Update app.py

app.py

@@ -1,77 +1,89 @@
-# app.py — supports text, audio (.mp3) and Excel (.xlsx) inputs
+# app.py – przywrócony layout oryginalnego benchmarku z integracją GAIA agent
 
 import os
 import requests
 import pandas as pd
 import gradio as gr
-import asyncio
-import tempfile
 
-from agent import (
-    answer_question,
-    transcribe_audio,
-    extract_excel_total_food_sales
-)
+from agent import answer_question, transcribe_audio, extract_excel_total_food_sales
 
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 
 class GAIALlamaAgent:
-    def __call__(self, question: str, file) -> str:
-        if file:
-            ext = os.path.splitext(file.name)[1].lower()
-            if ext == ".mp3":
-                return transcribe_audio(file.name)
-            if ext in (".xls", ".xlsx"):
-                return extract_excel_total_food_sales(file.name)
-        return asyncio.run(answer_question(question))
+    def __call__(self, question: str) -> str:
+        return answer_question_sync(question)
 
 def run_and_submit_all(profile: gr.OAuthProfile | None):
+    space_id = os.getenv("SPACE_ID")
     if not profile or not profile.username:
-        return "Please log in to Hugging Face.", None
-    username = profile.username
-    space_id = os.getenv("SPACE_ID", "")
-    agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
+        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"
 
     try:
-        questions = requests.get(f"{DEFAULT_API_URL}/questions", timeout=15).json()
+        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
 
     agent = GAIALlamaAgent()
-    payload, log = [], []
+    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)
+        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})
 
-    for q in questions:
-        ans = agent(q["question"], None)
-        payload.append({"task_id": q["task_id"], "submitted_answer": ans})
-        log.append({"Task ID": q["task_id"], "Question": q["question"], "Answer": ans})
+    submission_data = {"username": username, "agent_code": agent_code, "answers": answers_payload}
 
     try:
-        res = requests.post(f"{DEFAULT_API_URL}/submit",
-                            json={"username": username, "agent_code": agent_code, "answers": payload},
-                            timeout=60).json()
-        status = f"✅ Score: {res.get('score')}% ({res.get('correct_count')}/{res.get('total_attempted')})"
+        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.')}"
+        )
+        return final_status, pd.DataFrame(results_log)
     except Exception as e:
-        status = f"❌ Submission failed: {e}"
-
-    return status, pd.DataFrame(log)
+        return f"Submission Failed: {e}", pd.DataFrame(results_log)
 
+# --- Gradio Interface matching original benchmark ---
 with gr.Blocks() as demo:
-    gr.Markdown("# GAIA Agent")
+    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.
+    """)
+
     gr.LoginButton()
-    with gr.Row():
-        question = gr.Textbox(label="Question")
-        file_in = gr.File(label="Optional file (.mp3, .xlsx)")
-        ask_btn = gr.Button("Ask")
-        output = gr.Textbox(label="Answer")
-    ask_btn.click(lambda q, f: GAIALlamaAgent()(q, f), inputs=[question, file_in], outputs=output)
-    gr.Markdown("## Or run full GAIA evaluation")
-    eval_btn = gr.Button("Run Evaluation & Submit")
-    status = gr.Textbox(label="Status", lines=4)
-    table = gr.DataFrame()
-    eval_btn.click(run_and_submit_all, outputs=[status, table])
+
+    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")
+
+    run_button.click(fn=run_and_submit_all, outputs=[status_output, results_table])
 
 if __name__ == "__main__":
-    print("🔁 App starting")
-    if os.getenv("SPACE_ID"):
-        print("🔗 Space:", os.getenv("SPACE_ID"))
+    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)