
 
                 content = ""
-                # Process the file based on its extension
                 if filename.lower().endswith(".pdf"):
                     try:
-                        import pymupdf # type: ignore
+                        # Asegúrate de que pymupdf esté instalado en requirements.txt
                         doc = pymupdf.open(temp_filepath)
                         for page in doc:
                             content += page.get_text()
@@ -96,15 +92,13 @@ class BasicAgent:
                     with open(temp_filepath, 'r', encoding='utf-8') as f:
                         content = f.read()
                 elif filename.lower().endswith((".png", ".jpg", ".jpeg", ".gif")):
-                    # Para imágenes, necesitarías OCR. Esto es más complejo.
-                    # Por ahora, solo indicamos que se descargó.
                     content = f"Image file '{filename}' downloaded. OCR not implemented."
                 else:
                     content = f"Unsupported file type for {filename}. Cannot extract content."
 
-                os.remove(temp_filepath) # Clean up the temporary file
+                os.remove(temp_filepath)
 
-                return f"Content of {filename}:\n{content[:1000]}..." # Return first 1000 chars for brevity
+                return f"Content of {filename}:\n{content[:1000]}..."
             except requests.exceptions.RequestException as e:
                 return f"Error downloading file '{filename}' from {file_url}: {e}"
             except Exception as e:
@@ -121,19 +115,10 @@ class BasicAgent:
                 func=download_and_read_task_file,
                 description="Descarga y lee el contenido de un archivo asociado a una tarea específica. Necesita 'task_id' (string) y 'filename' (string, e.g., 'document.pdf', 'data.csv'). Útil cuando la pregunta menciona archivos.",
             ),
-            # Puedes añadir más herramientas aquí:
-            # - Python REPL si necesitas ejecutar código Python
-            # - Wikipedia si quieres una fuente de conocimiento enciclopédico
-            # - Herramienta de cálculo, etc.
         ]
         print(f"Agent initialized with {len(self.tools)} tools.")
 
-
         # --- 4. Construir el Agente ReAct ---
-        # El prompt estándar de ReAct para modelos de chat
-        # prompt = hub.pull("hwchase17/react-chat") # Puedes probar este también
-
-        # Customización del prompt para "EXACT MATCH"
         custom_prompt_template = """Responde la siguiente pregunta de forma concisa y directa. Tu objetivo es proporcionar un "EXACT MATCH" con la respuesta correcta.
 
         INSTRUCCIONES CLAVE:
@@ -150,51 +135,34 @@ class BasicAgent:
         {agent_scratchpad}"""
 
         self.prompt = PromptTemplate.from_template(custom_prompt_template)
-
-        # Para create_react_agent, necesitamos decirle qué herramientas están disponibles y sus nombres.
-        # Esto se hace automáticamente si usas hub.pull("hwchase17/react-chat-json") o similar
-        # Pero con un prompt customizado, lo hacemos explícito.
         self.prompt = self.prompt.partial(
             tools="\n".join([f"{tool.name}: {tool.description}" for tool in self.tools]),
             tool_names=", ".join([tool.name for tool in self.tools]),
         )
 
-
         self.agent = create_react_agent(self.llm, self.tools, self.prompt)
-        # verbose=True es ESENCIAL para depurar y ver el razonamiento del agente.
-        # handle_parsing_errors=True para que el agente intente recuperarse de errores de formato.
         self.agent_executor = AgentExecutor(
             agent=self.agent,
             tools=self.tools,
             verbose=True,
             handle_parsing_errors=True,
-            max_iterations=15, # Limita el número de pasos para evitar bucles infinitos
-            agent_kwargs={"handle_parsing_errors": True} # También en el agente
+            max_iterations=15,
+            agent_kwargs={"handle_parsing_errors": True}
         )
         print("AgentExecutor initialized.")
 
     def __call__(self, question: str) -> str:
         print(f"\n--- Processing new question (first 100 chars): {question[:100]}...")
         try:
-            # Si la pregunta incluye "Task ID: [ID]", extrae el task_id.
-            # GAIA a menudo hace esto para indicar el archivo.
             task_id_match = re.search(r"Task ID:\s*([\w-]+)", question)
             current_task_id = task_id_match.group(1) if task_id_match else None
             print(f"Detected Task ID for question: {current_task_id}")
 
-
-            # Invocar al agente. Aquí es donde el agente usa el LLM y las herramientas.
-            # Pasamos el task_id para que la herramienta de descarga de archivos pueda usarlo si es necesario.
-            # Algunos agentes pueden requerir un formato de input diferente, ReAct usa "input".
             response = self.agent_executor.invoke({"input": question, "task_id": current_task_id})
-            # La respuesta final del agente React suele estar en 'output'
             final_answer = response.get("output", "No answer generated by agent.")
 
-            # Post-procesamiento para asegurar EXACT MATCH y eliminar texto adicional
-            # Esto es CRÍTICO para el scoring.
             final_answer = final_answer.strip()
-            # Elimina cualquier texto como "La respuesta es:", "The final answer is:", etc.
-            # Haz esto solo si detectas que el LLM aún añade verbosidad.
+            # Puedes descomentar la siguiente línea si el LLM sigue añadiendo verbosidad
             # if final_answer.lower().startswith(("the answer is", "la respuesta es", "final answer:")):
             #     final_answer = re.sub(r"^[Tt]he [Aa]nswer is: |^[Ll]a [Rr]espuesta es: |^[Ff]inal [Aa]nswer: ", "", final_answer, flags=re.IGNORECASE).strip()
 
@@ -202,12 +170,174 @@ class BasicAgent:
             return final_answer
         except Exception as e:
             print(f"Error during agent execution: {e}")
-            # En caso de error, puedes devolver un mensaje de error o una cadena vacía.
-            # Para el scoring, una cadena vacía o un error puede contar como incorrecto.
             return f"ERROR: {e}"
 
-# El resto del código de `run_and_submit_all` y Gradio permanece igual.
-# ... (código existente) ...
+# --- The `run_and_submit_all` function (originally from the template) ---
+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")
+    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
+
+    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
+
+    # 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 (THIS IS WHERE YOUR COPIED CODE GOES)
+    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)}"
+        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() 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(
+        fn=run_and_submit_all,
+        outputs=[status_output, results_table]
+    )
+
+if __name__ == "__main__":
+    print("\n" + "-"*30 + " App Starting " + "-"*30)
+    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 should be: https://{space_host_startup}.hf.space")
+    else:
+        print("ℹ️  SPACE_HOST environment variable not found (running locally?).")
+
+    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")
+    else:
+        print("ℹ️  SPACE_ID environment variable not found (running locally?). Repo URL cannot be determined.")
 
-# Asegúrate de importar 're' al principio del archivo si lo usas para task_id_match
-import re
+    print("-"*(60 + len(" App Starting ")) + "\n")
+    print("Launching Gradio Interface for Basic Agent Evaluation...")
+    demo.launch(debug=True, share=False)