Update app.py

app.py

@@ -1,119 +1,247 @@
+"""
+Agent Evaluation Runner
+======================
+This module implements a framework for evaluating LLM agents against a set of questions
+and submitting the results to a scoring server.
+
+Main components:
+- BasicAgent: The agent implementation that processes questions
+- Evaluation functions: For running and submitting results
+- Gradio interface: For user interaction
+"""
+
 import os
-import inspect
+import logging
+from typing import Tuple, List, Dict, Any, Optional
+
 import gradio as gr
 import requests
 import pandas as pd
 from langchain_core.messages import HumanMessage
-from agent import build_graph
 
+from agent import build_graph
 
+# Configure logging
+logging.basicConfig(
+    level=logging.INFO,
+    format="%(asctime)s - %(levelname)s - %(message)s",
+    datefmt="%Y-%m-%d %H:%M:%S"
+)
+logger = logging.getLogger(__name__)
 
-# (Keep Constants as is)
 # --- Constants ---
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
-
-# --- Basic Agent Definition ---
-# ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
+REQUEST_TIMEOUT = 60  # seconds
 
 
 class BasicAgent:
-    """A langgraph agent."""
+    """
+    A LangGraph-based agent that answers questions using a graph-based workflow.
+    
+    This agent takes natural language questions, processes them through a 
+    predefined graph workflow, and returns the answer.
+    
+    Attributes:
+        graph: The LangGraph workflow that processes the questions
+    """
+    
     def __init__(self):
-        print("BasicAgent initialized.")
+        """Initialize the agent with a graph-based workflow."""
+        logger.info("Initializing BasicAgent")
         self.graph = build_graph()
-
+        
     def __call__(self, question: str) -> str:
-        print(f"Agent received question (first 50 chars): {question[:50]}...")
+        """
+        Process a question and return an answer.
+        
+        Args:
+            question: The natural language question to process
+            
+        Returns:
+            The agent's answer to the question
+        """
+        logger.info(f"Processing question (first 50 chars): {question[:50]}...")
+        
         # Wrap the question in a HumanMessage from langchain_core
         messages = [HumanMessage(content=question)]
+        
+        # Process through the graph
         messages = self.graph.invoke({"messages": messages})
+        
+        # Extract and clean the answer
         answer = messages['messages'][-1].content
-        return answer[14:]
+        
+        # Remove the "FINAL ANSWER:" prefix if present
+        return answer[14:] if answer.startswith("FINAL ANSWER:") else answer
 
 
-def run_and_submit_all( profile: gr.OAuthProfile | None):
+def fetch_questions(api_url: str) -> List[Dict[str, Any]]:
     """
-    Fetches all questions, runs the BasicAgent on them, submits all answers,
-    and displays the results.
+    Fetch questions from the evaluation server.
+    
+    Args:
+        api_url: Base URL of the evaluation API
+        
+    Returns:
+        List of question data dictionaries
+        
+    Raises:
+        requests.exceptions.RequestException: If there's an error fetching questions
     """
-    # --- 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"
+    logger.info(f"Fetching questions from: {questions_url}")
+    
+    response = requests.get(questions_url, timeout=REQUEST_TIMEOUT)
+    response.raise_for_status()
+    
+    questions_data = response.json()
+    if not questions_data:
+        raise ValueError("Fetched questions list is empty or invalid format")
+    
+    logger.info(f"Successfully fetched {len(questions_data)} questions")
+    return questions_data
 
-    # 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
-
-    # 3. Run your Agent
+def run_agent_on_questions(
+    agent: BasicAgent,
+    questions_data: List[Dict[str, Any]]
+) -> Tuple[List[Dict[str, Any]], List[Dict[str, Any]]]:
+    """
+    Run the agent on a list of questions.
+    
+    Args:
+        agent: The agent to run
+        questions_data: List of question data dictionaries
+        
+    Returns:
+        Tuple of (answers_payload, results_log)
+    """
     results_log = []
     answers_payload = []
-    print(f"Running agent on {len(questions_data)} questions...")
+    
+    logger.info(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}")
+            logger.warning(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})
+            
+            # Prepare answer for submission
+            answers_payload.append({
+                "task_id": task_id,
+                "submitted_answer": submitted_answer
+            })
+            
+            # Log result for display
+            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}"})
+            logger.error(f"Error running agent on task {task_id}: {e}", exc_info=True)
+            
+            # Log error in results
+            results_log.append({
+                "Task ID": task_id,
+                "Question": question_text,
+                "Submitted Answer": f"AGENT ERROR: {e}"
+            })
+    
+    return answers_payload, results_log
 
-    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)
+def submit_answers(
+    api_url: str,
+    username: str,
+    agent_code: str,
+    answers_payload: List[Dict[str, Any]]
+) -> Dict[str, Any]:
+    """
+    Submit answers to the evaluation server.
+    
+    Args:
+        api_url: Base URL of the evaluation API
+        username: Hugging Face username
+        agent_code: URL to the agent code repository
+        answers_payload: List of answer dictionaries
+        
+    Returns:
+        Response data from the server
+        
+    Raises:
+        requests.exceptions.RequestException: If there's an error during submission
+    """
+    submit_url = f"{api_url}/submit"
+    
+    # Prepare submission data
+    submission_data = {
+        "username": username.strip(),
+        "agent_code": agent_code,
+        "answers": answers_payload
+    }
+    
+    logger.info(f"Submitting {len(answers_payload)} answers to: {submit_url}")
+    
+    # Submit answers
+    response = requests.post(submit_url, json=submission_data, timeout=REQUEST_TIMEOUT)
+    response.raise_for_status()
+    
+    result_data = response.json()
+    logger.info("Submission successful")
+    
+    return result_data
+
 
