Update app.py

app.py

@@ -1,3 +1,10 @@
+import os
+import gradio as gr
+import requests
+import pandas as pd
+#from smolagents import Agent, tool
+from duckduckgo_search import DDGS
+from transformers import pipeline
 from smolagents import tool
 
 # TOOL 1: Wikipedia-based Search Tool
@@ -98,9 +105,89 @@ class BasicAgent:
         except Exception as e:
             return f"Agent error: {str(e)}"
 
-# CLI test loop
+# --- Evaluation Logic ---
+DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
+
+def run_and_submit_all(profile: gr.OAuthProfile | None):
+    space_id = os.getenv("SPACE_ID")
+    if profile:
+        username = profile.username
+    else:
+        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"
+
+    try:
+        agent = BasicAgent()
+    except Exception as e:
+        return f"Error initializing agent: {e}", None
+
+    agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
+
+    try:
+        response = requests.get(questions_url, timeout=15)
+        response.raise_for_status()
+        questions_data = response.json()
+    except Exception as e:
+        return f"Error fetching questions: {e}", None
+
+    results_log = []
+    answers_payload = []
+
+    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:
+            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:
+            results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": f"AGENT ERROR: {e}"})
+
+    if not answers_payload:
+        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
+    }
+
+    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.')}"
+        )
+        results_df = pd.DataFrame(results_log)
+        return final_status, results_df
+    except Exception as e:
+        return f"Submission Failed: {e}", pd.DataFrame(results_log)
+
+# --- Gradio UI ---
+with gr.Blocks() as demo:
+    gr.Markdown("# Smart Agent Evaluation Runner")
+    gr.Markdown("""
+    **Instructions:**
+    1. Login to your HF account using the button.
+    2. Click 'Run Evaluation & Submit All Answers' to test your agent.
+    """)
+
+    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__":
-    agent = BasicAgent()
-    while True:
-        q = input("Ask GAIA: ")
-        print(agent(q))
+    demo.launch()