Modified files

app.py

@@ -1,75 +1,34 @@
 import os
 import gradio as gr
 import requests
-import inspect
 import pandas as pd
+from agent import initialize_agent # Import the agent initialization function
 
-# (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 ------
-class BasicAgent:
-    def __init__(self):
-        print("BasicAgent initialized.")
-    def __call__(self, question: str) -> str:
-        print(f"Agent received question (first 50 chars): {question[:50]}...")
-        fixed_answer = "This is a default answer."
-        print(f"Agent returning fixed answer: {fixed_answer}")
-        return fixed_answer
-
-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
-
-    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
+# --- Helper Functions ---
+def _fetch_questions(api_url: str) -> list:
+    """Fetches evaluation questions from the API."""
     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
+            raise ValueError("Fetched questions list is empty or invalid format.")
         print(f"Fetched {len(questions_data)} questions.")
+        return questions_data
     except requests.exceptions.RequestException as e:
-        print(f"Error fetching questions: {e}")
-        return f"Error fetching questions: {e}", None
+        raise RuntimeError(f"Error fetching questions: {e}") from e
     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
+        raise RuntimeError(f"Error decoding JSON response from questions endpoint: {e}. Response: {response.text[:500]}") from e
     except Exception as e:
-        print(f"An unexpected error occurred fetching questions: {e}")
-        return f"An unexpected error occurred fetching questions: {e}", None
+        raise RuntimeError(f"An unexpected error occurred fetching questions: {e}") from e
 
-    # 3. Run your Agent
+def _run_agent_on_questions(agent, questions_data: list) -> tuple[list, list]:
+    """Runs the agent on each question and collects answers and logs."""
     results_log = []
     answers_payload = []
     print(f"Running agent on {len(questions_data)} questions...")
@@ -84,34 +43,19 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
             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)
+            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}"})
+    return answers_payload, results_log
 
-    # 5. Submit
-    print(f"Submitting {len(answers_payload)} answers to: {submit_url}")
+def _submit_answers(api_url: str, username: str, agent_code_url: str, answers_payload: list) -> dict:
+    """Submits the agent's answers to the evaluation API."""
+    submit_url = f"{api_url}/submit"
+    submission_data = {"username": username.strip(), "agent_code": agent_code_url, "answers": answers_payload}
+    print(f"Submitting {len(answers_payload)} answers for user '{username}' 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
+        return response.json()
     except requests.exceptions.HTTPError as e:
         error_detail = f"Server responded with status {e.response.status_code}."
         try:
@@ -119,40 +63,98 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
             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
+        raise RuntimeError(f"Submission Failed: {error_detail}") from e
     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
+        raise RuntimeError("Submission Failed: The request timed out.") from e
     except requests.exceptions.RequestException as e:
-        status_message = f"Submission Failed: Network error - {e}"
-        print(status_message)
+        raise RuntimeError(f"Submission Failed: Network error - {e}") from e
+    except Exception as e:
+        raise RuntimeError(f"An unexpected error occurred during submission: {e}") from e
+
+# --- Main Gradio Function ---
+def run_and_submit_all(profile: gr.OAuthProfile | None):
+    """
+    Orchestrates the fetching of questions, running the agent, and submitting answers.
+    """
+    username = None
+    if profile:
+        username = profile.username
+        print(f"User logged in: {username}")
+    else:
+        print("User not logged in.")
+        return "Please Login to Hugging Face with the button.", None
+
+    if not username:
+        return "Hugging Face username not found. Please ensure you are logged in.", None
+
+    space_id = os.getenv("SPACE_ID")
+    if not space_id:
+        print("SPACE_ID environment variable not found. Cannot determine agent_code URL.")
+        return "Error: SPACE_ID not set. Cannot determine agent_code URL.", None
+    agent_code_url = f"https://huggingface.co/spaces/{space_id}/tree/main"
+
+    status_message = ""
+    results_df = pd.DataFrame()
+
+    try:
+        # 1. Instantiate Agent
+        print("Initializing agent...")
+        agent = initialize_agent()
+        if agent is None:
+            raise RuntimeError("Agent initialization failed. Check agent.py for details.")
+        print("Agent initialized successfully.")
+
+        # 2. Fetch Questions
+        questions_data = _fetch_questions(DEFAULT_API_URL)
+
+        # 3. Run Agent on Questions
+        answers_payload, results_log = _run_agent_on_questions(agent, questions_data)
+        if not answers_payload:
+            status_message = "Agent did not produce any answers to submit."
+            return status_message, pd.DataFrame(results_log)
+
+        # 4. Submit Answers
+        submission_result = _submit_answers(DEFAULT_API_URL, username, agent_code_url, answers_payload)
+
+        final_status = (
+            f"Submission Successful!\n"
+            f"User: {submission_result.get('username')}\n"
+            f"Overall Score: {submission_result.get('score', 'N/A')}% "
+            f"({submission_result.get('correct_count', '?')}/{submission_result.get('total_attempted', '?')} correct)\n"
+            f"Message: {submission_result.get('message', 'No message received.')}"
+        )
+        status_message = final_status
         results_df = pd.DataFrame(results_log)
-        return status_message, results_df
+
+    except RuntimeError as e:
+        status_message = f"Operation Failed: {e}"
+        print(status_message)
+        # If an error occurs during agent run, results_log might be partially filled
+        # Ensure results_df is created even if answers_payload is empty due to early error
+        if 'results_log' in locals():
+            results_df = pd.DataFrame(results_log)
+        else:
+            results_df = pd.DataFrame([{"Status": "Error", "Details": str(e)}])
     except Exception as e:
-        status_message = f"An unexpected error occurred during submission: {e}"
+        status_message = f"An unexpected critical error occurred: {e}"
         print(status_message)
-        results_df = pd.DataFrame(results_log)
-        return status_message, results_df
+        results_df = pd.DataFrame([{"Status": "Critical Error", "Details": str(e)}])
 
+    return status_message, results_df
 
-# --- Build Gradio Interface using Blocks ---
+# --- Gradio Interface Definition ---
 with gr.Blocks() as demo:
-    gr.Markdown("# Basic Agent Evaluation Runner")
+    gr.Markdown("# GAIA Benchmark Evaluation with smolagent")
     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.
+        1.  Clone this Space and modify `agent.py` to define your agent's logic, tools, and necessary packages.
+        2.  Log in to your Hugging Face account using the button below. Your HF username will be used for submission.
+        3.  Click 'Run Evaluation & Submit All Answers' to fetch questions, run your agent, submit answers, and see your 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.
+        **Important Notes:**
+        *   The evaluation process can take some time as the agent processes all questions.
+        *   This Space provides a basic setup. You are encouraged to develop a more robust solution (e.g., caching answers, asynchronous processing) for production use.
         """
     )
 
@@ -161,7 +163,6 @@ with gr.Blocks() as demo:
     run_button = gr.Button("Run Evaluation & Submit All Answers")
 
     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(
@@ -173,7 +174,7 @@ 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
+    space_id_startup = os.getenv("SPACE_ID")
 
     if space_host_startup:
         print(f"✅ SPACE_HOST found: {space_host_startup}")
@@ -181,7 +182,7 @@ if __name__ == "__main__":
     else:
         print("ℹ️  SPACE_HOST environment variable not found (running locally?).")
 
-    if space_id_startup: # Print repo URLs if SPACE_ID is found
+    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")