Update app.py

app.py

@@ -1,6 +1,7 @@
 
 
 import os
+import re
 import gradio as gr
 import requests
 import pandas as pd
@@ -8,7 +9,7 @@ import pandas as pd
 from smolagents import CodeAgent, DuckDuckGoSearchTool
 from smolagents.models import OpenAIServerModel
 
-# System prompt as per your instructions
+# ---------------- SYSTEM PROMPT ----------------
 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].
@@ -17,12 +18,19 @@ 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"
 
+
+# ---------------- 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}"
+
+
+# ---------------- AGENT WRAPPER ----------------
 class MyAgent:
     def __init__(self):
-        # Initialize model WITHOUT system_message or system_prompt
-        self.model = OpenAIServerModel(
-            model_id="gpt-4"
-        )
+        self.model = OpenAIServerModel(model_id="gpt-4")
         self.agent = CodeAgent(
             tools=[DuckDuckGoSearchTool()],
             model=self.model
@@ -34,18 +42,21 @@ class MyAgent:
             {"role": "user", "content": question}
         ]
         try:
-            return self.model.run(messages)
+            response = self.model.chat(messages)
+            raw_output = response["content"]
+            return extract_final_answer(raw_output)
         except Exception as e:
             import traceback
             traceback.print_exc()
             return f"AGENT ERROR: {e}"
 
 
+# ---------------- RUN AND SUBMIT ----------------
 def run_and_submit_all(profile: gr.OAuthProfile | None):
-    """
-    Fetches questions, runs the agent, submits answers, returns status and results table.
-    """
     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
@@ -54,55 +65,56 @@ 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:
-        print(f"Error initializing agent: {e}")
         return f"Error initializing agent: {e}", None
 
     agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
-    print(f"Agent code URL: {agent_code}")
-
     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
 
     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 invalid item: {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}")
+    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()
@@ -114,7 +126,6 @@ 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.')}"
         )
-        print("Submission successful.")
         results_df = pd.DataFrame(results_log)
         return final_status, results_df
     except requests.exceptions.HTTPError as e:
@@ -124,18 +135,14 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
             error_detail += f" Detail: {error_json.get('detail', e.response.text)}"
         except Exception:
             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)
+        return f"Submission Failed: {error_detail}", pd.DataFrame(results_log)
     except requests.exceptions.Timeout:
-        status_message = "Submission Failed: The request timed out."
-        print(status_message)
-        return status_message, pd.DataFrame(results_log)
+        return "Submission Failed: The request timed out.", pd.DataFrame(results_log)
     except Exception as e:
-        status_message = f"An unexpected error occurred during submission: {e}"
-        print(status_message)
-        return status_message, pd.DataFrame(results_log)
+        return f"An unexpected error occurred during submission: {e}", pd.DataFrame(results_log)
+
 
+# ---------------- UI ----------------
 with gr.Blocks() as demo:
     gr.Markdown("# Basic Agent Evaluation Runner")
     gr.Markdown(
@@ -157,8 +164,10 @@ with gr.Blocks() as demo:
 
     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")
 
@@ -175,8 +184,7 @@ 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)