Update app.py

app.py

@@ -3,17 +3,16 @@ import gradio as gr
 import requests
 import re
 import pandas as pd
+from transformers import pipeline, set_seed
 
 # --- Constants ---
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 
-# --- Basic Agent Definition ---
-from transformers import pipeline, set_seed
-
+# --- Smarter Basic Agent ---
 class BasicAgent:
     def __init__(self):
         print("BasicAgent initialized.")
-        set_seed(42)  # ensure reproducible outputs
+        set_seed(42)
         self.generator = pipeline(
             "text2text-generation",
             model="google/flan-t5-large",
@@ -21,90 +20,91 @@ class BasicAgent:
         )
 
     def __call__(self, question: str) -> str:
-        prompt = (
-            "Give ONLY the exact answer. "
-            "No explanation. No extra words.\n"
-            f"{question}"
-        )
-
+        # --- Detect question type ---
+        q_lower = question.lower()
+
+        # Boolean detection
+        if any(x in q_lower for x in ["true or false", "yes or no", "is it", "does it", "can it"]):
+            prompt = (
+                "Answer only True or False exactly. "
+                "No explanations or extra words.\n"
+                f"Q: {question}\nA:"
+            )
+        # Multiple choice detection
+        elif any(x in question for x in ["A)", "B)", "C)", "D)", "choose", "options"]):
+            prompt = (
+                "Answer only with one option exactly: A, B, C, or D. "
+                "No explanations or extra words.\n"
+                f"Q: {question}\nA:"
+            )
+        # Numeric detection (digits in question or ask for a number)
+        elif re.search(r"number|digits|how many|count|what is \d", q_lower):
+            prompt = (
+                "Answer only with the number, no words or punctuation.\n"
+                f"Q: {question}\nA:"
+            )
+        # Default: let model generate
+        else:
+            prompt = (
+                "Give ONLY the exact answer. "
+                "No explanation or extra words.\n"
+                f"Q: {question}\nA:"
+            )
+
+        # --- Generate answer ---
         result = self.generator(prompt)[0]["generated_text"]
 
-        # --- Strong cleanup for GAIA exact answers ---
+        # --- Post-process answer ---
         answer = result.strip()
-        # Remove common prefixes
-        answer = re.sub(r"(?i)^(the answer is|answer:)\s*", "", answer)
-        # Take only first line or sentence
-        answer = re.split(r"[.\n]", answer)[0].strip()
-        # Remove trailing punctuation
-        answer = answer.rstrip(".,;:")
-
-        print(f"Final answer: {answer}")
+        answer = re.sub(r"(?i)^(the answer is|answer:)\s*", "", answer)  # remove prefixes
+        answer = re.split(r"[.\n]", answer)[0].strip()  # first line or sentence
+        answer = answer.rstrip(".,;:")  # remove trailing punctuation
+
+        # Enforce boolean formatting
+        if answer.lower() in ["true", "false"]:
+            answer = answer.capitalize()
+
+        print(f"Question: {question}\nFinal answer: {answer}\n")
         return answer
 
 
 # --- Run and Submit Function ---
 def run_and_submit_all(profile: gr.OAuthProfile | None):
-    """
-    Fetches all questions, runs the BasicAgent on them, submits all answers,
-    and displays the results.
-    """
     space_id = os.getenv("SPACE_ID")
 
     if profile:
-        username = f"{profile.username}"
-        print(f"User logged in: {username}")
+        username = profile.username
     else:
-        print("User not logged in.")
         return "Please Login to Hugging Face with the button.", pd.DataFrame()
 
     api_url = DEFAULT_API_URL
     questions_url = f"{api_url}/questions"
     submit_url = f"{api_url}/submit"
 
-    # --- Instantiate Agent ---
     try:
         agent = BasicAgent()
     except Exception as e:
-        print(f"Error instantiating agent: {e}")
         return f"Error initializing agent: {e}", pd.DataFrame()
 
-    # --- Agent Code URL ---
-    if space_id:
-        agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
-    else:
-        agent_code = "Agent code URL not available."
-    print(agent_code)
+    agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main" if space_id else "Agent code URL not available."
 
     # --- Fetch Questions ---
-    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.", pd.DataFrame()
-        print(f"Fetched {len(questions_data)} questions.")
-    except requests.exceptions.RequestException as e:
-        print(f"Error fetching questions: {e}")
-        return f"Error fetching questions: {e}", pd.DataFrame()
-    except requests.exceptions.JSONDecodeError as e:
-        print(f"Error decoding JSON response: {e}")
-        print(f"Response text: {response.text[:500]}")
-        return f"Error decoding server response for questions: {e}", pd.DataFrame()
     except Exception as e:
-        print(f"Unexpected error fetching questions: {e}")
-        return f"Unexpected error fetching questions: {e}", pd.DataFrame()
+        return f"Error fetching questions: {e}", pd.DataFrame()
 
-    # --- Run Agent ---
     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 item with missing task_id or question: {item}")
             continue
         try:
             submitted_answer = agent(question_text)
@@ -115,7 +115,6 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
                 "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,
@@ -123,18 +122,10 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
             })
 
     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)
 
-    # --- Prepare Submission ---
-    submission_data = {
-        "username": username.strip(),
-        "agent_code": agent_code,
-        "answers": answers_payload
-    }
-    print(f"Submitting {len(answers_payload)} answers for user '{username}'...")
+    submission_data = {"username": username.strip(), "agent_code": agent_code, "answers": answers_payload}
 
-    # --- Submit Answers ---
     try:
         response = requests.post(submit_url, json=submission_data, timeout=60)
         response.raise_for_status()
@@ -146,65 +137,22 @@ 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.RequestException as e:
-        status_message = f"Submission Failed: {e}"
-        print(status_message)
-        results_df = pd.DataFrame(results_log)
-        return status_message, results_df
     except Exception as e:
-        status_message = f"Unexpected error during submission: {e}"
-        print(status_message)
-        results_df = pd.DataFrame(results_log)
-        return status_message, results_df
+        return f"Submission Failed: {e}", pd.DataFrame(results_log)
 
 
 # --- Gradio Interface ---
 with gr.Blocks() as demo:
-    gr.Markdown("# Basic Agent Evaluation Runner")
-    gr.Markdown(
-        """
-        **Instructions:**
-
-        1. Clone this space and modify the code to define your agent's logic.
-        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 the score.
-        """
-    )
-
+    gr.Markdown("# GAIA Smarter Agent Runner")
     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, outputs=[status_output, results_table])
 
 
-# --- Startup Logs ---
 if __name__ == "__main__":
-    print("\n" + "-"*30 + " App Starting " + "-"*30)
-    space_host_startup = os.getenv("SPACE_HOST")
-    space_id_startup = os.getenv("SPACE_ID")
-
-    if space_host_startup:
-        print(f"✅ SPACE_HOST found: {space_host_startup}")
-        print(f"   Runtime URL: https://{space_host_startup}.hf.space")
-    else:
-        print("ℹ️ SPACE_HOST not found (running locally?)")
-
-    if space_id_startup:
-        print(f"✅ SPACE_ID found: {space_id_startup}")
-        print(f"   Repo URL: https://huggingface.co/spaces/{space_id_startup}")
-        print(f"   Repo Tree URL: https://huggingface.co/spaces/{space_id_startup}/tree/main")
-    else:
-        print("ℹ️ SPACE_ID not found (running locally?)")
-
-    print("-"*(60 + len(" App Starting ")) + "\n")
-    print("Launching Gradio Interface for Basic Agent Evaluation...")
     demo.launch(debug=True, share=False)