-    # 5. Submit
-    print(f"Submitting {len(answers_payload)} answers to: {submit_url}")
+def run_and_submit_all(profile: Optional[gr.OAuthProfile] = None) -> Tuple[str, pd.DataFrame]:
+    """
+    Fetches all questions, runs the BasicAgent on them, submits all answers,
+    and displays the results.
+    
+    Args:
+        profile: Gradio OAuth profile containing user information
+        
+    Returns:
+        Tuple of (status_message, results_dataframe)
+    """
+    # Check if user is logged in
+    if not profile:
+        logger.warning("User not logged in")
+        return "Please Login to Hugging Face with the button.", None
+    
+    username = profile.username
+    logger.info(f"User logged in: {username}")
+    
+    # Get the space ID for linking to code
+    space_id = os.getenv("SPACE_ID")
+    api_url = DEFAULT_API_URL
+    agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
+    
     try:
-        response = requests.post(submit_url, json=submission_data, timeout=60)
-        response.raise_for_status()
-        result_data = response.json()
+        # 1. Instantiate Agent
+        agent = BasicAgent()
+        
+        # 2. Fetch Questions
+        questions_data = fetch_questions(api_url)
+        
+        # 3. Run Agent on Questions
+        answers_payload, results_log = run_agent_on_questions(agent, questions_data)
+        
+        if not answers_payload:
+            logger.warning("Agent did not produce any answers to submit")
+            return "Agent did not produce any answers to submit.", pd.DataFrame(results_log)
+        
+        # 4. Submit Answers
+        result_data = submit_answers(api_url, username, agent_code, answers_payload)
+        
+        # 5. Format and Return Results
         final_status = (
             f"Submission Successful!\n"
             f"User: {result_data.get('username')}\n"
@@ -121,86 +249,119 @@ 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:
+        # Handle HTTP errors with detailed error information
         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)
+        logger.error(status_message)
+        
+        results_df = pd.DataFrame(results_log if 'results_log' in locals() else [])
         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)
+        status_message = f"Submission Failed: The request timed out after {REQUEST_TIMEOUT} seconds"
+        logger.error(status_message)
+        
+        results_df = pd.DataFrame(results_log if 'results_log' in locals() else [])
         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)
+        status_message = f"An unexpected error occurred: {str(e)}"
+        logger.error(status_message, exc_info=True)
+        
+        results_df = pd.DataFrame(results_log if 'results_log' in locals() else [])
         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.
-        """
-    )
+def create_gradio_interface() -> gr.Blocks:
+    """
+    Create and configure the Gradio interface.
+    
+    Returns:
+        Configured Gradio Blocks interface
+    """
+    with gr.Blocks() as demo:
+        gr.Markdown("# Agent Evaluation Runner")
+        gr.Markdown(
+            """
+            ## Instructions
+            
+            1. **Clone this space** and modify the code to define your agent's logic, tools, and dependencies
+            2. **Log in to your Hugging Face account** using the button below (required for submission)
+            3. **Run Evaluation** to fetch questions, run your agent, and submit answers
+            
+            ## Important Notes
+            
+            - The evaluation process may take several minutes to complete
+            - This agent framework is intentionally minimal to allow for your own improvements
+            - Consider implementing caching or async processing for better performance
+            """
+        )
+
+        gr.LoginButton()
 
-    gr.LoginButton()
+        run_button = gr.Button("Run Evaluation & Submit All Answers", variant="primary")
 
-    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
+        )
 
-    status_output = gr.Textbox(label="Run Status / Submission Result", lines=5, interactive=False)
-    # Removed max_rows=10 from DataFrame constructor
-    results_table = gr.DataFrame(label="Questions and Agent Answers", wrap=True)
+        run_button.click(
+            fn=run_and_submit_all,
+            outputs=[status_output, results_table]
+        )
+        
+    return demo
 
-    run_button.click(
-        fn=run_and_submit_all,
-        outputs=[status_output, results_table]
-    )
 
-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")
+def check_environment() -> None:
+    """
+    Check and log environment variables at startup.
+    """
+    logger.info("-" * 30 + " App Starting " + "-" * 30)
+    
+    # Check for SPACE_HOST
+    space_host = os.getenv("SPACE_HOST")
+    if space_host:
+        logger.info(f"✅ SPACE_HOST found: {space_host}")
+        logger.info(f"   Runtime URL should be: https://{space_host}.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")
+        logger.info("ℹ️  SPACE_HOST environment variable not found (running locally?).")
+    
+    # Check for SPACE_ID
+    space_id = os.getenv("SPACE_ID")
+    if space_id:
+        logger.info(f"✅ SPACE_ID found: {space_id}")
+        logger.info(f"   Repo URL: https://huggingface.co/spaces/{space_id}")
+        logger.info(f"   Repo Tree URL: https://huggingface.co/spaces/{space_id}/tree/main")
     else:
-        print("ℹ️  SPACE_ID environment variable not found (running locally?). Repo URL cannot be determined.")
+        logger.info("ℹ️  SPACE_ID environment variable not found (running locally?).")
+    
+    logger.info("-" * (60 + len(" App Starting ")) + "\n")
 
-    print("-"*(60 + len(" App Starting ")) + "\n")
 
-    print("Launching Gradio Interface for Basic Agent Evaluation...")
+if __name__ == "__main__":
+    # Check environment at startup
+    check_environment()
+    
+    # Create and launch Gradio interface
+    logger.info("Launching Gradio Interface for Agent Evaluation...")
+    demo = create_gradio_interface()
     demo.launch(debug=True, share=False)