Update app.py

app.py

@@ -9,7 +9,7 @@ import pandas as pd
 from smolagents import CodeAgent, DuckDuckGoSearchTool
 from smolagents.models import OpenAIServerModel
 
-# ---------------- SYSTEM PROMPT ----------------
+# System prompt required by GAIA
 SYSTEM_PROMPT = """You are a general AI assistant. I will ask you a question.
 Report your thoughts, and finish your answer with the following template:
 FINAL ANSWER: [YOUR FINAL ANSWER].
@@ -18,16 +18,13 @@ of numbers and/or strings. If you are asked for a number, don't use comma to wri
 
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 
+# Extract FINAL ANSWER
 
-# ---------------- FINAL ANSWER EXTRACTOR ----------------
-def extract_final_answer(output: str) -> str:
-    match = re.search(r"FINAL ANSWER:\s*(.*)", output, re.IGNORECASE)
-    if match:
-        return match.group(1).strip()
-    return f"PARSE ERROR: FINAL ANSWER not found in output: {output}"
+def extract_final_answer(response: str) -> str:
+    match = re.search(r"FINAL ANSWER:\s*(.*)", response, re.IGNORECASE)
+    return match.group(1).strip() if match else response.strip()
 
-
-# ---------------- AGENT WRAPPER ----------------
+# MyAgent class
 class MyAgent:
     def __init__(self):
         self.model = OpenAIServerModel(model_id="gpt-4")
@@ -37,24 +34,22 @@ class MyAgent:
         )
 
     def __call__(self, question: str) -> str:
-        # Combine system prompt and user question as a single input
-        full_prompt = f"{SYSTEM_PROMPT}\n\nUser question: {question}"
+        messages = [
+            {"role": "system", "content": SYSTEM_PROMPT},
+            {"role": "user", "content": question}
+        ]
         try:
-            output = self.model.run(full_prompt)
-            return extract_final_answer(output)
+            response = self.model.chat(messages)
+            return extract_final_answer(response)
         except Exception as e:
             import traceback
             traceback.print_exc()
             return f"AGENT ERROR: {e}"
 
+# Evaluation and submission
 
-# ---------------- RUN AND SUBMIT ----------------
 def run_and_submit_all(profile: gr.OAuthProfile | None):
     space_id = os.getenv("SPACE_ID")
-    api_url = DEFAULT_API_URL
-    questions_url = f"{api_url}/questions"
-    submit_url = f"{api_url}/submit"
-
     if profile:
         username = profile.username
         print(f"User logged in: {username}")
@@ -62,13 +57,16 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
         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"
+
     try:
         agent = MyAgent()
     except Exception as e:
         return f"Error initializing agent: {e}", None
 
     agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
-    print(f"Fetching questions from: {questions_url}")
 
     try:
         response = requests.get(questions_url, timeout=15)
@@ -81,8 +79,6 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
 
     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")
@@ -91,27 +87,14 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
         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
-            })
+            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}"
-            })
+            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
-    }
-
+    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()
@@ -138,33 +121,27 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
     except Exception as e:
         return f"An unexpected error occurred during submission: {e}", pd.DataFrame(results_log)
 
-
-# ---------------- UI ----------------
+# Gradio UI
 with gr.Blocks() as demo:
     gr.Markdown("# Basic Agent Evaluation Runner")
-    gr.Markdown(
-        """
-        **Instructions:**
-        1. Clone this space, modify code to define your agent's logic, tools, and packages.
-        2. Log in to your Hugging Face account using the button below.
-        3. Click 'Run Evaluation & Submit All Answers' to fetch questions, run your agent, submit answers, and see your score.
-        
-        **Note:** Submitting can take some time.
-        """
-    )
+    gr.Markdown("""
+    **Instructions:**
+    1. Clone this space, modify code to define your agent's logic, tools, and packages.
+    2. Log in to your Hugging Face account using the button below.
+    3. Click 'Run Evaluation & Submit All Answers' to fetch questions, run your agent, submit answers, and see your score.
+
+    **Note:** Submitting can take some time.
+    """)
 
     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])
 
-
-# ---------------- MAIN ----------------
 if __name__ == "__main__":
-    print("\n" + "-" * 30 + " App Starting " + "-" * 30)
+    print("\n" + "-"*30 + " App Starting " + "-"*30)
     space_host = os.getenv("SPACE_HOST")
     space_id = os.getenv("SPACE_ID")
 
@@ -181,10 +158,10 @@ if __name__ == "__main__":
     else:
         print("ℹ️  SPACE_ID environment variable not found (running locally?).")
 
-    print("-" * (60 + len(" App Starting ")) + "\n")
+    print("-"*(60 + len(" App Starting ")) + "\n")
+
     print("Launching Gradio Interface for Basic Agent Evaluation...")
     demo.launch(debug=True, share=False)
 
 
 
-