Update app.py

app.py

@@ -1,53 +1,67 @@
 import os
+import gradio as gr
 import requests
 import pandas as pd
-import gradio as gr
-
+import time
 from agent import BasicAgent
 
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 
-class GAIAAgent:
-    def __init__(self):
-        self.agent = BasicAgent()
-    def __call__(self, question: str, task_id: str) -> str:
-        return self.agent(question, task_id)
-
 def run_and_submit_all(profile: gr.OAuthProfile | None):
     space_id = os.getenv("SPACE_ID")
-    if not profile or not profile.username:
+    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
 
-    username = profile.username.strip()
-    agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main" if space_id else ""
     questions_url = f"{DEFAULT_API_URL}/questions"
     submit_url = f"{DEFAULT_API_URL}/submit"
+    agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main" if space_id else ""
 
+    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 Exception as e:
+        print(f"Error fetching questions: {e}")
         return f"Error fetching questions: {e}", None
 
-    agent = GAIAAgent()
+    agent = BasicAgent()
     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, task_id)
+            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})
+            time.sleep(2)
         except Exception as e:
-            submitted_answer = f"[ERROR] {e}"
-        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})
+            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}"})
 
-    submission_data = {"username": username, "agent_code": agent_code, "answers": answers_payload}
+    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)
 
+    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"Submitting {len(answers_payload)} answers to: {submit_url}")
     try:
         response = requests.post(submit_url, json=submission_data, timeout=60)
         response.raise_for_status()
@@ -59,30 +73,33 @@ 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.')}"
         )
-        return final_status, pd.DataFrame(results_log)
+        print("Submission successful.")
+        results_df = pd.DataFrame(results_log)
+        return final_status, results_df
     except Exception as e:
-        return f"Submission Failed: {e}", pd.DataFrame(results_log)
+        status_message = f"Submission Failed: {e}"
+        print(status_message)
+        results_df = pd.DataFrame(results_log)
+        return status_message, results_df
 
 with gr.Blocks() as demo:
     gr.Markdown("# Basic Agent Evaluation Runner")
     gr.Markdown("""
     **Instructions:**
-    1. Please clone this space and modify the agent logic.
-    2. Log in to Hugging Face with the button.
-    3. Click 'Run Evaluation & Submit All Answers' to run the full GAIA test.
+    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.
     """)
-
     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")
-
+    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===== Application Startup =====")
-    space_id = os.getenv("SPACE_ID")
-    if space_id:
-        print(f"🔗 Space: https://huggingface.co/spaces/{space_id}")
-    demo.launch(debug=True)
+    print("Launching Gradio Interface for Basic Agent Evaluation...")
+    demo.launch(debug=True, share=False)