Update app.py

app.py

@@ -6,34 +6,21 @@ import pandas as pd
 from smolagents import CodeAgent, DuckDuckGoSearchTool
 from smolagents.models import OpenAIServerModel
 
-# System prompt as per your instructions
-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].
-YOUR FINAL ANSWER should be a number OR as few words as possible OR a comma separated list 
-of numbers and/or strings. If you are asked for a number, don't use comma to write your number neither use units such as $ or percent sign unless specified otherwise. If you are asked for a string, don't use articles, neither abbreviations (e.g. for cities), and write the digits in plain text unless specified otherwise. If you are asked for a comma separated list, apply the above rules depending of whether the element to be put in the list is a number or a string."""
-
+# --- Constants ---
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 
-class MyAgent:
-    def __init__(self):
-        # Initialize model with system prompt
-        self.model = OpenAIServerModel(
-            model_id="gpt-4",
-            system_message=SYSTEM_PROMPT
-        )
-        self.agent = CodeAgent(
-            tools=[DuckDuckGoSearchTool()],
-            model=self.model
-        )
-
-    def __call__(self, question: str) -> str:
-        # Run agent on the question
-        return self.agent.run(question)
+# --- System prompt for the model ---
+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].
+YOUR FINAL ANSWER should be a number OR as few words as possible OR a comma separated list 
+of numbers and/or strings. If you are asked for a number, don't use comma to write your number neither use units such as $ or percent sign unless specified otherwise. If you are asked for a string, don't use articles, neither abbreviations (e.g. for cities), and write the digits in plain text unless specified otherwise. If you are asked for a comma separated list, 
+apply the above rules depending of whether the element to be put in the list is a number or a string.
+"""
 
 def run_and_submit_all(profile: gr.OAuthProfile | None):
     """
-    Fetches questions, runs the agent, submits answers, returns status and results table.
+    Fetch all questions, run the agent on them, submit answers, and display results.
     """
     space_id = os.getenv("SPACE_ID")
 
@@ -42,21 +29,31 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
         print(f"User logged in: {username}")
     else:
         print("User not logged in.")
-        return "Please Login to Hugging Face with the button.", None
+        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"
 
+    # Instantiate Agent with fixed system_prompt keyword
     try:
-        agent = MyAgent()
+        agent = CodeAgent(
+            model=OpenAIServerModel(
+                model_id="gpt-4o-mini",
+                system_prompt=SYSTEM_PROMPT
+            ),
+            tools=[DuckDuckGoSearchTool()]
+        )
+        print("Agent initialized successfully.")
     except Exception as e:
         print(f"Error initializing agent: {e}")
         return f"Error initializing agent: {e}", None
 
+    # Link to code repo on Hugging Face
     agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
-    print(f"Agent code URL: {agent_code}")
+    print(agent_code)
 
+    # Fetch questions
     print(f"Fetching questions from: {questions_url}")
     try:
         response = requests.get(questions_url, timeout=15)
@@ -66,10 +63,14 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
             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:
+    except requests.exceptions.RequestException as e:
         print(f"Error fetching questions: {e}")
         return f"Error fetching questions: {e}", None
+    except Exception as e:
+        print(f"Unexpected error fetching questions: {e}")
+        return f"Unexpected error fetching questions: {e}", None
 
+    # Run agent on questions
     results_log = []
     answers_payload = []
     print(f"Running agent on {len(questions_data)} questions...")
@@ -77,22 +78,37 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
         task_id = item.get("task_id")
         question_text = item.get("question")
         if not task_id or question_text is None:
-            print(f"Skipping invalid item: {item}")
+            print(f"Skipping item with missing task_id or question: {item}")
             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})
+            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}"})
+            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)
 
-    submission_data = {"username": username.strip(), "agent_code": agent_code, "answers": answers_payload}
-    print(f"Submitting {len(answers_payload)} answers to: {submit_url}")
+    # Prepare submission payload
+    submission_data = {
+        "username": username.strip(),
+        "agent_code": agent_code,
+        "answers": answers_payload
+    }
+    print(f"Submitting {len(answers_payload)} answers for user '{username}'...")
+
+    # Submit answers
     try:
         response = requests.post(submit_url, json=submission_data, timeout=60)
         response.raise_for_status()
@@ -116,36 +132,51 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
             error_detail += f" Response: {e.response.text[:500]}"
         status_message = f"Submission Failed: {error_detail}"
         print(status_message)
-        return status_message, pd.DataFrame(results_log)
+        results_df = pd.DataFrame(results_log)
+        return status_message, results_df
     except requests.exceptions.Timeout:
         status_message = "Submission Failed: The request timed out."
         print(status_message)
-        return status_message, pd.DataFrame(results_log)
+        results_df = pd.DataFrame(results_log)
+        return status_message, results_df
+    except requests.exceptions.RequestException as e:
+        status_message = f"Submission Failed: Network error - {e}"
+        print(status_message)
+        results_df = pd.DataFrame(results_log)
+        return status_message, results_df
     except Exception as e:
-        status_message = f"An unexpected error occurred during submission: {e}"
+        status_message = f"Unexpected error during submission: {e}"
         print(status_message)
-        return status_message, pd.DataFrame(results_log)
+        results_df = pd.DataFrame(results_log)
+        return status_message, results_df
+
 
+# --- Gradio Interface ---
 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.
+        1. Please clone this space, then modify the code to define your agent's logic, tools, 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:**
+        Submission can take time depending on the number of questions and model latency.
+        This space provides a basic setup and encourages you to improve it further.
         """
     )
 
-    gr.LoginButton()
+    login_button = 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])
+    run_button.click(
+        fn=run_and_submit_all,
+        inputs=[login_button],
+        outputs=[status_output, results_table]
+    )
 
 if __name__ == "__main__":
     print("\n" + "-"*30 + " App Starting " + "-"*30)
@@ -156,14 +187,14 @@ if __name__ == "__main__":
         print(f"✅ SPACE_HOST found: {space_host}")
         print(f"   Runtime URL should be: https://{space_host}.hf.space")
     else:
-        print("ℹ️  SPACE_HOST environment variable not found (running locally?).")
+        print("ℹ️ SPACE_HOST environment variable not found (running locally?).")
 
     if space_id:
         print(f"✅ SPACE_ID found: {space_id}")
         print(f"   Repo URL: https://huggingface.co/spaces/{space_id}")
         print(f"   Repo Tree URL: https://huggingface.co/spaces/{space_id}/tree/main")
     else:
-        print("ℹ️  SPACE_ID environment variable not found (running locally?).")
+        print("ℹ️ SPACE_ID environment variable not found (running locally?). Repo URL cannot be determined.")
 
     print("-"*(60 + len(" App Starting ")) + "\n")