Update app.py

app.py

@@ -1,21 +1,19 @@
 import os
 import gradio as gr
 import requests
-import inspect
+import re
 import pandas as pd
 
-# (Keep Constants as is)
 # --- Constants ---
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 
 # --- Basic Agent Definition ---
-# ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
-from transformers import pipeline
-import re
+from transformers import pipeline, set_seed
 
 class BasicAgent:
     def __init__(self):
         print("BasicAgent initialized.")
+        set_seed(42)  # ensure reproducible outputs
         self.generator = pipeline(
             "text2text-generation",
             model="google/flan-t5-large",
@@ -31,69 +29,74 @@ class BasicAgent:
 
         result = self.generator(prompt)[0]["generated_text"]
 
-        # Strong cleanup
+        # --- Strong cleanup for GAIA exact answers ---
         answer = result.strip()
-        answer = answer.replace("The answer is", "")
-        answer = re.split(r"[.\n,]", answer)[0]
-        answer = answer.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}")
         return answer
 
 
-    
-
-def run_and_submit_all( profile: gr.OAuthProfile | None):
+# --- 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.
     """
-    # --- Determine HF Space Runtime URL and Repo URL ---
-    space_id = os.getenv("SPACE_ID") # Get the SPACE_ID for sending link to the code
+    space_id = os.getenv("SPACE_ID")
 
     if profile:
-        username= f"{profile.username}"
+        username = f"{profile.username}"
         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.", pd.DataFrame()
 
     api_url = DEFAULT_API_URL
     questions_url = f"{api_url}/questions"
     submit_url = f"{api_url}/submit"
 
-    # 1. Instantiate Agent ( modify this part to create your agent)
+    # --- Instantiate Agent ---
     try:
         agent = BasicAgent()
     except Exception as e:
         print(f"Error instantiating agent: {e}")
-        return f"Error initializing agent: {e}", None
-    # In the case of an app running as a hugging Face space, this link points toward your codebase ( usefull for others so please keep it public)
-    agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
+        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)
 
-    # 2. Fetch Questions
+    # --- 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.", None
+            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}", None
+        return f"Error fetching questions: {e}", pd.DataFrame()
     except requests.exceptions.JSONDecodeError as e:
-         print(f"Error decoding JSON response from questions endpoint: {e}")
-         print(f"Response text: {response.text[:500]}")
-         return f"Error decoding server response for questions: {e}", None
+        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"An unexpected error occurred fetching questions: {e}")
-        return f"An unexpected error occurred fetching questions: {e}", None
+        print(f"Unexpected error fetching questions: {e}")
+        return f"Unexpected error fetching questions: {e}", pd.DataFrame()
 
-    # 3. Run your Agent
+    # --- Run Agent ---
     results_log = []
     answers_payload = []
     print(f"Running agent on {len(questions_data)} questions...")
@@ -106,22 +109,32 @@ 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:
-             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}"})
+            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}"
+            })
 
     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)
 
-    # 4. Prepare Submission 
-    submission_data = {"username": username.strip(), "agent_code": agent_code, "answers": answers_payload}
-    status_update = f"Agent finished. Submitting {len(answers_payload)} answers for user '{username}'..."
-    print(status_update)
+    # --- Prepare Submission ---
+    submission_data = {
+        "username": username.strip(),
+        "agent_code": agent_code,
+        "answers": answers_payload
+    }
+    print(f"Submitting {len(answers_payload)} answers for user '{username}'...")
 
-    # 5. Submit
-    print(f"Submitting {len(answers_payload)} answers to: {submit_url}")
+    # --- Submit Answers ---
     try:
         response = requests.post(submit_url, json=submission_data, timeout=60)
         response.raise_for_status()
@@ -136,58 +149,35 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
         print("Submission successful.")
         results_df = pd.DataFrame(results_log)
         return final_status, results_df
-    except requests.exceptions.HTTPError as e:
-        error_detail = f"Server responded with status {e.response.status_code}."
-        try:
-            error_json = e.response.json()
-            error_detail += f" Detail: {error_json.get('detail', e.response.text)}"
-        except requests.exceptions.JSONDecodeError:
-            error_detail += f" Response: {e.response.text[:500]}"
-        status_message = f"Submission Failed: {error_detail}"
-        print(status_message)
-        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)
-        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}"
+        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"An unexpected error occurred during submission: {e}"
+        status_message = f"Unexpected error during submission: {e}"
         print(status_message)
         results_df = pd.DataFrame(results_log)
         return status_message, results_df
 
 
-# --- Build Gradio Interface using Blocks ---
+# --- Gradio Interface ---
 with gr.Blocks() as demo:
     gr.Markdown("# Basic Agent Evaluation Runner")
     gr.Markdown(
         """
         **Instructions:**
 
-        1.  Please clone this space, then modify the code to define your agent's logic, the tools, the necessary 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:**
-        Once clicking on the "submit button, it can take quite some time ( this is the time for the agent to go through all the questions).
-        This space provides a basic setup and is intentionally sub-optimal to encourage you to develop your own, more robust solution. For instance for the delay process of the submit button, a solution could be to cache the answers and submit in a seperate action or even to answer the questions in async.
+        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.LoginButton()
-
     run_button = gr.Button("Run Evaluation & Submit All Answers")
 
     status_output = gr.Textbox(label="Run Status / Submission Result", lines=5, interactive=False)
-    # Removed max_rows=10 from DataFrame constructor
     results_table = gr.DataFrame(label="Questions and Agent Answers", wrap=True)
 
     run_button.click(
@@ -195,26 +185,26 @@ with gr.Blocks() as demo:
         outputs=[status_output, results_table]
     )
 
+
+# --- Startup Logs ---
 if __name__ == "__main__":
     print("\n" + "-"*30 + " App Starting " + "-"*30)
-    # Check for SPACE_HOST and SPACE_ID at startup for information
     space_host_startup = os.getenv("SPACE_HOST")
-    space_id_startup = os.getenv("SPACE_ID") # Get SPACE_ID at startup
+    space_id_startup = os.getenv("SPACE_ID")
 
     if space_host_startup:
         print(f"✅ SPACE_HOST found: {space_host_startup}")
-        print(f"   Runtime URL should be: https://{space_host_startup}.hf.space")
+        print(f"   Runtime URL: https://{space_host_startup}.hf.space")
     else:
-        print("ℹ️  SPACE_HOST environment variable not found (running locally?).")
+        print("ℹ️ SPACE_HOST not found (running locally?)")
 
-    if space_id_startup: # Print repo URLs if SPACE_ID is found
+    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 environment variable not found (running locally?). Repo URL cannot be determined.")
+        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)
+    demo.launch(debug=True, share=False)